华东师范大学学报(自然科学版) ›› 2024, Vol. 2024 ›› Issue (5): 57-69.doi: 10.3969/j.issn.1000-5641.2024.05.006

• 教育知识图谱与大语言模型 • 上一篇    下一篇

知识图谱与大语言模型协同的教育资源内容审查

刘佳1(), 孙新2, 张宇晴2   

  1. 1. 教育部教育技术与资源发展中心(中央电化教育馆), 北京 100031
    2. 北京理工大学 计算机学院, 北京 100081
  • 收稿日期:2024-07-11 接受日期:2024-05-30 出版日期:2024-09-25 发布日期:2024-09-23
  • 作者简介:刘 佳, 女, 助理研究员, 研究方向为教育信息化、智慧教育、大数据分析等. E-mail: liujia@moe.edu.cn
  • 基金资助:
    国家重点研发计划 (2022YFC3303500)

Educational resource content review method based on knowledge graph and large language model collaboration

Jia LIU1(), Xin SUN2, Yuqing ZHANG2   

  1. 1. Center for Educational Technology and Resource Development, Ministry of Education P. R. China (National Center for Educational Technology, NCET), Beijing 100031, China
    2. School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100081, China
  • Received:2024-07-11 Accepted:2024-05-30 Online:2024-09-25 Published:2024-09-23

摘要:

数字教育资源自动化内容审查是教育信息化时代的迫切需求, 特别是对教育资源是否超标的适用性审查, 存在知识点难定位和难理解的问题. 针对这一需求, 提出了一种基于教育知识图谱和大语言模型(简称“大模型”)协同的教育资源内容审查方法. 具体地, 首先利用“本体”思想, 设计并构建一个面向中小学教育的知识图谱; 之后, 利用大模型在文本生成和排序任务上的优势, 设计基于教学内容生成和排序剪枝的知识定位方法; 最后, 通过教学内容核心知识子图与知识图谱教学路径的冲突检测, 实现超标教学内容识别. 实验结果表明, 所提出的方法可有效应对教育资源内容的超标知识审查任务, 为基于知识图谱及大语言模型协同的教育应用开辟新的技术路径.

关键词: 知识图谱, 大语言模型应用, 教育资源内容审查

Abstract:

Automated content reviews on digital educational resources are urgently in demand in the educational informatization era. Especially in the applicability review of whether educational resources exceed the standard, there are problems with knowledge which are easy to exceed national curriculum standards and difficult to locate. In response to this demand, this study proposed a review method for educational resources based on the collaboration of an educational knowledge graph and a large language model . Specifically, this study initially utilized the ontology concept to design and construct a knowledge graph for curriculum education in primary and secondary schools. A knowledge localization method was subsequently designed based on teaching content generation, sorting, and pruning, by utilizing the advantages of large language models for text generation and sorting tasks. Finally, by detecting conflicts between the core knowledge sub-graph of teaching content and the knowledge graph teaching path, the goal of recognizing teaching content that exceeded the national standard was achieved. Experimental results demonstrate that the proposed method effectively addresses the task of reviewing exceptional standard knowledge in educational resource content. This opens up a new technological direction for educational application based on the knowledge graph and large language model collaboration.

Key words: knowledge graph, large language model application, educational resource content review

中图分类号: