基于知识图谱的AI课程建设——以研究生课程《随机过程》为例

AI Course Construction Based on Knowledge Graph—A Case Study of the Graduate Course “Stochastic Processes”

摘要: 考虑到研究生课程《随机过程》存在理论抽象、知识点分散、教学手段单一及思政融入不足等问题，文章提出了一种基于知识图谱的AI技术深度融合的课程建设和教学改革方案。通过构建《随机过程》知识图谱，将离散知识点系统化，实现从“静态知识传授”向“动态知识探索”的教学模式转变。首先，利用AI技术构建四大资源库(专业案例库、思政元素库、科研实践项目库、阅读材料库)，为教学改革提供内容支撑；其次，建立“课前–课中–课后”全流程的线上线下混合教学模式，融入案例教学、小组讨论与AI分析，以激发学生兴趣，培养其批判性思维与自主学习能力；再次，实施AI辅助的课程管理，通过学情数据分析实现个性化教学与精准辅导。通过多项举措，能有效促进教学与科研、专业实践的有机结合，在夯实学生理论基础的同时，助力其创新能力和综合素质的提升，为人工智能时代的高等教育课程改革提供了可资借鉴的实践路径。

Abstract: This paper addresses some issues in the graduate course “Stochastic Processes”—including its abstract theory, fragmented knowledge structure, traditional teaching methods, and a lack of ideological and political integration—by proposing a reform plan for course construction and teaching. This plan is deeply integrated with AI technology and built upon a knowledge graph. The creation of a “Stochastic Processes” knowledge graph systematizes discrete knowledge points, enabling a shift in the teaching model from “static knowledge transmission” to “dynamic knowledge exploration.” The strategy unfolds in three key aspects. First, AI technology is employed to develop four foundational resource libraries: a professional case library, an ideological-political elements library, a research practice project library, and a reading materials library, thereby providing substantial content support for the reform. Second, a comprehensive blended learning model is established, encompassing the entire instructional process from pre-class to in-class and post-class stages. This model integrates case-based teaching, group discussions, and AI analysis to enhance student engagement and develop their critical thinking and self-directed learning skills. Third, an AI-assisted course management system is implemented, which utilizes learning behavior data analysis to facilitate personalized instruction and precise academic guidance. These coordinated measures effectively foster the integration of teaching, research, and professional practice. The reform not only consolidates students’ theoretical groundwork but also strengthens their innovative capacity and overall quality, thereby providing a transferable model for higher education curriculum reform in the artificial intelligence era.