從《十二年國民基本教育課程綱要》實施以來，教學現場強調素養導向與差異化教學。但在實務上，書商所提供的標準化教師手冊多屬於通案性質，往往無法直接對應不同班級的在地化需求。為了將這些公版教材轉化為合適的教學內容，教師常需仰賴社群共備來解構教材並激發靈感。然而，前期的資料蒐集與文書整理耗費了大量時間，反而壓縮了教師之間實質的對話與討論空間，無形中增加了備課壓力。 為減輕教師在備課初期的文書負擔，本研究以探討教師備課需求為出發點，進而導入 AI 輔助，探究如何將生成式人工智慧（Generative AI）轉化為實用的「備課小幫手」。考量到直接使用傳統 AI 容易產生內容不正確，或給出偏離教學現場的建議，本研究導入了檢索增強生成（Retrieval-Augmented Generation， RAG）技術。透過這項技術，教師可以先上傳自己的教材來建立專屬知識庫；系統能依據這些確切的文本內容，協助進行資料收斂，幫助教師在短時間內完成初步的教材整理與提供備課的內容建議。 基於上述背景，本研究開發並初步評估了一套結合生成式 AI 與 RAG 技術的教師備課平台。在系統定位上，本研究提供教學發想與教材整合的建議。為避免取代教師專業，系統在設計上不提供「直接產出完整教案」的功能，以確保教學設計的最終決策權回歸教師本身。在成效評估方面，本研究以科技接受模式為理論框架，邀請 39 位具備教案撰寫經驗的現職國中小教師進行問卷調查，藉此了解他們對該平台的知覺有用性、知覺易用性及使用意願。 研究結果顯示，參與測試的教師大多對此平台給予正面評價。量化與質性回饋指出，這套教師備課平台有助於減少整理公版教材所需的時間，並能在活動設計上提供多元的參考方向，多數教師也表達了願意持續使用的意圖。綜合而言，本研究除了回應教學現場對備課資源整合的需求，也初步支持以「輔助收斂」取代「自動生成」的系統設計，在教育實務中具有良好的應用價值，可供未來推動智慧教學輔助工具作為參考。;Since the implementation of Taiwan’s 12-Year Basic Education Curriculum， the educational field has emphasized literacy-oriented and differentiated instruction. In practice， however， the standardized teacher manuals provided by publishers are mostly generalized and often fail to directly meet the localized needs of different classrooms. To transform these standardized materials into suitable instructional content， teachers frequently rely on collaborative lesson planning to deconstruct materials and inspire ideas. However， the initial data collection and document organization consume a significant amount of time， which in turn compresses the space for actual dialogue and discussion among teachers， inadvertently increasing the pressure of lesson preparation. To alleviate teachers′ document burden in the early stages of lesson preparation， this study starts from exploring teachers′ lesson planning needs， introduces AI assistance， and investigates how to transform Generative Artificial Intelligence (GenAI) into a practical "lesson planning assistant." Considering that directly using traditional AI easily produces incorrect content or suggestions that deviate from the teaching context， this study introduces Retrieval-Augmented Generation (RAG) technology. Through this technology， teachers can first upload their own materials to build a dedicated knowledge base; the system can then assist in data consolidation based on these exact texts， helping teachers complete preliminary material organization and providing content suggestions for lesson preparation in a short time. Based on the above background， this study developed and preliminarily evaluated a teacher lesson planning platform that integrates GenAI and RAG technology. Regarding system positioning， this study provides suggestions for instructional inspiration and material integration. To avoid replacing teachers′ professionalism， the system is designed not to provide the function of "directly generating complete lesson plans，" ensuring that the final decision-making authority for instructional design returns to the teachers themselves. In terms of effectiveness evaluation， this study used the Technology Acceptance Model (TAM) as the theoretical framework and invited 39 in-service K-12 teachers with lesson planning experience to participate in a questionnaire survey， aiming to understand their perceived usefulness， perceived ease of use， and intention to use the platform. The research results showed that most participating teachers gave positive evaluations of this platform. Quantitative and qualitative feedback indicated that this teacher lesson planning platform help to reduce the time required to organize standardized materials and provide diverse reference directions for activity design. Most teachers also expressed their intention to continue using it. In summary， in addition to responding to the needs of the educational field for integrating lesson planning resources， this study also preliminarily supports that a system design replacing "automatic generation" with "assisted consolidation" has good application value in educational practice and can serve as a reference for promoting intelligent instructional support tools in the future.
