物理与工程

知识图谱推动人工智能技术与教育教学的深度融合，为实现课程的数智化建设与实践提供了技术路线和策略。本文展示了构建大学物理课程知识图谱的思路和流程，并分析了提取知识点及关联知识点时，教学目标导向、跨课程关联、思政知识点关联等的影响和作用。本文结合大学物理课程知识图谱实例，展示了知识图谱的生成方式、图谱表现形式，以及知识点关联的设置等。此外，结合教学实践，本文还展示了学生利用知识图谱进行个性化学习并完成自我评价，教师利用知识图谱在大规模教学班实施“线上线下混合式”教学，对学生进行实时督学、指导及反馈，实现人工智能技术赋能一流课程建设。

Knowledge graph promotes the deep integration of artificial intelligence technology and education, providing a technical route and strategy for the digital construction and practice of courses. This paper demonstrates the ideas and processes of constructing a knowledge graph for university physics courses, and analyzes the impact and role of teaching goal orientation, cross course correlation, and ideological and political knowledge point correlation when extracting knowledge points and related knowledge points. By combining examples of university physics course knowledge graphs, the paper shows the generation methods of knowledge graphs, the forms of graph representation, and the settings of knowledge point associations. Based on teaching practice, it was demonstrated that students use knowledge graphs for personalized learning and complete self-evaluation. Teachers use knowledge graphs to implement a “blended online and offline” teaching approach in large-scale classes, providing real-time supervision, guidance, and feedback to students, achieving the empowerment of artificial intelligence technology to build first-class courses.