标题： 与人工智能协同设计跨学科设计项目 显示英文标题

标题： Co-Designing Interdisciplinary Design Projects with AI

摘要： 创建跨学科设计项目对教师来说既耗时又需要高度的认知努力，需要课程对齐、跨学科整合和仔细的顺序安排。 国际研究报道了教师越来越多地使用人工智能，同时面临持续的工作负担压力，突显了规划支持的必要性。 本文介绍了跨学科设计项目规划师（IDPplanner），这是一个基于GPT的规划助手，其基础是设计创新原则，与新加坡中学课程大纲一致，并符合21世纪的能力要求。 在一个同主题、平衡的研讨会中，33名在职教师参与了同一项目的两个版本：手动版本和AI辅助版本，随后使用六维评分标准进行了自我评价和同伴评价。 AI辅助版本在课程对齐、设计思维应用以及连贯性和流程方面获得了更高的分数，在评估策略方面有轻微的优势。 教师反思表明，AI辅助规划提高了结构、顺序和想法生成，而将内容与当地课程大纲、班级概况和学生需求相结合仍然是教师主导的。 贡献包括一个专门构建的规划工具，该工具将想法组织成一个包含十个组件的流程，配有可直接调整的提示、模板和评估建议；一个基于评分标准的实证规划质量比较；以及证据表明人工智能可以作为教学规划伙伴发挥作用。 建议强调混合教师-AI工作流程以增强课程对齐并减少规划复杂性，并为开发者提供设计建议以加强情境定制、迭代设计支持和本地化评分标准。 尽管该工具是基于新加坡课程开发的，但规划流程和评分标准是框架无关的，可以参数化用于其他系统。 显示英文摘要

摘要： Creating interdisciplinary design projects is time-consuming and cognitively demanding for teachers, requiring curriculum alignment, cross-subject integration, and careful sequencing. International research reports increasing teacher use of AI alongside persistent workload pressures, underscoring the need for planning support. This paper presents the Interdisciplinary Design Project Planner (IDPplanner), a GPT-based planning assistant grounded in Design Innovation principles, alignment with Singapore secondary school syllabuses, and 21st-century competencies. In a within-subject, counterbalanced workshop with 33 in-service teachers, participants produced two versions of the same project: manual and AI-assisted, followed by self- and peer-evaluations using a six-dimensional rubric. The AI-assisted version received higher scores for Curriculum Alignment, Design Thinking Application, and Coherence and Flow, with a marginal advantage for Assessment Strategies. Teacher reflections indicated that AI-assisted planning improved structure, sequencing, and idea generation, while contextualization to local syllabuses, class profiles, and student needs remained teacher-led. Contributions include a purpose-built planning tool that organizes ideas into a ten-component flow with ready-to-adapt prompts, templates, and assessment suggestions; an empirical, rubric-based comparison of planning quality; and evidence that AI can function as a pedagogical planning partner. Recommendations emphasize hybrid teacher-AI workflows to enhance curriculum alignment and reduce planning complexity, and design suggestions for developers to strengthen contextual customization, iterative design support, and localized rubrics. Although instantiated with a Singapore-based curriculum, the planning flow and rubric are framework-agnostic and can be parameterized for other systems.