大学化学

上一篇    下一篇

人工智能辅助师生共建动态知识图谱的教学改革与实践

朱奇珍1, 乔宁1, 牛津1, 孙宁2, 王菊琳1, 徐斌1,3   

  1. 1 北京化工大学材料科学与工程学院, 北京 100029;
    2 贵州民族大学化学工程学院, 贵州 贵阳 550025;
    3 延安大学化学与化工学院, 陕西 延安 716000
  • 收稿日期:2026-05-27 录用日期:2026-07-08
  • 通讯作者: 朱奇珍 E-mail:zhuqz@mail.buct.edu.cn Qizhen Zhu
  • 基金资助:
    北京化工大学人工智能在教育教学改革与教学管理中的应用专项教改项目“基于AI赋能的《材料合成制备与加工》课程教学创新与实践探索”(2026BUCTJGY12)；北京高校青年教师创新教研工作室项目(2024)

Teaching reform and practice of AI-assisted teacher-student coconstruction of dynamic knowledge graphs

Qizhen Zhu1, Ning Qiao1, Jin Niu1, Ning Sun2, Julin Wang1, Bin Xu1,3   

  1. 1 College of Materials Science and Engineering, Beijing University of Chemical Technology, Beijing 100029, China;
    2 School of Chemical Engineering, Guizhou Minzu University, Guiyang 550025, Guizhou Province, China;
    3 School of Chemistry and Chemical Engineering, Yan'an University, Yan'an 716000, Shaanxi Province, China
  • Received:2026-05-27 Accepted:2026-07-08
  • Contact: Qizhen Zhu E-mail:zhuqz@mail.buct.edu.cn

PDF

30

赞

摘要： 材料合成制备与加工课程覆盖材料门类广、技术更新快，缺乏知识统整标准，教学中存在学生学习动力不足、体系化认知困难、学用衔接不畅等问题。文章将建构主义学习理论、人工智能技术与知识图谱建构深度融合，创设“人工智能辅助师生共建动态知识图谱”的教学模式，以“学生课后绘制思维导图→AI批量处理与初步分析→教师重构与整合→师生协同共建与动态优化→AI个性化学习路径推送”为实施路径，并将学生贡献度与过程性评价紧密关联，引导学生在深度参与知识图谱构建中实现知识内化，提升系统思维与工程实践能力，培养科学态度和协同创新意识。该模式为无固定知识统整标准的同类课程数字化教学改革提供了参考。

关键词: 知识图谱, 师生共建, 人工智能, 过程性评价, 材料合成制备与加工

Abstract: The course “material synthesis, preparation, and processing” covers a broad range of material types and undergoes rapid technological updates, yet lacks unified standards for knowledge integration. As a result, teaching in this course faces prominent challenges, including low student motivation, difficulties in systematic understanding, and a weak connection between learning and practical application. This study deeply integrates constructivist learning theory, artificial intelligence technology, and knowledge graph construction to develop a teaching model termed “AI-assisted teacher-student co-construction of dynamic knowledge graphs”. The implementation pathway follows the sequence: “students draw mind maps after class → AI batch processing and preliminary analysis → teacher reconstruction and integration → teacher-student collaborative coconstruction and dynamic optimization → AI-driven personalized learning path recommendation”. This model closely links student contributions with process-oriented evaluation, guiding students to achieve knowledge internalization through active participation in knowledge graph construction, thereby enhancing their systematic thinking and engineering practice abilities, as well as fostering scientific attitudes and collaborative innovation awareness. It offers a reference for the digital teaching reform of similar courses that lack fixed knowledge integration standards.

Key words: Knowledge graph, Teacher-student co-construction, Aartificial intelligence, Formative assessment, Material synthesis, preparation and processing