<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/">
    <channel>
        <title>煎餃的調味實驗室</title>
        <link>https://gyozalab.com/</link>
        <description>這裡記錄了一個非本科文組生的 AI 自學筆記。最近在玩的東西：Claude、Notion、Obsidian，正在試著打造一套個人知識 Agent，未來也會陸續更新更多 AI 基礎入門教學與工作流分享，敬請期待。</description>
        <lastBuildDate>Tue, 09 Jun 2026 19:48:25 GMT</lastBuildDate>
        <docs>https://validator.w3.org/feed/docs/rss2.html</docs>
        <generator>https://github.com/jpmonette/feed</generator>
        <language>zh-TW</language>
        <copyright>All rights reserved 2026, 閃電煎餃</copyright>
        <item>
            <title><![CDATA[n8n 怎麼連上你的 Gmail 跟 Drive？Google OAuth 設定 20 分鐘搞定]]></title>
            <link>https://gyozalab.com/n8n-google-oauth-setup</link>
            <guid>https://gyozalab.com/n8n-google-oauth-setup</guid>
            <pubDate>Tue, 02 Jun 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[n8n 要動你的 Google 資料，不能用 API Key，要走 OAuth 授權。這篇教你在 GCP 跟 n8n 之間設好一把鑰匙，20 分鐘搞定，打通 Drive、Gmail、Sheets、Calendar！]]></description>
            <content:encoded><![CDATA[<div id="notion-article" class="mx-auto overflow-hidden "><main class="notion light-mode notion-page notion-block-37170f01963480a5b794cdef15aa7982"><div class="notion-viewport"></div><div class="notion-collection-page-properties"></div><div class="notion-callout notion-block-97bc427b37dd4efe8797f0ab6d923978"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="🎯">🎯</span></div><div class="notion-callout-text"><div class="notion-text notion-block-a114e7b944c24ab4954f1ff228b9fe60">n8n 要動你的 Google 個人資料，不能用 API Key，只能走 OAuth 授權。整套流程分四段：GCP 建專案、啟用 API、設同意畫面，最後在 n8n 跟 GCP 之間來回貼 Redirect URL 和 Client ID，全程 20 分鐘，設定一次 Drive、Gmail、Sheets、Calendar 全通。</div></div></div><div class="notion-text notion-block-88accae894784a1aab67f9743b3d0ed0">n8n 要代替你操作 Gmail、Drive、Sheets 這些 Google 服務，不能像一般 API 那樣貼一串 Key 就好。Google 強制要求走 OAuth 授權：你要「親自同意」讓 n8n 動你的東西。還沒有裝 n8n 的話，可以先看<a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://gyozalab.com/docker-n8n-guide">用 Docker 在本機部署 n8n</a>，15 分鐘跑起來之後再回來設定 OAuth。</div><div class="notion-text notion-block-6f6ff9c7339d4e8c9138e0da2314c0d4">這篇教你在 Google Cloud 跟 n8n 之間設好一把 OAuth 鑰匙。設一次，之後 Drive、Gmail、Sheets、Calendar 全通。全程圖解，20 分鐘內搞定。</div><hr class="notion-hr notion-block-5e4ff48ec3f74580a9c857a187e431a2"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-b209d62a550d499d85c2022ad518ac1d" data-id="b209d62a550d499d85c2022ad518ac1d"><span><div id="b209d62a550d499d85c2022ad518ac1d" class="notion-header-anchor"></div><a class="notion-hash-link" href="#b209d62a550d499d85c2022ad518ac1d" title="一、為什麼不能直接輸入 API Key？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">一、為什麼不能直接輸入 API Key？</span></span></h3><div class="notion-text notion-block-6157c822bfe14e1796dabe2991cca43a">因為你要 n8n 去動<b>「你的」</b> Drive、Gmail、Sheets 資料。Google 不能光憑一串密碼就把你的東西交給 n8n，它要你<b>「親自授權」</b>。</div><div class="notion-text notion-block-ca21e120f6194582822e115930aaf015">差別像這樣：</div><table class="notion-simple-table notion-block-0c017b7656ca4e12a700bfcf8b99a32d"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-6edce2be02a444cc835946bd402b9970"><td class="" style="width:103.00000762939453px"><div class="notion-simple-table-cell">類型</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>API Key</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>OAuth 2.0</b></div></td></tr><tr class="notion-simple-table-row notion-block-2d8dca618b9d4dc7b590186a7bd37eb3"><td class="" style="width:103.00000762939453px"><div class="notion-simple-table-cell">比喻</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">房子的鑰匙（給誰就能進去）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">飯店的房卡（本人去櫃台辦理、授權給特定人、可隨時撤銷）</div></td></tr><tr class="notion-simple-table-row notion-block-92f494c21b404545aafeb9ead1fe966a"><td class="" style="width:103.00000762939453px"><div class="notion-simple-table-cell">適用場景</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">公開資料（查天氣、翻譯）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">會碰到你個人資料的服務（Gmail、Drive、Sheets）</div></td></tr><tr class="notion-simple-table-row notion-block-eaac7a7ea9bc4042899efb5200a9fdd5"><td class="" style="width:103.00000762939453px"><div class="notion-simple-table-cell">安全性</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">低（拿到就能用）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">高（要本人按同意、可隨時收回）</div></td></tr></tbody></table><div class="notion-text notion-block-3129377a753e4b4b8430a385f7c0cb7a">Drive 跟 Gmail 這種會碰到個人資料的，Google 強制要走 OAuth，沒得選。</div><hr class="notion-hr notion-block-addbee5b51de422fbeb37c91fbe8f09a"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-d3ee1b6940044387ad45d3ef2c6c4828" data-id="d3ee1b6940044387ad45d3ef2c6c4828"><span><div id="d3ee1b6940044387ad45d3ef2c6c4828" class="notion-header-anchor"></div><a class="notion-hash-link" href="#d3ee1b6940044387ad45d3ef2c6c4828" title="二、先搞懂三方關係"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">二、先搞懂三方關係</span></span></h3><div class="notion-text notion-block-8d1a429edd31441ebc13c71c5a5dc63a">整套 OAuth 就是三個角色在互動：</div><table class="notion-simple-table notion-block-915ad509cd0b4e99b445c9a43d19eeed"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-6a69f3e7881243fcbcd8e50d65f7aa00"><td class="" style="width:92.00000762939453px"><div class="notion-simple-table-cell">角色</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>你（資料主人）</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>n8n（仲介）</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>Google（資料保管者）</b></div></td></tr><tr class="notion-simple-table-row notion-block-3ccc865e3cad4176ae64b8f0873866c3"><td class="" style="width:92.00000762939453px"><div class="notion-simple-table-cell">做什麼</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Gmail / Drive / Sheets 都是你的，你說了算</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">想代表你去存取 Google 資料做自動化</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">手上有你的資料，只認你授權給誰</div></td></tr></tbody></table><div class="notion-text notion-block-becfd4d762ad4394b7d3710a8ad35db7">所以我們要做的事：<b>到 Google 那邊登記一個叫 n8n 的「應用程式」</b>（PART 1-3 在 GCP 做），<b>然後在 n8n 用這個身份去敲 Google 的門</b>（PART 4 在 n8n 做）。中間 Google 會跳視窗問你「你真的要授權 n8n 嗎？」按同意，n8n 才能用。</div><hr class="notion-hr notion-block-825905f9cca448d289e8c98163f32772"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-f4f7ba7711a54e1c97910114f631343f" data-id="f4f7ba7711a54e1c97910114f631343f"><span><div id="f4f7ba7711a54e1c97910114f631343f" class="notion-header-anchor"></div><a class="notion-hash-link" href="#f4f7ba7711a54e1c97910114f631343f" title="三、流程總覽"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">三、流程總覽</span></span></h3><table class="notion-simple-table notion-block-ef534a47d680414ba84a25e9fc43cc82"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-eef80e746f044dc0a063a82d61018f4f"><td class="" style="width:109.00000762939453px"><div class="notion-simple-table-cell">階段</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">做什麼</div></td><td class="" style="width:176.24038696289062px"><div class="notion-simple-table-cell">在哪裡做</div></td><td class="" style="width:93.00000762939453px"><div class="notion-simple-table-cell">花多久</div></td></tr><tr class="notion-simple-table-row notion-block-42c439fc9a48436c81744be6940371a2"><td class="" style="width:109.00000762939453px"><div class="notion-simple-table-cell"><b>PART 1</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">建專案 + 啟用你需要的 Google API</div></td><td class="" style="width:176.24038696289062px"><div class="notion-simple-table-cell">Google Cloud Console</div></td><td class="" style="width:93.00000762939453px"><div class="notion-simple-table-cell">5 分鐘</div></td></tr><tr class="notion-simple-table-row notion-block-a385d10dad0f4425b2a992c94d7ab188"><td class="" style="width:109.00000762939453px"><div class="notion-simple-table-cell"><b>PART 2</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">設 OAuth 同意畫面（Google 強制順序）</div></td><td class="" style="width:176.24038696289062px"><div class="notion-simple-table-cell">Google Cloud Console</div></td><td class="" style="width:93.00000762939453px"><div class="notion-simple-table-cell">5 分鐘</div></td></tr><tr class="notion-simple-table-row notion-block-5071e05514e2412da275333e1db939e2"><td class="" style="width:109.00000762939453px"><div class="notion-simple-table-cell"><b>PART 3</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">建 OAuth 用戶端，拿到 ID + Secret</div></td><td class="" style="width:176.24038696289062px"><div class="notion-simple-table-cell">Google Cloud Console</div></td><td class="" style="width:93.00000762939453px"><div class="notion-simple-table-cell">3 分鐘</div></td></tr><tr class="notion-simple-table-row notion-block-911c98a1bc3f4cd591cb50522bf1cca5"><td class="" style="width:109.00000762939453px"><div class="notion-simple-table-cell"><b>PART 4</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">n8n ↔ GCP 來回接線，按授權</div></td><td class="" style="width:176.24038696289062px"><div class="notion-simple-table-cell">n8n + GCP 交叉操作</div></td><td class="" style="width:93.00000762939453px"><div class="notion-simple-table-cell">5 分鐘</div></td></tr></tbody></table><div class="notion-callout notion-block-a68eb95cc3be4ff89d5bf9aba62df46c"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-cf25356be106422093fad66b65bd4127">PART 1-3 只做一次。之後想加 Gmail、Sheets、Calendar，只要重複 PART 1 的「啟用 API」+ PART 4 的「建憑證」就好。全部確認能跑之後，記得回 PART 2 步驟 3 處把 App 發布成正式版，避免 7 天斷線。</div></div></div><hr class="notion-hr notion-block-8db40c0c633d42f9aed13e1212afbd7b"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-5bec687da3e243db84fb7523c5d158b1" data-id="5bec687da3e243db84fb7523c5d158b1"><span><div id="5bec687da3e243db84fb7523c5d158b1" class="notion-header-anchor"></div><a class="notion-hash-link" href="#5bec687da3e243db84fb7523c5d158b1" title="四、PART 1：建專案 + 啟用你需要的 API"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">四、PART 1：建專案 + 啟用你需要的 API</span></span></h3><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-2d41b1a9a436467c88585acd8f5fc2bc" data-id="2d41b1a9a436467c88585acd8f5fc2bc"><span><div id="2d41b1a9a436467c88585acd8f5fc2bc" class="notion-header-anchor"></div><a class="notion-hash-link" href="#2d41b1a9a436467c88585acd8f5fc2bc" title="步驟 1｜登入 Google Cloud，建一個專案"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 1｜登入 Google Cloud，建一個專案</span></span></h4><div class="notion-row notion-block-37270f01963480b4bd2af1db191f7edd"><div class="notion-column notion-block-37270f0196348074aa9be98579d8b689" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37270f019634801cbd01cdd052ef73c7"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A2fd3a15a-2ffb-43c1-9c26-30e642f11886%3An8n-gcp-select-project-button.png?table=block&amp;id=37270f01-9634-801c-bd01-cdd052ef73c7&amp;t=37270f01-9634-801c-bd01-cdd052ef73c7&amp;width=321&amp;cache=v2" alt="Google Cloud Console 首頁，標示頂端「選取專案」按鈕" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Google Cloud Console 首頁，標示頂端「選取專案」按鈕</figcaption></div></figure><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37270f0196348033a7d1e08a5ada36d2"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A91938ced-c28a-4f8c-af7f-87aad17a2ef1%3An8n-gcp-create-project-name.png?table=block&amp;id=37270f01-9634-8033-a7d1-e08a5ada36d2&amp;t=37270f01-9634-8033-a7d1-e08a5ada36d2&amp;width=321&amp;cache=v2" alt="Google Cloud 新增專案視窗，專案名稱欄填入 n8n-001" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Google Cloud 新增專案視窗，專案名稱欄填入 n8n-001</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37270f01963480bea73bd6341b1a56e7" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-a98735484e7244bfbb6434f358b35372"><b>目的</b>：Google Cloud 用「專案」分裝你的東西。建一個專門給 n8n 用的專案，未來所有 n8n 相關設定集中在這裡。</div><ol start="1" class="notion-list notion-list-numbered notion-block-d5644af6a4934ac7880d5e3586eecaeb" style="list-style-type:decimal"><li>去 <a target="_blank" rel="noopener noreferrer" class="notion-link" href="http://console.cloud.google.com">console.cloud.google.com</a>，用你常用的 Google 帳號登入</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-09bf2c49a08e4ce2b9d1554db8a77c64" style="list-style-type:decimal"><li>第一次登入：選國家 Taiwan、勾同意條款、按<b>同意並繼續</b></li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-06f2f46b5f9a4e4ea90c3bed53dcb7ee" style="list-style-type:decimal"><li>畫面頂端中央點<b>「選取專案」</b>按鈕</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-a459fb8034d8497990ebf5e3dbf3dcee" style="list-style-type:decimal"><li>跳出視窗右上角點<b>新增專案</b></li></ol><ol start="5" class="notion-list notion-list-numbered notion-block-6cc667df53964241a8c018e32dfe8e36" style="list-style-type:decimal"><li>專案名稱填 <code class="notion-inline-code">n8n-001</code>（或你喜歡的名字），按<b>建立</b></li></ol><div class="notion-text notion-block-9b29a28fc3a249c1b038d39bf8f5596a">✅ <b>成功標誌</b>：畫面頂端顯示你取的專案名稱（如 <code class="notion-inline-code">n8n-001</code>）。</div></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-f7479a180a4e4a10895611b04b3d8538"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-cf702d1311e54ef98a88f6348e8fe15a">第一次用 Google Cloud 可能要綁信用卡。Drive、Gmail、Sheets 這三個 API 在免費額度內通常不產生費用。建議進 GCP 左側選單「帳單 → 預算與快訊」設一個 NT$0 的預算警示，一花到錢就會通知你。</div></div></div><div class="notion-callout notion-block-fa3cd06fcfd8494abe2634e8446e6ef5"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="⚠️">⚠️</span></div><div class="notion-callout-text"><div class="notion-text notion-block-a7d92b2ec458489db7865def8611f21f">建議用<b>個人 Gmail</b> 而不是學校或公司帳號。學校和公司帳號常被組織政策擋，會導致後面步驟過不了。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-ff91922858994beebb5dab08fa015f47" data-id="ff91922858994beebb5dab08fa015f47"><span><div id="ff91922858994beebb5dab08fa015f47" class="notion-header-anchor"></div><a class="notion-hash-link" href="#ff91922858994beebb5dab08fa015f47" title="步驟 2｜啟用你需要的 Google API"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 2｜啟用你需要的 Google API</span></span></h4><div class="notion-text notion-block-e945765c6cf04c8d8a85e970a8f21b34"><b>目的</b>：Google Cloud 預設什麼 API 都沒開。要用哪個服務，就要去找到那個 API 的開關按啟用。</div><div class="notion-text notion-block-8a3404ec7d5e4d2ba021323d005781c2">常用的 Google 服務對應 API：</div><table class="notion-simple-table notion-block-ed0228b1aea6497bbfd751f28df0bdcd"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-9e163a123f5b42af9fc27eb8dad28353"><td class="" style="width:120px"><div class="notion-simple-table-cell">你想在 n8n 用的服務</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">要啟用的 API 名稱</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">搜尋關鍵字</div></td></tr><tr class="notion-simple-table-row notion-block-e74f9601872e4801814f4e2d590568d4"><td class="" style="width:120px"><div class="notion-simple-table-cell">Google Drive（雲端硬碟）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Google Drive API</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><code class="notion-inline-code">drive</code></div></td></tr><tr class="notion-simple-table-row notion-block-908692b6dece46eeb0b1d57ea430771e"><td class="" style="width:120px"><div class="notion-simple-table-cell">Gmail（收發信）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Gmail API</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><code class="notion-inline-code">gmail</code></div></td></tr><tr class="notion-simple-table-row notion-block-719e0a90210a4a94b1bdaf44f2d0330b"><td class="" style="width:120px"><div class="notion-simple-table-cell">Google Sheets（試算表）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Google Sheets API</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><code class="notion-inline-code">sheets</code></div></td></tr><tr class="notion-simple-table-row notion-block-17d2e6a85700445688c4348f4d44ab71"><td class="" style="width:120px"><div class="notion-simple-table-cell">Google Calendar（日曆）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Google Calendar API</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><code class="notion-inline-code">calendar</code></div></td></tr></tbody></table><div class="notion-row notion-block-37270f01963480f388ebf45767c896d4"><div class="notion-column notion-block-37270f01963480ed94acdb629154db91" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37270f019634800385a1e5d0b12559a4"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Afaa225a9-6a65-411b-a740-06027667f30b%3An8n-gcp-project-search-icon.png?table=block&amp;id=37270f01-9634-8003-85a1-e5d0b12559a4&amp;t=37270f01-9634-8003-85a1-e5d0b12559a4&amp;width=321&amp;cache=v2" alt="專案建立完成，頂端顯示 n8n-001 與右上角搜尋放大鏡" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">專案建立完成，頂端顯示 n8n-001 與右上角搜尋放大鏡</figcaption></div></figure><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37270f01963480b7b08ccb9612995106"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A5fc13735-dec3-4f1f-a062-2d937f3a0699%3An8n-gcp-search-bar-expanded.png?table=block&amp;id=37270f01-9634-80b7-b08c-cb9612995106&amp;t=37270f01-9634-80b7-b08c-cb9612995106&amp;width=321&amp;cache=v2" alt="Google Cloud 頂端搜尋列展開，可輸入 API 名稱" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Google Cloud 頂端搜尋列展開，可輸入 API 名稱</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37270f01963480d084a4c4731abbce1a" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-dde4a220a3494c39a1a5cee3c06f526f">以 Drive 為例（其他服務同一個操作，只是換搜尋關鍵字）：</div><ol start="1" class="notion-list notion-list-numbered notion-block-2a0cbd6d91e9447ea12e6357fea82506" style="list-style-type:decimal"><li>頁面頂端右邊找<b>放大鏡圖示</b>（搜尋按鈕），點它</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-ac0131df1d5e47bc9b1d97ad50421b3c" style="list-style-type:decimal"><li>搜尋列輸入 <code class="notion-inline-code">drive</code></li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-0e0498e8f8984ff69b5b86f3920453c4" style="list-style-type:decimal"><li>結果第一筆是 <b>Google Drive API</b>（旁邊寫 Marketplace），點它</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-0436298d8ffb46c7a3f78461dd04c15c" style="list-style-type:decimal"><li>進到產品詳細資料頁，按<b>啟用</b></li></ol><ol start="5" class="notion-list notion-list-numbered notion-block-27d260c814b4418388eb76a102322afa" style="list-style-type:decimal"><li>重複以上動作，分別搜 <code class="notion-inline-code">gmail</code>、<code class="notion-inline-code">sheets</code>、<code class="notion-inline-code">calendar</code>，把你需要的 API 全部啟用</li></ol><div class="notion-text notion-block-4f56f9542f644d14829e09a414822008">✅ <b>成功標誌</b>：每個 API 按完啟用後，看到「已啟用 API」或進入該 API 管理頁面。</div></div><div class="notion-spacer"></div></div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37270f0196348086a8c4e8c6fe5abef1"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Ace42fb02-8f2a-4611-add9-de4994a0aacc%3An8n-gcp-search-drive-api-result.png?table=block&amp;id=37270f01-9634-8086-a8c4-e8c6fe5abef1&amp;t=37270f01-9634-8086-a8c4-e8c6fe5abef1&amp;width=703.9896240234375&amp;cache=v2" alt="搜尋 drive，第一筆結果為 Google Drive API" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">搜尋 drive，第一筆結果為 Google Drive API</figcaption></div></figure><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37270f01963480afa53fe280224d4893"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A5ec14727-60cf-44a4-b888-56c8e0a078a1%3An8n-gcp-enable-drive-api-button.png?table=block&amp;id=37270f01-9634-80af-a53f-e280224d4893&amp;t=37270f01-9634-80af-a53f-e280224d4893&amp;width=703.9896240234375&amp;cache=v2" alt="Google Drive API 產品詳細資料頁，標示「啟用」按鈕" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Google Drive API 產品詳細資料頁，標示「啟用」按鈕</figcaption></div></figure><div class="notion-callout notion-block-01930dd198a5401cb9d14f2f49b81faa"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-09b319400bdd40339c6c84bfd23c0496">啟用是一次性動作。同一個專案下，一個 API 啟用過就永遠是開的，不用重複操作。</div></div></div><hr class="notion-hr notion-block-955496dd717443748d86102b20abd558"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-d4fa94d5854f40f3b38a842038db2df7" data-id="d4fa94d5854f40f3b38a842038db2df7"><span><div id="d4fa94d5854f40f3b38a842038db2df7" class="notion-header-anchor"></div><a class="notion-hash-link" href="#d4fa94d5854f40f3b38a842038db2df7" title="五、PART 2：設 OAuth 同意畫面"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">五、PART 2：設 OAuth 同意畫面</span></span></h3><div class="notion-callout notion-block-a0900f4d6104489896435118aa5cb4bc"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="⚠️">⚠️</span></div><div class="notion-callout-text"><div class="notion-text notion-block-159168d6a9d34ec7bb86d9054cce7b5b">這段是 Google 強制的順序：<b>必須先設好同意畫面，才能建用戶端</b>。沒設就沒視窗可跳，整套 OAuth 走不通。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-e900f14f5abb432ca4345e433a0fbd0e" data-id="e900f14f5abb432ca4345e433a0fbd0e"><span><div id="e900f14f5abb432ca4345e433a0fbd0e" class="notion-header-anchor"></div><a class="notion-hash-link" href="#e900f14f5abb432ca4345e433a0fbd0e" title="步驟 1｜進到「OAuth 同意畫面」設定"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 1｜進到「OAuth 同意畫面」設定</span></span></h4><div class="notion-row notion-block-37370f01963480cab1c6d21429dff19a"><div class="notion-column notion-block-37370f019634808a8152d8c3e63d0a5e" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f019634805a80d2fe66f818d867"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A8f6a78a9-4182-4bd6-9dbb-d927d39013d0%3An8n-gcp-credentials-oauth-consent-menu.png?table=block&amp;id=37370f01-9634-805a-80d2-fe66f818d867&amp;t=37370f01-9634-805a-80d2-fe66f818d867&amp;width=1080&amp;cache=v2" alt="API 和服務憑證頁，左側選單標示「OAuth 同意畫面」" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">API 和服務憑證頁，左側選單標示「OAuth 同意畫面」</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37370f0196348063ae23c764df888473" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-ba5011a7ac79499fa2f54e6263c73213"><b>目的</b>：找到 OAuth 同意畫面設定的入口。</div><ol start="1" class="notion-list notion-list-numbered notion-block-7cd3f7835dd842cf807e189082864bc3" style="list-style-type:decimal"><li>左上角點漢堡選單（三條橫線），找 <b>API 和服務</b>，子選單點<b>憑證</b></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-33bcf5afe5794c6aa037fcb54b7ab2ce" style="list-style-type:decimal"><li>左側選單點<b>「OAuth 同意畫面」</b></li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-989f204b08d443e59b49fd0e399881ac" style="list-style-type:decimal"><li>第一次進去會出現「Google Auth Platform」歡迎畫面，按引導開始設定</li></ol><div class="notion-text notion-block-0052a33244a14262ac6d7d4ac8367630">✅ <b>成功標誌</b>：看到引導流程的第一頁（要你填應用程式資訊）。</div></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-e97a3a7892834dcfa1a74b75bfc3c462"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-0d8ac59825ef45a18906b1417948fcfb">2024 年底 Google 把這塊整理成「Google Auth Platform」獨立功能區，左側選單分成品牌、目標對象、用戶端等好幾頁。第一次進去 Google 會用引導流程帶你設好，跟著按就好。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-f84c293126ff420ab5551e3417d73083" data-id="f84c293126ff420ab5551e3417d73083"><span><div id="f84c293126ff420ab5551e3417d73083" class="notion-header-anchor"></div><a class="notion-hash-link" href="#f84c293126ff420ab5551e3417d73083" title="步驟 2｜填應用程式資訊 + 目標對象選「外部」"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 2｜填應用程式資訊 + 目標對象選「外部」</span></span></h4><div class="notion-row notion-block-37370f019634801bb3b8f34142744592"><div class="notion-column notion-block-37370f01963480949491dfc0eee486fe" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f01963480a29198e946b4bac5cc"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A652a7e36-ec44-41ee-b594-6d6e01364e2b%3An8n-gcp-oauth-audience-external.png?table=block&amp;id=37370f01-9634-80a2-9198-e946b4bac5cc&amp;t=37370f01-9634-80a2-9198-e946b4bac5cc&amp;width=1080&amp;cache=v2" alt="Google Auth Platform 目標對象設定，選擇「外部」" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Google Auth Platform 目標對象設定，選擇「外部」</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37370f019634802db1badf21da7b0c13" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-54266c0d2c03448b89a366ea99e26f2d"><b>目的</b>：告訴 Google 這個 App 叫什麼、誰能用。</div><ol start="1" class="notion-list notion-list-numbered notion-block-f70efa10a92c48b498a461cc10bea05d" style="list-style-type:decimal"><li>第一頁「應用程式資訊」：名稱填 <code class="notion-inline-code">n8n</code>，使用者支援電子郵件選你的 Gmail。按<b>下一步</b></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-eda2d1e3a7034ef5a430354823f1fadd" style="list-style-type:decimal"><li>第二頁「目標對象」：選<b>外部</b>（個人帳號只有這個選項）。按<b>下一步</b></li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-ef5a0167d3c4429b9b2003b07e23166f" style="list-style-type:decimal"><li>第三頁「聯絡資訊」：開發人員電子郵件填你的 Gmail。按<b>下一步</b></li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-8821913b5be64d26a900260eacbb8316" style="list-style-type:decimal"><li>最後一頁勾「我同意 Google API 服務條款」，按<b>建立</b></li></ol></div><div class="notion-spacer"></div></div><div class="notion-text notion-block-accfae7bd89249c8915cc28e09544b04">✅ <b>成功標誌</b>：跳回 Google Auth Platform 主畫面，左側出現「總覽 / 品牌 / 目標對象 / 用戶端」分頁。</div><div class="notion-callout notion-block-560c1cad15024c31a9216ee74b1217f9"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-7c4669e747274eb099970e72e3adacb7">「內部」要有付費 Google Workspace 帳號才能選，個人 Gmail 看不到這個選項。個人用一律選「外部」。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-7d948e4e08ee4679a9cb86b917ef72a0" data-id="7d948e4e08ee4679a9cb86b917ef72a0"><span><div id="7d948e4e08ee4679a9cb86b917ef72a0" class="notion-header-anchor"></div><a class="notion-hash-link" href="#7d948e4e08ee4679a9cb86b917ef72a0" title="步驟 3｜加測試使用者（不加會被擋）"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 3｜加測試使用者（不加會被擋）</span></span></h4><div class="notion-row notion-block-37370f019634804e926fc7df012b8d76"><div class="notion-column notion-block-37370f01963480caa0b5e15c87c26d7c" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f01963480c6872de2afc45c7eb3"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A14d48249-f7c2-46b9-929f-970e726aa9ce%3An8n-gcp-test-users-add-button.png?table=block&amp;id=37370f01-9634-80c6-872d-e2afc45c7eb3&amp;t=37370f01-9634-80c6-872d-e2afc45c7eb3&amp;width=1080&amp;cache=v2" alt="Google Auth Platform 目標對象頁，測試使用者區的 Add users 按鈕" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Google Auth Platform 目標對象頁，測試使用者區的 Add users 按鈕</figcaption></div></figure><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f0196348066a7bbca80e349a097"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A34bca238-9777-421b-8325-9c2675afb118%3An8n-gcp-test-user-email-input.png?table=block&amp;id=37370f01-9634-8066-a7bb-ca80e349a097&amp;t=37370f01-9634-8066-a7bb-ca80e349a097&amp;width=1080&amp;cache=v2" alt="新增測試使用者視窗，輸入 Gmail 帳號" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">新增測試使用者視窗，輸入 Gmail 帳號</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37370f01963480c7a287de2783d56885" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-4ba0258cc94e400ebc6f57764d761481"><b>目的</b>：剛建的 App 是「測試」狀態，只有列在「測試使用者」清單裡的帳號才能授權。你一定要把自己加進去。</div><ol start="1" class="notion-list notion-list-numbered notion-block-7b64400055f34316b3ab6c79f0d0d51d" style="list-style-type:decimal"><li>左側選單點<b>「目標對象」</b></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-19df48e4433842e9858a60a70ba571d5" style="list-style-type:decimal"><li>頁面捲到下面找「測試使用者」區，按 <b>+ Add users</b></li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-98ea04dfe5c546ea9b2f5299b176866e" style="list-style-type:decimal"><li>輸入你自己的 Gmail（就是你要被 n8n 代理存取的那個帳號）</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-a7bb12c78f6b458aa4170351c73275b6" style="list-style-type:decimal"><li>按<b>儲存</b></li></ol><div class="notion-text notion-block-a23c5466e94846f9a071ae9d8d989bcb">✅ <b>成功標誌</b>：你的 Gmail 出現在測試使用者清單中。</div></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-8811f5da76b24b6d91519eb564079456"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-68c34357f1e2405b9cf844bff9a0d24c">Testing 狀態有一個坑：<b>Google 會讓你的授權每 7 天自動過期</b>，n8n 的自動化會靜默斷線，你得回去重新按一次授權。</div><div class="notion-text notion-block-fbce2067bb44437cbee1f20727ee8846"><b>長期使用的解法</b>：回 Google Auth Platform 左側選單「發布應用程式」，按下去改成正式版（In Production）。個人自用通常不需通過 Google 審核，只是授權時會多一個「未驗證」警告畫面。（如果你的授權範圍涉及 Gmail 完整存取等敏感權限，Google 可能會要求額外驗證，一般 Drive + Sheets 不會。）<b>發布後回 n8n 把原本的憑證斷開再重新授權</b>（點憑證 → 斷開連線 → 重新 Sign in with Google），這樣拿到的新 Token 才不受 7 天限制。不用刪掉重建，同一組 Client ID 跟 Secret 繼續用就好。</div></div></div><hr class="notion-hr notion-block-e0e6344ad87845aa8e4f6116b85fa31e"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-8fae1aa1ad8a41cfbb7964564a3096fb" data-id="8fae1aa1ad8a41cfbb7964564a3096fb"><span><div id="8fae1aa1ad8a41cfbb7964564a3096fb" class="notion-header-anchor"></div><a class="notion-hash-link" href="#8fae1aa1ad8a41cfbb7964564a3096fb" title="六、PART 3：建立 OAuth 用戶端"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">六、PART 3：建立 OAuth 用戶端</span></span></h3><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-f1aea0a7fb4b4f6e92e0fff723bf80c1" data-id="f1aea0a7fb4b4f6e92e0fff723bf80c1"><span><div id="f1aea0a7fb4b4f6e92e0fff723bf80c1" class="notion-header-anchor"></div><a class="notion-hash-link" href="#f1aea0a7fb4b4f6e92e0fff723bf80c1" title="步驟 1｜按「建立 OAuth 用戶端」"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 1｜按「建立 OAuth 用戶端」</span></span></h4><div class="notion-row notion-block-37370f0196348039b16ce2a13617c424"><div class="notion-column notion-block-37370f019634806ab7a8f5555920b41c" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f019634808c9681c14d78e200f4"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A3cdb8367-9085-42fe-ae0e-34c172e3e6c0%3An8n-gcp-create-oauth-client-button.png?table=block&amp;id=37370f01-9634-808c-9681-c14d78e200f4&amp;t=37370f01-9634-808c-9681-c14d78e200f4&amp;width=1080&amp;cache=v2" alt="Google Auth Platform 總覽頁，標示「建立 OAuth 用戶端」按鈕" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Google Auth Platform 總覽頁，標示「建立 OAuth 用戶端」按鈕</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37370f01963480dfb170f205e5fd0317" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-fbd08972d6744c24a6493229ac57c221"><b>目的</b>：建用戶端就是建一張「應用程式身份證」，建好後會拿到 ID 跟 Secret 兩串字。</div><ol start="1" class="notion-list notion-list-numbered notion-block-9566d630d2dd40c0b4bf81551a4c6584" style="list-style-type:decimal"><li>Google Auth Platform 左側選單點<b>總覽</b></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-13bc8ca840b04805b894927679f82570" style="list-style-type:decimal"><li>頁面中央找到<b>「建立 OAuth 用戶端」</b>按鈕，點它</li></ol><div class="notion-text notion-block-45693ff6a30b49ff80996919739d4bb8">✅ <b>成功標誌</b>：跳出「建立 OAuth 用戶端 ID」表單頁面。</div></div><div class="notion-spacer"></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-46df7f798a0a44d3a948c26ec506b974" data-id="46df7f798a0a44d3a948c26ec506b974"><span><div id="46df7f798a0a44d3a948c26ec506b974" class="notion-header-anchor"></div><a class="notion-hash-link" href="#46df7f798a0a44d3a948c26ec506b974" title="步驟 2｜選「網頁應用程式」，名稱填 n8n"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 2｜選「網頁應用程式」，名稱填 n8n</span></span></h4><div class="notion-row notion-block-37370f019634806db8cde90e2681805c"><div class="notion-column notion-block-37370f01963480d5a392f181f50ae5b2" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f0196348095ba47ffde8c79dd5c"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A5c67a6db-bf09-4724-a2f3-1bb950be8d1b%3An8n-gcp-oauth-client-web-app-form.png?table=block&amp;id=37370f01-9634-8095-ba47-ffde8c79dd5c&amp;t=37370f01-9634-8095-ba47-ffde8c79dd5c&amp;width=1080&amp;cache=v2" alt="建立 OAuth 用戶端表單，應用程式類型選網頁應用程式、名稱填 n8n" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">建立 OAuth 用戶端表單，應用程式類型選網頁應用程式、名稱填 n8n</figcaption></div></figure><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f019634805f8468fb2b1db505b8"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A0be3f5b0-73b0-4ce0-aaa9-a96eca55d77f%3An8n-gcp-oauth-client-id-secret-created.png?table=block&amp;id=37370f01-9634-805f-8468-fb2b1db505b8&amp;t=37370f01-9634-805f-8468-fb2b1db505b8&amp;width=1080&amp;cache=v2" alt="OAuth 用戶端已建立彈窗，顯示用戶端 ID 與密鑰（已遮蔽）" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">OAuth 用戶端已建立彈窗，顯示用戶端 ID 與密鑰（已遮蔽）</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37370f01963480f9a1a5e60d688a51a0" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-ca8373c15bc84e4aaa6270df5e25d00b"><b>目的</b>：n8n 是跑在瀏覽器裡的網頁應用，授權完 Google 要把你導回 n8n 的網址，只有選「網頁應用程式」才支援這個機制。</div><ol start="1" class="notion-list notion-list-numbered notion-block-1e07a6f6fac24be78a70de43acf03e1f" style="list-style-type:decimal"><li>應用程式類型下拉選 <code class="notion-inline-code">網頁應用程式</code></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-0a9dd3d266ed405fb3810247ea4abe20" style="list-style-type:decimal"><li>名稱填 <code class="notion-inline-code">n8n</code></li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-70d275c2275d4314827182d42d6d068f" style="list-style-type:decimal"><li>「已授權的 JavaScript 來源」<b>留空</b></li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-b713f3b9c3224b42aaa8adf2af80d6ab" style="list-style-type:decimal"><li>「已授權的重新導向 URI」<b>先留空</b>（下一段從 n8n 拿）</li></ol><ol start="5" class="notion-list notion-list-numbered notion-block-f806c971a1bc4236859297f882ee773b" style="list-style-type:decimal"><li>按<b>建立</b></li></ol><ol start="6" class="notion-list notion-list-numbered notion-block-815f94da31bf413e98a034f5ea543922" style="list-style-type:decimal"><li>跳出視窗顯示<b>用戶端 ID</b> 跟<b>用戶端密鑰</b>，<b>先別關視窗</b></li></ol><div class="notion-text notion-block-1a179a7fbd4046b691b633f84a54c73f">✅ <b>成功標誌</b>：看到「OAuth 用戶端已建立」彈窗，裡面有兩串長字串。</div></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-feefa0b6902d4a60b28d9795aa134b2e"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="⚠️">⚠️</span></div><div class="notion-callout-text"><div class="notion-text notion-block-efc788e23cc64c39be6d09dd14c2c442">「重新導向 URI」現在留空是正常的。那個網址要從 n8n 拿，接下來 PART 4 教你怎麼拿。</div></div></div><hr class="notion-hr notion-block-f328997b73374a1a929387474f71ea4d"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-2586d398f8cf4e1ea0350bdbf7a9d166" data-id="2586d398f8cf4e1ea0350bdbf7a9d166"><span><div id="2586d398f8cf4e1ea0350bdbf7a9d166" class="notion-header-anchor"></div><a class="notion-hash-link" href="#2586d398f8cf4e1ea0350bdbf7a9d166" title="七、PART 4：在 n8n 跟 GCP 之間來回接線"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">七、PART 4：在 n8n 跟 GCP 之間來回接線</span></span></h3><div class="notion-text notion-block-c699fab8891a43669b88c2314e9c5e5e">這段是幫 n8n 跟 Google <b>互相認識、牽線</b>：n8n 給 GCP 一個網址（讓 Google 知道授權完把人送回哪），GCP 給 n8n 兩串字（ID + Secret，讓 n8n 證明自己是合法的）。雙方都填完對方的資料，才會通。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-277f501552f04953b29a51cb1c3d3b88" data-id="277f501552f04953b29a51cb1c3d3b88"><span><div id="277f501552f04953b29a51cb1c3d3b88" class="notion-header-anchor"></div><a class="notion-hash-link" href="#277f501552f04953b29a51cb1c3d3b88" title="步驟 1｜在 n8n 建 Google Drive OAuth2 憑證，拿 Redirect URL"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 1｜在 n8n 建 Google Drive OAuth2 憑證，拿 Redirect URL</span></span></h4><div class="notion-row notion-block-37370f019634802bbe63eccce89967ee"><div class="notion-column notion-block-37370f01963480d98b7be2094dc7d9c5" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f0196348077a38fe0a3e57e6874"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A1f505168-b9be-4ce9-be3f-49e4f3a0fedd%3An8n-create-credential-button.png?table=block&amp;id=37370f01-9634-8077-a38f-e0a3e57e6874&amp;t=37370f01-9634-8077-a38f-e0a3e57e6874&amp;width=1080&amp;cache=v2" alt="n8n Credentials 頁，標示右上角 Create credential 按鈕" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">n8n Credentials 頁，標示右上角 Create credential 按鈕</figcaption></div></figure><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f019634806bad50c25fcb2cd552"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Abab4033e-ee8c-4310-b7cb-f909ae3765a8%3An8n-search-google-drive-oauth2-api.png?table=block&amp;id=37370f01-9634-806b-ad50-c25fcb2cd552&amp;t=37370f01-9634-806b-ad50-c25fcb2cd552&amp;width=1080&amp;cache=v2" alt="n8n 新增憑證視窗，搜尋 drive 並選取 Google Drive OAuth2 API" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">n8n 新增憑證視窗，搜尋 drive 並選取 Google Drive OAuth2 API</figcaption></div></figure><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f01963480118e98c9ec26717ed7"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A6c472e06-33f6-4185-9672-4758d65f04a1%3An8n-credential-redirect-url-client-fields.png?table=block&amp;id=37370f01-9634-8011-8e98-c9ec26717ed7&amp;t=37370f01-9634-8011-8e98-c9ec26717ed7&amp;width=1080&amp;cache=v2" alt="n8n 憑證頁，標出名稱、OAuth Redirect URL、Client ID、Client Secret 四個欄位" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">n8n 憑證頁，標出名稱、OAuth Redirect URL、Client ID、Client Secret 四個欄位</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37370f019634807791a9d77ee7806f9d" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-b8d862b297bc4d96a3de726f1fd7e11a"><b>目的</b>：先在 n8n 這邊開一個憑證頁面，拿到它自動產生的 Redirect URL。</div><ol start="1" class="notion-list notion-list-numbered notion-block-aee75a2234ec465d82e4b5f0ef838f2b" style="list-style-type:decimal"><li>打開 n8n（http://localhost:5678）</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-68e4161ed8c14623b87fb983a720d3bd" style="list-style-type:decimal"><li>左側選單點 <b>Credentials</b>，右上角按紅色 <b>Create credential</b></li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-32c040c2e3564c33870c03741a5d7714" style="list-style-type:decimal"><li>搜尋列輸入 <code class="notion-inline-code">drive</code>，點 <b>Google Drive OAuth2 API</b></li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-1d4646b078864ca6aeaf9646faa6439c" style="list-style-type:decimal"><li>上面幫憑證命名（例如 <code class="notion-inline-code">我的 Google Drive</code>）</li></ol><ol start="5" class="notion-list notion-list-numbered notion-block-86e8c4a9f9294744aaf9d0225dba23f9" style="list-style-type:decimal"><li>看到欄位 <b>OAuth Redirect URL</b>，右邊有複製按鈕，<b>複製這個 URL</b></li></ol><div class="notion-text notion-block-daa95eb3577b42aebd8a733571b0b9b2">✅ <b>成功標誌</b>：剪貼簿裡有一串像 <code class="notion-inline-code">http://localhost:5678/rest/oauth2-credential/callback</code> 的網址。</div><div class="notion-callout notion-block-24ab62161cb642d785799d34a07f8342"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="⚠️">⚠️</span></div><div class="notion-callout-text"><div class="notion-text notion-block-2548b72d5184471cbb0adcbee6938f61">n8n 視窗先別關。等一下還要回來貼 ID 跟 Secret。直接開新分頁去 GCP。</div></div></div><div class="notion-blank notion-block-37370f01963480d88b25dfa0182689fa"> </div></div><div class="notion-spacer"></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-aea1f23ed5d149a8a3b817947dc04331" data-id="aea1f23ed5d149a8a3b817947dc04331"><span><div id="aea1f23ed5d149a8a3b817947dc04331" class="notion-header-anchor"></div><a class="notion-hash-link" href="#aea1f23ed5d149a8a3b817947dc04331" title="步驟 2｜回 GCP，把 Redirect URL 貼到用戶端"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 2｜回 GCP，把 Redirect URL 貼到用戶端</span></span></h4><div class="notion-row notion-block-37370f0196348063aff9fdc19af5436a"><div class="notion-column notion-block-37370f01963480d88e5fe6c83030a54d" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f01963480afae51ef108dc444f1"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A684029f0-c88b-4b56-ba6e-c1318d38ae4e%3An8n-gcp-paste-redirect-uri.png?table=block&amp;id=37370f01-9634-80af-ae51-ef108dc444f1&amp;t=37370f01-9634-80af-ae51-ef108dc444f1&amp;width=1080&amp;cache=v2" alt="GCP 編輯用戶端頁，將 n8n 的 Redirect URL 貼到「已授權的重新導向 URI」" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">GCP 編輯用戶端頁，將 n8n 的 Redirect URL 貼到「已授權的重新導向 URI」</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37370f01963480f1874dedaf982ef3d5" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-bc6362f2a18743b5913ebd05c18243e4"><b>目的</b>：Google 收到這個 URL 後，才知道授權完成要把使用者送回 n8n。沒填會報 <code class="notion-inline-code">redirect_uri_mismatch</code> 錯誤。</div><ol start="1" class="notion-list notion-list-numbered notion-block-4fb7595d96084b4bbb100a6aeff5675e" style="list-style-type:decimal"><li>切回 Google Auth Platform，左側點<b>用戶端</b></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-92bbefb15f3a4bd5827ac673c5709b58" style="list-style-type:decimal"><li>點剛建的 <b>n8n</b> 用戶端名稱進去編輯</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-5cf60df7307b40dda5600f42a1cbf5fa" style="list-style-type:decimal"><li>找到「已授權的重新導向 URI」區塊，按 <b>+ 新增 URI</b></li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-c558e4ebb4a64efca16d24764acc48d3" style="list-style-type:decimal"><li>把從 n8n 複製的網址<b>貼進去</b></li></ol><ol start="5" class="notion-list notion-list-numbered notion-block-698b69e8016843338ed04dbfa22971d7" style="list-style-type:decimal"><li>按<b>儲存</b></li></ol><div class="notion-text notion-block-94d239384f204e36aa1681bfb44007e0">✅ <b>成功標誌</b>：URI 欄位顯示你貼的 localhost 網址，頁面沒有報錯。</div></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-adb26a2f193a49339b399cba9dac7de9"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-a7c8f4da904949149698040dc889eb14">同一個頁面右上角可以看到用戶端 ID 跟用戶端密鑰，下一步要複製這兩串。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-dd1cb6f299434f4d9f5a9457617b3bd6" data-id="dd1cb6f299434f4d9f5a9457617b3bd6"><span><div id="dd1cb6f299434f4d9f5a9457617b3bd6" class="notion-header-anchor"></div><a class="notion-hash-link" href="#dd1cb6f299434f4d9f5a9457617b3bd6" title="步驟 3｜回 n8n，貼上用戶端 ID 跟密鑰"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 3｜回 n8n，貼上用戶端 ID 跟密鑰</span></span></h4><div class="notion-row notion-block-37370f0196348030baa9cdf6ac1609a3"><div class="notion-column notion-block-37370f0196348078babcd1b4ac9ffda3" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f0196348014bc62e9b00bcc4fd8"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A6c18b7d7-8278-49d3-b846-94f9a7b6bd4b%3An8n-credential-redirect-url-client-fields.png?table=block&amp;id=37370f01-9634-8014-bc62-e9b00bcc4fd8&amp;t=37370f01-9634-8014-bc62-e9b00bcc4fd8&amp;width=1080&amp;cache=v2" alt="圖中 Client ID / Client Secret 欄位就是貼這兩串的位置（不需另外拖一張）" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">圖中 Client ID / Client Secret 欄位就是貼這兩串的位置（不需另外拖一張）</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37370f019634807a8521c4f3205dea53" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-e7b6eb0936114b379dffc6856600fd9c"><b>目的</b>：用戶端 ID 是 n8n 的「身份證號碼」，密鑰是「密碼」。Google 認得這兩串，才把授權當合法。</div><ol start="1" class="notion-list notion-list-numbered notion-block-5d0fac11928b4909949b8a4d4f9abd14" style="list-style-type:decimal"><li>從 GCP 複製<b>用戶端 ID</b>，貼到 n8n 的 <code class="notion-inline-code">Client ID</code> 欄位</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-448008df606f4ddf9d71c6269668d1db" style="list-style-type:decimal"><li>從 GCP 複製<b>用戶端密鑰</b>，貼到 n8n 的 <code class="notion-inline-code">Client Secret</code> 欄位</li></ol><div class="notion-text notion-block-55c607cdc84849e294fbdb103b73475c">✅ <b>成功標誌</b>：n8n 憑證頁面三個欄位都有值（Redirect URL 是自動的、ID 跟 Secret 是你貼的）。</div></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-6d9cc7f05b62467385356033b7c6041a"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="⚠️">⚠️</span></div><div class="notion-callout-text"><div class="notion-text notion-block-aca18c7ee2a44817a5455ec1e1fc4ae2">用戶端密鑰跟密碼一樣，不要外流、不要 push 到 GitHub。萬一外流就回 GCP 重新產生。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-f97ecfdd20994a848c8d0d3f947c3369" data-id="f97ecfdd20994a848c8d0d3f947c3369"><span><div id="f97ecfdd20994a848c8d0d3f947c3369" class="notion-header-anchor"></div><a class="notion-hash-link" href="#f97ecfdd20994a848c8d0d3f947c3369" title="步驟 4｜按授權，看到 Connected 就成功"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 4｜按授權，看到 Connected 就成功</span></span></h4><div class="notion-text notion-block-1155af04d04f414fb405f8fe83645211"><b>目的</b>：所有資料填好後，按授權讓 Google 跳出同意視窗。按同意，n8n 才真正拿到操作權限。</div><div class="notion-row notion-block-37370f01963480a58976f555514dc1cf"><div class="notion-column notion-block-37370f0196348073a541f8594c12ae29" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37370f019634809b99a7c3396d622430"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A1bb3c52d-a1d3-4025-8359-d4e5ed80a2ef%3An8n-google-oauth-sign-in-select-all.png?table=block&amp;id=37370f01-9634-809b-99a7-c3396d622430&amp;t=37370f01-9634-809b-99a7-c3396d622430&amp;width=1080&amp;cache=v2" alt="n8n 按 Sign in with Google 後跳出 Google 授權視窗，勾選全選" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">n8n 按 Sign in with Google 後跳出 Google 授權視窗，勾選全選</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37370f01963480d193c9fcc9a79b5555" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><ol start="1" class="notion-list notion-list-numbered notion-block-bf5e6309b64d484b8cab52c21cf3bada" style="list-style-type:decimal"><li>在 n8n 憑證頁面按 <b>Sign in with Google</b></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-37370f019634808f8328ceb2e74cb717" style="list-style-type:decimal"><li>選你在「測試使用者」加的那個 Google 帳號</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-37370f019634802fa10dda86c31550e0" style="list-style-type:decimal"><li>看到「Google 尚未驗證這個應用程式」警告，按<b>進階</b>，再按<b>前往 n8n（不安全）</b></li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-37370f01963480bdabccff9bf4893388" style="list-style-type:decimal"><li>看到權限範圍清單，<b>測試階段先勾全選</b>，按<b>繼續</b></li></ol><ol start="5" class="notion-list notion-list-numbered notion-block-37370f019634800fbbddeb0d1953a466" style="list-style-type:decimal"><li>視窗關閉，回到 n8n。憑證標題出現綠色 <b>Connected</b> 字樣</li></ol><ol start="6" class="notion-list notion-list-numbered notion-block-37370f01963480138524e0540e661cf6" style="list-style-type:decimal"><li>按 <b>Save</b> 儲存</li></ol><div class="notion-text notion-block-37370f01963480d583c9e0d9fe691112">✅ <b>成功標誌</b>：綠色 Connected 字樣出現。</div></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-bf3aaeb421f74da7ab498ee013f0e5be"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="⚠️">⚠️</span></div><div class="notion-callout-text"><div class="notion-text notion-block-52f87dca02f7459d92bb512f38fc7f01"><b>「未驗證應用程式」警告是正常的。</b> 因為這是你自己的 App，不會通過 Google 正式審查。個人用按進階繼續就好。</div></div></div><div class="notion-callout notion-block-57bad6987d644ab084f85dc7bfd43d82"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-4e2019c095ac40ac895813fde0dee3f3"><b>真接通驗收（30 秒）：</b> 別只看到 Connected 就跑掉。馬上做一次小測試：新建一個 workflow → 拖一個 Google Drive 節點 → Credential 欄選你剛建的憑證 → Operation 選 Search → 按 Execute step。看到回傳你 Drive 裡的檔案列表，才算真接通。如果報 <code class="notion-inline-code">insufficient permission</code>，回步驟 4 重做授權，記得勾全選。</div></div></div><hr class="notion-hr notion-block-c4afe2fa3a8445c68b87fd24d9124a18"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-2be06fa6aae441d2ac29f75904a2aff5" data-id="2be06fa6aae441d2ac29f75904a2aff5"><span><div id="2be06fa6aae441d2ac29f75904a2aff5" class="notion-header-anchor"></div><a class="notion-hash-link" href="#2be06fa6aae441d2ac29f75904a2aff5" title="八、日後加其他 Google 服務"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">八、日後加其他 Google 服務</span></span></h3><div class="notion-text notion-block-79bf73243d46434b9bfc304041eda5fc">Drive 通了之後，想加 Gmail、Sheets、Calendar 只做兩件事：</div><ol start="1" class="notion-list notion-list-numbered notion-block-c1ab95fb522b41b6a5598541a5bc798a" style="list-style-type:decimal"><li><b>回 PART 1 步驟 2</b>，啟用對應的 API（搜 <code class="notion-inline-code">gmail</code> / <code class="notion-inline-code">sheets</code> / <code class="notion-inline-code">calendar</code>）</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-475e066e3af543d1a6f59f39329ad737" style="list-style-type:decimal"><li><b>重複 PART 4 步驟 1</b>，在 n8n 建對應的憑證（Gmail OAuth2 API / Google Sheets OAuth2 API 等），<b>用同一組 GCP 用戶端 ID 跟密鑰</b></li></ol><div class="notion-text notion-block-36324a4036c04bf589da34878ae4ac9c">Redirect URL 都一樣，不用再回 GCP 改。一組用戶端 ID + Secret 可以給所有 Google 服務共用。</div><hr class="notion-hr notion-block-d68d8bf0472d498eb56551b2f8a606f9"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-ca751853e02747d8aec5b1156edafd3f" data-id="ca751853e02747d8aec5b1156edafd3f"><span><div id="ca751853e02747d8aec5b1156edafd3f" class="notion-header-anchor"></div><a class="notion-hash-link" href="#ca751853e02747d8aec5b1156edafd3f" title="安全守則"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">安全守則</span></span></h3><div class="notion-callout notion-block-3084b4ade8ec479da2f0b295f9b76f08"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="⚠️">⚠️</span></div><div class="notion-callout-text"><div class="notion-text notion-block-662c8cef40974a8ab0c07ec33f21b64c">OAuth Client Secret 跟密碼一樣重要。外流的話別人可以冒充你的 App 騙別人授權。</div></div></div><ul class="notion-list notion-list-disc notion-block-22feeec0d0a346e3a37d62292795d122"><li><b>Client Secret 不要外流。</b> 發現外流立刻去 GCP 把用戶端刪掉，重建一個</li></ul><ul class="notion-list notion-list-disc notion-block-5fcd9823474f4e39868603b2a815fac4"><li><b>n8n 資料夾不要放到公開的地方。</b> 你的憑證存在 n8n 資料夾裡（如 <code class="notion-inline-code">C:\n8n</code>），不要把這個資料夾分享給別人或上傳到任何地方</li></ul><ul class="notion-list notion-list-disc notion-block-2b3967f91bef48e3a39129908eed392e"><li><b>建議發布成正式版。</b> 前面有講，Testing 狀態 7 天會斷線。發布後不需要 Google 審核，個人用直接按發布就好</li></ul><ul class="notion-list notion-list-disc notion-block-808d6543c8604a48b76adfafd729ff4f"><li><b>授權範圍只給 workflow 真的有用到的。</b> 用 n8n 做自動化，讀寫權限是正常需求。但如果某條 workflow 只讀不寫，就只勾讀取相關的範圍</li></ul><ul class="notion-list notion-list-disc notion-block-c164bceea86140b7bd8b1cd3216d05ed"><li><b>定期檢查授權。</b> Google 帳號「安全性」頁面有「具有帳戶存取權的第三方應用程式」，不用了的 App 撤銷授權</li></ul><hr class="notion-hr notion-block-d815804c235c469a86b813812a9b8d28"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-bc78b4572b9448e5be9e3f4f800456bb" data-id="bc78b4572b9448e5be9e3f4f800456bb"><span><div id="bc78b4572b9448e5be9e3f4f800456bb" class="notion-header-anchor"></div><a class="notion-hash-link" href="#bc78b4572b9448e5be9e3f4f800456bb" title="搞定，開始自動化吧"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">搞定，開始自動化吧</span></span></h3><div class="notion-text notion-block-2bba3a1eac904408a3d75fd90bf33028">恭喜！Google 家族的服務授權拿到手了囉！</div><div class="notion-text notion-block-7467da77c8ed4ebcba1177faeea59958">回 n8n 拖任何 Google 節點（Drive、Gmail、Sheets、Calendar），Credential 欄選你剛建好的那組憑證，就能直接操作。</div><div class="notion-text notion-block-7536231f50f1481fa8ac1c58986ce0c2">下次想多接一個 Google 服務，只要兩步：啟用那個 API，再到 n8n 建一組對應的憑證，同一把鑰匙直接開門。</div><div class="notion-text notion-block-016952e614e948b3939667f9a357dd78">授權搞定，可以動手做你的第一條自動化流程了！</div><div class="notion-blank notion-block-37370f01963480d381afdc862148d9f9"> </div></main></div>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[自己養機器人不用錢！地端部署 n8n × Docker 15 分鐘上手]]></title>
            <link>https://gyozalab.com/docker-n8n-guide</link>
            <guid>https://gyozalab.com/docker-n8n-guide</guid>
            <pubDate>Sat, 30 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[養一隻不用月費的自動化機器人在電腦裡！Windows × Docker × n8n 完整圖解，15 分鐘從零上手，資料留在自家硬碟。]]></description>
            <content:encoded><![CDATA[<div id="notion-article" class="mx-auto overflow-hidden "><main class="notion light-mode notion-page notion-block-37070f01963480a1b006db057b5b599c"><div class="notion-viewport"></div><div class="notion-collection-page-properties"></div><div class="notion-callout notion-brown_background_co notion-block-37670f01963480549479f37365326cb7"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="🎯">🎯</span></div><div class="notion-callout-text"><div class="notion-text notion-block-37670f01963480508c5cdccbbc6d53c1">這篇是在教完全沒程式基礎的人，用 Docker 在 Windows 電腦上本機部署 n8n。重點是免費、資料留在自己硬碟、適合個人自動化；但電腦關機就會停止，也不能像雲端一樣 24 小時運作。跟著步驟裝 Docker、更新 WSL、下載官方 n8n、設定 port 與資料夾，就能用 <code class="notion-inline-code">localhost:5678</code> 開始做自己的自動化工作流。</div></div></div><div class="notion-text notion-block-fddf887feb154e9f8dd4ef8174c89ffe">n8n 是一套開源的自動化工具。</div><div class="notion-text notion-block-731fbd24faf84607ba671edd99da7a92">「收到 Email 就自動存進 Google Sheet」「有人填表單就發 LINE 通知」，這類每天在做的重複動作，設定一次就不用再手動處理。n8n 跑起來之後，下一步通常是串接 Google 服務，相關的 <a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://gyozalab.com/n8n-google-oauth-setup">OAuth 授權設定</a>可以一起看。</div><div class="notion-text notion-block-bd2abbb6bfc445eeaddc9ed0be922e54">重點是：<b>裝在自己電腦上，完全免費。</b></div><div class="notion-text notion-block-8a10b24444fc46058c4adc106345baf2">這篇教你用 Docker 在 15 分鐘內把 n8n 跑起來。全程圖解、指令都能複製貼上，不需要任何程式基礎。Windows 10／11 都適用。</div><hr class="notion-hr notion-block-374b657dc46248aca8f8ed9af53f45cf"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-26f779d867e94260b70ecc5cdf981e63" data-id="26f779d867e94260b70ecc5cdf981e63"><span><div id="26f779d867e94260b70ecc5cdf981e63" class="notion-header-anchor"></div><a class="notion-hash-link" href="#26f779d867e94260b70ecc5cdf981e63" title="一、裝在自己電腦上，好處和限制"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">一、裝在自己電腦上，好處和限制</span></span></h3><div class="notion-text notion-block-e5ecd995beaa4e5582e55b3a193ee8f1"><b>好處：</b></div><ul class="notion-list notion-list-disc notion-block-0687e97f5f62495d96b701d9c80a215d"><li>完全免費，不用月租、不用綁信用卡</li></ul><ul class="notion-list notion-list-disc notion-block-b1a58f8e0c3b4b899f010fb54717009e"><li>資料全留在自己硬碟，不經過任何第三方伺服器</li></ul><ul class="notion-list notion-list-disc notion-block-cee1c4303ee54db99239e6f42d566ccb"><li>本機直接跑，速度快、幾乎沒延遲</li></ul><div class="notion-text notion-block-86baf143f3564e23aba6b3d1289258e4"><b>限制：</b></div><ul class="notion-list notion-list-disc notion-block-db3206b76a7b4091aba8846c77fb65ea"><li>電腦關機 n8n 就停，不像雲端 24 小時運轉</li></ul><ul class="notion-list notion-list-disc notion-block-7eb4c47618b04a1183e8247990b39fa2"><li>只有這台電腦能開，手機或別台電腦連不進來</li></ul><ul class="notion-list notion-list-disc notion-block-66277812bac34158b8c65c48864217e7"><li>更新要自己動手（但只要三步，後面會教）</li></ul><div class="notion-text notion-block-0020455a421d458c99195877adef6591">大多數個人自動化場景（手動觸發、上班時間跑就好），地端完全夠用。如果你需要 24 小時不間斷運行，可以另外研究雲端部署方案。</div><hr class="notion-hr notion-block-03a3996245a842f5acc00426aab4f219"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-353fc87a7b22423e824399c1ba200c05" data-id="353fc87a7b22423e824399c1ba200c05"><span><div id="353fc87a7b22423e824399c1ba200c05" class="notion-header-anchor"></div><a class="notion-hash-link" href="#353fc87a7b22423e824399c1ba200c05" title="二、先搞懂三個詞"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">二、先搞懂三個詞</span></span></h3><table class="notion-simple-table notion-block-5e1a060ce7f64ae0a5435c211d12647c"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-77c441f3373a40679cd490752ba648c8"><td class="notion-simple-table-header-cell" style="width:120px"><div class="notion-simple-table-cell">名詞</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>n8n</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>Docker</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>WSL</b></div></td></tr><tr class="notion-simple-table-row notion-block-869f37ae30c44e94b74ae0cada023ed0"><td class="notion-simple-table-header-cell" style="width:120px"><div class="notion-simple-table-cell">白話解釋</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">自動化工具，把重複的事變自動執行。例如「收到信就存進 Google Sheet」「IG 有人留言就通知 LINE」。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">程式專用的「便當盒」，把程式跟它需要的東西裝在一個隔離盒子裡，不會弄亂你電腦的設定。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Windows 裡的 Linux 子系統，Docker 運作需要的「廚房」基礎設施。</div></td></tr></tbody></table><hr class="notion-hr notion-block-30bf94a7c92a492fad27a8daef7be910"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-9148b51e0d364b5dbab2bc08ff497c99" data-id="9148b51e0d364b5dbab2bc08ff497c99"><span><div id="9148b51e0d364b5dbab2bc08ff497c99" class="notion-header-anchor"></div><a class="notion-hash-link" href="#9148b51e0d364b5dbab2bc08ff497c99" title="三、安裝總覽"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">三、安裝總覽</span></span></h3><div class="notion-text notion-block-3e678a2b49a140be84ecfa733a6d4c54">整個流程只有兩大段。裝過一次之後，日常開 n8n 只要點兩下：</div><table class="notion-simple-table notion-block-3847e853b23643869c6fcd52e460cdcf"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-1f6cd5ac5c814e24b22125ef72fc7796"><td class="" style="width:120px"><div class="notion-simple-table-cell">階段</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">做什麼</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">花多久</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">只做一次？</div></td></tr><tr class="notion-simple-table-row notion-block-5b85a334d7454cc3b5cfe14557dd3b4c"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>1、安裝 Docker Desktop</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">下載 Docker + 更新 WSL</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">5～10 分鐘</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">✅ 一次</div></td></tr><tr class="notion-simple-table-row notion-block-fb7679999c754c38afdce99168518509"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>2、用 Docker 跑起 n8n</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">下載 n8n 映像檔並啟動容器</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">3～5 分鐘</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">✅ 一次</div></td></tr><tr class="notion-simple-table-row notion-block-48021f0d3dd04a13a8d3c2ef2b263d63"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>3、日後使用</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">打開 Docker → 點 Containers → 點啟動</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">30 秒</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">🔁 每次</div></td></tr></tbody></table><hr class="notion-hr notion-block-4b582783f98e43dd82a3eabe705ad90a"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-9ed2130e617c415cb8f2e1c95b39322f" data-id="9ed2130e617c415cb8f2e1c95b39322f"><span><div id="9ed2130e617c415cb8f2e1c95b39322f" class="notion-header-anchor"></div><a class="notion-hash-link" href="#9ed2130e617c415cb8f2e1c95b39322f" title="四、安裝 Docker Desktop"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">四、安裝 Docker Desktop</span></span></h3><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-ad98db464c7d40b9afb4cfdb0a50a9cd" data-id="ad98db464c7d40b9afb4cfdb0a50a9cd"><span><div id="ad98db464c7d40b9afb4cfdb0a50a9cd" class="notion-header-anchor"></div><a class="notion-hash-link" href="#ad98db464c7d40b9afb4cfdb0a50a9cd" title="步驟 1｜下載 Docker Desktop"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 1｜下載 Docker Desktop</span></span></h4><div class="notion-row notion-block-37070f0196348019b42ada327eb62459"><div class="notion-column notion-block-37070f01963480b49239e0b70a441f7e" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f019634802a8d5cc67a8b075dd5"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:320.9765625px;max-width:100%;flex-direction:column"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Ae4012cf6-bdae-46b4-bf26-1a7381ce7b21%3Adocker-desktop-download-version.png?table=block&amp;id=37070f01-9634-802a-8d5c-c67a8b075dd5&amp;t=37070f01-9634-802a-8d5c-c67a8b075dd5&amp;width=320.9765625&amp;cache=v2" alt="Docker Desktop 下載頁面展開版本選單，顯示 Mac Apple Silicon、Mac Intel Chip、Windows AMD64、Windows ARM64 與 Linux 下載選項，供使用者依電腦系統選擇正確安裝檔。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Docker Desktop 下載頁面展開版本選單，顯示 Mac Apple Silicon、Mac Intel Chip、Windows AMD64、Windows ARM64 與 Linux 下載選項，供使用者依電腦系統選擇正確安裝檔。</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37070f019634802e821be3412ee84cd9" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-blank notion-block-c80e4dfa7a9b4ed380e6e70361acd761"> </div><div class="notion-text notion-block-c1baaf63a2b54ed694b4fa5ed8d087cb"><b>目的</b>：拿到「便當盒」管理工具。</div><ol start="1" class="notion-list notion-list-numbered notion-block-c40f19aed08c4c06bb50a50da2b4d33d" style="list-style-type:decimal"><li>打開瀏覽器，進入 <a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://www.docker.com/products/docker-desktop/">Docker 官網</a></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-a3df14af09ca468f92bb36d6122dbd71" style="list-style-type:decimal"><li>找 <b>Windows</b> 區塊，點 <b>Windows AMD64</b> 按鈕下載</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-c69c9ee43c634464a674c6cc10b76783" style="list-style-type:decimal"><li>下載到的檔案叫 <code class="notion-inline-code">Docker Desktop Installer.exe</code></li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-3398f5187bdc41048051e24c417f5752" style="list-style-type:decimal"><li>雙擊安裝，過程中會看到一個勾選畫面</li></ol><ol start="5" class="notion-list notion-list-numbered notion-block-37070f0196348051b459c21fea57ec83" style="list-style-type:decimal"><li>維持預設勾選「<b>Use WSL 2 instead of Hyper-V</b>」，按 OK。Windows 家用版只支援 WSL 2，選錯會裝不起來。其餘全部按「下一步」。</li></ol><ol start="6" class="notion-list notion-list-numbered notion-block-25dc7b6a079e448c8ca820b16c0e3c93" style="list-style-type:decimal"><li>裝完<b>重新開機</b></li></ol></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-370b5a1b72da44f79ac005b51e35fe08"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-d5daf6042f28477f806ddfdb3a7ba08e">大部分 Windows 電腦都是 AMD64。只有特殊的新款 ARM 筆電（如 Surface Pro X）才要選 ARM 版。不確定就選 AMD64。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-40fae77ea9fe47e0a72eb38aa6eb8836" data-id="40fae77ea9fe47e0a72eb38aa6eb8836"><span><div id="40fae77ea9fe47e0a72eb38aa6eb8836" class="notion-header-anchor"></div><a class="notion-hash-link" href="#40fae77ea9fe47e0a72eb38aa6eb8836" title="步驟 2｜安裝開啟後跳出「WSL needs updating」"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 2｜安裝開啟後跳出「WSL needs updating」</span></span></h4><div class="notion-row notion-block-37070f019634808eaa71c6a3209c9d50"><div class="notion-column notion-block-37070f01963480bf9d1afa4847e7a633" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f01963480f79fbffb50f1c7b6bf"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A01dc2a13-d449-4740-bcbb-d05c37c7448d%3Astep-wsl-update.png?table=block&amp;id=37070f01-9634-80f7-9fbf-fb50f1c7b6bf&amp;t=37070f01-9634-80f7-9fbf-fb50f1c7b6bf&amp;width=691.9896240234375&amp;cache=v2" alt="Docker 跳出 WSL needs updating 提示視窗，畫面中央有 wsl --update 指令" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Docker 跳出 WSL needs updating 提示視窗，畫面中央有 wsl --update 指令</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37070f01963480d4bdf8cf501537baa9" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-5ea9e9bca7734b14aa2589192568ef69"><b>目的</b>：接下來要更新 WSL 這個「廚房」環境。</div><ol start="1" class="notion-list notion-list-numbered notion-block-4f268805df824789908b20b055ddead6" style="list-style-type:decimal"><li>從桌面或開始選單點開 <b>Docker Desktop</b></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-656e202f0de44fe0b1406939b0cbdbd0" style="list-style-type:decimal"><li>跳出紅色驚嘆號視窗，標題寫 <b>WSL needs updating</b></li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-4dcf7d192fb04b74ac9ff0242e7fdfed" style="list-style-type:decimal"><li>視窗中間有一行黃框起來的指令 <code class="notion-inline-code">wsl --update</code>（先複製起來</li></ol></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-5bdb780df90b4e2d8be61b73fead269f"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="⚠️">⚠️</span></div><div class="notion-callout-text"><div class="notion-text notion-block-b2d830ed976e47ff82f241a8885e0358"><b>不要按 Try Again，也先不要關視窗</b>，直接做下一步。這個提示是正常的，每個第一次裝 Docker 的人都會遇到。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-bd931eca02394f56a9a53504796e0313" data-id="bd931eca02394f56a9a53504796e0313"><span><div id="bd931eca02394f56a9a53504796e0313" class="notion-header-anchor"></div><a class="notion-hash-link" href="#bd931eca02394f56a9a53504796e0313" title="步驟 3｜叫出「執行」視窗，輸入 cmd"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 3｜叫出「執行」視窗，輸入 cmd</span></span></h4><div class="notion-row notion-block-37070f0196348038ab4af6da557a910e"><div class="notion-column notion-block-37070f019634807facc3da967d7bf9f3" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f0196348054a733d338dc801d72"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A89e0567c-92cf-45dd-a742-34e4f0336e91%3Astep-run-cmd.png?table=block&amp;id=37070f01-9634-8054-a733-d338dc801d72&amp;t=37070f01-9634-8054-a733-d338dc801d72&amp;width=704&amp;cache=v2" alt="Windows 執行視窗中輸入 cmd" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Windows 執行視窗中輸入 cmd</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37070f01963480d0aacdd1b8647add0e" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-58612469d5644d58b2c1871dfedaa556"><b>目的</b>：打開命令提示字元，準備跑更新指令。</div><ol start="1" class="notion-list notion-list-numbered notion-block-bc5dc8dada9340feb8bbef2cd369e18f" style="list-style-type:decimal"><li>按鍵盤 <b>Win + R</b>（視窗圖示鍵 ＋ R）</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-b8e45ef3072546b4896771debeaf76d0" style="list-style-type:decimal"><li>左下角跳出「執行」小視窗</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-984b0ae715674f8e80d1114229614b02" style="list-style-type:decimal"><li>輸入 <b>cmd</b>，按「確定」</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-37070f0196348084a48bd2b58e646d23" style="list-style-type:decimal"><li>出現黑漆漆的「命令提示字元」視窗</li></ol><div class="notion-blank notion-block-37070f01963480cdb74cf6d109b19cad"> </div></div><div class="notion-spacer"></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-25de3e9299be424d998bc3c6fe0e6bc6" data-id="25de3e9299be424d998bc3c6fe0e6bc6"><span><div id="25de3e9299be424d998bc3c6fe0e6bc6" class="notion-header-anchor"></div><a class="notion-hash-link" href="#25de3e9299be424d998bc3c6fe0e6bc6" title="步驟 4｜貼上更新指令，按 Enter"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 4｜貼上更新指令，按 Enter</span></span></h4><div class="notion-text notion-block-ab5034db0eba4859abfbd11c6cfb6c2c"><b>目的</b>：執行 WSL 更新命令。</div><div class="notion-text notion-block-f2c12d15fb9146e1b4a0d98242bb2505">複製這行指令：</div><ol start="1" class="notion-list notion-list-numbered notion-block-2c39c38d1e424ee99519dc047d05b25c" style="list-style-type:decimal"><li>切回黑色「命令提示字元」視窗</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-8722d6bf61284bbea69ee8243008ce26" style="list-style-type:decimal"><li>在視窗裡按<b>滑鼠右鍵</b>，會自動貼上（不是 Ctrl+V）</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-5f0db0733b6b4a5b8d962992e1b2bfd6" style="list-style-type:decimal"><li>按 <b>Enter</b> 執行</li></ol><div class="notion-callout notion-block-be2e190e6cb2487aa367bc96d91c9043"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-b27111997ac14c0b99910a890de073b8">跳出「<b>wsl 不是內部或外部命令</b>」？代表你的 Windows 還沒裝過 WSL。先跑 <code class="notion-inline-code">wsl --install</code>，裝完重開機，再回來跑 <code class="notion-inline-code">wsl --update</code>。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-f5c1f30041cd48a0a9c03e52ade63016" data-id="f5c1f30041cd48a0a9c03e52ade63016"><span><div id="f5c1f30041cd48a0a9c03e52ade63016" class="notion-header-anchor"></div><a class="notion-hash-link" href="#f5c1f30041cd48a0a9c03e52ade63016" title="步驟 5｜等 WSL 下載完成"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 5｜等 WSL 下載完成</span></span></h4><div class="notion-row notion-block-37070f019634802697f0c5827246fd63"><div class="notion-column notion-block-37070f019634802296cbc9affffbfca1" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f019634809390ccef4a6282338c"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Ac8625881-b1f7-4931-beac-d425f44ba500%3Astep-downloading.png?table=block&amp;id=37070f01-9634-8093-90cc-ef4a6282338c&amp;t=37070f01-9634-8093-90cc-ef4a6282338c&amp;width=1080&amp;cache=v2" alt="命令提示字元正在下載 WSL，顯示進度條百分比" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">命令提示字元正在下載 WSL，顯示進度條百分比</figcaption></div></figure><div class="notion-text notion-block-e688ed3f341b427180680cfd61b25a80">⏱️ 預期時間：1～3 分鐘（網路慢會更久）。</div></div><div class="notion-spacer"></div><div class="notion-column notion-block-37070f01963480ad96dcd73b09ee11b4" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-815c3a152fff4408970265f590e3237a"><b>目的</b>：下載新版 WSL。</div><ol start="1" class="notion-list notion-list-numbered notion-block-30430be36c5148fba9ef4d1a57e26fe3" style="list-style-type:decimal"><li>盯著黑色視窗看進度條（會顯示百分比，例如 55.4%）</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-5b53b5dc0a0a45f2aa0e63fc21bf1c59" style="list-style-type:decimal"><li><b>什麼都別動</b>，不要關視窗</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-937892f44b7b453cbc903601591d5514" style="list-style-type:decimal"><li>等進度條跑到 100%</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-eb73a633dde9404fb76dd05ce14c6335" style="list-style-type:decimal"><li>看到「<b>WSL 已更新</b>」或 <code class="notion-inline-code">The operation completed successfully</code></li></ol></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-0a7b31bc1bcf46d9a62a596a782db19e"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-d6a2f4910c1b4f7eac4f4770ee06848d">卡住不動？關掉命令提示字元，重新開一個再跑一次 <code class="notion-inline-code">wsl --update</code>，會從斷點繼續。或者換個網路環境試試。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-6810f492177e4b81bf28833c0da9b69c" data-id="6810f492177e4b81bf28833c0da9b69c"><span><div id="6810f492177e4b81bf28833c0da9b69c" class="notion-header-anchor"></div><a class="notion-hash-link" href="#6810f492177e4b81bf28833c0da9b69c" title="步驟 6｜回 Docker，按藍色「Try Again」"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 6｜回 Docker，按藍色「Try Again」</span></span></h4><div class="notion-text notion-block-b8b70f2b2b62429a9d6083fc9f6c1329"><b>目的</b>：讓 Docker 偵測到已更新的 WSL。</div><ol start="1" class="notion-list notion-list-numbered notion-block-99c9faed4ae44d15890c5962ab53681e" style="list-style-type:decimal"><li>切回那個有紅色驚嘆號的 Docker 視窗（關掉了就重開 Docker Desktop）</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-5c3f7518e4494400bfe695135b9cedc4" style="list-style-type:decimal"><li>按藍色 <b>Try Again</b></li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-ce6cb7c0cc404534bea3f0d4ead7f0e8" style="list-style-type:decimal"><li>等 10～30 秒</li></ol><div class="notion-text notion-block-6a9e837c825e4bdc861ec10198a266cc">✅ <b>成功標誌</b>：畫面跳到 Docker 主畫面（藍色鯨魚或選單）。PART 1 完成！</div><hr class="notion-hr notion-block-5743476ad83c4039aa00355c1c91e29b"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-49b45c63bea94483b701af224ad62272" data-id="49b45c63bea94483b701af224ad62272"><span><div id="49b45c63bea94483b701af224ad62272" class="notion-header-anchor"></div><a class="notion-hash-link" href="#49b45c63bea94483b701af224ad62272" title="五、用 Docker 跑起 n8n"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">五、用 Docker 跑起 n8n</span></span></h3><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-a1e82a43530142049e0bb320c70bbfca" data-id="a1e82a43530142049e0bb320c70bbfca"><span><div id="a1e82a43530142049e0bb320c70bbfca" class="notion-header-anchor"></div><a class="notion-hash-link" href="#a1e82a43530142049e0bb320c70bbfca" title="步驟 1｜進到 Images 頁面"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 1｜進到 Images 頁面</span></span></h4><div class="notion-row notion-block-37070f019634809bbf2af85b6218c0b5"><div class="notion-column notion-block-37070f019634803b87bbff54fad85339" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f01963480aeb73fdfa657fd5ea6"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Aa978944c-6890-4e83-9bbe-01aff122ac30%3Astep-images-tab.png?table=block&amp;id=37070f01-9634-80ae-b73f-dfa657fd5ea6&amp;t=37070f01-9634-80ae-b73f-dfa657fd5ea6&amp;width=703.9896240234375&amp;cache=v2" alt="Docker Desktop 左側選單中的 Images 項目" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Docker Desktop 左側選單中的 Images 項目</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37070f019634802f9758c39050ac00dc" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-89ce335b3ae74eefa5fe6e8246f9d6aa"><b>目的</b>：進入安裝包（映像檔）列表。</div><ol start="1" class="notion-list notion-list-numbered notion-block-b78dc4370d8544f3b9a4f2c7b6e127e1" style="list-style-type:decimal"><li>確認 Docker Desktop 已開、顯示主畫面</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-2649f0aa48f7430996a42f2e1e98eca6" style="list-style-type:decimal"><li>左邊功能選單點 <b>Images</b>（立方體圖示）</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-c913bea61b97400796ea706fc0085d52" style="list-style-type:decimal"><li>右邊切到 Images 頁面（第一次用通常是空的）</li></ol></div><div class="notion-spacer"></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-b361f5877b794da69799f0c731bd2bce" data-id="b361f5877b794da69799f0c731bd2bce"><span><div id="b361f5877b794da69799f0c731bd2bce" class="notion-header-anchor"></div><a class="notion-hash-link" href="#b361f5877b794da69799f0c731bd2bce" title="步驟 2｜搜尋並下載 n8n"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 2｜搜尋並下載 n8n</span></span></h4><div class="notion-text notion-block-118f314c529d4b7da7c8d52baaab0dcb"><b>目的</b>：從 Docker Hub 抓取官方 n8n 安裝包。</div><div class="notion-row notion-block-37070f0196348039b2d7d2836f59a18d"><div class="notion-column notion-block-37070f01963480aa96e8c0897e827206" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f019634807da01bcb1bf4a590a2"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A4cd09447-ddfb-45e2-9a38-103f24d573f5%3Astep-search-n8n.png?table=block&amp;id=37070f01-9634-807d-a01b-cb1bf4a590a2&amp;t=37070f01-9634-807d-a01b-cb1bf4a590a2&amp;width=703.9896240234375&amp;cache=v2" alt="在 Docker 搜尋 n8n，第一個結果是 n8nio/n8n 官方版本" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">在 Docker 搜尋 n8n，第一個結果是 n8nio/n8n 官方版本</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37070f01963480c3a6e5ced4ee6aa524" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><ol start="1" class="notion-list notion-list-numbered notion-block-d4e50dc889e04542aa8405eaafa72d38" style="list-style-type:decimal"><li>Images 頁面中間，點藍色按鈕 <b>Search images to run</b></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-569745ef63ef4c57bce7cef08e07df2e" style="list-style-type:decimal"><li>搜尋框輸入 <b>n8n</b></li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-9d410d9e49154a61837dc26671c6e36a" style="list-style-type:decimal"><li>結果裡選 <b>n8nio/n8n</b>（名字旁邊有藍色驗證勾勾 ✓）</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-699fed01af6e44d4b891c1ec77c29608" style="list-style-type:decimal"><li>按那一行右邊的 <b>Pull</b> 開始下載</li></ol><div class="notion-text notion-block-fd1d774fee2742d292382e564fa5de71">⏱️ 下載約 1～2 分鐘（檔案約 2.5 GB）。</div><div class="notion-blank notion-block-37070f0196348020a08df417b906db9d"> </div></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-165074be64dd4d70b2a69c440069fb14"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="⚠️">⚠️</span></div><div class="notion-callout-text"><div class="notion-text notion-block-ba60074fc3e24ce894a0d24133c06119"><b>只選官方版 </b><code class="notion-inline-code"><b>n8nio/n8n</b></code>。其他像 <code class="notion-inline-code">vulhub/n8n</code>、<code class="notion-inline-code">crazymax/n8n</code> 都不要選，非官方版本可靠性不佳，更新也不同步。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-3d2ba460bdef43609f8985d3654cd69d" data-id="3d2ba460bdef43609f8985d3654cd69d"><span><div id="3d2ba460bdef43609f8985d3654cd69d" class="notion-header-anchor"></div><a class="notion-hash-link" href="#3d2ba460bdef43609f8985d3654cd69d" title="步驟 3｜按 Run 把它跑起來"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 3｜按 Run 把它跑起來</span></span></h4><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f019634808b8c96c9d41abfe8fd"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A4e95f274-f0e0-4e36-976d-2d0abb2588d4%3Astep-run-image.png?table=block&amp;id=37070f01-9634-808b-8c96-c9d41abfe8fd&amp;t=37070f01-9634-808b-8c96-c9d41abfe8fd&amp;width=703.9896240234375&amp;cache=v2" alt="Images 列表中 n8nio/n8n 旁的 Run 按鈕" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Images 列表中 n8nio/n8n 旁的 Run 按鈕</figcaption></div></figure><div class="notion-row notion-block-37070f01963480c88da5ff940279e99a"><div class="notion-column notion-block-37070f01963480d5a217d5a7aa7b6319" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-16834b929d434a0a97e360b56f623109">先搞懂這組比喻：</div><table class="notion-simple-table notion-block-d42b53df567144dcb7344d192c9e17a1"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-7a3ea0acf9354bf78326075ef318aadc"><td class="" style="width:120px"><div class="notion-simple-table-cell">Docker 術語</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">比喻</div></td></tr><tr class="notion-simple-table-row notion-block-cc30d34b8ebf4b8bbb5e346ef75fc100"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>Image</b>（安裝包）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">設計圖</div></td></tr><tr class="notion-simple-table-row notion-block-381ac5e1903e41b6a787c2f61437a4d7"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>Container</b>（容器）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">照設計圖蓋好的房子</div></td></tr><tr class="notion-simple-table-row notion-block-ba7f582ffde0434182ee3d8b9ec25d5f"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>Run</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">按下「開始施工」</div></td></tr></tbody></table></div><div class="notion-spacer"></div><div class="notion-column notion-block-37070f01963480cda311feb06bf4aa69" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-6e79a87cb3d941349c30b280c4e15e8f"><b>目的</b>：把安裝包模板變成實際運作的容器。</div><ol start="1" class="notion-list notion-list-numbered notion-block-52c90b4250d4471bb84dc9853d5fa416" style="list-style-type:decimal"><li>下載完會自動回到 Images 列表</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-7a147e6e250948f1ac16ddd7df51392c" style="list-style-type:decimal"><li>找到 <code class="notion-inline-code">n8nio/n8n</code> 那一行</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-1bf7073aa17f4849b68f9814979d2f49" style="list-style-type:decimal"><li>滑鼠移過去，右邊 <b>Actions</b> 欄會出現小圖示</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-884297a3388f40698e6ae6da8bfe3f82" style="list-style-type:decimal"><li>點<b>藍色三角形 ▶</b>（Run 按鈕）</li></ol></div><div class="notion-spacer"></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-e14016e788f946628716bdd4ea66c39b" data-id="e14016e788f946628716bdd4ea66c39b"><span><div id="e14016e788f946628716bdd4ea66c39b" class="notion-header-anchor"></div><a class="notion-hash-link" href="#e14016e788f946628716bdd4ea66c39b" title="步驟 4｜展開「Optional settings」"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 4｜展開「Optional settings」</span></span></h4><div class="notion-text notion-block-d5fb645702c74ee592fa4acfb6efea70"><b>目的</b>：設定 n8n 正常運作的必要參數。</div><div class="notion-callout notion-block-dacfe25a31404aa1bb7187337e2f2ac2"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="⚠️">⚠️</span></div><div class="notion-callout-text"><div class="notion-text notion-block-7a207879f1da4655a034a7b7b84c83c2"><b>這步不能跳！</b> 用預設值會導致：(1) 無法從瀏覽器打開 n8n (2) 容器一關資料就全部不見。</div></div></div><div class="notion-row notion-block-37070f01963480929aaedaed95fde683"><div class="notion-column notion-block-37070f019634802ba025c49ef1e5daf6" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f0196348086a497c7b46585d6a4"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Aa541fa64-58d0-4870-9a5e-c383ed1def11%3Astep-optional-settings.png?table=block&amp;id=37070f01-9634-8086-a497-c7b46585d6a4&amp;t=37070f01-9634-8086-a497-c7b46585d6a4&amp;width=691.96875&amp;cache=v2" alt="Run a new container 視窗中的 Optional settings 展開箭頭。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Run a new container 視窗中的 Optional settings 展開箭頭。</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37070f019634809b8813f071b7651318" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><ol start="1" class="notion-list notion-list-numbered notion-block-fa3549797b2b4136867aff6fc04e8bcd" style="list-style-type:decimal"><li>跳出 <b>Run a new container</b> 視窗</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-77f454f48d364301b4070b883026c088" style="list-style-type:decimal"><li>先<b>別按</b>右下角的 Run</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-2bb66f18204a4f04b8d3348d2b3b0b29" style="list-style-type:decimal"><li>找到 <b>Optional settings</b> 那行，右邊有個向下箭頭（v）</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-acfbed3ee4f74ba9b243ef17250e1c0a" style="list-style-type:decimal"><li>點箭頭展開，露出設定欄位</li></ol></div><div class="notion-spacer"></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-099af3dcf6a14abaa1197c7c44b0104d" data-id="099af3dcf6a14abaa1197c7c44b0104d"><span><div id="099af3dcf6a14abaa1197c7c44b0104d" class="notion-header-anchor"></div><a class="notion-hash-link" href="#099af3dcf6a14abaa1197c7c44b0104d" title="步驟 5｜照這三項填好，再按 Run"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 5｜照這三項填好，再按 Run</span></span></h4><div class="notion-row notion-block-37070f019634806bb062f4f2d035811d"><div class="notion-column notion-block-37070f019634802ab28ef517cf23ca41" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f01963480aab376cb105b30abda"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Af133958f-cb85-4d8b-b6b6-6bacc0d3649f%3Astep-container-config.png?table=block&amp;id=37070f01-9634-80aa-b376-cb105b30abda&amp;t=37070f01-9634-80aa-b376-cb105b30abda&amp;width=704&amp;cache=v2" alt="Run a new container 對話框，填好容器名稱、port 與資料存放路徑" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Run a new container 對話框，填好容器名稱、port 與資料存放路徑</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37070f01963480218413cd1181c7ff2c" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-2f91d7082e854a48aded1bf6e0f93f59"><b>目的</b>：設定容器名稱、連線 port、資料存儲位置。</div><ol start="1" class="notion-list notion-list-numbered notion-block-2be62965242447cb9bed91a935437867" style="list-style-type:decimal"><li>照表格把欄位填好</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-2bd8e118ecbe44a6a21f7c5404f8e1e5" style="list-style-type:decimal"><li>其他欄位（Environment variables、Network）<b>全部不動</b>，留空</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-963cc73cae494803872fd2796af7e4e3" style="list-style-type:decimal"><li>按視窗右下角 <b>Run</b></li></ol></div><div class="notion-spacer"></div></div><table class="notion-simple-table notion-block-ab1db6738f2e42ea8844ce0ea7666498"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-2b4ea83d179c41aa8fc5648df41c252a"><td class="" style="width:120px"><div class="notion-simple-table-cell">欄位</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">填入值</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">這是在做什麼</div></td></tr><tr class="notion-simple-table-row notion-block-d21e64f4826d4e2c90d64ec20ca8ec3e"><td class="" style="width:120px"><div class="notion-simple-table-cell">Container name</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>n8n_free</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">幫容器取名字，方便日後找到它（名稱隨你取，這裡只是舉例）</div></td></tr><tr class="notion-simple-table-row notion-block-75d6bee4817e409893ee653ddc136cee"><td class="" style="width:120px"><div class="notion-simple-table-cell">Ports → Host port</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>5678</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">設定瀏覽器要用 <code class="notion-inline-code">localhost:5678</code> 連進去</div></td></tr><tr class="notion-simple-table-row notion-block-3585e47dfce54e68926e7a32dd6b7677"><td class="" style="width:120px"><div class="notion-simple-table-cell">Volumes → Host path</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>C:/n8n</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">指定電腦上哪個資料夾來存 n8n 的資料（路徑自己選，放哪都行）</div></td></tr><tr class="notion-simple-table-row notion-block-4ddbd71e076045ed805788081209b286"><td class="" style="width:120px"><div class="notion-simple-table-cell">Volumes → Container path</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>/home/node/.n8n</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">n8n 程式內部固定的存檔位置（<b>不能改</b>）</div></td></tr></tbody></table><div class="notion-callout notion-block-0d8250b23e47416d8989594333473f36"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="📦">📦</span></div><div class="notion-callout-text"><div class="notion-text notion-block-81c301578567439fa232fb64e0aad082"><b>Volumes 在做什麼？</b></div><div class="notion-text notion-block-37070f01963480cfb08bde07e422e987">把電腦上的 <code class="notion-inline-code">C:\n8n</code> 跟容器內的 <code class="notion-inline-code">/home/node/.n8n</code> 連通。n8n 產生的資料（工作流、帳號、設定）實際存在你的硬碟裡。就算容器被刪掉，資料還在。重新 Run 一個新容器接回同一個資料夾就好。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-76683e636bab4ad88090a031a43f6f99" data-id="76683e636bab4ad88090a031a43f6f99"><span><div id="76683e636bab4ad88090a031a43f6f99" class="notion-header-anchor"></div><a class="notion-hash-link" href="#76683e636bab4ad88090a031a43f6f99" title="步驟 6｜打開 n8n，設定帳號"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">步驟 6｜打開 n8n，設定帳號</span></span></h4><div class="notion-row notion-block-37070f019634803e8ef3c3fa22f24e47"><div class="notion-column notion-block-37070f01963480048a70fa54f5443db3" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f0196348079ab8bd7ff7187c722"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A6bdc32be-272d-471e-a77d-597987209c96%3Adocker-desktop-n8n-container-localhost-access-url.png?table=block&amp;id=37070f01-9634-8079-ab8b-d7ff7187c722&amp;t=37070f01-9634-8079-ab8b-d7ff7187c722&amp;width=703.984375&amp;cache=v2" alt="Docker Desktop 的 n8n container 詳細頁面，畫面顯示 Logs 中出現「Editor is now accessible via http://localhost:5678」，並以紅框與說明標示這是 n8n 的本機存取網址，點擊連結或在瀏覽器輸入即可開啟 n8n 操作介面。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Docker Desktop 的 n8n container 詳細頁面，畫面顯示 Logs 中出現「Editor is now accessible via http://localhost:5678」，並以紅框與說明標示這是 n8n 的本機存取網址，點擊連結或在瀏覽器輸入即可開啟 n8n 操作介面。</figcaption></div></figure><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f0196348012b228c89fbb30c7ce"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A7af57c41-8b9a-43d7-b8ce-6af6b753dd19%3Astep-n8n-setup.png?table=block&amp;id=37070f01-9634-8012-b228-c89fbb30c7ce&amp;t=37070f01-9634-8012-b228-c89fbb30c7ce&amp;width=703.9896240234375&amp;cache=v2" alt="瀏覽器打開 n8n 後的 Set up owner account 設定帳號畫面" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">瀏覽器打開 n8n 後的 Set up owner account 設定帳號畫面</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37070f01963480b0bbe3deb4cd3b6a4e" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><div class="notion-text notion-block-af52fd3d83dc4525875c9653388b200c"><b>目的</b>：透過瀏覽器開啟 n8n 並建立管理員帳號。</div><ol start="1" class="notion-list notion-list-numbered notion-block-20896bb0141b4cd0831940895787fe04" style="list-style-type:decimal"><li>按 Run 後自動跳到 <b>Containers</b> 頁面</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-9d6bc66eeea14774b88793cc877da97b" style="list-style-type:decimal"><li>看到 <b>n8n_free</b> 那行，前面<b>綠色小圓點</b>＝正在跑</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-1f9c932a2f2e428e999a42620f33c21f" style="list-style-type:decimal"><li>點進去看 Logs（執行紀錄），捲到最下面找這行點入：</li><ol class="notion-list notion-list-numbered notion-block-1f9c932a2f2e428e999a42620f33c21f" style="list-style-type:lower-alpha"></ol></ol><ol start="4" class="notion-list notion-list-numbered notion-block-3be0fdf9e3ca43f99eb66c4b82010571" style="list-style-type:decimal"><li>填入 Email、First Name、Last Name、Password，按 <b>Next</b></li></ol><div class="notion-text notion-block-625273fda2dc4e14a4c59138ee2fd5d2">✅ <b>看到 n8n 的工作流編輯畫面，安裝全部完成！</b></div><div class="notion-blank notion-block-37070f0196348074a154ddce78c5b7c6"> </div></div><div class="notion-spacer"></div></div><hr class="notion-hr notion-block-a88f0a7def56470bb386233b23299786"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-f68a8ff3cddb4b59bf10c3518119aa22" data-id="f68a8ff3cddb4b59bf10c3518119aa22"><span><div id="f68a8ff3cddb4b59bf10c3518119aa22" class="notion-header-anchor"></div><a class="notion-hash-link" href="#f68a8ff3cddb4b59bf10c3518119aa22" title="六、日後使用：怎麼再開 n8n"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">六、日後使用：怎麼再開 n8n</span></span></h3><div class="notion-callout notion-block-88c35b482c8b4f68beeb7f9d5dd62c6d"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="🚫">🚫</span></div><div class="notion-callout-text"><div class="notion-text notion-block-58a5b6d0c92042e192579a9a4593ef2b"><b>千萬不要重做前面的步驟！</b> </div><div class="notion-text notion-block-37070f0196348009a6b0e897790a34dc">Image 裝過一次就不用再 Pull，也不用再 Run a new container。日常只要在 Containers 頁面點兩下。</div></div></div><div class="notion-row notion-block-37070f019634800b9f38d5b85659fef7"><div class="notion-column notion-block-37070f01963480d6934eebc72ca675e6" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-37070f019634805d93badc544b7678f8"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Ace10d09c-8c03-45de-8704-6bf105b5cbdc%3Adocker-desktop-open-n8n-container-port-guide.png?table=block&amp;id=37070f01-9634-805d-93ba-dc544b7678f8&amp;t=37070f01-9634-805d-93ba-dc544b7678f8&amp;width=703.9896240234375&amp;cache=v2" alt="Docker Desktop Containers 頁面，標出 Containers 選單與 Port(s) 欄的 5678:5678 連結" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Docker Desktop Containers 頁面，標出 Containers 選單與 Port(s) 欄的 5678:5678 連結</figcaption></div></figure></div><div class="notion-spacer"></div><div class="notion-column notion-block-37070f0196348045bdedfbfd125fcb69" style="width:calc((100% - (1 * min(32px, 4vw))) * 0.5)"><ol start="1" class="notion-list notion-list-numbered notion-block-e57c728fe2814618986aba0e962b974c" style="list-style-type:decimal"><li>打開 <b>Docker Desktop</b></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-1b9466a5e0da456eb86cd372f204526e" style="list-style-type:decimal"><li>左邊點 <b>Containers</b>（在 Images 上方）</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-c34e6379a52a4a8fbba53df56d09c6ec" style="list-style-type:decimal"><li>找到之前建好的 <code class="notion-inline-code">n8n_free</code></li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-995623a90305412eb3e6d82540f371b0" style="list-style-type:decimal"><li>看左邊小圓點判斷狀態：</li><ol class="notion-list notion-list-numbered notion-block-995623a90305412eb3e6d82540f371b0" style="list-style-type:lower-alpha"><ul class="notion-list notion-list-disc notion-block-0dda6005dd90496d9505ed458142ac1d"><li>🟢 <b>綠色</b>＝正在跑，直接跳到第 5 步</li></ul><ul class="notion-list notion-list-disc notion-block-a3b561026e1043ec9cc58ea155fc35d9"><li>⚪ <b>灰色</b>＝停著，滑鼠移過去點右邊的 <b>▶ 啟動鍵</b>，等 10～30 秒變綠</li></ul></ol></ol><ol start="5" class="notion-list notion-list-numbered notion-block-e9cdead3847c43c0bb91f0b72bc9a1c2" style="list-style-type:decimal"><li>點中間 <b>Port(s)</b> 欄的藍色 <code class="notion-inline-code">5678:5678</code> 連結，瀏覽器直接開 n8n</li></ol></div><div class="notion-spacer"></div></div><div class="notion-callout notion-block-daab1a17fb3e40d9b1e9f2344c284339"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="💡">💡</span></div><div class="notion-callout-text"><div class="notion-text notion-block-209459f3c45a412bb52a57d42d4bfb0e"><b>小撇步</b>：把 <code class="notion-inline-code">http://localhost:5678</code> 加進瀏覽器書籤，下次直接點書籤秒開（前提：Docker 和容器已啟動）。</div></div></div><div class="notion-callout notion-block-16688ac54bfa4a1096ea1cb6c83601e8"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="⚠️">⚠️</span></div><div class="notion-callout-text"><div class="notion-text notion-block-8c634564fee6461ca1dbc3c216fff8d4"><b>Containers 出現兩個 n8n？</b> 刪掉舊的那個，只留一個。兩個容器搶同一個 port 會互相打架，誰都連不上。看建立時間，留比較新的就好。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-4697ec6bd410431db77bbdab4a8d2dad" data-id="4697ec6bd410431db77bbdab4a8d2dad"><span><div id="4697ec6bd410431db77bbdab4a8d2dad" class="notion-header-anchor"></div><a class="notion-hash-link" href="#4697ec6bd410431db77bbdab4a8d2dad" title="想更新 n8n 到新版本？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">想更新 n8n 到新版本？</span></span></h4><div class="notion-text notion-block-c62b01b53de941d9a9603aeda0778b38">三步就好：</div><ol start="1" class="notion-list notion-list-numbered notion-block-83cda06e2e954aeba48531e44bac254f" style="list-style-type:decimal"><li>到 <b>Images</b> 頁面，重新搜尋 <code class="notion-inline-code">n8nio/n8n</code> 並 <b>Pull</b>（會自動抓最新版）</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-eb237a004bcd439bad945e764feadf93" style="list-style-type:decimal"><li>到 <b>Containers</b> 頁面，把舊的 <code class="notion-inline-code">n8n_free</code> <b>停止 → 刪除</b></li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-de651b03f5a7472dbbce0e5605d036e1" style="list-style-type:decimal"><li>從新的 Image 重新 <b>Run</b>，填跟之前一樣的設定</li></ol><div class="notion-text notion-block-81fcec2f161b417a930c3b70fbfed59c">因為資料存在你指定的資料夾裡，重新 Run 後工作流和帳號都還在。</div><hr class="notion-hr notion-block-b165ef8a10fc415aae1e1c73a231c619"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-51fb1bd7771f4686b525c4f586f4a705" data-id="51fb1bd7771f4686b525c4f586f4a705"><span><div id="51fb1bd7771f4686b525c4f586f4a705" class="notion-header-anchor"></div><a class="notion-hash-link" href="#51fb1bd7771f4686b525c4f586f4a705" title="七、恭喜，你有自己的自動化工具了"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">七、恭喜，你有自己的自動化工具了</span></span></h3><div class="notion-text notion-block-7d6a77c167d7440abbb4d88114836aff">走到這裡，你的電腦裡已經有一台免費、資料全在本機的 n8n。</div><div class="notion-text notion-block-f7d54e47420744cfaeb857a497be4018">幾件事記一下：</div><ul class="notion-list notion-list-disc notion-block-2d55c58c97ab40398b48bd3730ad6b35"><li>電腦開著 + Docker 開著 = n8n 就一直在跑。關機就停，開機再啟動就好，30 秒的事</li></ul><ul class="notion-list notion-list-disc notion-block-8faf3a55646b46dbbe2f6dbaa707d414"><li>工作流和帳號都存在你指定的資料夾裡，不會因為 Docker 更新而消失</li></ul><ul class="notion-list notion-list-disc notion-block-edad14c30046456798eacdff7f2a21dd"><li>碰到英文錯誤訊息看不懂？截圖丟給 AI 問最快，不用自己翻譯</li></ul><div class="notion-text notion-block-35df36caf8eb479ca48a21453a41572a">接下來就是你發揮的時間，打開 n8n，建你的第一條工作流吧！</div><div class="notion-text notion-block-a6e21000714f4ddc88fdac59e74e3a1d">（延伸閱讀：<a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://gyozalab.com/ipas-l121-ai-overview">No-Code/Low-Code 如何重新定義開發？</a>）</div></main></div>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[AI 教練 × 費曼學習法：利用瑣碑時間極限學習]]></title>
            <link>https://gyozalab.com/ai-learning-feynman-prompt-kit</link>
            <guid>https://gyozalab.com/ai-learning-feynman-prompt-kit</guid>
            <pubDate>Thu, 28 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[我做了一份費曼學習法 Prompt Kit，設計目的是讓 AI 不再「展現自己有多懂」，改成陪你一步一步把東西學進去。這篇文章拆解這句 Prompt 為什麼長這樣、每個元素在做什麼，以及為什麼我刻意把學習的過程設計得「不太舒服」。如果你想要的是系統性地學會一個東西，而不是丟給 AI 摘要一下就覺得自己學過了，這篇寫給你。]]></description>
            <content:encoded><![CDATA[<div id="notion-article" class="mx-auto overflow-hidden "><main class="notion light-mode notion-page notion-block-36e70f019634807b8a4cdea001d33ff9"><div class="notion-viewport"></div><div class="notion-collection-page-properties"></div><div class="notion-callout notion-block-da22fb02496640a59660f693ab764ab1"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="🎯">🎯</span></div><div class="notion-callout-text"><div class="notion-text notion-block-971141ed528d4185b5a7d7ac80d39700">AI 不會自己把你教好，因為它天生有「知識的詛咒」和流暢效應兩大盲點。這套 Prompt Kit 的核心設計：強迫 AI 用國中生程度教你，再用費曼學習法逼你自己講出來，透過「掙扎」讓知識真正內化，而非讀完就忘。</div></div></div><div class="notion-text notion-block-36e70f0196348002883ed35523eddf9a">你有沒有試過，把一篇文章丟給 AI 生成摘要？把一兩個小時的 YouTube 精華影片丟給 AI，讓它快速整理重點？</div><div class="notion-text notion-block-36e70f019634800e87fbc7cb7d986eb1">看完之後，好像知道了什麼。但少了一種踏實感。好像什麼都沒有真的學會。</div><div class="notion-text notion-block-36e70f01963480659f4ef618c69baa3e">我們可以利用 AI 來輔助學習，讓它幫我們整理、歸納、省時間。但 AI 沒辦法替我們思考。</div><div class="notion-text notion-block-36e70f01963480ae9b78e9f3391d745b">學習本身需要我們與知識產生連結，這段路，我們只能自己走。</div><div class="notion-text notion-block-36e70f019634803a8227d987f3dba0a8">這篇文章聊的就是那段路，以及我怎麼設計一套 Prompt，讓 AI 陪你走完它。</div><hr class="notion-hr notion-block-36e70f019634805d8578c2213c6e02d5"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-36f70f01963480b397d6f10e450d1e9d" data-id="36f70f01963480b397d6f10e450d1e9d"><span><div id="36f70f01963480b397d6f10e450d1e9d" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36f70f01963480b397d6f10e450d1e9d" title="一、AI 為什麼教不好你？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">一、AI 為什麼教不好你？</span></span></h3><div class="notion-text notion-block-36f70f0196348022b64feae3b241ced3">我自己跨領域學東西的時候，常常發現 AI 的回覆明顯太看得起我了。因為他沒辦法精確抓到我的知識背景，所以會用一堆專業詞彙淹沒我，每次都要重新告訴它「我不是這個領域的人」，才不會輸出一堆天書。</div><div class="notion-text notion-block-36f70f019634802eb669f3dc7a4edbe1">有時候使用 AI 就是這樣：問 AI 一個問題，它吐給你一大段回覆，讀完覺得「好像懂了」，關掉視窗。三天後連自己問了什麼都記不清楚。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36f70f019634808d8bb6c3fa04933ce3" data-id="36f70f019634808d8bb6c3fa04933ce3"><span><div id="36f70f019634808d8bb6c3fa04933ce3" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36f70f019634808d8bb6c3fa04933ce3" title="1. 知識的詛咒：學會了就忘記「不會」是什麼感覺"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">1. 知識的詛咒：學會了就忘記「不會」是什麼感覺</span></span></h4><div class="notion-text notion-block-36f70f01963480548ba4d8fd29a2d2a4">AI 跟人類專家犯了一樣的毛病：很會展現自己懂多少，但不太會替對方著想。</div><div class="notion-text notion-block-36f70f01963480ce8b63f78662057fe5">教育心理學裡有個概念叫<b>知識的詛咒</b>（Curse of Knowledge）：學會了之後，就很難想像「不會」是什麼感覺。你會不自覺地假設對方跟你有一樣的背景，跳過你覺得理所當然的步驟。</div><div class="notion-text notion-block-36f70f0196348033925bfaffa5f555de">心理學家 Elizabeth Newton 在史丹佛做過一個經典實驗。她讓一組人心裡想一首歌，用手指敲節奏給另一組人猜。敲的人預估對方有 50% 機率猜中，實際命中率只有 2.5%，差了二十倍。因為敲的人腦裡同時在播旋律和歌詞，覺得「這不是很明顯嗎」。聽的人只聽到一串孤立的敲擊聲。</div><div class="notion-text notion-block-36f70f01963480fba3fee9247e9171b0">AI 就是那個敲桌子的人。它腦裡什麼都有，所以覺得自己講得很清楚。你只接收到一堆拼不起來的碎片。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36f70f0196348092b7c9ea84a2bab0be" data-id="36f70f0196348092b7c9ea84a2bab0be"><span><div id="36f70f0196348092b7c9ea84a2bab0be" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36f70f0196348092b7c9ea84a2bab0be" title="2. 你的腦一次能處理多少？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">2. 你的腦一次能處理多少？</span></span></h4><div class="notion-text notion-block-36f70f01963480d5a594edd9764f6b13">AI 還有另一個問題：它不知道你的腦一次能裝多少。</div><div class="notion-text notion-block-36f70f01963480a09b2fd793696cef34">人的工作記憶大概只能同時處理四、五個新東西，超過這個量，後面的就會把前面的擠掉。但 AI 可以一口氣處理幾萬字，所以它預設你也可以。</div><div class="notion-text notion-block-36f70f0196348006a965f012f3b50d25">這就是為什麼 AI 的回覆常常讓你覺得「寫了很多，但讀完更累」。我們說一個人文筆好不好，看的是資訊密度，不是字數。用最短的文字講最多的東西，才叫文筆好。AI 寫了一大段讀完抓不到重點，就是密度太低。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36f70f0196348005960ac01c33aa3bd0" data-id="36f70f0196348005960ac01c33aa3bd0"><span><div id="36f70f0196348005960ac01c33aa3bd0" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36f70f0196348005960ac01c33aa3bd0" title="3. 你以為懂了，但其實你沒有"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">3. 你以為懂了，但其實你沒有</span></span></h4><div class="notion-text notion-block-36f70f01963480ea8aebda0c0a18449b">更麻煩的是，AI 寫得太流暢反而會讓你產生「我已經懂了」的錯覺。</div><div class="notion-text notion-block-36f70f0196348087b8dbe16b2f395434">心理學裡叫這個現象<b>流暢效應</b>（Fluency Illusion）：當資訊呈現得很順暢、很好讀，大腦會自動判斷「這個我理解了」。但理解文字和理解概念是兩回事。你讀懂了每一個字，不代表你能用自己的話重新講一遍。</div><div class="notion-text notion-block-36f70f01963480c7a5fed245acabf16c">AI 的回覆就是流暢效應的完美觸發器：排版漂亮、句子通順、分點列舉，看起來條理分明。讀完覺得自己學到了，隔天要用的時候什麼都想不起來。</div><div class="notion-text notion-block-36f70f019634805d809ccdc298168777">怎麼擋掉這個陷阱？第一步，先讓 AI 講人話，不要炫技賣弄術語。第二步，就算 AI 講得再好，你還是需要一個方法驗證自己到底有沒有真的懂。</div><div class="notion-text notion-block-36f70f01963480689d86fe1384ac6b23">先從第一步開始。</div><hr class="notion-hr notion-block-36e70f0196348006829ffb53ecd5b6a2"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-36e70f01963480d3a8a1c9281aaf3bfc" data-id="36e70f01963480d3a8a1c9281aaf3bfc"><span><div id="36e70f01963480d3a8a1c9281aaf3bfc" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f01963480d3a8a1c9281aaf3bfc" title="二、一句 Prompt 怎麼把 AI 拉回來？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">二、一句 Prompt 怎麼把 AI 拉回來？</span></span></h3><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36e70f019634805c8b18f8b7b02b13c4" data-id="36e70f019634805c8b18f8b7b02b13c4"><span><div id="36e70f019634805c8b18f8b7b02b13c4" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f019634805c8b18f8b7b02b13c4" title="1. 這句 Prompt 怎麼來的？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">1. 這句 Prompt 怎麼來的？</span></span></h4><div class="notion-text notion-block-36e70f0196348054b0fefb798864937c">我看到有研究生在用 AI 讀論文時，提示詞寫「我是一個智力低下的研究生，請解釋給我聽」。當時覺得有趣，但沒真的去用。</div><div class="notion-text notion-block-36e70f0196348045a5b6dbbb091d59e0">後來自己跨領域學東西碰到同樣的問題：AI 教金融知識用金融術語，教程式設計用工程師行話。每次都要重新跟它說「我不是這個領域的人」，我就突然想起那個研究生的提示詞。</div><div class="notion-text notion-block-36e70f01963480f2ae23e125c0a24a89">如果把自己在跨領域時的狀態老實講出來，把「我其實只有國中生程度」的感受直接寫進 Prompt，AI 會不會就可以開始講人話？</div><div class="notion-text notion-block-36e70f019634803ba675d4662cb183da">於是寫了第一版：</div><blockquote class="notion-quote notion-block-36e70f0196348093b947e2dfa786d5fa"><div><b>「我是一個智力低下的國中生，我完全看不懂你在寫什麼，請你盡可能地減輕我的認知負擔，一步一步用生活化的方式舉例，想辦法讓我明白核心概念。」</b></div></blockquote><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36e70f019634802cae82ee1cd1034f72" data-id="36e70f019634802cae82ee1cd1034f72"><span><div id="36e70f019634802cae82ee1cd1034f72" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f019634802cae82ee1cd1034f72" title="2. 六個元素，做同一件事"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">2. 六個元素，做同一件事</span></span></h4><div class="notion-text notion-block-36e70f01963480b89d5ddaa1d8f98131">這句話看起來短，拆開來有六個設計：</div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-36e70f0196348027ba10efcde1d09dd0"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Ae71ec64e-0825-4a44-bd36-561b4517942b%3Afeynman-prompt-6-elements.png?table=block&amp;id=36e70f01-9634-8027-ba10-efcde1d09dd0&amp;t=36e70f01-9634-8027-ba10-efcde1d09dd0&amp;width=703.9896240234375&amp;cache=v2" alt="費曼學習法 Prompt 的六個設計元素拆解：身份設定、強化謙卑、元術語、教學節奏、教學方法、目標導向" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">費曼學習法 Prompt 的六個設計元素拆解：身份設定、強化謙卑、元術語、教學節奏、教學方法、目標導向</figcaption></div></figure><div class="notion-text notion-block-36e70f019634805b96f4d24884f5aa37">六個元素合在一起，做的事情是同一件：強迫 AI 從「展現自己有多懂」切換到「替你著想」。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36e70f01963480dd98c4e992a6236880" data-id="36e70f01963480dd98c4e992a6236880"><span><div id="36e70f01963480dd98c4e992a6236880" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f01963480dd98c4e992a6236880" title="3. 為什麼用「國中生」而不是「新手」？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">3. 為什麼用「國中生」而不是「新手」？</span></span></h4><div class="notion-text notion-block-36e70f0196348035b26ed43e13330901">小學生太低，AI 會講得幼稚到浪費時間。大學生太高，AI 還是會假設你有學科基礎。國中生剛好：能讀字、有基本邏輯，但對專業知識完全沒有先備知識。</div><div class="notion-text notion-block-36e70f01963480a89b05d5b4060c7b36">跨領域學東西的時候，這就是我們大多數人的真實狀態。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36e70f01963480338561c1b666f65a61" data-id="36e70f01963480338561c1b666f65a61"><span><div id="36e70f01963480338561c1b666f65a61" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f01963480338561c1b666f65a61" title="4. 「認知負擔」這個詞為什麼重要？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">4. 「認知負擔」這個詞為什麼重要？</span></span></h4><div class="notion-text notion-block-36e70f0196348079be93fcd8f3cacfbe">「認知負擔」是教育心理學的術語，一般人不會想到寫在 Prompt 裡。</div><div class="notion-text notion-block-36e70f019634809587dac22c8c49343c">AI 什麼學科的知識都有，它讀過的論文比任何人都多，只是大家不知道怎麼跟它要。你用它聽得懂的專業詞去指導它，它做出來的效果比「講簡單一點」精準太多。</div><div class="notion-text notion-block-36e70f019634800ea795f2817114f959">「講簡單一點」是給 AI 一個模糊的方向。「減輕認知負擔」是給它一個具體的目標，它知道該怎麼動。</div><div class="notion-text notion-block-36e70f0196348099b65fd12d888c0fa3">設計這句 Prompt 的時候，第一輪的「白話」和「五行以內」花了最多時間調整。怎麼在幾句話裡把接收者程度、教學方法、教學節奏全部鎖死，在不同平台都可以遵從，試了很多版才定下來。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36f70f019634800abb97fdb7ef4da329" data-id="36f70f019634800abb97fdb7ef4da329"><span><div id="36f70f019634800abb97fdb7ef4da329" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36f70f019634800abb97fdb7ef4da329" title="5. AI 自動「修飾」了你的 Prompt"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">5. AI 自動「修飾」了你的 Prompt</span></span></h4><div class="notion-text notion-block-36f70f01963480008b49d0abf0324d85">順帶一提，我後來用 Claude 把這句 Prompt 做成 PDF 時，「智力低下」被它自動換成了「完全看不懂」。Claude 的訓練機制會主動過濾帶貶損意味的詞，即使是自嘲也一樣。原版的效果其實最好，但這件事本身值得注意：你以為 Prompt 是你寫的，有些詞 AI 會自己「修飾」掉。</div><div class="notion-text notion-block-36f70f0196348062ae53f3a7c18ec39e">到這裡，Prompt 解決了「AI 怎麼教」的問題。但就算 AI 教得再好，你有沒有真的學會，還需要另一關來驗證。</div><hr class="notion-hr notion-block-36e70f019634805da671f1833b9d1665"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-36e70f01963480939604fd72bc784f19" data-id="36e70f01963480939604fd72bc784f19"><span><div id="36e70f01963480939604fd72bc784f19" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f01963480939604fd72bc784f19" title="三、承認不會，是學習的起點"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">三、承認不會，是學習的起點</span></span></h3><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36e70f01963480599c52f8bbece2b752" data-id="36e70f01963480599c52f8bbece2b752"><span><div id="36e70f01963480599c52f8bbece2b752" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f01963480599c52f8bbece2b752" title="1. 費曼學習法：能講出來，才算學會"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">1. 費曼學習法：能講出來，才算學會</span></span></h4><div class="notion-text notion-block-36f70f019634800c8e86d3067db87b57"><b>費曼學習法</b>是後人從物理學家費曼的學習習慣整理出來的方法，名字就來自費曼本人。後來 Scott Young 在 2011 年的 MIT 自學挑戰裡大力實踐、推廣，這套方法才真正廣為人知。</div><div class="notion-text notion-block-36f70f01963480c0a2e3f584ce5e6ee2">它的判準很簡單俐落：能用自己的話講出來，才算學會。</div><div class="notion-text notion-block-36f70f019634802c870cfe7ae68548bf">看過不算。覺得自己懂也不算。你要能站在一個完全不懂的人面前，用你的話從頭講一遍。講不清楚的地方，就是你還沒學會的地方。</div><div class="notion-text notion-block-36f70f0196348092b4feffed4affbd53">這也是擋掉流暢效應最直接的方法。AI 寫得再漂亮，你讀完再覺得懂了，只要試著自己講一遍，馬上就知道哪裡是假的。</div><div class="notion-text notion-block-36f70f01963480228113d07e904644a3">試試看：你能不能用自己的話，把剛才讀到的「知識的詛咒」解釋給朋友聽？如果講到一半卡住了，那就是你還沒真的懂的地方。用自己的話講一遍，才是知識內化的過程。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36e70f01963480ac8e06f9068b81e9d4" data-id="36e70f01963480ac8e06f9068b81e9d4"><span><div id="36e70f01963480ac8e06f9068b81e9d4" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f01963480ac8e06f9068b81e9d4" title="2. 對 AI 說「我不會」，沒有社交成本"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">2. 對 AI 說「我不會」，沒有社交成本</span></span></h4><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-36e70f01963480339bd3d514fb9dc79d"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A8b64ec29-3523-477c-9445-daa3857fe9c4%3Aai-learning-zero-social-cost.png?table=block&amp;id=36e70f01-9634-8033-9bd3-d514fb9dc79d&amp;t=36e70f01-9634-8033-9bd3-d514fb9dc79d&amp;width=703.9896240234375&amp;cache=v2" alt="對人類說「我很笨」社交成本極高，對 AI 說「我是完全看不懂的國中生」零摩擦力，強制 AI 降維教學" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">對人類說「我很笨」社交成本極高，對 AI 說「我是完全看不懂的國中生」零摩擦力，強制 AI 降維教學</figcaption></div></figure><div class="notion-text notion-block-36e70f0196348072880eee706ad70060">但這整套東西能幫你的前提是：你得先願意承認自己不會。當你承認不懂並開口問的時候，對方才會用適合你的方式來解釋。</div><div class="notion-text notion-block-36e70f019634802881b8c6cc86b09c00">我們平常不會對人說「我真的很笨，你這樣講我聽不懂」，因為對方可能會手足無措，不知道該怎麼接。但對 AI 說這句話，零社交成本。它不會尷尬，不會覺得你煩，只會調整輸出方式。</div><div class="notion-text notion-block-36e70f019634809d85e5f7ab9b825e0a">所以卡你的從來不是 AI 能不能做到，是你自己願不願意把那句「我聽不懂」講出來。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36e70f0196348094acb8f1645170bf0c" data-id="36e70f0196348094acb8f1645170bf0c"><span><div id="36e70f0196348094acb8f1645170bf0c" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f0196348094acb8f1645170bf0c" title="3. 回答不出來，不代表你很笨"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">3. 回答不出來，不代表你很笨</span></span></h4><div class="notion-text notion-block-36e70f01963480a5a200c249d1fefb38">用這套 Prompt Kit 學東西的時候，AI 會追問你、要你用自己的話講一遍。有時候你會卡住，講不出來。</div><div class="notion-text notion-block-36e70f01963480c4a53cf0b3b13a42c2">有些人碰到這種狀況會馬上覺得自己很差勁，過去義務教育受過的苦像走馬燈一樣在腦海播放過一輪，或者覺得 AI 沒有馬上給到想要的東西，所以 AI 很爛。</div><div class="notion-text notion-block-36e70f01963480659dcbd78fddd9fc44">但學習就是這樣。回答不出來的那個瞬間，不是你的失敗，是你發現了自己真正不懂的地方。那個卡住的點，就是你接下來要去學的東西。</div><div class="notion-text notion-block-36e70f019634803fb706e717b4d6b62d">這條路每個人都要走，沒有人例外。承認自己的無知，是學習的第一步。</div><div class="notion-text notion-block-36e70f01963480948821c07a789bd854">心態上願意承認不會了，接下來的問題是：怎麼在設計上保護這段過程，讓你不會又被 AI 帶回舒適圈？</div><hr class="notion-hr notion-block-36e70f0196348052bc6dc72489f206ed"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-36e70f01963480e1a9c3dcc647363c70" data-id="36e70f01963480e1a9c3dcc647363c70"><span><div id="36e70f01963480e1a9c3dcc647363c70" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f01963480e1a9c3dcc647363c70" title="四、為什麼要刻意讓學習不舒服？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">四、為什麼要刻意讓學習不舒服？</span></span></h3><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36e70f019634808bb41ae518abdfcd56" data-id="36e70f019634808bb41ae518abdfcd56"><span><div id="36e70f019634808bb41ae518abdfcd56" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f019634808bb41ae518abdfcd56" title="1. 從 0 到 1 的過程，不能跳過"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">1. 從 0 到 1 的過程，不能跳過</span></span></h4><div class="notion-text notion-block-36e70f019634809ca8a9d3114727f2b8">如果你看過 Prompt Kit 的完整版，會發現裡面有很多禁止：不准第一輪出公式、不准問題洩漏答案、等我講完才能補細節、連續卡住就暫停不硬推。</div><div class="notion-text notion-block-36e70f01963480b79753d85d256c50fb">為什麼設這麼多限制？</div><div class="notion-text notion-block-36e70f019634800490cfd6c3ec0954ff">因為如果 AI 一開始就把公式丟給你，你會跳過自己摸索的階段，直接進入「看起來懂了」的錯覺。學習發生的地方，就在你掙扎的那幾分鐘：試著用自己的話說一遍、發現說不清楚、回去重新理解、再來一次。</div><div class="notion-text notion-block-36e70f019634808e94b5ff0377bfff92">很多人用 AI 學東西會掉進流暢效應的陷阱，就是因為省略了從 0 到 1 那段掙扎。但那段掙扎，才是學習本身。</div><div class="notion-text notion-block-36e70f01963480c1a8e9d9f3e365ec65">雖然很反直覺，但慢慢來，才會走得更快、更遠。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36e70f0196348050a8a3e5587d938092" data-id="36e70f0196348050a8a3e5587d938092"><span><div id="36e70f0196348050a8a3e5587d938092" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f0196348050a8a3e5587d938092" title="2. 80/20 兩輪制：先白話，再補公式"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">2. 80/20 兩輪制：先白話，再補公式</span></span></h4><div class="notion-text notion-block-36e70f01963480538e5bc257201263f8">Prompt Kit 把學習拆成兩輪。第一輪只給你最關鍵的 20%，用白話和比喻，不准出公式。你要先用自己的話講一遍，通過了，AI 才補剩下的 80%。</div><div class="notion-text notion-block-36e70f01963480e193e2de2a7f214c2c">根據 80/20法則，約 20% 的關鍵因素，會產生約 80% 的結果。</div><div class="notion-text notion-block-36e70f019634809c8241c23af75e29e5">在學習新知裡，我們可以運用 80/20法則，讓 AI 提煉出最核心的概念，再據此延伸細節。</div><div class="notion-text notion-block-36e70f01963480e98be5c9e92d6d8420">比方說你在學「沉沒成本」。AI 先用比喻教你：「你花了三百塊買了一張電影票，看了半小時覺得很難看。你會因為已經花了三百塊而繼續看嗎？如果會，那三百塊就是你的沉沒成本。」然後它問你：用你的話講一遍。你講完了，它才補經濟學的定義和公式。</div><div class="notion-text notion-block-36e70f01963480fc8facd01aac6d1c25">如果你講不出來，它不會直接告訴你答案，而是問你「卡在哪一步」，讓你練習表達自己為何不懂。講出自己哪裡不懂，本身就可以練習覺察跟表達能力，以及認識自己的能力邊界，而這些正是 AI 時代最需要的軟實力。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-36e70f0196348099badcf8ca02044c8f" data-id="36e70f0196348099badcf8ca02044c8f"><span><div id="36e70f0196348099badcf8ca02044c8f" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f0196348099badcf8ca02044c8f" title="3. 驗收怎麼設計？簡單，但要你自己回答"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">3. 驗收怎麼設計？簡單，但要你自己回答</span></span></h4><div class="notion-text notion-block-36e70f019634800fabb5c13bc543374b">驗收這一塊我是刻意設計過的。我希望它不要太複雜，但要有效地逼你自己回答問題。不是選擇題、不是填空，是要你用自己的話講出來。</div><div class="notion-text notion-block-36e70f019634804e8e12c32266ad6461">AI 問你的時候不會洩漏答案，不會暗示方向。你答對了，它問你「怎麼推到的」。你答錯了，它問你「卡在哪一步」。</div><div class="notion-text notion-block-36e70f019634804888a2d77e06e59068">前面的白話解說是開場，後面的追問和復盤，才是我們真正讓知識與自己產生連結的過程。</div><hr class="notion-hr notion-block-36e70f019634806eba8aff8bf0841e21"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-36e70f019634800dae25ff2a09a5920e" data-id="36e70f019634800dae25ff2a09a5920e"><span><div id="36e70f019634800dae25ff2a09a5920e" class="notion-header-anchor"></div><a class="notion-hash-link" href="#36e70f019634800dae25ff2a09a5920e" title="結語：走過的路，讓它留下來"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">結語：走過的路，讓它留下來</span></span></h3><div class="notion-text notion-block-36e70f019634801da17ff0aa2245c62f">回到一開始的問題：為什麼有時候用 AI 輔助學習，卻少了一種踏實感？</div><div class="notion-text notion-block-36e70f019634809bacb5f2563f1cec15">如果你有這種感覺，那可能是因為我們把學習過程中最關鍵的那一段外包給了 AI。讓它摘要、讓它整理、讓它洞察、讓它幫我們省掉那段掙扎。但省掉的那段，剛好就是學習本身。</div><div class="notion-text notion-block-36e70f019634804b9d73fdb688d32627">這套 Prompt Kit 做的事情很簡單：把解釋和整理的工作交給 AI，但把思考留給你自己。AI 負責用你聽得懂的方式教，你負責用自己的話講一遍。卡住了就承認卡住，講不出來就回去重學。</div><div class="notion-text notion-block-36e70f019634801ba411d916c799f0d3">最簡單的用法，就是把這套 Prompt 貼進任何 AI 開始學。如果你用 Claude 或 ChatGPT，還可以存成 Skill 或自訂指令，每次開新對話就自動載入，不用重貼。</div><div class="notion-text notion-block-36e70f01963480ada032d71a00f372e4">但更好的做法，是讓每次的深度學習都成為你的知識資產。</div><div class="notion-text notion-block-36e70f019634800cae74d07235be1fe1">每次對話結束後，讓 AI 把你剛才學到的核心概念整理成一張知識卡片，存成一份筆記。下次遇到相關問題，你不用從零開始，因為那張卡片記著你當時怎麼理解、卡在哪裡、最後怎麼想通的。</div><div class="notion-text notion-block-36e70f0196348061bbcdf5ffc3a8f604">AI 教練負責教，費曼學習法負責驗證你有沒有真的懂，卡片盒筆記法負責把學到的東西留住。三個疊在一起，知識就不再是讀過就忘的消耗品，而是可以不斷累積的資產。</div><div class="notion-text notion-block-36e70f01963480148e2de5ff5253806e">如何利用 md 文件讓 Agent 有自己的記憶系統，進而打造自己的知識庫，就是更進階的運用了👍</div><div class="notion-text notion-block-68fd6a0a0dbe487db874b356c3d4c26b">（延伸閱讀：<a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://gyozalab.com/prompt-to-context-engineering-evolution">別再跟 AI 雞同鴨講：2026 提示工程從入門到 Agent 實戰</a>）</div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-36e70f01963480b0b5a8f727167201e1"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A97f670b6-8140-4bd8-a744-1fbe0517f852%3Afeynman-knowledge-network.png?table=block&amp;id=36e70f01-9634-80b0-b5a8-f727167201e1&amp;t=36e70f01-9634-80b0-b5a8-f727167201e1&amp;width=703.9896240234375&amp;cache=v2" alt="煎餃角色仰望發光的知識網路，象徵學習的本質是跟世界產生關聯" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">煎餃角色仰望發光的知識網路，象徵學習的本質是跟世界產生關聯</figcaption></div></figure><blockquote class="notion-quote notion-block-36e70f0196348010a17edc4f1315b131"><div>💡 承認自己的無知，是學習的第一步。工具會一直變、知識會一直變，但學會怎麼學的人，永遠能重新開始。</div></blockquote><div class="notion-callout notion-brown_background_co notion-block-36e70f019634804e8eacedba50d79e2c"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="📌">📌</span></div><div class="notion-callout-text"><div class="notion-text notion-block-36e70f01963480c2b7dae6bd1b40df31">讀到這裡，你已經知道為什麼學習需要那段掙扎，也知道費曼學習法怎麼逼出你真正不懂的地方。剩下的，只差你願不願意現在就開始。</div><div class="notion-text notion-block-36f70f0196348049a6fae6e29915004c">如果你想要這個隨身的 AI 學習教練，我做了一份免費的 Prompt Kit，把這套設計打包成可以直接丟進任何 AI 的格式。</div><div class="notion-text notion-block-36e70f019634801cb996d52b9f1d0653">學習就是被虐的過程，不論是 Claude、ChatGPT 還是 Gemini，整包上傳就馬上開始 😎</div><div class="notion-text notion-block-36e70f01963480808777eb67ab451992">🥟<a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://portaly.cc/gyozalab/product/wSQRLKk0CQvUmxS97fTA"> 免費下載：煎餃的費曼學習法 Prompt Kit</a></div><div class="notion-text notion-block-36e70f0196348035a9a0f79aa073ceee">🎬 <a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://www.youtube.com/watch?v=R5b9xh7Oe_g">看完三秒就忘？用 AI + 費曼學習法打造私人家教：完整直播回放</a></div></div></div></main></div>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[AI 怎麼看懂一張照片？從像素到語意的電腦視覺全解析]]></title>
            <link>https://gyozalab.com/computer-vision-from-pixels-to-ethics</link>
            <guid>https://gyozalab.com/computer-vision-from-pixels-to-ethics</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[一張照片進到模型裡會經歷什麼？從 HOG 手工特徵到 ResNet 深度學習，拆解分類、偵測、分割 5 大視覺任務的原理與評估指標。附 COVID AI 誤判、人臉辨識偏差等真實失敗案例。]]></description>
            <content:encoded><![CDATA[<div id="notion-article" class="mx-auto overflow-hidden "><main class="notion light-mode notion-page notion-block-34470f019634806b8407ff1de4eb5b22"><div class="notion-viewport"></div><div class="notion-collection-page-properties"></div><div class="notion-callout notion-block-c46da4895b4744f5b40c4ba1e14c63d6"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="🎯">🎯</span></div><div class="notion-callout-text"><div class="notion-text notion-block-f8b3f629b49d43c1b488a1ae1c6026b9">電腦視覺從人工手設 HOG、SIFT 特徵，經 2012 年 AlexNet 讓 CNN 自學特徵；分類到全景分割五種任務各有評估指標，效果高度依賴人工標註品質。EU AI Act 將人臉辨識列高風險，視覺 AI 的演進已不只是技術問題，更是倫理與治理課題。</div></div></div><div class="notion-text notion-block-34e70f019634803ab232fd4fb1eb4a84">人類看一眼就能分辨貓狗，但對電腦而言，一張照片就像是一幅由數百萬塊馬賽克拼湊而成的巨型壁畫。電腦只知道一坨馬賽克，卻看不懂這些影像數據在真實世界的意義。</div><div class="notion-text notion-block-34470f0196348098abe0dade91aec292">為了跨越這道感知落差，科學家耗費半個世紀，試圖讓機器學會「看懂」圖片。</div><div class="notion-text notion-block-34e70f019634801a8e3cd9c179ca5f66">電腦視覺從早期 SIFT、Haar、HOG 等特徵工程方法，走到 2012 年 AlexNet 開啟的深度學習浪潮；分類、偵測、分割等任務各有不同輸出與評估標準，背後則高度依賴人工標註與資料治理。到了 2024 年，EU AI Act 正式生效，也讓電腦視覺不再只是技術問題，而是治理問題（延伸閱讀：<a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://gyozalab.com/ipas-l111-ai-overview">你信任 AI 的判斷嗎？人機協作、透明度與 AI 治理入門</a>）。</div><div class="notion-text notion-block-34470f019634805e82ddcd72866c789c">本文將深度拆解電腦視覺（Computer Vision, CV）的發展脈絡：從早期人類手動設計規則的「特徵工程」，到撕毀說明書、讓機器自學的「CNN 革命」，並進一步剖析現今主流的五大視覺任務與評估判準。你將會發現，機器之所以能精準辨識物體，並非因為它具備人類的意識，而是建立在強大的數學模型與海量的人工標註數據之上。</div><hr class="notion-hr notion-block-34470f01963480cbbd79c13a6128e296"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-34470f0196348075a4bbc11f669348e2" data-id="34470f0196348075a4bbc11f669348e2"><span><div id="34470f0196348075a4bbc11f669348e2" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34470f0196348075a4bbc11f669348e2" title="一、特徵工程時期：人類先替機器決定「該看什麼」（1999-2011）"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>一、特徵工程時期：人類先替機器決定「該看什麼」（1999-2011）</b></span></span></h3><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f01963480b0be10f57e1c19024a" data-id="34e70f01963480b0be10f57e1c19024a"><span><div id="34e70f01963480b0be10f57e1c19024a" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480b0be10f57e1c19024a" title="1. 機器眼中的世界：0 到 255 的亮度值"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>1. 機器眼中的世界：0 到 255 的亮度值</b></span></span></h4><div class="notion-callout notion-brown_background_co notion-block-34470f0196348078a79bdf2eecacf66d"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-34470f01963480f5ab57e8744ab0b0d9"><b>我們看貓是毛茸茸的可愛生物，機器看到的到底是什麼東西，才會連貓狗都分不出來？</b></div><div class="notion-text notion-block-34470f0196348065b1e0fe588fa8d0a2">機器其實是個「色盲且大近視」，它看到的不是貓，而是 0 到 255 的亮度值，對彩色影像而言，則通常是 RGB 三個通道共同組成。因為全是數字，人類才需要發明 <b>HOG</b> 或 <b>Haar Cascade</b> 這種「數學濾鏡」，把這些雜亂的數字理出線條。</div></div></div><div class="notion-text notion-block-34e70f0196348011b11de39f97321544">CNN 革命之前，機器就像一個剛出生的嬰兒，如果你不跟它說「貓耳朵是三角形的」，它就絕對看不出來。工程師必須親手設計「數學公式」（即特徵工程），告訴機器該看哪裡。</div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-34570f019634800a9aa9d8c46bb2b5d7"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A6032d937-f44b-41e4-ab86-1e5b8744976f%3Atraditional-computer-vision-feature-extraction.jpg.png?table=block&amp;id=34570f01-9634-800a-9aa9-d8c46bb2b5d7&amp;t=34570f01-9634-800a-9aa9-d8c46bb2b5d7&amp;width=704&amp;cache=v2" alt="解說傳統電腦視覺「人工設計特徵」的圖解，用貓咪偵探比喻 HOG（方向梯度直方圖）、SIFT（尺度不變特徵變換）與 Haar 級聯等數學濾鏡是如何捕捉影像邊緣與特徵點。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">解說傳統電腦視覺「人工設計特徵」的圖解，用貓咪偵探比喻 HOG（方向梯度直方圖）、SIFT（尺度不變特徵變換）與 Haar 級聯等數學濾鏡是如何捕捉影像邊緣與特徵點。</figcaption></div></figure><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f0196348045947bdd0cfd25da3c" data-id="34e70f0196348045947bdd0cfd25da3c"><span><div id="34e70f0196348045947bdd0cfd25da3c" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f0196348045947bdd0cfd25da3c" title="2. 特徵工程時代的三大代表工具"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>2. 特徵工程時代的三大代表工具</b></span></span></h4><div class="notion-text notion-block-34e70f0196348050a626f2c4fc4b3543">那段時期的開發者，主要依賴幾種代表性的手工特徵方法來賦予機器視覺。像是 SIFT 擅長找穩定的關鍵點，常用在影像匹配與拼接；Haar Cascade 擅長快速做人臉等目標的粗偵測；而 HOG 則在 2005 年後成為經典的行人偵測方法之一，透過統計局部梯度方向來描述輪廓結構。</div><div class="notion-text notion-block-34470f019634801e96a4cc4c3fef98d8">那段時期的開發者主要依賴以下三套工具來賦予機器視覺：</div><ul class="notion-list notion-list-disc notion-block-34470f0196348058a910fe7347ccc53a"><li><b>HOG（方向梯度直方圖）— 偵測邊緣的「素描大師」</b></li><ul class="notion-list notion-list-disc notion-block-34470f0196348058a910fe7347ccc53a"><li>工程師設定公式去計算影像中顏色變化的方向。它會把貓咪的照片切成無數個小格子，統計每一格的「線條斜度」。如果線條拼起來像個圓形，機器就覺得那是貓頭。</li><li><b>過去實作：</b> 最早被大量用在「行人偵測」。它能辨識出直立的人形輪廓，讓早期的智慧監視器知道有人經過。</li><li><b>缺點：</b> 禁不起<b>形變</b>。如果人是趴著、倒立，或是被雨傘遮住一半，HOG 就會因為線條對不上而認不出來。</li></ul></ul><ul class="notion-list notion-list-disc notion-block-34470f01963480bc9170fb755147abda"><li><b>SIFT（尺度不變特徵轉換）— 尋找印記的「偵探」</b></li><ul class="notion-list notion-list-disc notion-block-34470f01963480bc9170fb755147abda"><li>在影像中找出一些具有代表性的「關鍵點」（例如拐角、斑點），並幫這些點做標記。最厲害的是，不論物體變大、變小或旋轉，這些點的<b>相對特徵</b>都不會變。</li><li><b>過去實作：</b> 手機相機的「影像拼接」（全景模式）。它能找出兩張照片重疊處的關鍵點，像扣鈕扣一樣把兩張照片完美黏在一起。</li><li><b>缺點：</b> <b>運算成本高</b>。要在每一幀影像中搜尋並比對成千上萬個特徵點，對早期電腦的處理器（CPU）壓力很大。</li></ul></ul><ul class="notion-list notion-list-disc notion-block-34470f01963480438634f0cff5827ef7"><li><b>Haar Cascade （哈爾級聯）— 判斷光影的「五官快搜」</b></li><ul class="notion-list notion-list-disc notion-block-34470f01963480438634f0cff5827ef7"><li>利用簡單的黑白矩形滑過影像，計算兩者之間的<b>亮度差</b>。例如：眼睛區域通常比額頭暗、鼻樑比兩側亮，符合這些「光影比例」的就判定是臉。</li><li><b>過去實作：</b> 數位相機的「自動對焦框」。它能用極快的速度在畫面中亂掃，瞬間抓出人臉位置，讓你拍照時不會失焦。</li><li><b>缺點：</b> <b>環境適應力差</b>。只要光線太暗、陰影太重，或是人臉稍微側一點，光影比例一變，它就完全失效了。</li></ul></ul><div class="notion-text notion-block-34470f01963480ed9012c12c7ecda191">這套做法雖然運算輕巧，但天花板卡在工程師的腦袋。對於辨識貓狗或許還行，但遇到像 <b>X 光片診斷</b> 這種任務就卡死了，因為連醫生都難以用簡單的幾何特徵或光影比例，來定義什麼叫「肺部異常陰影」。</div><hr class="notion-hr notion-block-34e70f01963480cf9879fa2fc3afa12c"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-34470f01963480748900d4a2715f1f03" data-id="34470f01963480748900d4a2715f1f03"><span><div id="34470f01963480748900d4a2715f1f03" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34470f01963480748900d4a2715f1f03" title="二、CNN 革命：機器搶走特徵設計權（2012-2020）"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">二、CNN 革命：機器搶走特徵設計權（2012-2020）</span></span></h3><div class="notion-callout notion-brown_background_co notion-block-34470f0196348049b5a3df19afa545cf"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-34470f01963480128bf6f4b77803b4ad"><b>既然我們都能量出貓耳朵的角度、算出眼睛的光影，為什麼這套技術沒辦法一直用下去？</b></div><div class="notion-text notion-block-34470f019634803296b9e3a30d950e7c">人類可以寫出 100 種定義貓的公式，但現實世界有 1 萬種貓的樣子。當貓咪側躺、躲在紙箱、黑貓在黑沙發上，軟爛成一攤液體，這套技術就認不出來了！</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f01963480739ccbe7c22b2c6880" data-id="34e70f01963480739ccbe7c22b2c6880"><span><div id="34e70f01963480739ccbe7c22b2c6880" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480739ccbe7c22b2c6880" title="1. 2012 AlexNet 地震：CNN 時代的來臨"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>1. 2012 AlexNet 地震：CNN 時代的來臨</b></span></span></h4><div class="notion-text notion-block-34470f01963480119726c0be85e14ec2">到了 2012 年，AlexNet 幾乎像是按下了電腦視覺的換代鍵。它在影像辨識比賽中明顯打贏當時主流方法，讓大家開始相信：與其靠人類手工設計特徵，不如讓模型自己從海量圖片裡學規律。從這一刻開始，深度學習慢慢取代了特徵工程，成為主流。</div><div class="notion-text notion-block-34e70f01963480db885dc78249e6b691">AlexNet 不是孤獨的勝者，而是 CNN 模型線的引爆點。前後 17 年出現的代表模型，構成了一條從淺到深的演進線：</div><table class="notion-simple-table notion-block-34e70f0196348085b39bf50004d7d99c"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-34e70f01963480389f5cd00546d21fcb"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>年份</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>模型</b></div></td><td class="" style="width:79px"><div class="notion-simple-table-cell"><b>層數</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>關鍵突破</b></div></td></tr><tr class="notion-simple-table-row notion-block-34e70f0196348058bbadedaa403efff8"><td class="" style="width:120px"><div class="notion-simple-table-cell">1998</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>LeNet</b>（Yann LeCun）</div></td><td class="" style="width:79px"><div class="notion-simple-table-cell">5</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">最早的 CNN，用於手寫數字辨識</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f0196348045b344f3781341fe6a"><td class="" style="width:120px"><div class="notion-simple-table-cell">2012</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>AlexNet</b></div></td><td class="" style="width:79px"><div class="notion-simple-table-cell">8</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">引爆深度學習，ReLU + Dropout</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f01963480818fa7c6d4ec55c93a"><td class="" style="width:120px"><div class="notion-simple-table-cell">2014</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>VGG</b></div></td><td class="" style="width:79px"><div class="notion-simple-table-cell">19</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">證明「深度＝準確度」，全用 3×3 小卷積核</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f01963480299ba1c5fbf407243e"><td class="" style="width:120px"><div class="notion-simple-table-cell">2015</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>ResNet</b></div></td><td class="" style="width:79px"><div class="notion-simple-table-cell">152</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">殘差連接破解梯度消失</div></td></tr></tbody></table><div class="notion-text notion-block-34e70f0196348076a16ffc3310673977">每一代都解決了上一代的瓶頸：AlexNet 靠 ReLU 解決深層訓練梯度死掉、VGG 用小卷積核證明深度本身就是力量、ResNet 用殘差連接讓 152 層成為可能。</div><div class="notion-text notion-block-34470f01963480dcaf77e08d2265fe20">這意味著什麼？人類沒有從此完全退出，但特徵設計的重心改變了。過去工程師要手動規定機器看耳朵、看輪廓、看亮暗；進入深度學習時代後，工程師改成設計網路架構、準備資料、定義訓練目標，讓模型自己從大量樣本中學會有效表徵。</div><div class="notion-text notion-block-34470f01963480abbbd7d42435a465f4">過去，人類像個囉嗦的教練，拿著說明書一條一條教電腦：「貓有三角形的耳朵、圓形的臉」。但電腦死腦筋，貓一變胖就不認得了。</div><div class="notion-text notion-block-34570f01963480b0add8fae0828144cb">深度學習的崛起帶來了典範轉移，科學家決定把說明書撕掉，直接把一百萬張貓的照片砸到電腦臉上，跟它說：「你自己看著辦，找出牠們的共通點！」讓它自己去歸納規律。這個過程在學術上稱為表示學習 (Representation Learning)。</div><div class="notion-text notion-block-34470f019634801e80c8c0e5b500dead"><b>卷積神經網路 (CNN) </b>模仿人類視覺皮層運作，它的大腦裡有一層一層的「濾鏡」，像是一個闖關遊戲。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f01963480d7b453ca3160f4a71f" data-id="34e70f01963480d7b453ca3160f4a71f"><span><div id="34e70f01963480d7b453ca3160f4a71f" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480d7b453ca3160f4a71f" title="2. ResNet 殘差連接：怎麼讓 152 層的網路還記得最初那隻貓"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>2. ResNet 殘差連接：怎麼讓 152 層的網路還記得最初那隻貓</b></span></span></h4><div class="notion-callout notion-brown_background_co notion-block-34470f01963480b9aed4c9f7e5b0491a"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-34470f01963480b7b3bcc05f2ef99597"><b>大家都說深度學習的網路越深越好，那我們能不能疊個一百層？</b></div><div class="notion-text notion-block-34470f0196348053aeedc7b8c8d8044b">因為神經網路就像傳聲筒遊戲，一層一層將聲音傳遞到後面，又從後面將指令傳回第一個人，這樣來回排在最前面的網路根本聽不到修正指令，永遠學不會看特徵。</div><div class="notion-text notion-block-34470f01963480efbe63c29fbacfa6af">學術上稱為<b>梯度消失（Vanishing Gradient）</b>。</div></div></div><div class="notion-text notion-block-34470f0196348091ab45d4a00bd0bcfc">直到後來，微軟團隊提出了 ResNet 模型，發明了「<b>殘差連接 (Residual Connection)</b>」技術。這就像是在一層一層傳遞的網路中，架設了無數條直達一樓的專線電話，確保最原始的貓咪特徵不會在傳遞中被遺忘。ResNet 成功突破了 152 層的極限，徹底證明了「讓機器自動學特徵」這條路不僅走得通，而且深不可測。</div><div class="notion-text notion-block-34470f019634807ba13accda179798ab">電腦的眼睛，就此從被動測量的尺規，進化成能主動提取抽象概念的強大視覺系統。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f01963480ca9905fb8e26eaf08a" data-id="34e70f01963480ca9905fb8e26eaf08a"><span><div id="34e70f01963480ca9905fb8e26eaf08a" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480ca9905fb8e26eaf08a" title="3. CNN 的大腦構造：這五層濾鏡是如何分工的？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>3. CNN 的大腦構造：這五層濾鏡是如何分工的？</b></span></span></h4><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-34e70f019634804fb6e0efd1e7bfdeaa"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A6c0c62c4-813c-47d6-ae06-042031e3a1b5%3Acnn-five-layers-cat-analogy.jpg?table=block&amp;id=34e70f01-9634-804f-b6e0-efd1e7bfdeaa&amp;t=34e70f01-9634-804f-b6e0-efd1e7bfdeaa&amp;width=1080&amp;cache=v2" alt="透過擬人化貓咪演繹卷積神經網路 CNN 的五大核心架構，生動解釋從卷積層捕捉細微特徵、激活層過濾無效信號、池化層進行數據壓縮瘦身、全連接層推理特徵含義到最終輸出層分類結果的運作過程，是快速理解電腦視覺底層邏輯與深度學習模型運算原理的專業技術圖表，有助於掌握 AI 特徵提取的關鍵流程。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">透過擬人化貓咪演繹卷積神經網路 CNN 的五大核心架構，生動解釋從卷積層捕捉細微特徵、激活層過濾無效信號、池化層進行數據壓縮瘦身、全連接層推理特徵含義到最終輸出層分類結果的運作過程，是快速理解電腦視覺底層邏輯與深度學習模型運算原理的專業技術圖表，有助於掌握 AI 特徵提取的關鍵流程。</figcaption></div></figure><div class="notion-text notion-block-34e70f01963480a189f4ebcca357bfde">卷積神經網路（CNN）並非單一工具，而是由五個層次分工合作的精密系統。機器學習「抽特徵」的關鍵就在這五關：</div><table class="notion-simple-table notion-block-34e70f019634802e8f07efc66bdf1a28"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-34e70f01963480fc8d1de8668ab51cd9"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>層次</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>角色</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>動作</b></div></td></tr><tr class="notion-simple-table-row notion-block-34e70f019634801bbc58f77a611e87bc"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>卷積層</b>（Convolutional Layer）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">抽特徵</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">用卷積核掃過影像，產生特徵圖</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f0196348060af4af64d54029e05"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>池化層</b>（Pooling Layer）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">瘦身</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">壓縮特徵圖（最常用 Max-Pooling）</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f019634806e9130e56c8238d13b"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>激活層</b>（Activation Layer）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">加非線性</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">用 ReLU 等函數讓網路學得到複雜模式</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f0196348085ba4fd62984572fb9"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>全連接層</b>（Fully Connected Layer）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">整合</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">把抽出的特徵壓成一維向量</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f019634800598d5edfe91474571"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>輸出層</b>（Output Layer）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">給答案</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">用 Softmax 轉成各類別的機率</div></td></tr></tbody></table><div class="notion-text notion-block-34e70f019634809bbd84cd7e1fbd41f6">CNN 的三層濾鏡讓機器學會抽特徵，但中間怎麼壓縮、最後怎麼輸出，靠的是兩個關鍵元件：<b>Max-Pooling</b>（中間層瘦身）跟 <b>Softmax</b>（最後一層轉機率）。</div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-34d70f019634800797ead2cdaf9d4356"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Ad9715a96-ff24-461c-a122-45dad5ae821a%3Asoftmax-vs-max-pooling-difference-explained.png?table=block&amp;id=34d70f01-9634-8007-97ea-d2cdaf9d4356&amp;t=34d70f01-9634-8007-97ea-d2cdaf9d4356&amp;width=704&amp;cache=v2" alt="深度學習概念對照表：Softmax vs. Max-Pooling。Softmax 被描述為「雨露均霑」，將輸出轉換為機率分布，代表每個類別的可能性；Max-Pooling 被描述為「強者通吃」，僅保留區域內的最大值並捨棄其餘資訊。底部總結 Softmax 關注個體重要性（民主投票），Max-Pooling 關注最強信號（皇帝制度）。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">深度學習概念對照表：Softmax vs. Max-Pooling。Softmax 被描述為「雨露均霑」，將輸出轉換為機率分布，代表每個類別的可能性；Max-Pooling 被描述為「強者通吃」，僅保留區域內的最大值並捨棄其餘資訊。底部總結 Softmax 關注個體重要性（民主投票），Max-Pooling 關注最強信號（皇帝制度）。</figcaption></div></figure><ul class="notion-list notion-list-disc notion-block-34e70f01963480dcae2bed4233838ca1"><li><b>Softmax：把分數換成機率的最後一道門</b></li><ul class="notion-list notion-list-disc notion-block-34e70f01963480dcae2bed4233838ca1"><div class="notion-text notion-block-34e70f01963480ba8309e60e59dff1a3">CNN 做分類時，最後一層會吐一串原始分數，但這些數字直接看不出意義。Softmax 把它換成讀得懂的機率。</div><ol start="1" class="notion-list notion-list-numbered notion-block-34e70f01963480728e99d64cda568b69" style="list-style-type:decimal"><li><b>位置</b>：分類網路的<b>最後一層</b></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-34e70f01963480bbb167ce78f78025d6" style="list-style-type:decimal"><li><b>作用</b>：把原始分數轉成機率，全部類別加起來等於 1</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-34e70f0196348017a2acf6f68d742610" style="list-style-type:decimal"><li><b>比喻</b>：把全班成績單改成百分比。每個人還在表上，全班加起來剛好 100%</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-34e70f01963480418348e4e377da99a4" style="list-style-type:decimal"><li><b>例子</b>：原始分數「貓 8.2、狗 5.1、車 0.3」→ Softmax 後「貓 0.95、狗 0.04、車 0.01」</li></ol></ul></ul><ul class="notion-list notion-list-disc notion-block-34e70f01963480b98fb2d214fe0d8a3c"><li><b>Max-Pooling：在中間層壓縮特徵圖</b></li><ul class="notion-list notion-list-disc notion-block-34e70f01963480b98fb2d214fe0d8a3c"><div class="notion-text notion-block-34e70f0196348042a874f4f770baa3cd">CNN 一張圖經過卷積後會產生很多大張的「特徵圖（feature map）」，運算成本貴。Max-Pooling 在中間幫忙瘦身，只保留最強訊號。</div><ol start="1" class="notion-list notion-list-numbered notion-block-34e70f0196348024bfb4eedfbf5f1a2f" style="list-style-type:decimal"><li><b>位置</b>：CNN 網路的<b>中間層</b></li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-34e70f0196348033a945f8b2d1c56ec3" style="list-style-type:decimal"><li><b>作用</b>：把特徵圖切成小區塊（例如 2×2），每塊只留最大值，其他丟掉</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-34e70f01963480b29895d0a1eff350f4" style="list-style-type:decimal"><li><b>比喻</b>：每個班只留第一名。其他人不被記錄</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-34e70f0196348065b96ec1356cf39b77" style="list-style-type:decimal"><li><b>例子</b>：2×2 區塊「[3, 1] / [2, 8]」→ Max-Pooling 後只剩「8」</li></ol></ul></ul><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f0196348008ada8dc96b9733286" data-id="34e70f0196348008ada8dc96b9733286"><span><div id="34e70f0196348008ada8dc96b9733286" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f0196348008ada8dc96b9733286" title="4. CNN 三關闖關：從邊緣紋理到語意概念"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>4. CNN 三關闖關：從邊緣紋理到語意概念</b></span></span></h4><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-34e70f01963480ad840fd42272214c55"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Ae46eea91-6e05-45e6-8f69-6c962143a252%3Acnn-feature-extraction-layers-cat.jpg?table=block&amp;id=34e70f01-9634-80ad-840f-d42272214c55&amp;t=34e70f01-9634-80ad-840f-d42272214c55&amp;width=1080&amp;cache=v2" alt="圖解卷積神經網路（CNN）的貓隻識別技術，透過淺層、中層到深層濾波器，展示 AI 如何從邊緣紋理、局部肢體到完整識別出一隻貓的過程。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">圖解卷積神經網路（CNN）的貓隻識別技術，透過淺層、中層到深層濾波器，展示 AI 如何從邊緣紋理、局部肢體到完整識別出一隻貓的過程。</figcaption></div></figure><ul class="notion-list notion-list-disc notion-block-34e70f019634804bb6f8ddf3203ee616"><li><b>第一關（淺層濾鏡）：</b> 電腦像個大近視眼，只看得到畫面中最基本的線條、光影邊界（例如貓咪背部的一條弧線，或是一條斜線）。</li></ul><ul class="notion-list notion-list-disc notion-block-34e70f0196348061b45ae10716c50ab9"><li><b>第二關（中層濾鏡）幾何圖形：</b> 它把上一關的線條拼起來，發現「咦！兩條斜線可以拼成一個小三角形，幾條弧線可以圍成圓形」。</li></ul><ul class="notion-list notion-list-disc notion-block-34e70f0196348003ac53e897803af268"><li><b>第三關（深層濾鏡）語意概念 ：</b> 它再把形狀拼起來，突然頓悟了：「小三角形加圓形，再配上剛剛的直線，原來這組合起來就是『貓耳朵』和『貓臉』啊！」</li></ul><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34470f019634807ea11bcdd6b7b01215" data-id="34470f019634807ea11bcdd6b7b01215"><span><div id="34470f019634807ea11bcdd6b7b01215" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34470f019634807ea11bcdd6b7b01215" title="5. 特徵工程 vs CNN：兩階段對照表"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>5. 特徵工程 vs CNN：兩階段對照表</b></span></span></h4><table class="notion-simple-table notion-block-34470f019634806a8db1f0490b120c55"><tbody><tr class="notion-simple-table-row notion-block-34470f0196348050a550cded1b020735"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>比較維度</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>傳統特徵工程時代 (前 2012 年)</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>CNN 深度學習革命 (2012 年後)</b></div></td></tr><tr class="notion-simple-table-row notion-block-34470f01963480cdb3cfd566a654a4fb"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>核心概念</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>人工設計 (Hand-crafted)</b>
人類告訴電腦該看什麼。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>表示學習 (Representation Learning)</b>
機器自己從資料中找出規律。</div></td></tr><tr class="notion-simple-table-row notion-block-34470f0196348012ab8ccae2f9f79186"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>特徵擷取者</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>領域專家與工程師</b>
利用數學公式手動設計濾鏡（如 HOG 算梯度、SIFT 找極值點）。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>卷積層 (Convolutional Layers)</b>
神經網路透過反覆訓練，自動將像素組合成邊緣、形狀到語意。</div></td></tr><tr class="notion-simple-table-row notion-block-34470f019634808db05ff263fe0b4082"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>資料量依賴度</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>較低</b>
幾百或幾千張圖片即可運作，因為規則已經由人類寫死。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>極高</b>
需要海量標註數據（如 ImageNet 的百萬張圖）來讓機器「歸納」經驗。</div></td></tr><tr class="notion-simple-table-row notion-block-34470f01963480758169e4dec501e2f6"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>硬體運算需求</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>較低</b>
主要依賴 CPU 運算，適合早期資源受限的設備。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>極高</b>
強烈依賴 GPU 的平行運算能力來處理龐大的矩陣相乘。</div></td></tr><tr class="notion-simple-table-row notion-block-34470f01963480309425d3c14417d319"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>技術門檻重點</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>領域知識 (Domain Knowledge)</b>
需要深厚的數學與電腦視覺理論基礎才能設計出好特徵。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>架構與資料 (Architecture &amp; Data)</b>
重心轉移至模型架構設計（如 ResNet）與資料品質管理（MLOps）。</div></td></tr><tr class="notion-simple-table-row notion-block-34470f0196348042bb51eb953ccca6f5"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>效能天花板</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>容易遇到瓶頸</b>
面對複雜的光影、角度變化或遮擋，人工設計的規則很難窮舉。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>持續突破</b>
只要資料夠多、網路夠深、算力夠強，模型效能就能不斷提升。</div></td></tr></tbody></table><hr class="notion-hr notion-block-34470f01963480c989bbdd569418b4fe"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-34470f019634800e9cddf849ad3e381c" data-id="34470f019634800e9cddf849ad3e381c"><span><div id="34470f019634800e9cddf849ad3e381c" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34470f019634800e9cddf849ad3e381c" title="三、同一張圖，模型到底在回答什麼問題？五種任務與五套判準"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>三、同一張圖，模型到底在回答什麼問題？五種任務與五套判準</b></span></span></h3><div class="notion-callout notion-brown_background_co notion-block-34470f01963480a38f9fc1c1af41009a"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-34470f01963480149139d5d125b94282"> <b>CNN 都能認出貓狗了，為什麼還要分五種不同的看法？ 分類一個不夠用嗎？</b> </div><div class="notion-text notion-block-34470f01963480139e3ee28620cb596a">因為「是什麼」、「在哪裡」、「每個像素屬於誰」是三種截然不同的問題，一個模型架構回答不了全部。</div></div></div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-34d70f019634807595a1e3d4ff90012e"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A700c8acf-72d6-4c32-bcec-be5df9820e49%3Acomputer-vision-tasks-vs-segmentation-metrics-guide.jpg?table=block&amp;id=34d70f01-9634-8075-95a1-e3d4ff90012e&amp;t=34d70f01-9634-8075-95a1-e3d4ff90012e&amp;width=703.9896240234375&amp;cache=v2" alt="電腦視覺五大任務解析圖表。橫向比較：1. 影像分類（是非題）、2. 物件偵測（射箭比賽/框選）、3. 語意分割（填色比賽/像素分類）、4. 實例分割（剪紙檢定/輪廓切割）、5. 全景分割（全能運動會/個體與背景）。底部對應其專業評估指標 Accuracy, mAP, mIoU, AP mask, 與 PQ。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">電腦視覺五大任務解析圖表。橫向比較：1. 影像分類（是非題）、2. 物件偵測（射箭比賽/框選）、3. 語意分割（填色比賽/像素分類）、4. 實例分割（剪紙檢定/輪廓切割）、5. 全景分割（全能運動會/個體與背景）。底部對應其專業評估指標 Accuracy, mAP, mIoU, AP mask, 與 PQ。</figcaption></div></figure><div class="notion-text notion-block-34470f01963480cd88dddae669ee72db">當電腦具備了提取特徵的能力後，工程師開始對它提出更刁鑽的要求。差別不在於模型看的是不同圖片，而是它被要求輸出不同層級的答案。有的只要吐一個標籤，有的要框出位置，有的甚至要一塊塊像素分類。這也是為什麼電腦視覺會發展出分類、偵測、語意分割、實例分割與全景分割等不同任務。</div><div class="notion-text notion-block-34d70f019634809ea6c1c5f59ea5bb3c">輸出層級變了，評分的量尺也跟著變。雖然這些任務早期大多建立在 CNN 及其衍生架構上，但近年也已大量引入 Transformer 與 hybrid 架構。真正的差別，在於它要回答的問題層級不同。</div><table class="notion-simple-table notion-block-34d70f01963480868cb0ded634e828c1"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-34d70f01963480388019e0b9007bbff7"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>任務</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>回答的問題</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>輸出粒度</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>代表模型</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>主指標</b></div></td></tr><tr class="notion-simple-table-row notion-block-34d70f01963480d3a885f2ee6e6a1be8"><td class="" style="width:120px"><div class="notion-simple-table-cell">影像分類</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">這是什麼？</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">整張圖一個標籤</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">ResNet、VGG</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Accuracy</div></td></tr><tr class="notion-simple-table-row notion-block-34d70f0196348052831fce639952f023"><td class="" style="width:120px"><div class="notion-simple-table-cell">物件偵測</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">在哪裡？</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">邊界框 + 類別</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">YOLO、Faster R-CNN</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">IoU + mAP</div></td></tr><tr class="notion-simple-table-row notion-block-34d70f0196348096a458d52fe83a90a7"><td class="" style="width:120px"><div class="notion-simple-table-cell">語意分割</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">每像素是什麼？</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">像素類別</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">U-Net、FCN</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">mIoU + Dice</div></td></tr><tr class="notion-simple-table-row notion-block-34d70f01963480fab3a0cd824525edb8"><td class="" style="width:120px"><div class="notion-simple-table-cell">實例分割</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">每個個體是誰？</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">像素遮罩 + 實體 ID</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Mask R-CNN</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Mask AP</div></td></tr><tr class="notion-simple-table-row notion-block-34d70f019634805680e4d9a3050d1d28"><td class="" style="width:120px"><div class="notion-simple-table-cell">全景分割</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">類別 + 個體一次到位</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">像素類別 + 實體 ID</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Panoptic FPN</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">PQ</div></td></tr></tbody></table><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34470f01963480409a03d7a867bb0d38" data-id="34470f01963480409a03d7a867bb0d38"><span><div id="34470f01963480409a03d7a867bb0d38" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34470f01963480409a03d7a867bb0d38" title="1. 影像分類（Image Classification）：這張圖是什麼？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>1. 影像分類（Image Classification）：這張圖是什麼？</b></span></span></h4><ul class="notion-list notion-list-disc notion-block-34570f0196348034b0b2cce602f8ed6f"><li><b>定義</b>：對整張影像進行類別判斷，回答「這張圖是什麼」。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480a9a84cda6674bc6716"><li><b>實務應用</b>：手機相簿自動把貓的照片抓出來放在同一本相簿、社群內容過濾、商品辨識搜尋。</li></ul><ul class="notion-list notion-list-disc notion-block-34d70f01963480aba638d8ed76d5db37"><li><b>怎麼判準不準</b>：</li><ul class="notion-list notion-list-disc notion-block-34d70f01963480aba638d8ed76d5db37"><li><b>Accuracy（準確率）</b>：測試集裡分對的比例，最基礎。</li><li><b>Top-5 Error（前五錯誤率）</b>：模型預測前五名內含正確類別就算對。類別數量龐大時（如 ImageNet 1000 類）才有意義，光看 Top-1 太嚴。</li><li><b>混淆矩陣（Confusion Matrix）</b>：列出每個類別「實際 vs 預測」的分布，能看出模型把貓誤認成什麼類別——是把貓當狗、還是當沙發？</li></ul></ul><ul class="notion-list notion-list-disc notion-block-34570f019634808d92b1fec54c2ce218"><li><b>優點</b>：運算速度最快、訓練門檻最低。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f0196348053b7baf0c3394b7b1e"><li><b>缺點</b>：資訊太籠統，完全無法提供物件的位置資訊。</li></ul><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34470f01963480a8a57af9a677a919bc" data-id="34470f01963480a8a57af9a677a919bc"><span><div id="34470f01963480a8a57af9a677a919bc" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34470f01963480a8a57af9a677a919bc" title="2. 物件偵測 (Object Detection)：畫面裡有什麼、在哪裡？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>2. 物件偵測 (Object Detection)：畫面裡有什麼、在哪裡？</b></span></span></h4><ul class="notion-list notion-list-disc notion-block-34570f019634805b8b6de819d4c8fdd3"><li><b>定義</b>：找出影像中所有感興趣的目標，並用<b>邊界框 (Bounding Box)</b> 標示位置。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f0196348027b03dd0092d07ceee"><li>常見模型分三派：</li><ul class="notion-list notion-list-disc notion-block-34570f0196348027b03dd0092d07ceee"><li><b>YOLO（You Only Look Once）</b>：速度路線，一次回歸出所有框，適合即時監控。</li><li><b>Faster R-CNN</b>：準確度路線，先用區域提議網路找候選區再分類。</li><li><b>SSD（Single Shot Multibox Detector）</b>：折衷路線，用多尺度特徵在速度與精度之間取平衡。</li><li>速度優先選 YOLO，精度優先選 R-CNN 家族，折衷選 <b>SSD</b>。</li></ul></ul><ul class="notion-list notion-list-disc notion-block-34570f0196348082a526df27a601d83d"><li><b>實務應用</b>：<b>商店防竊監控</b>。偵測人手是否伸向商品，並標示出人的位置。</li></ul><ul class="notion-list notion-list-disc notion-block-34d70f0196348025b863f005566a397f"><li><b>怎麼判準不準</b>：指標分兩層：先用 <b>IoU</b> 判單一個框夠不夠準，再用 <b>mAP</b> 把所有類別統計成總分。</li><ul class="notion-list notion-list-disc notion-block-34d70f0196348025b863f005566a397f"><li><b>IoU（Intersection over Union，交並比）</b>：兩框重疊面積 ÷ 聯集面積。完全重合是 1、完全不重疊是 0。像兩張貓咪貼紙疊起來，重疊越多分數越高。</li><ul class="notion-list notion-list-disc notion-block-34d70f01963480bfb1a4fab56a1190d3"><li><b>IoU 閾值越高越嚴格</b>：0.75 比 0.5 嚴格，只有重疊夠多的框才算對。監控用 0.5 就夠、醫療要 0.8。</li></ul><li><b>mAP（mean Average Precision，平均精確率均值）</b>：每個類別算一個 AP，全部平均成綜合分數。像全班段考總平均，一個數字看整體水準。</li></ul></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480e5aed6d1d0e4b75a93"><li><b>優點</b>：能同時處理多個目標並定位，YOLO 模型能做到極高速度的即時辨識。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480aab8a2d9ff489578b1"><li><b>缺點</b>：框框是矩形的，當兩個物件重疊（例如貓疊在一起）時，框框會互撞導致誤判。</li></ul><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34470f01963480048f08deb122c81901" data-id="34470f01963480048f08deb122c81901"><span><div id="34470f01963480048f08deb122c81901" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34470f01963480048f08deb122c81901" title="3. 語意分割 (Semantic Segmentation)：每個像素分別屬於什麼？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>3. 語意分割 </b>(Semantic Segmentation)<b>：每個像素分別屬於什麼？</b></span></span></h4><ul class="notion-list notion-list-disc notion-block-34570f01963480049e69fb07a006d7ab"><li><b>定義</b>：將影像中的每個像素進行分類，區分不同區域的「含義」。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480e5b49ed3c7debb3689"><li><b>比喻</b>：<b>「視訊背景去背」</b>。把所有屬於「貓」的像素塗紅，剩下的背景塗黑。不管幾隻貓，在它眼裡都是同一團紅色。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480b38580cc65d10fc20a"><li><b>實務應用</b>：<b>醫療 X 光片腫瘤偵測</b>。精確勾勒出病灶的區域，幫助醫生判斷擴散程度。</li></ul><ul class="notion-list notion-list-disc notion-block-34d70f01963480c68ac6d1049057e36d"><li><b>怎麼判準不準</b>：指標從「框」改成「像素級別」，看 mIoU 跟 Dice。</li><ul class="notion-list notion-list-disc notion-block-34d70f01963480c68ac6d1049057e36d"><li><b>mIoU（mean IoU）</b>：跟 IoU 同公式，計算對象從「框」換成「每個類別的像素集合」，再跨類別平均。像描圖紙疊起來：路（紅）、人（綠）、天空（藍）各算 IoU 再平均。自駕車資料集 Cityscapes 看的就是這個。</li><li><b>Dice 係數</b>：跟 IoU 都是衡量重疊，但公式對<b>小目標更敏感</b>。腫瘤只佔 CT 片 2% 的像素時，IoU 漏掉幾乎不扣分，Dice 直接崩盤：這才是醫生要的警報。ISBI 等醫療分割競賽一律用 Dice。</li></ul></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480e7a927e084a102bb2c"><li><b>優缺點</b>：</li><ul class="notion-list notion-list-disc notion-block-34570f01963480e7a927e084a102bb2c"><li><b>優點</b>：達到像素級的精確度，比框框更細膩。</li><li><b>缺點</b>：<b>無法分辨個體</b>。如果兩隻貓靠在一起，它會覺得那是一坨巨大的雙頭貓。</li></ul></ul><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34470f01963480dc9b97e1f40df60873" data-id="34470f01963480dc9b97e1f40df60873"><span><div id="34470f01963480dc9b97e1f40df60873" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34470f01963480dc9b97e1f40df60873" title="4. 實例分割 (Instance Segmentation)：同樣都是車子，每一台分別是哪一台？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>4. 實例分割 (Instance Segmentation)：同樣都是車子，每一台分別是哪一台？</b></span></span></h4><ul class="notion-list notion-list-disc notion-block-34570f01963480a0afb2d59383dfddb1"><li><b>定義</b>：結合物件偵測與語意分割，區分同類別中的不同個體。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480ae814cd7ef336f1002"><li><b>比喻</b>：<b>「精準的剪紙藝術」</b>。它不僅把貓去背，還能分清「這塊肉體是小橘的、那塊是小黑的」。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f0196348019830de3ef578df42d"><li>代表模型 <b>Mask R-CNN：</b>它在偵測框之外，額外為每個實體預測一張遮罩。這類方法讓模型不只知道「有車」，還知道「這一台車的輪廓到哪裡」。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480a7a4b9ddceb6ee13c1"><li><b>實務應用</b>：<b>自動化果園採收</b>。機器手臂必須看清「這一顆」番茄的精確邊緣，才不會抓碎旁邊的番茄。</li></ul><ul class="notion-list notion-list-disc notion-block-34d70f01963480599f52e9135748bbb6"><li><b>怎麼判準不準</b>：</li><ul class="notion-list notion-list-disc notion-block-34d70f01963480599f52e9135748bbb6"><li><b>Mask AP（Mask Average Precision）</b>：把 mAP 的「框」換成「遮罩」。每個實體的遮罩各算 IoU，再算 AP，再跨類別平均。</li><li><b>框 vs 遮罩</b>：框 AP 寬鬆（方方正正就行），遮罩 AP 嚴格（AI 畫的「張先生那台 Tesla」輪廓得沿車體曲線走才算對）。COCO 實例分割 benchmark 看的就是 Mask AP。</li></ul></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480c7a399de7c3e83e50d"><li><b>優點</b>：能解決物件重疊問題，是目前最精細的物件識別技術之一。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480f5a202e4b20aaa6986"><li><b>缺點</b>：運算極其沉重，對電腦顯示卡（GPU）的要求非常高。</li></ul><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34470f01963480e180a8c585bb94d158" data-id="34470f01963480e180a8c585bb94d158"><span><div id="34470f01963480e180a8c585bb94d158" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34470f01963480e180a8c585bb94d158" title="5. 全景分割 (Panoptic Segmentation)：集五種看法之大成"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>5. 全景分割 (Panoptic Segmentation)：集五種看法之大成</b></span></span></h4><ul class="notion-list notion-list-disc notion-block-34570f019634808d97fcefe4e8d5c8b3"><li><b>定義</b>：視覺理解的終極任務。同時完成背景的「語意分割」與主角的「實例分割」。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f0196348084acf1f21b94715499"><li><b>比喻</b>：<b>「全知全能的上帝視角」</b>。AI 不僅認出每一隻貓，還看懂了貓踩的地板、後方的窗簾以及天空。整張照片沒有任何一處馬賽克。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480018340c9b8d29e7332"><li><b>實務應用</b>：<b>自動駕駛系統</b>。車子必須同時區分「行人 A、車輛 B」（個體）與「馬路、安全島」（背景）。</li></ul><ul class="notion-list notion-list-disc notion-block-34d70f0196348086bf29cdb93dc2682c"><li><b>怎麼判準不準</b>：用專用指標 <b>PQ（Panoptic Quality，全景品質）</b>，公式是 <b>PQ = SQ × RQ</b>。</li><ul class="notion-list notion-list-disc notion-block-34d70f0196348086bf29cdb93dc2682c"><li><b>SQ（Segmentation Quality，分割品質）</b>：切出來的遮罩跟真實遮罩的 IoU 平均。</li><li><b>RQ（Recognition Quality，識別品質）</b>：該抓的有沒有漏、不該抓的有沒有亂抓。</li><li><b>三關考試一次過</b>：類別分對（馬路 vs 天空）+ 身分分對（張先生 Tesla vs 李先生 Prius）+ 背景連成片（天空整片不破碎）。PQ 不漂亮等於告訴讀者「這車上路會出事」。</li></ul></ul><ul class="notion-list notion-list-disc notion-block-34570f0196348073a94fe7daf300531c"><li><b>優點</b>：提供最完美的環境理解，沒有死角。</li></ul><ul class="notion-list notion-list-disc notion-block-34570f01963480d29e36cc323e796926"><li><b>缺點</b>：模型最複雜、標註資料最昂貴，是目前技術天花板。</li></ul><hr class="notion-hr notion-block-34e70f019634808b9c67dd27ac1a7638"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-34e70f01963480c8b33ccdc4b8c11645" data-id="34e70f01963480c8b33ccdc4b8c11645"><span><div id="34e70f01963480c8b33ccdc4b8c11645" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480c8b33ccdc4b8c11645" title="四、誰教 AI 看圖？影像標註的世界"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>四、誰教 AI 看圖？影像標註的世界</b></span></span></h3><div class="notion-callout notion-brown_background_co notion-block-34e70f01963480e3ae55f09edab71d39"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-34e70f019634803896efdba9570b69e7"><b>AI 看圖看得這麼準，背後是誰教的？</b></div><div class="notion-text notion-block-34e70f01963480c6ac63e98241254584">是人。CV 模型不是天才，它得靠人類餵的「標準答案」一張一張學。影像標註做的就是把原始圖片變成「機器看得懂的標準答案」，標好標滿，模型才會準。</div></div></div><div class="notion-text notion-block-34e70f01963480e194bacd8f336ab346">CV 模型的命脈不是模型架構有多炫，而是<b>訓練資料的標註品質</b>。標註標得好，再普通的模型都能跑起來；標註偷工減料，再貴的模型架構也救不回來。</div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-34e70f019634801881cbc2a83ab415de"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A1efa4ffd-458f-49a3-a1fd-89d7cbb5e276%3Aai-image-annotation-types-cats.jpeg?table=block&amp;id=34e70f01-9634-8018-81cb-c2a83ab415de&amp;t=34e70f01-9634-8018-81cb-c2a83ab415de&amp;width=1080&amp;cache=v2" alt="展示教導 AI 看圖的六種主流影像標註方法，包含分類標籤、物件偵測邊框、多邊形輪廓勾勒、姿態識別關鍵點、像素級遮罩及文字辨識 OCR。圖表透過擬人貓咪範例，說明如何為 YOLO 或 Faster R-CNN 模型建立高品質訓練數據並優化機器學習辨識準確度，是理解影像資料前處理與數據標記生態系統的關鍵參考指南。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">展示教導 AI 看圖的六種主流影像標註方法，包含分類標籤、物件偵測邊框、多邊形輪廓勾勒、姿態識別關鍵點、像素級遮罩及文字辨識 OCR。圖表透過擬人貓咪範例，說明如何為 YOLO 或 Faster R-CNN 模型建立高品質訓練數據並優化機器學習辨識準確度，是理解影像資料前處理與數據標記生態系統的關鍵參考指南。</figcaption></div></figure><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f019634805e87aed7f3f0a59526" data-id="34e70f019634805e87aed7f3f0a59526"><span><div id="34e70f019634805e87aed7f3f0a59526" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f019634805e87aed7f3f0a59526" title="1. 影像標註：為機器建立標準答案的六大類型"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>1. 影像標註：為機器建立標準答案的六大類型</b></span></span></h4><ol start="1" class="notion-list notion-list-numbered notion-block-34e70f019634801ebdd2f2199660c7f5" style="list-style-type:decimal"><li><b>類別標籤 (Label)</b>：給整張圖貼一個類別（如「貓」「狗」「車」）。最便宜、最快，影像分類專用。</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-34e70f01963480ea8eefe6d4deb0d289" style="list-style-type:decimal"><li><b>Bounding Box</b>：用矩形框框住物體。最快、最便宜，是 YOLO 或 Faster R-CNN 的標準餵食格式。</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-34e70f019634804eaeadf622c84b0c32" style="list-style-type:decimal"><li><b>Polygon</b>：用多個頂點連成的封閉形狀框出輪廓。比矩形框精細，能貼合不規則邊緣。</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-34e70f01963480209ad7de3937878c46" style="list-style-type:decimal"><li><b>Keypoint</b>：標記特定點位（例如人臉的眼角、鼻尖、肩關節）。姿態估計與表情辨識常用。</li></ol><ol start="5" class="notion-list notion-list-numbered notion-block-34e70f0196348007b2acd9adb0976990" style="list-style-type:decimal"><li><b>Mask</b>：每個像素都標一個類別。成本最高，但對於自動駕駛或醫療影像來說是必備的生命線。</li></ol><ol start="6" class="notion-list notion-list-numbered notion-block-34e70f01963480479ee5e77b7e49698b" style="list-style-type:decimal"><li><b>OCR</b>：把文字區塊框出來並輸入正確字串，這是文字辨識模型訓練的基礎。</li></ol><div class="notion-text notion-block-34e70f019634800b80ace555b795fff0">不同任務需要不同精細度的標註，從快到慢、從便宜到貴：</div><table class="notion-simple-table notion-block-34e70f01963480e9b026d3302607f9d7"><tbody><tr class="notion-simple-table-row notion-simple-table-header-row notion-block-34e70f01963480d89bd3eb716dec7c3c"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>標註類型</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>精細度</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>標一張的時間</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>對應任務</b></div></td></tr><tr class="notion-simple-table-row notion-block-34e70f01963480839cd0ffcec688af8f"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>類別標籤（Label）</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">極低</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">3-10 秒</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">影像分類</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f01963480f9abb1fb0c2a5d3d43"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>Bounding Box（邊界框）</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">低</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">10-30 秒</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">物件偵測</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f01963480e9a7ded61881957f1a"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>Polygon（多邊形）</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">中</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">1-3 分鐘</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">細緻偵測、分割</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f019634803694d0dd7341995f28"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>Keypoint（關鍵點）</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">中</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">30 秒-2 分鐘</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">姿態估計、表情辨識</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f01963480a597cfea87c3593e19"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>Mask（像素遮罩）</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">高</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">5-15 分鐘</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">語意分割、實例分割</div></td></tr><tr class="notion-simple-table-row notion-block-34e70f01963480e58f79c1e994942d4b"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>OCR（文字框 + 字串）</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">中</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">1-2 分鐘</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">文字辨識</div></td></tr></tbody></table><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f01963480b4bec8c3014358682f" data-id="34e70f01963480b4bec8c3014358682f"><span><div id="34e70f01963480b4bec8c3014358682f" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480b4bec8c3014358682f" title="2. 資料前處理：讓模型「好消化」的精煉工序"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>2. 資料前處理：讓模型「好消化」的精煉工序</b></span></span></h4><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-34e70f0196348025ad22ff8618d797e1"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A66ba2a02-d8ab-4481-be9d-fef2b6658d8d%3Acat-ai-image-preprocessing-steps-guide.jpeg?table=block&amp;id=34e70f01-9634-8025-ad22-ff8618d797e1&amp;t=34e70f01-9634-8025-ad22-ff8618d797e1&amp;width=1080&amp;cache=v2" alt="透過趣味擬人橘貓展示 AI 圖像預處理的七大核心工序，包含影像縮放裁剪、像素歸一化、Gamma 校正增強、去噪處理、色彩空間轉換、資料擴增及序列統一。此專業圖表詳細解說如何透過數據清洗與格式標準化，有效提升電腦視覺模型的收斂速度、泛化能力與訓練效率，是學習機器學習工程與影像數據流水線設計的深度技術實務參考。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">透過趣味擬人橘貓展示 AI 圖像預處理的七大核心工序，包含影像縮放裁剪、像素歸一化、Gamma 校正增強、去噪處理、色彩空間轉換、資料擴增及序列統一。此專業圖表詳細解說如何透過數據清洗與格式標準化，有效提升電腦視覺模型的收斂速度、泛化能力與訓練效率，是學習機器學習工程與影像數據流水線設計的深度技術實務參考。</figcaption></div></figure><div class="notion-text notion-block-34e70f01963480b387b0fa04fba84da6">在標註完成後、餵進模型前，我們必須對影像進行「<b>資料前處理</b>」。主要目的是統一格式、增強品質，並提升訓練效率。</div><div class="notion-text notion-block-34e70f01963480e090b3feb78fa98ea4">以下是業界常見的七大前處理技術：</div><ul class="notion-list notion-list-disc notion-block-34e70f01963480f2a851c45dfd25aa37"><li><b>圖像尺寸處理 (Resize / Padding / Cropping)</b>：將影像統一為模型所需的輸入大小，避免形變或資訊遺失。</li></ul><ul class="notion-list notion-list-disc notion-block-34e70f019634806fb3f6c64913d5d0d3"><li><b>正規化處理 (Pixel Normalization)</b>：將像素值（如 0-255）轉為 0-1，或標準化至均值為 0、標準差為 1，幫助模型收斂。</li></ul><ul class="notion-list notion-list-disc notion-block-34e70f01963480b6924fe4e2c0eac78c"><li><b>像素增強 (直方圖均衡化、Gamma 校正)</b>：提升影像對比度與亮度，適合低光源或品質較差的原始影像。</li></ul><ul class="notion-list notion-list-disc notion-block-34e70f019634805cbb64d1dcd6d46dbc"><li><b>噪聲去除 (平滑濾波、邊緣保留濾波)</b>：減少感測器產生的雜訊（如高斯濾波、雙邊濾波）。</li></ul><ul class="notion-list notion-list-disc notion-block-34e70f019634809cbbc6dc0ea230a816"><li><b>色彩空間轉換 (RGB ↔ Grayscale, HSV)</b>：根據任務調整顏色通道，灰階處理常用於簡化輸入、節省算力。</li></ul><ul class="notion-list notion-list-disc notion-block-34e70f01963480e491c6fc79364c43f4"><li><b>資料擴增 (Data Augmentation)</b>：利用翻轉、旋轉、裁剪、模糊等手段，人為增加資料多樣性，增強模型泛化能力並對抗過擬合。</li></ul><ul class="notion-list notion-list-disc notion-block-34e70f0196348065bfa0f7383caa3f13"><li><b>序列統一</b>：在影片辨識中進行影格取樣，應用於動作辨識或影像序列建模任務。</li></ul><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f01963480059426c1c3cb78f582" data-id="34e70f01963480059426c1c3cb78f582"><span><div id="34e70f01963480059426c1c3cb78f582" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480059426c1c3cb78f582" title="3. 標註成本與品質控管"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>3. 標註成本與品質控管</b></span></span></h4><div class="notion-text notion-block-34e70f01963480a7847af951bfadd34c">CV 資料集動輒幾十萬到幾百萬張圖，全部找專家標不可能。產業常見的三層做法：</div><ul class="notion-list notion-list-disc notion-block-34e70f019634803e90f5ec05969a57e2"><li><b>群眾外包（Crowdsourcing）</b>：用 Amazon Mechanical Turk、Scale AI、Labelbox 等平台，把任務拆成小批丟給全球標註員。便宜，但品質參差，需要嚴格的品管機制。</li></ul><ul class="notion-list notion-list-disc notion-block-34e70f01963480a8b5bbcb3b92eb6997"><li><b>半自動標註</b>：先用 SAM（Segment Anything Model）這類預訓練模型粗標一輪，再讓人類校正。能把標註時間砍掉 70-80%，是 2023 年後業界主流。</li></ul><ul class="notion-list notion-list-disc notion-block-34e70f019634800b9d1acb90e61e2b1c"><li><b>品質控管機制</b>：同一張圖讓 3-5 個標註員獨立標，再看一致性（Inter-Annotator Agreement，IAA）。一致性低代表這張圖本身有歧義，需要重新檢視。</li></ul><blockquote class="notion-quote notion-block-34e70f0196348037bbf5dbab9f0cc55a"><div><b><a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://infosecu.technews.tw/2026/03/08/metas-ai-display-glasses-reportedly-share-intimate-videos-with-human-moderators/?st_source=ai_mode">外媒揭露，Meta AI＋AR 眼鏡會將用戶私密影片分享海外審核員</a></b><b>
</b><b><a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://www.managertoday.com.tw/articles/view/66450">ChatGPT 爆紅背後｜時薪僅 40 元、那些幫 AI「洗白」的血汗勞力，多少人在乎？</a></b></div></blockquote><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f01963480669c75c6859493280c" data-id="34e70f01963480669c75c6859493280c"><span><div id="34e70f01963480669c75c6859493280c" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480669c75c6859493280c" title="4. 標註偏誤：兩個醫師看同張片，誰是對的？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>4. 標註偏誤：兩個醫師看同張片，誰是對的？</b></span></span></h4><div class="notion-callout notion-brown_background_co notion-block-34e70f01963480b5b121ea58d9597156"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-34e70f0196348052a5ced1a0c0faab8a"><b>兩個放射科醫師看同一張 X 光片，A 醫師圈出 5 個可疑陰影、B 醫師圈出 3 個。AI 該信誰？</b></div><div class="notion-text notion-block-34e70f0196348092a22bc63690752d0a">CV 模型的「準」其實是「跟標註員的判斷一致」。如果標註員自己有偏見（例如某族裔的人臉特徵被誤標）、或不同標註員的標準不一致，模型學到的就是這套偏見。</div></div></div><div class="notion-text notion-block-34e70f019634806c8cbcc9c4a30d0729">標註偏誤的問題，不只會影響模型在 benchmark 上的分數，更會在高風險場景中放大成真實世界的代價。當模型被用在校園安防、執法或醫療時，一次誤判就可能不是「分數掉幾點」，而是直接影響人的處境。</div><div class="notion-text notion-block-34e70f01963480959cd3dfc063712891">這也是為什麼大型資料集（ImageNet、COCO）會反覆做品質審核，並在後續版本中修正錯誤標註。標註就是幫資料貼標籤。標註員的偏見會直接成為模型的偏見，進產線之後就是真實世界的傷害。</div><blockquote class="notion-quote notion-block-34e70f01963480c9b730e8f4e142e3bd"><div>💡 <b>真實案例</b>：16歲黑人學生艾倫（Taki Allen）足球練習後，將一包揉皺的<b>多力多滋空袋</b>塞進口袋。校園內的 AI 槍枝偵測系統（Omnilert）偵測到口袋裡的形狀，誤認為是手槍。系統觸發後，約 8 輛警車迅速趕到，警察持槍指著艾倫，命令他下跪並將他上銬搜身。
來源：<b><a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://tw.news.yahoo.com/%E8%A1%B0-%E5%90%83%E5%A4%9A%E5%8A%9B%E5%A4%9A%E6%BB%8B-ai%E5%88%A4%E5%AE%9A%E7%82%BA%E6%89%8B%E6%A7%8D-%E7%BE%8E16%E6%AD%B2%E5%AD%B8%E7%94%9F%E6%85%98%E9%81%AD%E5%8C%85%E5%9C%8D%E4%B8%8A%E9%8A%AC-225202671.html">衰！吃多力多滋「AI判定為手槍」 美16歲學生慘遭包圍上銬</a></b></div></blockquote><div class="notion-text notion-block-34e70f019634802e82f1c9c44d28e17e">美國國家標準與技術研究院（NIST）研究顯示，人臉辨識系統對黑人與亞洲人的誤判率，比對白人高出 <b>10 到 100 倍</b>。
</div><hr class="notion-hr notion-block-34e70f01963480ba9939d0ae0d70d323"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-34e70f0196348002a114d76feda25c2f" data-id="34e70f0196348002a114d76feda25c2f"><span><div id="34e70f0196348002a114d76feda25c2f" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f0196348002a114d76feda25c2f" title="五、CV 用起來不是萬能：技術挑戰與倫理風險"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>五、CV 用起來不是萬能：技術挑戰與倫理風險</b></span></span></h3><div class="notion-callout notion-brown_background_co notion-block-34e70f01963480e5a4ddd38650528f8a"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-34e70f0196348082b5d2e669f9909ea9"><b>AI 影像辨識在實驗室準到 99%，到了現場卻常出包，為什麼？</b></div><div class="notion-text notion-block-34e70f019634808a974bfcc1062f9ff1">CV 從訓練到部署中間有四個關卡：資料分佈、運算限制、倫理風險、法規應對。每一關都能讓模型翻車。<b>現場踩坑的故事比實驗室成功的論文多</b>。</div></div></div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-34e70f01963480aaa260e68ab0e2098c"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A5ab157b5-8675-4d84-ae78-56b6fe7dd8e9%3Acomputer-vision-real-world-challenges.jpeg?table=block&amp;id=34e70f01-9634-80aa-a260-e68ab0e2098c&amp;t=34e70f01-9634-80aa-a260-e68ab0e2098c&amp;width=1080&amp;cache=v2" alt="視覺化探討電腦視覺落地應用的四大難題，包含訓練數據與現實間的領域轉移、邊緣運算算力受限導致的硬體發熱、數據偏見引發的倫理難題及歐盟 AI 法案的合規壓力。透過幽默貓咪迷因演繹影像辨識部署時的延遲與法律遵循議題，是分析技術落地可行性與風險控管的專業參考，展現真實應用環境中複雜且多樣的變數。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">視覺化探討電腦視覺落地應用的四大難題，包含訓練數據與現實間的領域轉移、邊緣運算算力受限導致的硬體發熱、數據偏見引發的倫理難題及歐盟 AI 法案的合規壓力。透過幽默貓咪迷因演繹影像辨識部署時的延遲與法律遵循議題，是分析技術落地可行性與風險控管的專業參考，展現真實應用環境中複雜且多樣的變數。</figcaption></div></figure><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f01963480018e5edb762e41db9e" data-id="34e70f01963480018e5edb762e41db9e"><span><div id="34e70f01963480018e5edb762e41db9e" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480018e5edb762e41db9e" title="1. 資料挑戰：領域偏移（Domain Shift）"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>1. 資料挑戰：領域偏移（Domain Shift）</b></span></span></h4><div class="notion-text notion-block-34e70f01963480f3a6bcce2ec4225beb">模型在訓練資料上準到 95%，換到實際使用環境就崩盤。原因是訓練資料的分佈跟現場資料分佈不一樣，這叫領域偏移。</div><div class="notion-text notion-block-34e70f019634803e80b1d78ef9487e48">在 2020 年疫情爆發初期，由於疫情緊急，南韓有家公司用 AI 判讀 COVID 的 CT 影像，火速拿到 FDA 認證上市，結果不到三個月就失準下架，病毒一變種、影像特徵跑掉，AI 在實驗室準到 95% 的成績到醫院端全變錯誤。</div><div class="notion-text notion-block-34e70f01963480b39b84e1ea2dfec99a">在自駕車的領域，台灣複雜的混合車流（機車鑽縫、施工改道頻繁、招牌林立）產生的影像數據，與歐美地廣人稀的訓練數據截然不同。如果 AI 在實驗室準確率 95%，那是因為訓練數據是乾淨的歐美道路。一旦放到台灣，影像特徵如「雨後反光的標線」、「路邊違停閃爍的黃燈」或「密集的機車群」，就容易出現類似 COVID AI 在變種病毒出現後的「辨識斷層」。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f019634803da2f1f15f91ea7075" data-id="34e70f019634803da2f1f15f91ea7075"><span><div id="34e70f019634803da2f1f15f91ea7075" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f019634803da2f1f15f91ea7075" title="2. 部署挑戰：邊緣運算的算力限制"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>2. 部署挑戰：邊緣運算的算力限制</b></span></span></h4><div class="notion-text notion-block-34e70f01963480c8adf7d6afa3be744c">另一個常見問題不是模型不準，而是模型太肥。</div><div class="notion-text notion-block-34e70f019634806e80b2d1e965eca8b8">雲端跑得動的大模型，搬到手機、攝影機、車載系統就跑不動。</div><div class="notion-text notion-block-34e70f0196348009805ce7dcc3101d55">CV 模型部署常遇到「算力卡脖子」。雲端跑得動的大模型，搬到手機、攝影機、車載系統或邊緣設備時，可能就會遇到延遲、發熱、耗電與記憶體不足等限制。因此實務上常見的做法，不是盲目追求最大模型，而是透過量化（Quantization）、知識蒸餾（Knowledge Distillation）、模型剪枝與分級處理，在準確度、速度與硬體成本之間找平衡。</div><div class="notion-text notion-block-34e70f01963480b5a90cc271083b6638">模型不是越大越好。如果要在設備裡也跑得動，模型也要開始為了硬體而瘦身。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f01963480e6b3d1c8615f918fd2" data-id="34e70f01963480e6b3d1c8615f918fd2"><span><div id="34e70f01963480e6b3d1c8615f918fd2" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480e6b3d1c8615f918fd2" title="3. 倫理挑戰：人臉辨識偏誤 + Deepfake 詐騙"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>3. 倫理挑戰：人臉辨識偏誤 + Deepfake 詐騙</b></span></span></h4><div class="notion-text notion-block-34e70f01963480efabc1ccb76c84f055">CV 跨進臉部、生物特徵領域後，倫理問題就跟著來。最常見的兩個：訓練資料族群偏差（白人準、亞裔黑人不準）、Deepfake 換臉詐騙。</div><div class="notion-text notion-block-34e70f01963480b7bdf5d8856f643fd4">偏誤怎麼量化？看模型對不同族群的 誤檢（False Positive，把無辜當嫌犯）vs 漏檢（False Negative，把嫌犯放走） 比例，再用 AUC、精確率（Precision）、召回率（Recall） 跨群體比對。如果亞裔的 AUC 比白人低 5%，這套系統就不該上線執法。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-34e70f01963480c2818fc5fdc1bec35b" data-id="34e70f01963480c2818fc5fdc1bec35b"><span><div id="34e70f01963480c2818fc5fdc1bec35b" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480c2818fc5fdc1bec35b" title="4. 法規應對：EU AI Act 對 CV 的高風險規範"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>4. 法規應對：EU AI Act 對 CV 的高風險規範</b></span></span></h4><div class="notion-text notion-block-34e70f019634802f9aa5ed1ee69c9ce4">在 EU AI Act 之前，CV 相關合規常聚焦在資料層，例如 GDPR 對人臉與生物特徵資料的敏感個資要求，以及醫療資料在使用上的去識別化要求。EU AI Act 把規範從「資料怎麼用」升級到「AI 系統本身能不能用」</div><div class="notion-text notion-block-34e70f01963480ffaeb9e83b1927ade5">歐盟 AI 法案是全球第一部完整 AI 法案，把 AI 應用按風險分四級：<b>不可接受（Unacceptable）→ 高風險（High Risk）→ 有限風險（Limited Risk）→ 最低風險（Minimal Risk）</b>。CV 領域的人臉辨識、生物特徵識別大多被列入前兩級。</div><hr class="notion-hr notion-block-34e70f01963480f78348c49c1f361190"/><h2 class="notion-h notion-h1 notion-h-indent-0 notion-block-34e70f01963480a6b9fec6ed4cc9f24a" data-id="34e70f01963480a6b9fec6ed4cc9f24a"><span><div id="34e70f01963480a6b9fec6ed4cc9f24a" class="notion-header-anchor"></div><a class="notion-hash-link" href="#34e70f01963480a6b9fec6ed4cc9f24a" title="結語：CV 是 AI 的眼睛"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>結語：CV 是 AI 的眼睛</b></span></span></h2><div class="notion-text notion-block-34e70f0196348013b073d22ea2138563">從特徵工程時代靠人手設計規則，到 CNN 讓機器自己學會看見，再到影像分類、物件偵測、語意分割、實例分割與全景分割各自長出明確任務邏輯，視覺 AI 的進化，其實不只是模型越來越強，而是機器理解世界的方式越來越細緻。</div><div class="notion-text notion-block-34e70f019634801aaf98d028e4bf2437">但 AI 看懂影像從來不只靠演算法本身，它背後仰賴的是大量標註資料所塑造的世界觀，也因此必須面對標註偏誤、領域偏移、算力限制、倫理爭議與法規約束。從 1999 年的 SIFT 到 2024 年的 EU AI Act，這 25 年走過的，不只是技術升級史，更是一段人類不斷校準「如何讓機器看世界」的過程。</div><div class="notion-text notion-block-34e70f01963480dab55ae66821697ef3">當 CV 已經逐漸成為 AI 的眼睛，下一步要接上的，就是那雙會生成、會想像、甚至會重新拼裝視覺世界的手。當機器不再只是理解既有影像，而開始主動創造影像，視覺 AI 的故事，也將從「看懂世界」正式走向「生成世界」。</div><div class="notion-text notion-block-b5c7f0e2ca9a4a78a3b79d6c349778c9">（延伸閱讀：<a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://gyozalab.com/nlp-evolution-from-rules-to-gpt-guide">AI 語言處理演進史：從規則式到 GPT 的 NLP 變革</a>）</div><div class="notion-blank notion-block-34e70f019634805dae5bc937ffea5c4c"> </div></main></div>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Claude 額度燒光光，教你怎麼把 Gemini 也叫進來上班]]></title>
            <link>https://gyozalab.com/claude-code-gemini-cli-workflow</link>
            <guid>https://gyozalab.com/claude-code-gemini-cli-workflow</guid>
            <pubDate>Wed, 08 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Claude 額度動不動燒完？這篇分享如何把 Google 官方免費的 Gemini CLI 接進 Claude Code，讓 Gemini 幫忙搜尋網路和讀大檔案，省 Token 還能用多 AI 交叉驗證取代單押一家。五分鐘搞定 AI 雙引擎分工。]]></description>
            <content:encoded><![CDATA[<div id="notion-article" class="mx-auto overflow-hidden "><main class="notion light-mode notion-page notion-block-33c70f019634805f8503ded14b6defdf"><div class="notion-viewport"></div><div class="notion-collection-page-properties"></div><div class="notion-callout notion-block-55f9f9a7188a461d8ad41f4429f663d4"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="🎯">🎯</span></div><div class="notion-callout-text"><div class="notion-text notion-block-21e95c36d8cc42fd978e69e2b81fcda0">Claude 額度容易燒光，可把 Google 官方免費 Gemini CLI 接進 Claude Code 當副手，讓 Gemini 負責網路搜尋和大檔摘要以節省 Token，Claude 負責推理和最終決策。搭配 excludeTools 設定可封掉危險寫入權限，五分鐘完成雙引擎分工設定。</div></div></div><div class="notion-callout notion-gray_background_co notion-block-34170f01963480f39269e2639343630d"><div class="notion-callout-text"><div class="notion-text notion-block-34170f01963480ca9367ef46a316b5d4">📝 <b>更新日誌 (Changelog)</b></div><div class="notion-text notion-block-34170f01963480b68f74d935a64513ac"><b>2026.04.13</b></div><ul class="notion-list notion-list-disc notion-block-34170f01963480079a2cd29c157b6ced"><li>更新安全性的說明。</li></ul></div></div><div class="notion-text notion-block-33c70f019634808294d7dde9f759940b">買了 20 鎂的 Claude 不夠用，又課了 20 鎂 Codex，結果還是快燒完了。</div><div class="notion-text notion-block-33c70f01963480b6aa98cd707f347211">自從把 AI 徹底融入開發流程後，吸 Token 有一種無所不能的感覺，好像只要有想法，什麼都做得出來。但代價就是額度焦慮如影隨形。</div><div class="notion-text notion-block-33c70f01963480b58150e2c1fb06e9c7">我甚至還開發了一個開源桌面小工具 <b><a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://github.com/gyozalab/QuotaGem">QuotaGem</a></b>，專門拿來看 Claude 跟 Codex 的額度，結果因為用量太大，還是只能眼睜睜地看著他血條歸零。</div><div class="notion-text notion-block-33c70f01963480239f80eade0f3c02ac">後來我把免費的 <b>Gemini CLI</b> 接進 <b>Claude Code</b> 當小弟，想說可以節省了一點 Token 的開銷，結果最後變成看他們吵架，獲得了意外的樂趣。就寫了這篇來跟大家分享如何實作，以及我的心路歷程。</div><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-33c70f0196348033b6aad2ceb3a10858" data-id="33c70f0196348033b6aad2ceb3a10858"><span><div id="33c70f0196348033b6aad2ceb3a10858" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33c70f0196348033b6aad2ceb3a10858" title="一、20 美金的 Claude 不夠用"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">一、20 美金的 Claude 不夠用</span></span></h3><div class="notion-text notion-block-33c70f01963480e79fa0ff75db1f5014">不知道現在大家一個月花多少錢在訂閱 AI工具？</div><div class="notion-text notion-block-33c70f01963480f38758ff3db54d517b">為了打造我自己的工作流程，我現在的主力是 20 美金的 Claude，為了有備胎跟更多 Token 又補了 Codex 的 20 美金，結果額度還是動不動就燒光光。</div><div class="notion-text notion-block-33c70f019634803fa581ef465413da01">問題出在它「太好用」，導致我們什麼事都想叫它做，越買用量還跟著變大。</div><div class="notion-text notion-block-33c70f01963480819b19cb571d02bcd6">（先不提 Antigravity，雖然我有訂閱，但他還是無預警大砍額度，傷透了我的心）</div><div class="notion-text notion-block-33c70f01963480359b86d9d7534ee7d8">Claude 的使用限制相當嚴格，無論是計算五小時內的額度還是每週上限，如果不打算直上 100 甚至 200 美金的 Max 版本，就必須學會精打細算。</div><div class="notion-text notion-block-33c70f019634802b9c6bd7d8833ee855">我後來想通了，不管預算如何增加，我的用量也會跟著增加，現在也很難戒掉不用，不如找一些節省 Token的方式，比如說把 Gemini 抓來幫忙分擔雜事。</div><blockquote class="notion-quote notion-block-33c70f0196348048b8e2e49ef61faeb4"><div><b><a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://geminicli.com/docs/">Gemini CLI</a></b>：Google 官方推出的命令列 AI 工具，用 Google 帳號登入就能用，免費版每天 1,000 次請求。</div></blockquote><div class="notion-text notion-block-33c70f01963480458812eefab3d567f2">分工邏輯就是，拿 Claude 當大腦，Gemini 當小弟！</div><hr class="notion-hr notion-block-33c70f01963480368cc4e4090aa4333a"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-33c70f01963480578142d2fe947bab54" data-id="33c70f01963480578142d2fe947bab54"><span><div id="33c70f01963480578142d2fe947bab54" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33c70f01963480578142d2fe947bab54" title="二、Gemini 能幫什麼忙？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">二、Gemini 能幫什麼忙？</span></span></h3><div class="notion-text notion-block-33c70f0196348050a3b4d862376ccef3">目前個人使用體感上，Gemini 的推理和寫程式比不上 Claude，但他還是有優點喔！</div><div class="notion-text notion-block-33d70f01963480f5ac3af8bdd0c53171">判斷要不要把任務丟給 Gemini，就問一個問題：<b>「這個任務會讓誰讀最多資料？」</b><div class="notion-text-children"><div class="notion-text notion-block-1f824a7ed47d4666a14c0523aad8b87b">如果是 Gemini 讀，就叫他做；如果 Claude 做更好、更快、量也不多，就別轉包。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33d70f019634804b8780dbadf34fdcb1" data-id="33d70f019634804b8780dbadf34fdcb1"><span><div id="33d70f019634804b8780dbadf34fdcb1" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33d70f019634804b8780dbadf34fdcb1" title="1. 節省搜尋額度"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">1. 節省搜尋額度</span></span></h4><div class="notion-text notion-block-33d70f019634809682d0f2f9eeebb91c">大量搜尋資料很耗 Token，因為 AI 要讀大量網頁、篩選、整理，這些輸入 Token 加起來很可觀。Gemini CLI 有內建 <code class="notion-inline-code"><a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://geminicli.com/docs/tools/web-search/">google_web_search</a></code> 工具，而且搜尋本來就是 Google 的主場。</div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33c70f01963480e7b6d3d56707f639b8"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A8db768d7-3694-49cb-992e-7e79c7d51463%3Aclaude-code-delegates-to-gemini-cli-web-search.jpg?table=block&amp;id=33c70f01-9634-80e7-b6d3-d56707f639b8&amp;t=33c70f01-9634-80e7-b6d3-d56707f639b8&amp;width=703.991455078125&amp;cache=v2" alt="Claude Code 透過 Bash 呼叫 Gemini CLI 搜尋網路資訊的終端機畫面，顯示 gemini -y -p 指令與 google_web_search 搜尋結果" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Claude Code 透過 Bash 呼叫 Gemini CLI 搜尋網路資訊的終端機畫面，顯示 gemini -y -p 指令與 google_web_search 搜尋結果</figcaption></div></figure><div class="notion-text notion-block-33c70f019634807f9e8be7a9769eb86f">這個是 Claude Code 透過 Bash 呼叫 Gemini CLI 搜尋網路資訊的終端機畫面，Gemini 搜尋回來後，Claude 整理出來的結果。</div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33c70f019634808ca1aff378e816f52f"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A521402fb-040c-44ad-8d02-305fe837b2ed%3Agemini-cli-search-result-with-hallucination-warning.jpg?table=block&amp;id=33c70f01-9634-808c-a1af-f378e816f52f&amp;t=33c70f01-9634-808c-a1af-f378e816f52f&amp;width=703.9772338867188&amp;cache=v2" alt="實測畫面：Claude 派 Gemini 上網查最新功能更新，Gemini 查到了正確資料，但 Claude 仍主動提醒「Gemini 有幻覺前科，建議對照官方來源」，跑腿負責查，大腦負責把關。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption"><em>實測畫面：Claude 派 Gemini 上網查最新功能更新，Gemini 查到了正確資料，但 Claude 仍主動提醒「Gemini 有幻覺前科，建議對照官方來源」，跑腿負責查，大腦負責把關。</em></figcaption></div></figure><div class="notion-text notion-block-33c70f01963480c29bbeed210c66ff01">其實 Gemini 這次是對的，但 Claude 不相信他🤣</div><div class="notion-text notion-block-33d70f01963480b080ebca6450c231d2">如果怕兩個模型都有幻覺，也可以叫他們都去查，查完交叉驗證。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33d70f01963480bd838ef02126249506" data-id="33d70f01963480bd838ef02126249506"><span><div id="33d70f01963480bd838ef02126249506" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33d70f01963480bd838ef02126249506" title="2. 長內容處理"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">2. 長內容處理</span></span></h4><div class="notion-text notion-block-33d70f019634800c9bf4c65732632fc1">這是省額度的第二大場景，邏輯跟搜尋一樣：<b>讓 Gemini 讀大量資料，Claude 拿走結論。</b></div><div class="notion-text notion-block-33d70f0196348083bdd7ffeb8ec5b519">假設你有 10 個各 5,000 字的會議紀錄要摘要。如果你把內容貼給 Claude，光是輸入就吃掉 5 萬字的 Token。但如果 Claude 只下一行 Bash 指令，把檔案路徑丟給 Gemini，讓 Gemini 直接從硬碟讀，那 5 萬字從頭到尾沒進過 Claude 的 Context。</div><div class="notion-text notion-block-33d70f01963480c091d5ecc0e8bf66f7">Gemini 有 1M token 的上下文視窗，幾萬行的大檔案整份餵進去，然後告訴他你要他回報什麼內容。如果是要極限省 Token，可以請他回報極簡摘要，但我怕他濃縮過頭，把重點也濃縮掉了，所以還是會要求盡量維持完整脈絡。</div><blockquote class="notion-quote notion-block-33c70f0196348000968cf92ac91d285f"><div>⚠️ 要讓 Gemini 自己去讀檔案，Claude 只傳路徑就好。如果 Claude 先把整份檔案讀進來再轉交給 Gemini，Claude 的 Token 照樣被吃光，會變成兩邊各跑一次，比 Claude 自己做摘要還浪費喔。</div></blockquote><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33d70f019634801385c2e36246e39902" data-id="33d70f019634801385c2e36246e39902"><span><div id="33d70f019634801385c2e36246e39902" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33d70f019634801385c2e36246e39902" title="3. 第二意見"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">3. 第二意見</span></span></h4><div class="notion-text notion-block-33d70f01963480569d1bcf9b4dfc8fb1">這個用法不是為了省錢，而是為了提升決策品質。當 Claude 在跟你揮，你們的討論逐漸開始鑽牛角尖，而你想確認有沒有其他做法，可以叫 Claude 去問 Gemini 怎麼看，由你自己來判斷誰講得比較有道理。</div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33c70f01963480ee9575cf9f5d007acc"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Ae3e9f4a7-9997-460d-9a7c-f19a8aa4037d%3Agemini-cli-second-opinion-result.jpg?table=block&amp;id=33c70f01-9634-80ee-9575-cf9f5d007acc&amp;t=33c70f01-9634-80ee-9575-cf9f5d007acc&amp;width=703.991455078125&amp;cache=v2" alt="Claude Code 對話截圖：Gemini 建議加入影片作為延伸閱讀，Claude 自己判斷「放參考資料區就好，不用另開延伸閱讀區塊」，使用者回「誰理他」" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption"><em>Claude Code 對話截圖：Gemini 建議加入影片作為延伸閱讀，Claude 自己判斷「放參考資料區就好，不用另開延伸閱讀區塊」，使用者回「誰理他」</em></figcaption></div></figure><div class="notion-text notion-block-33d70f01963480f58148e95edf1e9d49">要注意的是：如果你讓 Claude 重跑一遍 Gemini 的工作來「驗證」，那等於做了兩次，完全沒省到額度。這種時候不如一開始就讓 Claude 做。交叉驗證的意思是<b>兩邊各做一次，你自己看結果</b>，這招不會省 Token 喔！</div><hr class="notion-hr notion-block-33c70f0196348023befac40296e123ab"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-33c70f019634800a99edd242fb616126" data-id="33c70f019634800a99edd242fb616126"><span><div id="33c70f019634800a99edd242fb616126" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33c70f019634800a99edd242fb616126" title="三、五分鐘設定，讓 Claude 自動叫 Gemini 跑腿"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">三、五分鐘設定，讓 Claude 自動叫 Gemini 跑腿</span></span></h3><div class="notion-text notion-block-33c70f019634808496bbc715631c2265">怎麼讓 Claude 自己判斷什麼時候該叫 Gemini？</div><div class="notion-text notion-block-33c70f0196348063841aea18a09008e8">在 CLAUDE.md 裡寫一段分工規則就好。Claude Code 每次啟動都會讀這份檔案，看到規則就會自動在背景用 Bash 呼叫 Gemini CLI，整合結果後再回報給你。不用手動切換，不用另外開視窗。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33c70f0196348081a9fed0a5c91a9302" data-id="33c70f0196348081a9fed0a5c91a9302"><span><div id="33c70f0196348081a9fed0a5c91a9302" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33c70f0196348081a9fed0a5c91a9302" title="1. 安裝與首次登入"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">1. 安裝與首次登入</span></span></h4><div class="notion-text notion-block-33c70f0196348097b563ef6c677757f4">安裝和登入都在<b>終端機</b>裡完成。如果你不確定怎麼打開：</div><ul class="notion-list notion-list-disc notion-block-33c70f01963480d9af7eca6cc419c4ba"><li><b>Mac</b>：按 <code class="notion-inline-code">Cmd + 空白鍵</code>，輸入 <code class="notion-inline-code">Terminal</code>，按 Enter</li></ul><ul class="notion-list notion-list-disc notion-block-33c70f01963480b59703f5f5652d5e16"><li><b>Windows</b>：按 <code class="notion-inline-code">Win + R</code>，輸入 <code class="notion-inline-code">cmd</code>，按 Enter（或搜尋「命令提示字元」）</li></ul><div class="notion-text notion-block-33c70f019634801e92c6dee2a32cc20e">前置需求：<a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://nodejs.org/">Node.js</a> （裝最新版即可）和一個 Google 帳號。（詳細步驟見 <a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://geminicli.com/docs/get-started/installation/">官方安裝指南</a>）</div><div class="notion-text notion-block-33c70f0196348083a754cc35c9832203">打開終端機後，按照以下順序分別輸入：</div><div class="notion-text notion-block-33c70f01963480f2ba17e5d06e342521">執行 <code class="notion-inline-code">gemini</code> 後，瀏覽器會自動跳出 Google 登入畫面，授權完成後認證就存在你的電腦裡了。（認證細節見 <a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://geminicli.com/docs/get-started/authentication/">官方認證文件</a>）</div><div class="notion-text notion-block-33c70f01963480a9bc4eed101e619b0d">這是唯一需要打開終端機的時候。之後全部透過 Claude Code 在背景呼叫，你不用再碰 Gemini CLI。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33c70f01963480099cf7d203042ff1d2" data-id="33c70f01963480099cf7d203042ff1d2"><span><div id="33c70f01963480099cf7d203042ff1d2" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33c70f01963480099cf7d203042ff1d2" title="2. 跟你的 Claude 討論分工規則"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">2. 跟你的 Claude 討論分工規則</span></span></h4><div class="notion-text notion-block-33d70f019634809aa557f88924c60595">裝好之後，你可以直接把這篇文章丟給你的 Claude，跟它討論怎麼設定分工規則，然後請他把結論寫入 CLAUDE.md。</div><div class="notion-text notion-block-33d70f01963480559d88fdb9333cd4b1">之所以這樣可以，是因為 CLAUDE.md 對 Claude 來說等於系統指令，你把這篇文章丟給他，然後跟他討論 Gemini 之於你而言適合擔任什麼工作、以及觸發 Gemini 的時機。</div><div class="notion-text notion-block-33d70f01963480ec860df9bf58f430f5">我自己的規則也是這樣跟 Claude 聊出來的。每個人的使用習慣不同，與其我給你一段固定的 Prompt 去複製貼上，不如讓你的 Claude 根據你的需求，自己決定什麼時候該叫 Gemini 幫忙。</div><div class="notion-text notion-block-33d70f01963480449235c7cbb8907d78">你要做的就是把想法講清楚，然後 Claude 讀完就會自己安排了！</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33c70f01963480a0869df853b96046c2" data-id="33c70f01963480a0869df853b96046c2"><span><div id="33c70f01963480a0869df853b96046c2" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33c70f01963480a0869df853b96046c2" title="3. 關於 Gemini CLI 的工具權限"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">3. <b>關於 Gemini CLI 的工具權限</b></span></span></h4><div class="notion-text notion-block-34170f01963480839376ccf60029277a">Gemini CLI 有很多內建工具：搜尋網頁、讀寫檔案、跑終端機指令。用 <code class="notion-inline-code">-p</code> 非互動模式呼叫時，這些工具預設都需要手動確認——但背景模式下沒有人能按確認，工具就不會啟動。</div><div class="notion-text notion-block-34170f019634805696b4d3c9302ea6d3">問題是，Gemini 不會老實告訴你「我沒有工具可以用」。</div><div class="notion-text notion-block-34170f01963480b696d1cfd87fadaedf">我請 Claude 叫 Gemini 去抓一個網頁做摘要。Gemini 很快就回了一篇，標題、段落、重點整理都有，格式漂亮。</div><div class="notion-text notion-block-34170f0196348055b4f6cce32b46fe80">結果怎麼看都是在唬爛。</div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33c70f019634805986fddd8e5520c8df"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A8f8fd161-8fd7-42c5-b741-46a050ffc67b%3Agemini-cli-url-fetch-hallucination.png?table=block&amp;id=33c70f01-9634-8059-86fd-dd8e5520c8df&amp;t=33c70f01-9634-8059-86fd-dd8e5520c8df&amp;width=704.0056762695312&amp;cache=v2" alt="Claude Code 對話截圖：測試 Gemini 能否直接讀取網址，結果發現它在 -p 模式下沒有 web_fetch 工具卻不報錯，直接捏造了一篇假文章內容。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption"><em>Claude Code 對話截圖：測試 Gemini 能否直接讀取網址，結果發現它在 -p 模式下沒有 web_fetch 工具卻不報錯，直接捏造了一篇假文章內容。</em></figcaption></div></figure><div class="notion-text notion-block-33c70f019634804c8554d10bbf1dd55c">攏洗ㄍㄟˋ欸啦！</div><div class="notion-text notion-block-33d70f0196348020ac1df416210d5e68">沒有給他任何權限，Gemini 在背景模式下用不了搜尋工具，但它不會告訴你「我沒有工具可以用」，而是直接假裝做到了，整篇瞎掰。</div><div class="notion-text notion-block-34170f0196348059bc12c57124a4bbf8">所以如果你想讓它真的去搜尋或讀網頁，就得額外做設定。</div><div class="notion-text notion-block-33d70f01963480e58867fe167ae81d56">YOLO 模式雖然可以讓 Gemini 自動授權所有工具呼叫，但他授權的指令範圍太廣了，連覆寫檔案、甚至刪東西，全程不會問你。</div><div class="notion-text notion-block-34170f0196348059874ac89f111e2f1d">我們叫 Gemini 做的事其實很單純，其實就查資料、讀檔案、摘要網頁。這些都是唯讀操作，也不用開到 YOLO。</div><div class="notion-text notion-block-34170f0196348014bce3fcd986e0e503">更好的做法：用 <code class="notion-inline-code">excludeTools</code> 封掉危險工具。</div><div class="notion-text notion-block-34170f01963480e3b3c8d1c1aeecfbb1">在 Gemini CLI 的設定檔 <code class="notion-inline-code">~/.gemini/settings.json</code>（Windows 是 <code class="notion-inline-code">%USERPROFILE%\.gemini\settings.json</code>）加上這段：</div><div class="notion-text notion-block-34170f0196348028b62ff9a19cdb6686">加完之後，搜尋和讀檔照常運作，但 Gemini <b>完全無法寫入、修改或刪除你的檔案，</b>連繞道用子代理都會被擋下來。實測過，三條路全封死。</div><hr class="notion-hr notion-block-33c70f019634805e8341ca7b3ef866f7"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-33d70f019634806faf51d2c98fa64f90" data-id="33d70f019634806faf51d2c98fa64f90"><span><div id="33d70f019634806faf51d2c98fa64f90" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33d70f019634806faf51d2c98fa64f90" title="四、使用提醒"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">四、使用提醒</span></span></h3><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33d70f0196348062b614cc795ec34357" data-id="33d70f0196348062b614cc795ec34357"><span><div id="33d70f0196348062b614cc795ec34357" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33d70f0196348062b614cc795ec34357" title="1. 同時別派太多 Gemini"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">1. 同時別派太多 Gemini</span></span></h4><div class="notion-text notion-block-33d70f019634806ea497ed0fabc4a94e">雖然每天有 1,000 次請求的免費額度，但每分鐘上限是 60 次。一個查詢背後可能觸發好幾次內部請求（搜尋 + 讀網頁 + 整合），我的經驗是同時跑超過兩個就容易撞限、回傳錯誤。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33d70f0196348041bc94e40ca56fd09e" data-id="33d70f0196348041bc94e40ca56fd09e"><span><div id="33d70f0196348041bc94e40ca56fd09e" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33d70f0196348041bc94e40ca56fd09e" title="2. Gemini 的幻覺有救嗎"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">2. Gemini 的幻覺有救嗎</span></span></h4><div class="notion-text notion-block-33d70f01963480f0b330cbd426281375">如果每次都讓 Claude 重跑一遍 Gemini 的工作來「驗證」，那等於沒省到。如果你不放心 Gemini 的說法，那就別用，直接讓 Claude 做。但如果你誰都不相信，那很適合讓他們監督彼此！</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33d70f019634804b80e7ee1adf12a21f" data-id="33d70f019634804b80e7ee1adf12a21f"><span><div id="33d70f019634804b80e7ee1adf12a21f" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33d70f019634804b80e7ee1adf12a21f" title="3. 安全性"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">3. 安全性</span></span></h4><div class="notion-text notion-block-33d70f01963480279e06fb2387756757">這招使用的是 Google 官方的 <code class="notion-inline-code"><a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://github.com/google-gemini/gemini-cli">@google/gemini-cli</a></code>，走正規瀏覽器 OAuth 登入，不需要第三方工具。Claude 只是在你的電腦上幫你在終端機輸入指令，不會把你的 Token 傳給第三方伺服器，不是龍蝦，但要不要 ban 還是看 Google 心情。</div><hr class="notion-hr notion-block-33c70f01963480e28fc1e06352ad6f16"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-33d70f019634807192ffcfbfb2614a3e" data-id="33d70f019634807192ffcfbfb2614a3e"><span><div id="33d70f019634807192ffcfbfb2614a3e" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33d70f019634807192ffcfbfb2614a3e" title="結語：吸 Token 有一種無所不能的感覺"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>結語：吸 Token 有一種無所不能的感覺</b></span></span></h3><div class="notion-text notion-block-33d70f019634800593a4f8f3712ed24b">原本研究這個只是想解決額度不夠用的問題，但現在看到 AI 彼此吵架的樣子，真的好好玩。尤其後來我把 Codex 也接進來了，三家一起吵比我單押一家安心多了。畢竟 AI 幻覺無法避免，他們先吵一輪，我也比較放心。</div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33d70f019634807ebb11d3bfa07c22e4"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A6e85670f-4ba8-4dfb-a27f-e097e5a29fa3%3Aclaude-code-dispatches-gemini-and-codex-for-cross-validation.jpg?table=block&amp;id=33d70f01-9634-807e-bb11-d3bfa07c22e4&amp;t=33d70f01-9634-807e-bb11-d3bfa07c22e4&amp;width=703.977294921875&amp;cache=v2" alt="Claude Code 對話截圖：Claude 同時派 Gemini CLI 與 Codex CLI 平行讀取同一篇文章做交叉驗證，畫面顯示 Ran 2 commands 與兩條同步執行的 Bash 指令。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">Claude Code 對話截圖：Claude 同時派 Gemini CLI 與 Codex CLI 平行讀取同一篇文章做交叉驗證，畫面顯示 Ran 2 commands 與兩條同步執行的 Bash 指令。</figcaption></div></figure><div class="notion-text notion-block-33d70f019634801994f8e907cd74cfe1">我怕記錯內容，所以寫這篇文章時，有請 Claude、Gemini、Codex 三個一起做事實查核<em>，</em>畫面有點壯觀。</div><div class="notion-text notion-block-33d70f0196348069bb45c429e8103f19">結果這樣玩，省到了什麼額度⋯⋯</div><div class="notion-text notion-block-33d70f0196348085bf60d4cab2660771">呃⋯⋯</div></main></div>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[機器真的聽懂人話嗎？一次搞懂 NLP：Transformer、BERT 與 GPT]]></title>
            <link>https://gyozalab.com/nlp-evolution-from-rules-to-gpt-guide</link>
            <guid>https://gyozalab.com/nlp-evolution-from-rules-to-gpt-guide</guid>
            <pubDate>Sun, 29 Mar 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[用圖解走一遍 NLP 60 年演化：規則比對 → 統計模型 → Transformer 自注意力機制。搞懂 BERT 雙向理解和 GPT 單向生成的本質差異，以及為什麼傳統方法在 LLM 時代還沒過時。]]></description>
            <content:encoded><![CDATA[<div id="notion-article" class="mx-auto overflow-hidden "><main class="notion light-mode notion-page notion-block-33270f01963480d08f92d889b9d4f2b8"><div class="notion-viewport"></div><div class="notion-collection-page-properties"></div><div class="notion-callout notion-block-8ae1ab44a37d41eb850ac85c1f2e1f32"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="🎯">🎯</span></div><div class="notion-callout-text"><div class="notion-text notion-block-d299fe323376427fb51c7f2ea9567c3f">NLP 從規則死背、統計算機率，走到 Transformer 的自注意力機制，讓機器從「數字計算」進化到「動態理解語意」。BERT 擅長雙向理解，GPT 擅長流暢生成，兩者並非競爭而是各擅其場，幻覺與算力則是當前 LLM 仍待突破的天花板。</div></div></div><div class="notion-text notion-block-33270f01963480108714d2e62337f031">對人類來說，說話像呼吸一樣自然；但對電腦而言，人類語言是一場混亂的災難。同一個詞「<b>bank</b>」，在金融情境中是銀行，在地理情境中是河岸。電腦最初只是一台只認得 0 與 1 的冷酷計算機，要讓它理解文字中的情緒、雙關與邏輯，人類經歷了長達半個世紀的技術長征。</div><div class="notion-text notion-block-33270f01963480588609ddf60c011313">自然語言處理（<b>Natural Language Processing</b>, NLP）的本質，就是一場將「感性訊號」轉譯為「數學邏輯」的煉金術。這篇文章將帶你穿梭時空，看機器如何從死背規則的「複讀機」，演化成具備動態雷達的「通才巨人」。</div><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-33270f01963480c4add6db4c4005d9a4" data-id="33270f01963480c4add6db4c4005d9a4"><span><div id="33270f01963480c4add6db4c4005d9a4" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480c4add6db4c4005d9a4" title="一、NLP 的核心疆域：理解與生成的二重奏"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>一、NLP 的核心疆域：理解與生成的二重奏</b></span></span></h3><div class="notion-callout notion-gray_background_co notion-block-33270f0196348038ad79f59282365bc4"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f019634803b8cf0d24f89344fd8"><b>NLP 不就是把文字丟進模型裡跑嗎？為什麼還需要分 NLU 和 NLG？這對開發者來說有什麼實質意義？ </b></div><div class="notion-text notion-block-33270f0196348051aa6dd8598f6de078">NLP 就是讓電腦「讀懂」並「說話」的技術。<b>NLU</b> 負責<b>理解</b>（像大腦聽懂指令），<b>NLG</b> 負責<b>生成</b>（像嘴巴回話）。區分兩者能讓開發者按需求選工具，精準省時又不浪費資源！</div></div></div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33270f019634801eac20f4f00ac92b1f"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A68babdc7-879f-4ecc-b131-732635343c60%3Anlp-nlu-nlg-explanation-cat-meme-infographic-taichung-creators.png?table=block&amp;id=33270f01-9634-801e-ac20-f4f00ac92b1f&amp;t=33270f01-9634-801e-ac20-f4f00ac92b1f&amp;width=1080&amp;cache=v2" alt="一張極簡灰背景的擬人化貓咪資訊圖表，以幽默方式解釋 NLP。左側為「NLU 理解」：一隻戴眼鏡的橘貓看著手機，思維氣泡顯示將毛線球轉化為小魚。右側為「NLG 生成」：橘貓一臉不屑地在發光鍵盤上敲字，周圍環繞詩歌、笑話和智慧家庭圖示。標題為「自然語言理解與生成的貓言貓語大揭秘」。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">一張極簡灰背景的擬人化貓咪資訊圖表，以幽默方式解釋 NLP。左側為「NLU 理解」：一隻戴眼鏡的橘貓看著手機，思維氣泡顯示將毛線球轉化為小魚。右側為「NLG 生成」：橘貓一臉不屑地在發光鍵盤上敲字，周圍環繞詩歌、笑話和智慧家庭圖示。標題為「自然語言理解與生成的貓言貓語大揭秘」。</figcaption></div></figure><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f0196348000bc45d46accb8711d" data-id="33270f0196348000bc45d46accb8711d"><span><div id="33270f0196348000bc45d46accb8711d" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f0196348000bc45d46accb8711d" title="1.1 分類的意義：追求「對不對」還是「好不好」？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>1.1 分類的意義：追求「對不對」還是「好不好」？</b></span></span></h4><div class="notion-text notion-block-33270f019634803d9c5de23b6e140ac8">為什麼我們要特地把 NLP 切分成 NLU（理解）與 NLG（生成）？這不只是學術上的分類，更是因為兩者的「成功定義」完全不同。當你作為開發者在評估模型時，這套標準能幫你決定資源該投在哪：</div><ol start="1" class="notion-list notion-list-numbered notion-block-33270f01963480108ed9db47f005f118" style="list-style-type:decimal"><li><b>NLU 追求的是「對不對」</b>：</li><ol class="notion-list notion-list-numbered notion-block-33270f01963480108ed9db47f005f118" style="list-style-type:lower-alpha"><div class="notion-text notion-block-33270f01963480508a4be5b64a6aed79">這是一個關於「精確率」與「召回率」的比賽。當使用者說「我要退貨」，模型必須 100% 精準地辨識出意圖，不能把退貨誤判為下單。在這裡，我們容不下模糊空間，目標是從成千上萬種說法中，找到唯一的正確答案。</div></ol></ol><ol start="2" class="notion-list notion-list-numbered notion-block-33270f0196348062aaa7c1ff6a54ad45" style="list-style-type:decimal"><li><b>NLG 追求的是「好不好」</b>：</li><ol class="notion-list notion-list-numbered notion-block-33270f0196348062aaa7c1ff6a54ad45" style="list-style-type:lower-alpha"><div class="notion-text notion-block-33270f0196348093a9b8eee7657d530c">這是一個關於「流暢度」與「相關性」的挑戰。AI 回覆使用者的文字，沒有絕對的標準答案。重點在於語氣是否自然？邏輯是否連貫？內容是否真的解決了問題？在這裡，我們追求的是一種人性化的溝通體驗。</div></ol></ol><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480d2b3c5f94e8fccafd6" data-id="33270f01963480d2b3c5f94e8fccafd6"><span><div id="33270f01963480d2b3c5f94e8fccafd6" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480d2b3c5f94e8fccafd6" title="1.2 技術底層：機器處理語言的三個任務層級"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>1.2 技術底層：機器處理語言的三個任務層級</b></span></span></h4><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33270f01963480d181efe8cb5825bff2"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A143f19ad-fb51-4f09-8b02-d071b4e10f22%3Anlp-workflow-stages-cat-meme-taichung-ai-automation.png?table=block&amp;id=33270f01-9634-80d1-81ef-e8cb5825bff2&amp;t=33270f01-9634-80d1-81ef-e8cb5825bff2&amp;width=1080&amp;cache=v2" alt="一張標題為「機器語言處理三層次」的專業迷因圖。分為三個區塊：1. 理解（Understanding）：一隻憂鬱貓咪抱怨不舒服，AI 嘗試解析情感；2. 處理（Processing）：橘貓在複雜的神經網絡與邏輯運算中思考暗示；3. 生成（Generating）：橘貓自信地拿著熱水杯說「多喝熱水！」，旁邊配上完美回應的成功男孩梗圖。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">一張標題為「機器語言處理三層次」的專業迷因圖。分為三個區塊：1. 理解（Understanding）：一隻憂鬱貓咪抱怨不舒服，AI 嘗試解析情感；2. 處理（Processing）：橘貓在複雜的神經網絡與邏輯運算中思考暗示；3. 生成（Generating）：橘貓自信地拿著熱水杯說「多喝熱水！」，旁邊配上完美回應的成功男孩梗圖。</figcaption></div></figure><div class="notion-text notion-block-33270f019634807c882fe4f425becc84">要達成上述目標，NLP 系統在技術上必須經歷三個遞進的處理層級，這也是所有 NLP 模型的共同基石：</div><ol start="1" class="notion-list notion-list-numbered notion-block-33270f01963480eca2f2cfffc6911426" style="list-style-type:decimal"><li><b>理解 (Understand)</b>：這是 NLU 的主戰場。機器必須從混亂的非結構化文字中，解析出語法結構（<b>Syntax</b>）與語意邏輯（<b>Semantics</b>）。這涉及辨識語者的意圖、偵測情緒，並從背景知識中提取出隱含的邏輯。</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-33270f0196348082b46cd37f3c64fad3" style="list-style-type:decimal"><li><b>處理 (Process)</b>：將人類語言轉換為電腦可操作的結構。這通常涉及「特徵提取」，例如將句子變成高維度向量，讓機器能在座標系中計算詞語間的距離。</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-33270f0196348036af93cb7f4745ec1d" style="list-style-type:decimal"><li><b>生成 (Generate)</b>：NLG 的終極目標。根據處理後的語意座標，模型必須重新建構語句，產出自然、流暢且具備邏輯的文字。這不只是拼湊單字，還需要考慮上下文的一致性（<b>Coherence</b>）。</li></ol><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480a8ad4feaa643930c9a" data-id="33270f01963480a8ad4feaa643930c9a"><span><div id="33270f01963480a8ad4feaa643930c9a" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480a8ad4feaa643930c9a" title="1.3 開發者的最終目標：解決哪種商業問題？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>1.3 開發者的最終目標：解決哪種商業問題？</b></span></span></h4><div class="notion-text notion-block-33270f01963480b3bac3c76254783ed5">在實務應用中，我們會根據任務屬性來選擇技術路徑。下表整理了 NLP 的核心任務分佈：</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f0196348095aab5c0fb7ad7b262" data-id="33270f0196348095aab5c0fb7ad7b262"><span><div id="33270f0196348095aab5c0fb7ad7b262" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f0196348095aab5c0fb7ad7b262" title="模組一：自然語言理解 (NLU)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>模組一：自然語言理解 (NLU)</b></span></span></h4><div class="notion-text notion-block-33270f0196348070911ac91dbe3990b8"><b>核心目標：</b> 將非結構化文字轉化為電腦可處理的標籤、類別或數據。</div><table class="notion-simple-table notion-block-33270f01963480328c9be2b2fabbe8c1"><tbody><tr class="notion-simple-table-row notion-block-33270f01963480238041eb1ce92965fa"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>任務名稱</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>技術細節 (底層邏輯)</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>實務應用場景</b></div></td></tr><tr class="notion-simple-table-row notion-block-33270f0196348013b34bef46a93562e6"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>意圖辨識 (Intent Recognition)</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">把語句分類到預設標籤（如：詢問天氣、退貨）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">客服機器人分流、語音指令解析。</div></td></tr><tr class="notion-simple-table-row notion-block-33270f0196348008930fe3a77f5cb7e8"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>命名實體辨識 (NER)</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">從文本中提取人名、地名、機構。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">法律文件自動標記、醫囑資訊抓取。</div></td></tr><tr class="notion-simple-table-row notion-block-33270f01963480e694f2d49ee3786528"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>情感分析 (Sentiment Analysis)</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">判斷語氣是正向、負向還是中立。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">社群輿情監控、電商評論自動彙整。</div></td></tr></tbody></table><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f0196348040a08be9d337070efb" data-id="33270f0196348040a08be9d337070efb"><span><div id="33270f0196348040a08be9d337070efb" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f0196348040a08be9d337070efb" title="模組二：自然語言生成 (NLG)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">模組二：自然語言生成 (NLG)</span></span></h4><div class="notion-text notion-block-33270f0196348071b496e134eee5972e"><b>核心目標：</b> 根據已理解的資訊或數據，重新組織成人類可讀的流暢文字。</div><table class="notion-simple-table notion-block-33270f0196348070a254efe778d71182"><tbody><tr class="notion-simple-table-row notion-block-33270f01963480b1bd62f53f94a2cbf1"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>任務名稱</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>技術細節 (底層邏輯)</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>實務應用場景</b></div></td></tr><tr class="notion-simple-table-row notion-block-33270f01963480779f29f9344eb2d580"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>自動摘要 (Summarization)</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">壓縮長篇大論，只保留核心重點。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">新聞快報、會議記錄自動摘要。</div></td></tr><tr class="notion-simple-table-row notion-block-33270f0196348086b812d18e76a7e6c1"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>對話生成 (Response Generation)</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">根據上下文邏輯，產生流暢的回覆。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">ChatGPT 對答、虛擬助理互動。</div></td></tr><tr class="notion-simple-table-row notion-block-33270f01963480feab13df63f247366b"><td class="" style="width:120px"><div class="notion-simple-table-cell">機器翻譯 (Machine Translation)</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">跨語言轉換：語意對齊並重新建構語句。</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">跨國文件翻譯、即時語音翻譯。</div></td></tr></tbody></table><hr class="notion-hr notion-block-33270f01963480778f1df9b8ab15b4b8"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-33270f0196348001aefbc69a1151d6ad" data-id="33270f0196348001aefbc69a1151d6ad"><span><div id="33270f0196348001aefbc69a1151d6ad" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f0196348001aefbc69a1151d6ad" title="二、演進史：從規則編碼到預訓練時代"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>二、演進史：從規則編碼到預訓練時代</b></span></span></h3><div class="notion-callout notion-gray_background_co notion-block-33270f0196348084a25ef2b680c6b902"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f0196348060bfa4d693d17a2d33"><b>既然現在的 GPT 這麼強，我們還有必要學規則式方法（Rule-based）或是統計模型（N-gram）嗎？ 那不都以前的東西了？學最新的不就好了？</b></div><div class="notion-text notion-block-33270f0196348058ab38e155bd7dc10a">即使 GPT 強大，學習基礎技術仍有三大核心意義：</div><ul class="notion-list notion-list-disc notion-block-33270f019634808f9bdbf54e217ffb14"><li><b>技術底層邏輯</b>：現代 Transformer 是從詞向量、統計模型演化而來。不學基礎，難以理解模型為何出錯或如何調優。 </li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634802a9aede30b495018f7"><li><b>實務場景限制</b>：在斷網、低運算設備或高隱私需求下，輕量的傳統方法是唯一解。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634807bb03ae0d5067fc346"><li><b>混合式架構</b>：最強的系統通常是「規則＋模型」。用規則過濾敏感資訊，再用 GPT 生成內容，兼具安全與靈活性。 </li></ul><div class="notion-text notion-block-33270f019634807e8f78cd9d5ddc92b5">這也是為什麼 <b>iPAS AI 規劃師</b> 鑑定仍將這些列為必考重點！</div></div></div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33270f0196348023a359ed2d32f17514"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Acc672976-0157-4dfd-8bed-a4b786bb2208%3Anlp-history-four-generations-cat-infographic-taichung-ai-automation.png?table=block&amp;id=33270f01-9634-8023-a359-ed2d32f17514&amp;t=33270f01-9634-8023-a359-ed2d32f17514&amp;width=1080&amp;cache=v2" alt="NLP 四代演進資訊圖：橘貓化身四種角色。從 80 年代死守 Rulebook 的嚴格規則、90 年代撥算盤的統計機率、2010 年連結神經網絡的深度學習，到現今戴方帽坐擁書山的預訓練時代。生動呈現從「不准變通」到「博學多才」的 AI 演化歷程。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">NLP 四代演進資訊圖：橘貓化身四種角色。從 80 年代死守 Rulebook 的嚴格規則、90 年代撥算盤的統計機率、2010 年連結神經網絡的深度學習，到現今戴方帽坐擁書山的預訓練時代。生動呈現從「不准變通」到「博學多才」的 AI 演化歷程。</figcaption></div></figure><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f0196348058884df6f20468d826" data-id="33270f0196348058884df6f20468d826"><span><div id="33270f0196348058884df6f20468d826" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f0196348058884df6f20468d826" title="2.1 第一世代：規則式方法 (1980s - 1990s)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>2.1 第一世代：規則式方法 (1980s - 1990s)</b></span></span></h4><div class="notion-text notion-block-33270f01963480b9a7ecfe68582231b8">這是一個「語言學家治國」時代。人類手動編寫語法辭典與邏輯規則。系統不具備真正的智能，僅是按照「如果...就...（<b>If-Then</b>）」的邏輯運行。</div><ul class="notion-list notion-list-disc notion-block-33270f019634809ba4cedd60db327908"><li><b>代表技術</b>：<b>ELIZA</b>、專家系統。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634803b9e2fdca2173a7e6e"><li><b>優勢</b>：高可解釋性。系統若判斷錯了，你可以精準找到是哪條規則寫歪了。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480b9ac83f5443cd060b8"><li><b>痛點</b>：維護成本極高。語言是活的，當新詞（如「很雷」）出現時，系統必須手動更新，否則就會徹底失效。</li></ul><blockquote class="notion-quote notion-block-33270f01963480ed8481d494e590cb06"><div><b>經典案例：ELIZA (1966 年)</b>
這是史上第一個聊天機器人，它模擬的是一位「心理醫生」。它完全沒有智慧，只是利用關鍵字替換來反問使用者。</div><ul class="notion-list notion-list-disc notion-block-33270f01963480d3948ef06158d20c79"><li><b>使用者</b>：「我最近跟我媽吵架了。」</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480d09f91db2e18deb3be"><li><b>ELIZA 規則</b>：只要看到「我媽」，就回覆「再多跟我聊聊你的家人吧」。
結果：使用者會覺得「它聽得懂我在說什麼」，但其實它只是在玩文字接龍。</li></ul></blockquote><div class="notion-callout notion-gray_background_co notion-block-33270f01963480b8b1cbdb4cee8512cf"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f0196348056aedad172e6d5c05d"><b>規則式方法 (Rule-based) 現在還有人用嗎？</b></div><div class="notion-text notion-block-33270f019634807f810cfc09ede4bfa5"><b>有的！雖然 GPT 很強，但規則式方法在「準確度」與「成本」上有不可取代的地位。</b></div><ol start="1" class="notion-list notion-list-numbered notion-block-33270f019634803ea82ae91337bc6ce0" style="list-style-type:decimal"><li><b>身分證字號檢查 💳</b>：這是最經典的應用。透過預設的數學邏輯（如：首字母代表地區、檢查碼運算）來驗證格式。這種「非黑即白」的任務，用規則式處理比 AI 亂猜更精準。</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-33270f01963480398003debce3a497a4" style="list-style-type:decimal"><li><b>LINE 官方帳號機器人 🤖</b>：許多企業的自動回覆系統仍使用「關鍵字觸發」。當使用者輸入特定詞彙（如：門市資訊、運費），系統便立即丟出預設內容，反應速度極快且成本極低。</li></ol></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f0196348076a711c3a842275edc" data-id="33270f0196348076a711c3a842275edc"><span><div id="33270f0196348076a711c3a842275edc" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f0196348076a711c3a842275edc" title="2.2 第二世代：統計語言模型 (1990s - 2010s)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>2.2 第二世代：統計語言模型 (1990s - 2010s)</b></span></span></h4><div class="notion-text notion-block-33270f019634807bb123dd0a2a7f5571">在深度學習出現之前，機器讀語言靠的是統計規律，也就是數算詞出現的頻率。核心概念是：如果一個詞組合在過去經常出現，那它在未來出現的機率也比較高。</div><div class="notion-callout notion-gray_background_co notion-block-33270f01963480a1a1aafe6901ec7bd5"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f01963480b3aacac02f0869d877"><b>為什麼放棄規則，改學機率？</b></div><div class="notion-text notion-block-33270f019634808093cfe57d63398a5d">因為人類語言太難預測了！規則寫再多也寫不完例外。統計派不再強迫電腦「理解」語法，而是讓它當個「算命師」：根據過去發生的數據，預測下一個字最可能出現什麼。這就是從「教電腦釣魚」轉向「給電腦看一萬張魚的照片」的過程。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f0196348023a553ddee2fee2978" data-id="33270f0196348023a553ddee2fee2978"><span><div id="33270f0196348023a553ddee2fee2978" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f0196348023a553ddee2fee2978" title="① N-gram 語言模型 (N-gram Language Model)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">① N-gram 語言模型 (N-gram Language Model)</span></span></h4><ul class="notion-list notion-list-disc notion-block-33270f019634808bb6f1db8b446c5e7f"><li><b>核心邏輯</b>：靠前面幾個詞預測下一個詞的機率。N 是你往回看的「窗格大小」。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634801887c2f3c06af84987"><li><b>致命限制</b>：<b>長距離依賴問題 (Long-range Dependencies)</b>。N-gram 只能看固定長度的窗格。句子太長時，它會「瞬間斷片」，忘記句子開頭說了什麼。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634809e9ac8c14e42e89d48"><li><b>痛點</b>：資料稀疏問題。當 N 增大時，許多詞組組合在語料庫中從未出現，機率會變為零。</li></ul><blockquote class="notion-quote notion-block-33270f01963480ff8deff898e09aab08"><div><b>Google 搜尋建議</b>。當你輸入「台北」，系統會根據統計機率跳出「台北天氣」、「台北捷運」，因為這些組合在數據庫中出現次數最多。</div></blockquote><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f019634803b8e26e5915fc98c01" data-id="33270f019634803b8e26e5915fc98c01"><span><div id="33270f019634803b8e26e5915fc98c01" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f019634803b8e26e5915fc98c01" title="② TF-IDF 詞頻-逆文件頻率 (Term Frequency-Inverse Document Frequency)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">② TF-IDF 詞頻-逆文件頻率 (Term Frequency-Inverse Document Frequency)</span></span></h4><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33270f01963480959764daed436bf028"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A9353e7b8-1063-41c1-aae3-d011b2f0b481%3Atf-idf-algorithm-explained-gyoza-cat-meme-taichung-ai-creator.png?table=block&amp;id=33270f01-9634-8095-9764-daed436bf028&amp;t=33270f01-9634-8095-9764-daed436bf028&amp;width=1080&amp;cache=v2" alt="一張標題為「TF-IDF 的奧義：從餃子看懂關鍵詞權重！」的趣味資訊圖表。三格漫畫形式說明：1. 詞頻 (TF)：橘白貓面對滿桌普通餃子，暗示出現頻率高不代表最重要；2. 逆向檔案頻率 (IDF)：貓咪發現稀有的綠色抹茶餃子，象徵獨特性；3. TF-IDF 核心：貓咪舉起閃閃發光的抹茶餃子，公式顯示「高 TF x 高 IDF = 超重要」，結論是找出最獨特的那顆餃子。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">一張標題為「TF-IDF 的奧義：從餃子看懂關鍵詞權重！」的趣味資訊圖表。三格漫畫形式說明：1. 詞頻 (TF)：橘白貓面對滿桌普通餃子，暗示出現頻率高不代表最重要；2. 逆向檔案頻率 (IDF)：貓咪發現稀有的綠色抹茶餃子，象徵獨特性；3. TF-IDF 核心：貓咪舉起閃閃發光的抹茶餃子，公式顯示「高 TF x 高 IDF = 超重要」，結論是找出最獨特的那顆餃子。</figcaption></div></figure><ul class="notion-list notion-list-disc notion-block-33270f01963480519a7dc8882b2206de"><li><b>核心邏輯</b>：它是「字詞計數器」。在單篇出現多（TF 高），但在所有文章中罕見（IDF 高），則該字最能代表主題。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480f2aa69f8091f3cb4aa"><li><b>沒辦法處理「一詞多義」：</b>如果你搜尋「蘋果」，TF-IDF 分不出你是在找吃的「水果」，還是在找「手機」。它只會數次數，不會看上下文。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634803491ffea12328686e0"><li><b>完全不懂「意思」 (語意鴻溝)</b>：在 TF-IDF 眼中，「貓咪」和「喵星人」是兩個截然不同的東西，分數完全不互通。如果你搜尋「貓咪」，它可能漏掉所有寫「喵星人」的超棒文章。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480278532e3c32806e4a4"><li><b>停用詞（Stopwords）過濾</b></li><ul class="notion-list notion-list-disc notion-block-33270f01963480278532e3c32806e4a4"><li>想像你在聽一場演講，講者每講三句話就加一個「然後」、「那個」。這些詞對理解演講核心毫無貢獻，卻佔據了你的聽力帶寬。在 NLP 中，這就是「停用詞」。</li><li><b>核心功能</b>：去除如「的」、「了」、「在」或英文的 &quot;is&quot;, &quot;the&quot; 等高頻但語意貢獻低的詞。</li><li><b>減少運算量</b>：過濾掉佔文本 30%-50% 的廢話，能讓模型訓練快上一倍。</li></ul></ul><blockquote class="notion-quote notion-block-33270f0196348086a895c54cae1750e9"><div><b>傳統 SEO 玩法</b>：在那個 Google 還沒像現在這麼聰明的時代（大約 2010 年代以前），TF-IDF 是搜尋引擎排名的核心技術之一。網站管理員會計算競爭對手的網頁中，哪些關鍵字的 TF-IDF 分數最高，然後在自己的網頁裡刻意增加這些「稀有且重要」的詞彙，好讓 Google 覺得這篇文章「最有重點」。</div></blockquote><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f0196348091886ac0f585d2e374" data-id="33270f0196348091886ac0f585d2e374"><span><div id="33270f0196348091886ac0f585d2e374" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f0196348091886ac0f585d2e374" title="2.3 第三世代：深度學習時代 (2010s - 2018)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>2.3 第三世代：深度學習時代 (2010s - 2018)</b></span></span></h4><div class="notion-callout notion-gray_background_co notion-block-33270f019634807b9dddf30348721955"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f0196348094bce9ef2cef38b3a5"><b>N-gram 跟 RNN、LSTM 都是健忘的金魚腦，那他們差在哪裡？</b></div><div class="notion-text notion-block-33270f01963480aaa9f9e3772aa5190f">從統計時代（N-gram）跨越到深度學習時代（RNN/LSTM），最關鍵的差別在於電腦看待語言的方式從「<b>數次數</b>」變成了「<b>向量化與狀態記憶</b>」。</div><ul class="notion-list notion-list-disc notion-block-33270f01963480479691e9e038bb5af7"><li><b>統計時代 (N-gram)</b>：像是一個只有幾秒記憶的收銀員。他只記得你剛剛說的最後 1-2 個字。如果你說了一長串需求，他只會根據最後一個字來猜你要什麼。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480729e11fd08adcc69f3"><li><b>深度學習時代 (RNN/LSTM)</b>：像是一個帶著筆記本的速記員。他會把讀過的每個字轉化成「隱藏狀態（Hidden State）」，這就像是在筆記本上記錄摘要。雖然筆記本空間有限，寫太長會模糊（梯度消失），但他試圖保證整句話的語意是連貫的。</li></ul></div></div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33270f019634803db598c2d718224256"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Aedc48381-b2b1-4426-9a34-2d66d0e4d896%3Arnn-vs-lstm-memory-comparison-cat-infographic-taichung-ai.png?table=block&amp;id=33270f01-9634-803d-b598-c2d718224256&amp;t=33270f01-9634-803d-b598-c2d718224256&amp;width=1080&amp;cache=v2" alt="一張標題為「RNN vs LSTM：記憶力大對決！」的貓咪教學圖表。左側 RNN 被形容為「短期記憶金魚腦」，顯示一隻拿著揉皺紙條、驚慌失措的貓，思維氣泡裡只有 3 秒記憶的金魚，象徵處理長序列會斷片。右側 LSTM 被形容為「學霸筆記王」，顯示一隻戴眼鏡、拿著井然有序筆記本的學霸貓，思維氣泡裡有大腦與長期記憶庫，象徵其具備遺忘門與記憶門機制，能有效處理長序列。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">一張標題為「RNN vs LSTM：記憶力大對決！」的貓咪教學圖表。左側 RNN 被形容為「短期記憶金魚腦」，顯示一隻拿著揉皺紙條、驚慌失措的貓，思維氣泡裡只有 3 秒記憶的金魚，象徵處理長序列會斷片。右側 LSTM 被形容為「學霸筆記王」，顯示一隻戴眼鏡、拿著井然有序筆記本的學霸貓，思維氣泡裡有大腦與長期記憶庫，象徵其具備遺忘門與記憶門機制，能有效處理長序列。</figcaption></div></figure><div class="notion-text notion-block-33270f01963480789340f12cb1ba5fe8">神經網路進入戰場，<b>RNN</b> 與 <b>LSTM</b> 成為霸主。在這個時期，電腦不再只是數算機率，而是試圖模仿人類大腦的「隱藏狀態（Hidden State）」，將語言視為有順序的<b>時間序列</b>，讓模型具備了初步的記憶力。</div><ul class="notion-list notion-list-disc notion-block-33270f01963480fbbb0ffda54dd10086"><li><b>RNN (循環神經網路)：初步的記憶力</b></li><ul class="notion-list notion-list-disc notion-block-33270f01963480fbbb0ffda54dd10086"><li><b>核心邏輯</b>：它像是一個帶著筆記本的速記員，讀到每個字都會在筆記本上記錄摘要（隱藏狀態），試圖把前面的語意帶到後面的句子。</li><li><b>致命傷</b>：<b>梯度消失 (Gradient Vanishing)</b>。它的筆記本空間有限，一旦句子超過 20 個字，後面的記錄就會蓋掉前面的，導致它「看到後面就忘了前面」。</li><li><b>應用：</b>自動選字、語音辨識</li></ul></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480d08428ee1d8e0eef9e"><li><b>LSTM (長短期記憶網路)：進化的記憶開關</b></li><ul class="notion-list notion-list-disc notion-block-33270f01963480d08428ee1d8e0eef9e"><li><b>白話差別</b>：它是 RNN 的升級版。LSTM 在筆記本上加裝了「門控機制（Gates）」，像是有<b>立可帶</b>（忘記門）和<b>螢光筆</b>（輸入門）。它能智慧地判斷哪些廢話該忘記、哪些重點該長久記住，因此能處理比 RNN 更長的句子。</li><li>這樣可以把重要的資訊「鎖」在記憶裡，傳遞到 100 個字甚至更遠之後。又稱<b>長距離依賴 (Long-term Dependencies)。</b></li></ul></ul><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480699fd2dbfce67e613c" data-id="33270f01963480699fd2dbfce67e613c"><span><div id="33270f01963480699fd2dbfce67e613c" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480699fd2dbfce67e613c" title="2.4 第四世代：預訓練時代 (2018 至今)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>2.4 第四世代：預訓練時代 (2018 至今)</b></span></span></h4><div class="notion-callout notion-gray_background_co notion-block-33270f019634804c8065ca003d2c08f4"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f019634808e94cbed38c8fbdcfc"><b>為什麼有了 LSTM，我們最後還是發明了更強大的 Transformer (ChatGPT 的祖先)？</b></div><div class="notion-text notion-block-33270f0196348018affec7f890f6166f">自注意力機制（Self-Attention）解決了 LSTM 的<b>順序依賴</b>與<b>資訊損耗</b>問題。</div><ol start="1" class="notion-list notion-list-numbered notion-block-33270f0196348018938fc8f95c171e7a" style="list-style-type:decimal"><li><b>並行處理</b>：LSTM 像排隊領餐，必須一個接一個讀；自注意力則像一眼掃視全場，所有字同時運算，大幅提升效率。 </li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-33270f01963480079c0cf14c9ea5ca43" style="list-style-type:decimal"><li><b>瞬移對焦</b>：無論兩個字離多遠，自注意力都能直接建立聯繫，不必像 LSTM 經過長距離傳遞導致記憶模糊。 </li></ol></div></div><div class="notion-text notion-block-33270f01963480539684ffeaf144370f"><b>Transformer</b> 出現，終結了「排隊讀字」的時代。<div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f0196348068a8e5d6a6d63ccdd0"><li><b>突破點：並行運算與自注意力機制</b>。模型不再需要逐字處理，而是一次掃描全局，這讓訓練大規模數據成為可能。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634806495feec7aaf34c646"><li><b>核心思維</b>：不再只看「前一個字」，而是計算「全文字之間」的關聯性權重。</li></ul></div></div><div class="notion-text notion-block-33270f01963480c2874cc531c168a9d2">過往的技術讓我們解決了「記憶」問題，但 Transformer 帶領我們進入了「理解關係」的境界。究竟電腦是如何把一段文字拆解、轉換並產生這種神奇的「注意力」？我們將在第三章拆解它的底層黑盒子。</div><hr class="notion-hr notion-block-33270f01963480fb9809e00528c07b45"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-33270f0196348087aedbcb949b709214" data-id="33270f0196348087aedbcb949b709214"><span><div id="33270f0196348087aedbcb949b709214" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f0196348087aedbcb949b709214" title="三、拆解 Token、向量與注意力的連鎖反應"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">三、拆解 Token、向量與注意力的連鎖反應</span></span></h3><div class="notion-text notion-block-33270f01963480699abad6b5dd11279a">如果說 NLP 是一座自動化工廠，那麼這一章就是這座工廠的「生產線核心」。當我們輸入一段文字，它並不是直接被丟進黑盒子，而是經歷了一連串精密的物理變換。</div><div class="notion-callout notion-gray_background_co notion-block-33270f0196348066a0b5fbbabba787e7"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f019634800994fccd42bc6b3ebe"><b>既然電腦已經有強大的 CPU 了，為什麼不能直接讀取文字檔？為什麼一定要把句子拆得稀巴爛？</b></div><div class="notion-text notion-block-33270f0196348034be16f99b390ca50d">因為電腦的本質是「大型計算機」。文字對它而言太模糊、太感性。我們必須先透過「剪裁（Tokenization）」把語言變成零件，再透過「座標（Embedding）」把零件變成數字，最後用「雷達（Attention）」讓數字之間產生連結。這三個步驟缺一不可，這就是機器理解語言的連鎖反應。</div></div></div><div class="notion-text notion-block-33270f01963480c082accb9ec681326b">在深入探討之前，我們必須建立一個共識：<div class="notion-text-children"><ol start="1" class="notion-list notion-list-numbered notion-block-33270f019634805a8d83e314aac66697" style="list-style-type:decimal"><li><b>Token 是零件</b>：電腦不讀句子，它讀的是被剪碎後的符號。透過子詞（<b>Subword</b>）技術，我們解決了遇到新詞就當機的問題。</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-33270f019634805db7e0c079bee61f70" style="list-style-type:decimal"><li><b>向量是座標</b>：電腦不認得「貓」，它只認得座標 <code class="notion-inline-code">[0.6, 0.9, ...]</code>。讓相似的詞在空間中「住在一起」，是機器理解的第一步。</li></ol></div></div><div class="notion-callout notion-gray_background_co notion-block-33270f019634806180b1ea5314256e21"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="📍">📍</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f01963480d2808dde9de7f5f051"><b>關於切分 (Tokenization) 跟向量化 (Embedding) 的基礎說明，可參考站內相關文章段落</b></div><div class="notion-text notion-block-33270f019634803f8846c4c3b8117d7d"><b><a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://gyozalab.com/ipas-l114-ai-overview#2c670f019634802ea44dc302b4d7885f">大型語言模型 (LLM) 是怎麼煉成的？</a></b></div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f019634800c9879de2693a913dc" data-id="33270f019634800c9879de2693a913dc"><span><div id="33270f019634800c9879de2693a913dc" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f019634800c9879de2693a913dc" title="3.1 現代大模型的秘密：BPE 子詞切分"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>3.1 </b>現代大模型的秘密：BPE 子詞切分</span></span></h4><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33270f019634802392aec30e647fbd8d"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A2d687631-084e-47bd-89bf-63184591bda6%3Anlp-tokenization-methods-cat-meme-infographic-taichung-ai.png?table=block&amp;id=33270f01-9634-8023-92ae-c30e647fbd8d&amp;t=33270f01-9634-8023-92ae-c30e647fbd8d&amp;width=1080&amp;cache=v2" alt="一張標題為「文本分詞方法大揭秘：從死記硬背到 AI 絕招」的資訊圖表。分為三個階段：左側「詞彙方法」顯示一隻戴學士帽的貓在死背書堆，暗示效率低；中間「字符方法」顯示一隻貓幼兒玩字母積木，暗示只認字母不懂語意；右側「子詞方法 (BPE)」顯示一隻戴高科技風鏡的貓手持透明平板，被形容為現代大模型的秘密武器。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">一張標題為「文本分詞方法大揭秘：從死記硬背到 AI 絕招」的資訊圖表。分為三個階段：左側「詞彙方法」顯示一隻戴學士帽的貓在死背書堆，暗示效率低；中間「字符方法」顯示一隻貓幼兒玩字母積木，暗示只認字母不懂語意；右側「子詞方法 (BPE)」顯示一隻戴高科技風鏡的貓手持透明平板，被形容為現代大模型的秘密武器。</figcaption></div></figure><div class="notion-text notion-block-33270f0196348005aa15c0dfd923b546">電腦不讀「句子」，它讀的是被剪碎後的零件，稱為 <b>Token</b>。但怎麼剪，是一門大學問！子詞切分（<b>Subword segmentation</b>）是目前最主流的解決方案。</div><div class="notion-text notion-block-33270f0196348029bc26c455a6e5f61a"><b>BPE (Byte Pair Encoding)</b> 是其中一種「積木化」的分詞技術。它會統計語料中出現頻率最高的字符組合，將常見的詞保留為完整積木，將罕見詞拆解成基礎組件（<b>Subwords</b>）。<div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f019634802fae50d10dfee143bf"><li><b>全詞法 (Word-based)</b>：像是死背單字的學生。</li><ul class="notion-list notion-list-disc notion-block-33270f019634802fae50d10dfee143bf"><li>拆解結果：<code class="notion-inline-code">[抹茶煎餃]</code>（如果字典沒這詞，它就直接當機 😵）。</li></ul></ul><ul class="notion-list notion-list-disc notion-block-33270f0196348089858cf035f34b5248"><li><b>字元法 (Character-based)</b>：像是只認字母的幼兒。</li><ul class="notion-list notion-list-disc notion-block-33270f0196348089858cf035f34b5248"><li>拆解結果：<code class="notion-inline-code">[抹]</code>、<code class="notion-inline-code">[茶]</code>、<code class="notion-inline-code">[煎]</code>、<code class="notion-inline-code">[餃]</code>。雖然不會當機，但每個字都太碎了，電腦很難一眼看出「抹茶」是一個完整的味道。</li></ul></ul><ul class="notion-list notion-list-disc notion-block-33270f019634802aa99de51005d64573"><li><b>子詞法 (Subword-based / BPE)</b>：這就是現代大模型的秘密武器。</li><ul class="notion-list notion-list-disc notion-block-33270f019634802aa99de51005d64573"><li>拆解結果：<code class="notion-inline-code">[抹茶]</code> + <code class="notion-inline-code">[煎]</code> + <code class="notion-inline-code">[餃]</code>。它保有了「抹茶」這個有意義的單位，同時又把「煎」跟「餃」拆開，只要認識這些「積木」，它就能拼湊出大致語意，大幅提升了模型的泛化能力。</li></ul></ul></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480b98756f72b31ecd5d7" data-id="33270f01963480b98756f72b31ecd5d7"><span><div id="33270f01963480b98756f72b31ecd5d7" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480b98756f72b31ecd5d7" title="3.2 詞形正規化：Lemmatization vs. Stemming"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">3.2 詞形正規化：Lemmatization vs. Stemming</span></span></h4><div class="notion-text notion-block-33270f01963480dab7aecaeccb15d385">當機器看到 &quot;running&quot;, &quot;ran&quot;, &quot;runs&quot;，它應該知道這都是同一個動作。<div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f0196348063a951d70b676d4e39"><li><b>詞幹提取 (Stemming)</b></li><ul class="notion-list notion-list-disc notion-block-33270f0196348063a951d70b676d4e39"><li>暴力剪裁。如將 &quot;running&quot; 剪成 &quot;run&quot;。速度快，但可能產出不存在的字（會把 <code class="notion-inline-code">flies</code> 剪成 <code class="notion-inline-code">fli</code>）。</li><li>如果使用者搜尋 <code class="notion-inline-code">fishing</code>，詞幹提取會把它變成 <code class="notion-inline-code">fish</code>。這樣系統就能同時抓到包含 fish、<code class="notion-inline-code">fished</code>、<code class="notion-inline-code">fisher</code>的文章。這種「寧可錯殺，不可放過」的特性，有助於提高<b>召回率 (Recall)</b>。</li></ul></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480028541c9d6f2f160c9"><li><b>詞形還原 (Lemmatization)</b></li><ul class="notion-list notion-list-disc notion-block-33270f01963480028541c9d6f2f160c9"><li>依賴字典與語法規則還原為原型（如 <code class="notion-inline-code">saw</code>根據語境還原為 <code class="notion-inline-code">see</code>）。這對深度語意分析至關重要。</li></ul></ul></div></div><table class="notion-simple-table notion-block-33270f019634808faccaeca464c9286a"><tbody><tr class="notion-simple-table-row notion-block-33270f01963480e39d99f60968f648a0"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>特性</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>詞幹提取 (Stemming)</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>詞形還原 (Lemmatization)</b></div></td></tr><tr class="notion-simple-table-row notion-block-33270f01963480909ba9f9c0611a6395"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>技術手段</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">規則剪裁（去字尾）✂️</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">字典查詢、語法分析 📖</div></td></tr><tr class="notion-simple-table-row notion-block-33270f01963480558ed6e7f3a6e50267"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>準確度</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">較低（可能產生 <code class="notion-inline-code">fli</code> 這種怪字）</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">高（還原為真正的原型 <code class="notion-inline-code">fly</code>）</div></td></tr><tr class="notion-simple-table-row notion-block-33270f019634806d888adb85b7571a64"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>速度</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">極快 🏎️</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">較慢 🚶</div></td></tr><tr class="notion-simple-table-row notion-block-33270f019634806f8888e7cd21290753"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>典型應用</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">大規模搜尋引擎、快速過濾</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">聊天機器人、精準翻譯</div></td></tr></tbody></table><div class="notion-callout notion-gray_background_co notion-block-33270f01963480e6bd78ff4a20cadec7"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f01963480b08f4febde2e9237d4"><b>停用詞去哪裡了？在深度學習時代的停用詞處理，跟在統計時代差在哪裡？</b></div><div class="notion-text notion-block-33270f01963480c2abcac01fd31b1b46">這是一個非常關鍵的觀念差異！</div><div class="notion-text notion-block-33270f01963480768fdbda94a326d033">① <b>統計時代 (TF-IDF)</b>：我們必須主動過濾掉「的」、「了」、「the」等停用詞。因為這些詞出現頻率極高，如果不濾掉，模型會誤以為這些廢話才是關鍵字，產生嚴重的噪音</div><div class="notion-text notion-block-33270f019634807db878c9c27af42123">② <b>深度學習時代 (LLMs)</b>：我們通常「<b>不再</b>」主動移除停用詞。因為像 BERT 或 GPT 這種模型需要理解完整的上下文脈絡（Context）。例如 &quot;Flight <b>to</b> Taipei&quot; 與 &quot;Flight <b>from</b> Taipei&quot; 的意義截然不同，那個關鍵的介系詞（原本的停用詞）反而是機器理解方向的靈魂。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f019634804486d0f31028e55732" data-id="33270f019634804486d0f31028e55732"><span><div id="33270f019634804486d0f31028e55732" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f019634804486d0f31028e55732" title="3.3 靜態向量三劍客 (Word2Vec, GloVe, FastText)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>3.3 靜態向量三劍客 (Word2Vec, GloVe, FastText)</b></span></span></h4><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33270f019634802f86afd4c03ef876c5"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A70a893a8-48d1-44b7-8adf-35029f4562ba%3Astatic-word-vector-word2vec-glove-fasttext-cat-meme-taichung.png?table=block&amp;id=33270f01-9634-802f-86af-d4c03ef876c5&amp;t=33270f01-9634-802f-86af-d4c03ef876c5&amp;width=1080&amp;cache=v2" alt="一張標題為「靜態向量圖解：喵星人視角」的專業資訊圖表。分為三部分：左側 Word2Vec 貓咪拼湊 King/Queen 拼圖（腦中想著分心男友迷因）；中間 GloVe 貓咪戴會計帽撥算盤（腦中想著 Stonks 迷因），象徵全局統計；右側 FastText 貓咪戴護目鏡用鐵鎚拆解 Unbelievable 積木（腦中想著 This is Fine 迷因），象徵處理字根。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">一張標題為「靜態向量圖解：喵星人視角」的專業資訊圖表。分為三部分：左側 Word2Vec 貓咪拼湊 King/Queen 拼圖（腦中想著分心男友迷因）；中間 GloVe 貓咪戴會計帽撥算盤（腦中想著 Stonks 迷因），象徵全局統計；右側 FastText 貓咪戴護目鏡用鐵鎚拆解 Unbelievable 積木（腦中想著 This is Fine 迷因），象徵處理字根。</figcaption></div></figure><div class="notion-text notion-block-33270f0196348016a1ece91447a7159b">在 Transformer 統一江湖之前，NLP 的天下是由這三位開創者打下來的。它們的共通任務只有一個：<b>幫每一個詞找到最完美的「語意座標」</b>。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480518b2ee8bd66decb02" data-id="33270f01963480518b2ee8bd66decb02"><span><div id="33270f01963480518b2ee8bd66decb02" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480518b2ee8bd66decb02" title="① Word2Vec：靠鄰居猜字的「算命師」"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">① Word2Vec：靠鄰居猜字的「算命師」</span></span></h4><div class="notion-text notion-block-33270f019634803ab764ff2b20082974">由 Google 在 2013 年推出，它是現代詞嵌入的鼻祖。<div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f01963480128a95e98fe44a8522"><li><b>核心邏輯</b>：它相信「物以類聚」。透過預測一個詞的鄰居（<b>Skip-gram</b>）或根據鄰居預測中心詞（<b>CBOW</b>），它學會了語意。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634807994dad5445638ef67"><li><b>技術細節</b>：它讓「<b>國王</b>」 - 「<b>男人</b>」 + 「<b>女人</b>」 = 「<b>女王</b>」這種數學運算成為可能。</li></ul></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480348955c7d548cada8c" data-id="33270f01963480348955c7d548cada8c"><span><div id="33270f01963480348955c7d548cada8c" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480348955c7d548cada8c" title="② GloVe：看透全局的「統計學家」"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">② GloVe：看透全局的「統計學家」</span></span></h4><div class="notion-text notion-block-33270f01963480ee88dfe1efb6e0d210">由史丹佛大學提出，它覺得 Word2Vec 太過局部。<div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f01963480208dc6ea36fcf9f91d"><li><b>核心邏輯</b>：它不只看鄰居，而是先掃描整個語料庫，建立一張巨大的「共現矩陣」。它觀察「<b>冰</b>」跟「<b>冷</b>」出現的比例，與「<b>冰</b>」跟「<b>熱</b>」出現的比例，進而推導出更穩定的語意。</li></ul></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f019634805c841efc89e7e6c609" data-id="33270f019634805c841efc89e7e6c609"><span><div id="33270f019634805c841efc89e7e6c609" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f019634805c841efc89e7e6c609" title="③ FastText：連骨頭都看的「解剖學家」"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">③ FastText：連骨頭都看的「解剖學家」</span></span></h4><div class="notion-text notion-block-33270f0196348052be97e2acd9f7daa1">Facebook 的得意之作，它解決了 Word2Vec 遇到陌生詞就失靈的痛點。<div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f019634801faf7eef2d8b1c657d"><li><b>核心邏輯</b>：它不把單詞當成最小單位，而是拆解成子詞（<b>n-grams</b>）。例如看到「<b>煎餃</b>」，它會同時學習「<b>煎</b>」、「<b>餃</b>」的含義。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480cc90dec4d37a0718d5"><li><b>優點</b>：即使你打錯字成「<b>天餃</b>」，它也能透過「<b>餃</b>」這個字根，猜出這可能跟食物有關。對中文這種拼塊語言特別有效。</li></ul></div></div><div class="notion-callout notion-gray_background_co notion-block-33270f0196348061acd3e1450ddbc843"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f019634804794cbec7826495801"><b>向量三劍客這麼厲害，為何還需要自注意力機制？</b></div><div class="notion-text notion-block-33270f01963480208080e4eaf8c592f3">因為它們都是「靜態」的。不管句子怎麼變，「<b>蘋果</b>」的座標永遠在那裡。<div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f01963480e1b377daf7b4b7c3b0"><li>在「<b>蘋果</b>真好吃」裡，它是水果。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480588095ffbfd0ffdb5d"><li>在「<b>蘋果</b>手機真貴」裡，它是電子產品。</li></ul></div></div><div class="notion-text notion-block-33270f01963480ad9bbaca8c43ebebe3">對於靜態向量來說，這兩個「<b>蘋果</b>」的數位身份完全相同，這就是語意歧義的終極天花板。</div></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480278567e27c54e67552" data-id="33270f01963480278567e27c54e67552"><span><div id="33270f01963480278567e27c54e67552" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480278567e27c54e67552" title="3.4 終極進化：Self-Attention (Q, K, V) "><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title"><b>3.4 終極進化：Self-Attention (Q, K, V) </b></span></span></h4><div class="notion-text notion-block-33270f01963480b8a46ec2157828805c">2017 年，Google 的論文《Attention Is All You Need》拋出了一個炸彈：不需要 RNN，不需要 CNN，光靠<b>注意力機制</b>就能處理語言。Transformer 架構從此改寫了 NLP 的歷史。</div><div class="notion-text notion-block-33270f01963480eb87b5c3a2d0b6bc35">這是 NLP 史上第一次打破「靜態座標」的限制，讓單詞具備了「根據身邊的人，即時調整自己身份」的能力。在 Transformer 中，每個詞都像裝了雷達，主動去偵測周圍。</div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33270f019634801c8f9dca4b89d81908"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Ad55f25ee-e476-44f8-a288-3b9747fe809e%3Aself-attention-mechanism-qkv-explained-cat-meme-taichung-ai.png?table=block&amp;id=33270f01-9634-801c-8f9d-ca4b89d81908&amp;t=33270f01-9634-801c-8f9d-ca4b89d81908&amp;width=1080&amp;cache=v2" alt="自我注意力機制：晚餐選擇大挑戰」的幽默圖表，用來解釋 NLP 中的 Q、K、V。左側一隻貓咪抱頭思考，思維氣泡顯示「想要熱的」、「不要太油」等需求作為 Query (Q)；中間展示三家店：拉麵店、沙拉店、便利商店作為 Key (K) 的特徵比對（配上 Doge、哭泣貓、青蛙 Pepe 迷因）；右側則是貓咪開心地端著飯碗「真香！」，象徵最後得到的 Value (V) 實際能量與體驗。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">自我注意力機制：晚餐選擇大挑戰」的幽默圖表，用來解釋 NLP 中的 Q、K、V。左側一隻貓咪抱頭思考，思維氣泡顯示「想要熱的」、「不要太油」等需求作為 Query (Q)；中間展示三家店：拉麵店、沙拉店、便利商店作為 Key (K) 的特徵比對（配上 Doge、哭泣貓、青蛙 Pepe 迷因）；右側則是貓咪開心地端著飯碗「真香！」，象徵最後得到的 Value (V) 實際能量與體驗。</figcaption></div></figure><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f019634804ea991fbceb0e421f9" data-id="33270f019634804ea991fbceb0e421f9"><span><div id="33270f019634804ea991fbceb0e421f9" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f019634804ea991fbceb0e421f9" title="🍎 為什麼會變成「水果」而不是「手機」？"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">🍎 <b>為什麼會變成「水果」而不是「手機」？</b></span></span></h4><div class="notion-text notion-block-33270f019634805cabecfed366186d0f">假設句子是：「這盒<b>蘋果</b>禮盒真貴。」電腦會透過以下三步驟來決定「蘋果」的語意：</div><ol start="1" class="notion-list notion-list-numbered notion-block-33270f019634801488a9d64004d38455" style="list-style-type:decimal"><li><b>發出訊號 Query (Q) ：</b>「蘋果」跳出來發問：「我現在身邊有誰？誰能告訴我我是哪種蘋果？」</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-33270f01963480c494b2d9109b3af858" style="list-style-type:decimal"><li><b>查看標籤 Key (K) ：</b>句子裡的其他詞會露出自己的「名片」：</li><ol class="notion-list notion-list-numbered notion-block-33270f01963480c494b2d9109b3af858" style="list-style-type:lower-alpha"><ul class="notion-list notion-list-disc notion-block-33270f019634800db434ffb91d879487"><li><b>「禮盒」的名片寫著：【食品、送禮、包裝盒】</b></li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480fda98ff5b0681fde94"><li><b>「真貴」的名片寫著：【價格、高級、金錢】</b></li></ul></ol></ol><ol start="3" class="notion-list notion-list-numbered notion-block-33270f01963480eb9c45c05286972cb2" style="list-style-type:decimal"><li><b>計算分數 (Q x K)：</b>「蘋果」拿著自己的需求去比對。它發現「禮盒」名片上的【食品】跟自己（潛在的水果身份）關聯度超級高！比「真貴」更具備決定性。</li></ol><ol start="4" class="notion-list notion-list-numbered notion-block-33270f01963480e7a805fa9da80367b2" style="list-style-type:decimal"><li><b>吸收營養 Value (V) ：</b>因為「禮盒」的分數最高，電腦會讓「蘋果」去吸收「禮盒」所代表的實質意義 (<b>V)。</b>這時候，「蘋果」的數位座標就會被拉向「食物/水果」那一區。</li></ol><div class="notion-text notion-block-33270f0196348074b212f1ec23bef22c"><b>反之亦然</b>：如果句子換成「<b>蘋果</b>手機」，它掃描到的是「手機」的名片（科技、通訊），座標就會轉向「科技公司」區。這就是<b>動態語意理解</b>！</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f019634805aa0d7c252feb996d0" data-id="33270f019634805aa0d7c252feb996d0"><span><div id="33270f019634805aa0d7c252feb996d0" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f019634805aa0d7c252feb996d0" title="🚀 進階：不只看一眼，而是全方位掃描 (Multi-Head Attention)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">🚀 進階：不只看一眼，而是全方位掃描 (Multi-Head Attention)</span></span></h4><div class="notion-text notion-block-33270f019634808b97c5db37386b1e72">想像你參加一場聯誼，如果你只有單頭注意力，你整晚只能用一種標準來觀察別人。</div><ul class="notion-list notion-list-disc notion-block-33270f01963480a699a3f4d20966659e"><li><b>單頭</b>：你只看「對方的職業」。雖然你能找到職業最契合的人，但你可能會忽略他的性格、興趣或價值觀。</li></ul><div class="notion-text notion-block-33270f0196348073882bed184bf0c51c"><b>多頭（Multi-Head）</b> 就像是你分身出了好幾個自己，同時從不同角度觀察：<div class="notion-text-children"><ol start="1" class="notion-list notion-list-numbered notion-block-33270f0196348092b565c5e39119968f" style="list-style-type:decimal"><li><b>一號</b>：專門看「對方的共同興趣」（比如都喜歡看電影）。</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-33270f019634805087a7f8889fd300b8" style="list-style-type:decimal"><li><b>二號</b>：專門看「對方的幽默感」。</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-33270f0196348052afe8f9975fcb43e5" style="list-style-type:decimal"><li><b>三號</b>：專門看「對方的未來規劃」。</li></ol></div></div><div class="notion-text notion-block-33270f019634805a9ac7f5ddce4f12b7">最後，這幾個頭會把觀察到的資訊「拼湊」起來，讓你對眼前的這個人（Token）有最完整的理解。</div><div class="notion-text notion-block-33270f0196348050a18dfa354aaaccca">這種「看場合」的能力，實現了真正的動態語意理解！</div><div class="notion-callout notion-gray_background_co notion-block-33270f01963480a58044e6c2cb243de0"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f01963480cd8853cb6311344ea2"><b>自注意力機制會分心嗎？</b></div><div class="notion-text notion-block-33270f01963480d5b052dde30fb5d07a">會的，自注意力機制確實會「分心」。當模型對所有字的注意力都差不多，我們稱這種現象為 <b>「注意力崩潰」（Attention Collapse）</b>，就像一個學生看書每一行都畫重點，等於沒畫。</div><div class="notion-text notion-block-33270f01963480a0a3cfdd055b6dac57"><b>正確解法</b>：<b>稀疏化約束 (Sparsity Constraint)</b>。強迫模型只能選少數幾個最重要的詞來對焦。</div></div></div><hr class="notion-hr notion-block-33270f01963480248867e0376ce30924"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-33270f01963480718919c43bc8dc0361" data-id="33270f01963480718919c43bc8dc0361"><span><div id="33270f01963480718919c43bc8dc0361" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480718919c43bc8dc0361" title="四、巨人誕生：BERT vs. GPT 的終極決戰"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">四、<b>巨人誕生：</b>BERT vs. GPT <b>的終極決戰</b></span></span></h3><div class="notion-text notion-block-33270f01963480658149f4a304862d6e">Transformer 架構的出現，將 NLP 世界切分成了兩條截然不同的進化路線。</div><div class="notion-callout notion-gray_background_co notion-block-33270f01963480fa8e6ce0e61223d76f"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f0196348064908ff2cda0a8f1bf"><b>既然大家都是用 Transformer 的零件蓋出來的，為什麼還有分什麼 BERT 跟 GPT？</b></div><div class="notion-text notion-block-33270f0196348090840acd82a937bf72">這取決於你如何使用這座巨人的軀體。你可以只留下一雙擅長觀察的眼睛（<b>Encoder</b>），也可以只留下一張擅長說話的嘴巴（<b>Decoder</b>）。</div></div></div><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33270f0196348086b839c6b59230c65e"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3Ae80359ab-b3c4-4aae-a189-f9cb99cff1f5%3Abert-vs-gpt-cat-ai-models-comparison.png?table=block&amp;id=33270f01-9634-8086-b839-c6b59230c65e&amp;t=33270f01-9634-8086-b839-c6b59230c65e&amp;width=1080&amp;cache=v2" alt="一張解釋 BERT 和 GPT 人工智慧模型差異的教育性資訊圖表。中央標題是「BERT vs. GPT」。左側是「BERT」貓，穿著福爾摩斯風格的偵探帽和眼鏡，雙手拿著放大鏡。繁體中文文本描述其為「雙向理解」，並有一個對話泡泡總結為「像戴眼鏡的貓，左右兼顧，精確分析」。右側是「GPT」貓，戴著貝雷帽，手持羽毛筆和捲軸，口中噴出彩虹流，其中包含 Nyan Cat、Doge 迷因和照片。中文文本描述其為「創意生成」，泡泡描述其為「像藝術家貓，口吐彩虹文，腦洞大開」。此圖表將 BERT 的精確語境分析與 GPT 的創意文本生成進行了對比。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">一張解釋 BERT 和 GPT 人工智慧模型差異的教育性資訊圖表。中央標題是「BERT vs. GPT」。左側是「BERT」貓，穿著福爾摩斯風格的偵探帽和眼鏡，雙手拿著放大鏡。繁體中文文本描述其為「雙向理解」，並有一個對話泡泡總結為「像戴眼鏡的貓，左右兼顧，精確分析」。右側是「GPT」貓，戴著貝雷帽，手持羽毛筆和捲軸，口中噴出彩虹流，其中包含 Nyan Cat、Doge 迷因和照片。中文文本描述其為「創意生成」，泡泡描述其為「像藝術家貓，口吐彩虹文，腦洞大開」。此圖表將 BERT 的精確語境分析與 GPT 的創意文本生成進行了對比。</figcaption></div></figure><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480d69d09ce5476da34d4" data-id="33270f01963480d69d09ce5476da34d4"><span><div id="33270f01963480d69d09ce5476da34d4" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480d69d09ce5476da34d4" title="4.1 BERT：全方位理解型選手 (The Master of Reading)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">4.1 BERT：全方位理解型選手 (The Master of Reading)</span></span></h4><div class="notion-text notion-block-33270f01963480dfae37e8e8a1558ac9"><b>BERT (Bidirectional Encoder Representations from Transformers)</b> 代表了「理解」的巔峰。</div><div class="notion-text notion-block-33270f0196348003adf3d17db42e6afa">他的方式非常暴力：它把課本裡的字挖掉（<b>Masked LM</b>），強迫自己根據左右兩邊的內容把字猜回來。<div class="notion-text-children"><ol start="1" class="notion-list notion-list-numbered notion-block-33270f0196348022a1f5e3f4abefe24b" style="list-style-type:decimal"><li><b>核心特性：雙向 (Bidirectional) 訓練</b>：BERT 同時看左邊與右邊，精準判斷語意。</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-33270f01963480d59ccaf2fe8cf37cb5" style="list-style-type:decimal"><li><b>底層武器：遮罩語言模型 (MLM)</b>：隨機遮住 15% 的詞讓模型去「猜」，練就深厚的語意底蘊。</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-33270f0196348040a794eb7c7a12e9c5" style="list-style-type:decimal"><li><b>核心優勢</b>：它對上下文的「雙向關係」極度敏感。如果你要讓 AI 幫你改考卷、分信件、或是做搜尋優化，BERT 至今依然是效率最高的王者。</li></ol></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480d7b94acdb735ca351e" data-id="33270f01963480d7b94acdb735ca351e"><span><div id="33270f01963480d7b94acdb735ca351e" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480d7b94acdb735ca351e" title="4.2 GPT：流暢生成型選手 (The Master of Storytelling)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">4.2 GPT：流暢生成型選手 (The Master of Storytelling)</span></span></h4><div class="notion-text notion-block-33270f019634808c8f67f2bc38101135"><b>GPT (Generative Pre-trained Transformer)</b> 是「生成」領域的教主。</div><div class="notion-text notion-block-33270f0196348043a631ceb4bce10ed5">他是另一種極端。它不看後文，只看前文，然後拚命猜下一個字是什麼。<div class="notion-text-children"><ol start="1" class="notion-list notion-list-numbered notion-block-33270f0196348074b11efd588b8a13c3" style="list-style-type:decimal"><li><b>核心特性：單向自回歸 (Autoregressive) 訓練</b>：預測下一個字時只看前文，練就了極強的「續寫能力」。</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-33270f01963480249e5af8a1c2c780c0" style="list-style-type:decimal"><li><b>GPT 的接龍遊戲（Causal LM）</b>：老師只給開頭，叫 GPT 一路寫下去。為了不辭窮且講得通，它必須學會捕捉語言的流暢度和創造力。</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-33270f01963480aabbd7d3e214b62a38" style="list-style-type:decimal"><li><b>湧現能力 (Emergence)</b>：當模型規模大到一定程度，這種「猜下一個字」的簡單任務，竟然讓 GPT 學會了邏輯推理、寫程式、甚至是冷幽默。</li></ol></div></div><div class="notion-callout notion-gray_background_co notion-block-33270f0196348013860bc8e574d84d5e"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f0196348013979dd708c6f150cf"><b>為什麼 GPT 能「後發先至」？</b></div><div class="notion-text notion-block-33270f01963480e69234f318306e4034">BERT 剛出來時，橫掃了所有學術比賽，Google 搜尋引擎至今也還在用它來理解你的意圖。但為什麼現在大眾只聽過 GPT？這涉及了三個關鍵的技術轉折：</div><ul class="notion-list notion-list-disc notion-block-33270f01963480daa79ffee1d00ca829"><li><b>從「專才」到「通才」</b>
BERT 需要針對不同任務（如翻譯、改錯）進行二次訓練（Fine-tuning）。而 GPT 發現，只要模型夠大，它就能透過「對話」直接處理所有事。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480c6a507fa0a87928f2c"><li><b>規模化定律（Scaling Laws）</b>
OpenAI 賭贏了一個技術直覺：當參數量增加到千億等級時（GPT-3），模型會產生「湧現能力」，突然學會了原本沒教過的推理。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f0196348067ad8fd1dac4d65d4a"><li><b>對齊技術（RLHF）</b>
這是最關鍵的轉折！GPT 透過「人類回饋戴補強學習」，學會了<b>說話的語氣</b>要像人類，而不只是冷冰冰的機率計算。</li></ul></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f0196348079af4ceac07ef7fb9d" data-id="33270f0196348079af4ceac07ef7fb9d"><span><div id="33270f0196348079af4ceac07ef7fb9d" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f0196348079af4ceac07ef7fb9d" title="4.3 BART 與 Seq2Seq：混血兒與翻譯的底層邏輯"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">4.3 <b>BART 與 Seq2Seq：混血兒與翻譯的底層邏輯</b></span></span></h4><div class="notion-text notion-block-33270f01963480f9b8c0cde8fb3fa77e">當我們不再滿足於「只理解」或「只生成」，而是想要「讀完一段話，吐出另一段話」時，混血架構就誕生了。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480cfab59f7850613aa69" data-id="33270f01963480cfab59f7850613aa69"><span><div id="33270f01963480cfab59f7850613aa69" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480cfab59f7850613aa69" title="① Seq2Seq：翻譯的底層邏輯"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">① Seq2Seq：翻譯的底層邏輯</span></span></h4><div class="notion-text notion-block-33270f01963480c1ab96ccb807dc968f">序列到序列（Seq2Seq: Sequence-to-Sequence）模型是所有輸入/輸出轉換任務的通用框架。</div><div class="notion-text notion-block-33270f019634805dbf67f27bf20aac4f">你可以把它想像成一個「翻譯官」，先聽懂（Encoder），再說出來（Decoder）。</div><div class="notion-text notion-block-33270f0196348055948fd43836c34fd6"><b>優點 ✅</b><div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f01963480739f5cda0790f8a49b"><li><b>處理變長序列</b>：輸入 10 個字，輸出 5 個字 (摘要) 或 15 個字 (翻譯) 都沒問題。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634800d822fd6f8f78cbe2e"><li><b>端到端學習 (End-to-End)</b>：直接從輸入學習到輸出，不需要中間複雜的人工規則。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634800e80d2f781657d3184"><li><b>語意對齊</b>：能學會不同語言或格式之間的神祕對應關係。</li></ul></div></div><div class="notion-text notion-block-33270f019634806e8e08fae88215a78a"><b>缺點 ❌</b><div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f019634802a889bc6fe6cc8d262"><li><b>資訊瓶頸 (Information Bottleneck)</b>：如果輸入太長，Encoder 可能無法將所有資訊壓縮進小小的向量裡。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480faa274ff459631d78e"><li><b>慢速生成</b>：Decoder 必須一個字接一個字噴出來，無法像 Encoder 那樣平行處理。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634804bb361fc4196cafcdb"><li><b>曝光偏差 (Exposure Bias)</b>：訓練時看正確答案，生成時看自己前一個錯字，可能導致錯誤連鎖反應。</li></ul></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480198d50e479ab196751" data-id="33270f01963480198d50e479ab196751"><span><div id="33270f01963480198d50e479ab196751" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480198d50e479ab196751" title="②BART：把兩個靈魂裝進同一個身體"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">②BART：把兩個靈魂裝進同一個身體</span></span></h4><div class="notion-text notion-block-33270f01963480a2a488fc586d26e2a9"><b>BART (Bidirectional and Auto-Regressive Transformers)</b> 是 BERT 與 GPT 的完美混血。</div><div class="notion-text notion-block-33270f019634806aabe9f60cfd49a5dd">他是 Transformer 時代中，Seq2Seq 架構最完美的<b>實例之一</b>。它結合了 BERT 的雙向理解力（Encoder）與 GPT 的自回歸生成力（Decoder）。</div><div class="notion-text notion-block-33270f01963480d6b8edc7b701c39f62">這讓它既能像 BERT 一樣「看清全局」，又能像 GPT 一樣「流暢表達」。</div><div class="notion-text notion-block-33270f01963480bfb855c27075c88530"><b>核心優勢 🌟</b><div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f019634803e8aacdbff22f601eb"><li><b>靈活度極高</b>：能處理所有「輸入一段話、輸出另一段話」的任務。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480c2a621d8ae7ad26b77"><li><b>抗噪能力強</b>：預訓練時學會從亂序或殘缺的文字中還原真相。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480878e22e43d76cd309d"><li><b>摘要大師</b>：在內容精簡與重點擷取上，表現往往比純 GPT 穩定。</li></ul></div></div><div class="notion-text notion-block-33270f0196348005b04ec29de6058b22"><b>缺點與痛點 ⚠️</b><div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f0196348077bdfedb2cc01ff149"><li><b>運算成本較高</b>：同時跑兩套架構（Encoder + Decoder）比單一套更吃資源。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480d7abbddf7e97ed45a5"><li><b>生成長度受限</b>：雖然擅長摘要，但在「無中生有」的長篇創作上不如 GPT 系列。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634809bbbdff022d382701a"><li><b>訓練難度</b>：需要大量的清洗數據來進行「去噪還原」訓練。</li></ul></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480e7905feb1fa4c10c98" data-id="33270f01963480e7905feb1fa4c10c98"><span><div id="33270f01963480e7905feb1fa4c10c98" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480e7905feb1fa4c10c98" title="4.4 Transformer 家族大車拼"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">4.4 Transformer 家族大車拼</span></span></h4><table class="notion-simple-table notion-block-33270f01963480a09706d182f33921af"><tbody><tr class="notion-simple-table-row notion-block-33270f0196348036b8caf971c5355e48"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>特性</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>BERT (讀書高手)</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>GPT (作文高手)</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>BART (翻譯/摘要高手)</b></div></td></tr><tr class="notion-simple-table-row notion-block-33270f0196348079a65eed661966e0d1"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>出現時間</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">2018 年 10 月</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">2019 - 2020 年</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>2019 年 10 月</b></div></td></tr><tr class="notion-simple-table-row notion-block-33270f01963480dbba88f4c7931f31a6"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>代表模型</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">BERT</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">GPT-2/3</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>BART</b></div></td></tr><tr class="notion-simple-table-row notion-block-33270f01963480d08094f70e694b056d"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>拿手好戲</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">理解、分類、問答</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">生成、對話、接龍</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>翻譯、摘要、改寫</b></div></td></tr><tr class="notion-simple-table-row notion-block-33270f019634804abae3c6fe739af3fa"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>架構重點</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Encoder Only</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">Decoder Only</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>Encoder-Decoder</b></div></td></tr><tr class="notion-simple-table-row notion-block-33270f01963480988f65c876194f8bb7"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>訓練方向</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">雙向 (Bidirectional)</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">單向 (由左至右)</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>先雙向理解，再單向生成</b></div></td></tr><tr class="notion-simple-table-row notion-block-33270f01963480998b5be3988c1341af"><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>預訓練任務</b></div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">MLM (遮罩預測)</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell">自回歸 (預測下一字)</div></td><td class="" style="width:120px"><div class="notion-simple-table-cell"><b>混合雜訊還原 (Denoising)</b></div></td></tr></tbody></table><div class="notion-callout notion-gray_background_co notion-block-33270f01963480ecb8eaf1a891a43410"><div class="notion-page-icon-inline notion-page-icon-span"><span class="notion-page-icon" role="img" aria-label="❓">❓</span></div><div class="notion-callout-text"><div class="notion-text notion-block-33270f019634804bb17bd02f3b706868"><b>既然自注意力機制那麼厲害，那是不是 AI 就無所不能了？</b></div><div class="notion-text notion-block-33270f0196348090ad3be62809709fff">雖然自注意力機制極大地提升了 AI 處理資訊的能力，但它並非萬能。它仍面臨三大挑戰：<div class="notion-text-children"><ol start="1" class="notion-list notion-list-numbered notion-block-33270f01963480a586c5f6eb09eb226c" style="list-style-type:decimal"><li><b>資源消耗</b>：計算量隨長度平方增長，極其耗能。</li></ol><ol start="2" class="notion-list notion-list-numbered notion-block-33270f0196348087a77ac93e279982f0" style="list-style-type:decimal"><li><b>缺乏真理</b>：僅靠機率關聯，容易產生「幻覺」。</li></ol><ol start="3" class="notion-list notion-list-numbered notion-block-33270f01963480aabf2cfcdf87705f26" style="list-style-type:decimal"><li><b>物理限制</b>：難以理解真實世界的因果與物理規律。</li></ol></div></div><div class="notion-text notion-block-33270f01963480beb347e1e9a8cebacc">它擅長找關聯，但還不具備真正的智慧。</div></div></div><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-33270f01963480e5a9d8f6651a0a2c30" data-id="33270f01963480e5a9d8f6651a0a2c30"><span><div id="33270f01963480e5a9d8f6651a0a2c30" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480e5a9d8f6651a0a2c30" title="五、Transformer 的極限與未來進化"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">五、Transformer 的極限與未來進化</span></span></h3><figure class="notion-asset-wrapper notion-asset-wrapper-image notion-block-33270f01963480c4963ad13ebc6b80d8"><div style="position:relative;display:flex;justify-content:center;align-self:center;width:100%;max-width:100%;flex-direction:column;height:100%"><img style="object-fit:cover" src="https://www.notion.so/image/attachment%3A91668d64-ca3a-47e4-abc0-77817a46639b%3Atransformer-limits-ai-cat-meme-complexity-long-context-hallucination.png?table=block&amp;id=33270f01-9634-80c4-963a-d13ebc6b80d8&amp;t=33270f01-9634-80c4-963a-d13ebc6b80d8&amp;width=1080&amp;cache=v2" alt="三隻貓解構 Transformer 缺陷：左貓面對 N^2算力黑洞崩潰；中貓握長捲軸陷入金魚記憶；右貓將香蕉標為魚，演示自信的 AI 幻覺。將二次計算複雜度、長文本遺忘與「一本正經胡說八道」具象化，揭示模型技術極限。" loading="lazy" decoding="async"/><figcaption class="notion-asset-caption">三隻貓解構 Transformer 缺陷：左貓面對 N^2算力黑洞崩潰；中貓握長捲軸陷入金魚記憶；右貓將香蕉標為魚，演示自信的 AI 幻覺。將二次計算複雜度、長文本遺忘與「一本正經胡說八道」具象化，揭示模型技術極限。</figcaption></div></figure><div class="notion-text notion-block-33270f0196348091ace6fef70af57b3a">Transformer 靠著 Self-Attention 橫掃 NLP 領域，但在實務應用上，它依然面臨兩個「魔王級」的挑戰：<b>運算太貴</b>與<b>會說謊</b>。</div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f0196348001b261ed1ae28a5da7" data-id="33270f0196348001b261ed1ae28a5da7"><span><div id="33270f0196348001b261ed1ae28a5da7" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f0196348001b261ed1ae28a5da7" title="5.1 沉重的代價：計算複雜度的平方級增長"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">5.1 沉重的代價：計算複雜度的平方級增長</span></span></h4><div class="notion-text notion-block-33270f0196348068b0e2ea66ac373c23">自注意力機制（<b>Self-Attention</b>）最致命的弱點在於它的計算量會隨文本長度呈「平方級」增長。這在數學上表示為 O(n²)。<div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f019634806e83c7e90f2babf961"><li><b>現象</b>：當你讓 AI 讀 2 倍長的文章，它花的算力不是 2 倍，而是 <b>4 倍</b>！</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480c59468d73170f119d4"><li><b>痛點</b>：這導致處理超長文本（如整本法律百科）時，硬體成本會變得異常昂貴，顯存（<b>VRAM</b>）需求也會爆表。</li></ul></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480d6add8eb36c9fccd6c" data-id="33270f01963480d6add8eb36c9fccd6c"><span><div id="33270f01963480d6add8eb36c9fccd6c" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480d6add8eb36c9fccd6c" title="5.2 過目不忘的挑戰：超長上下文 (Long Context)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">5.2 過目不忘的挑戰：超長上下文 (Long Context)</span></span></h4><div class="notion-text notion-block-33270f0196348003928ad5be5c78d051">為了讓 AI 不再是「過目即忘的短跑選手」，近幾年的研究朝著「讓平方增長不那麼可怕」的方向猛攻。</div><div class="notion-text notion-block-33270f01963480d6b5aedfb9d29b3470">目前最具代表性的解法是 <b>Flash Attention</b>，它重新設計了注意力的計算順序，讓記憶體存取效率大幅提升，在不犧牲準確度的前提下，把速度壓了下來。</div><div class="notion-text notion-block-33270f0196348027830dee02e017564d">效果顯著：現在的主流模型已經能一次處理百萬級 Token。你可以把整套法律全書或一整年的財報丟給它，它依然能精準掃描出你要的段落。<div class="notion-text-children"><ul class="notion-list notion-list-disc notion-block-33270f019634808f9792ead2ee36d767"><li><b>進化</b>：現在的 AI（如 <b>Gemini 1.5 Pro</b>）已經能一次讀完十幾本書或長達數小時的影片，這都要歸功於對自注意力機制的數學優化。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f019634808a9c84cc00b96ebff3"><li><b>線性注意力的價值</b>：讓模型能在大海撈針般的數百萬字中，依然精準定位到特定的細節資訊。</li></ul></div></div><h4 class="notion-h notion-h3 notion-h-indent-1 notion-block-33270f01963480c5b1a2d560e633e56f" data-id="33270f01963480c5b1a2d560e633e56f"><span><div id="33270f01963480c5b1a2d560e633e56f" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480c5b1a2d560e633e56f" title="5.3 完美的謊言：幻覺問題 (Hallucination)"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">5.3 完美的謊言：幻覺問題 (Hallucination)</span></span></h4><div class="notion-text notion-block-33270f01963480f697f8c455e98b6d38">這是目前 LLM 最難根治的痛點。</div><ul class="notion-list notion-list-disc notion-block-33270f019634802b8efeecfb117e1e35"><li><b>原因</b>：自注意力機制本質上是在找「單詞之間的關聯機率」，它擅長聯想但不擅長查證。模型可能會為了語句的流暢性（NLG 的成功定義），而犧牲事實的準確性。</li></ul><ul class="notion-list notion-list-disc notion-block-33270f01963480b985d8dfda3d8e1bde"><li><b>未來解法</b>：這也是為什麼我們需要結合知識圖譜（Knowledge Graph）或 <b>RAG</b>。</li><ul class="notion-list notion-list-disc notion-block-33270f01963480b985d8dfda3d8e1bde"><div class="notion-text notion-block-33270f01963480f7859bfb1393f3cda1">① <b>RAG (檢索增強生成)</b>：給 AI 一本外掛的「百科全書」，回答前先查證。</div><div class="notion-text notion-block-33270f019634804fadedc696db9fd762">② <b>知識圖譜</b>：賦予 AI 一個結構化的真實世界地圖（例如：明確標記 A 是 B 的父親），而不僅僅是讓它在機率的汪洋中漂流。</div></ul></ul><hr class="notion-hr notion-block-33270f0196348082b6a6e1fe3f0fb4ad"/><h3 class="notion-h notion-h2 notion-h-indent-0 notion-block-33270f01963480a0ba83ee94080fd214" data-id="33270f01963480a0ba83ee94080fd214"><span><div id="33270f01963480a0ba83ee94080fd214" class="notion-header-anchor"></div><a class="notion-hash-link" href="#33270f01963480a0ba83ee94080fd214" title="結語：每一代技術，都在補上一代的缺口"><svg viewBox="0 0 16 16" width="16" height="16"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a><span class="notion-h-title">結語：每一代技術，都在補上一代的缺口</span></span></h3><div class="notion-text notion-block-33270f01963480a99b7cda01b9ef62e4">NLP 這幾十年的進化，其實就是一場「打怪升級」的遊戲。（延伸閱讀：<a target="_blank" rel="noopener noreferrer" class="notion-link" href="https://gyozalab.com/prompt-to-context-engineering-evolution">從提示詞工程到情境工程：AI 協作的典範轉移</a>）</div><div class="notion-text notion-block-33270f01963480d6956bd6897fd4177b">從「讓電腦讀懂一句話」開始，最早的「規則派」像個嚴格的老師，想把語法教死，結果發現語言太調皮，根本教不完；後來的「統計派」改當算命師，雖然機率算得準，卻把說話的順序給弄丟了。後來的 RNN 和 LSTM 雖然試著寫筆記來幫機器增加記憶力，但不是筆記本太小，就是寫字速度太慢，始終跟不上人類說話的節奏。</div><div class="notion-text notion-block-33270f019634805081bcf3ce44a89bf3">直到 2017 年那篇《Attention Is All You Need》出現， Transformer 讓機器學會了「抓重點」，這才有了現在能讀會寫的 BERT 和 GPT。但大家千萬別誤會，新技術出現並不代表舊的就要被淘汰。你現在搜尋 Google、填寫網頁表單，背後其實都還有那些「老前輩」在默默工作。</div><div class="notion-text notion-block-33270f01963480ac8697fae34e73014c">Transformer 不是終點。TF-IDF 的邏輯還活在 SEO 工具鏈裡，BERT 還在幫 Google 讀你的搜尋意圖，規則式的比對邏輯還跑在每一套表單驗證裡。技術的演進不是一場淘汰賽，而是一場疊加賽。舊的解法撞牆了，新的解法就試著繞過去。技術的迭代會一直持續下去，直到超級人工智慧出現的那一天。</div><div class="notion-blank notion-block-33270f0196348008b6c8d4e1c5961681"> </div></main></div>]]></content:encoded>
        </item>
    </channel>
</rss>