计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (6): 93-101.doi: 10.11896/jsjkx.250600154

• 智能教育技术 • 上一篇    下一篇

基于知识图谱的个性化在线课程推荐方法

赵蕾1,2, 杨雨露1, 袁波1   

  1. 1 西安财经大学信息学院 西安 710100
    2 智财协同可信计算陕西省高等学校重点实验室 西安 710100
  • 收稿日期:2025-06-22 修回日期:2025-09-12 出版日期:2026-06-15 发布日期:2026-06-09
  • 通讯作者: 杨雨露(2329947287@qq.com)
  • 作者简介:(leizhao@xaufe.edu.cn)
  • 基金资助:
    2024年西安财经大学研究生创新基金项目(23YC035)

Personalized Course Recommendation System Based on Knowledge Graph

ZHAO Lei1,2, YANG Yulu1, YUAN Bo1   

  1. 1 College of Information,Xi'an University of Finance and Economics,Xi'an 710100,China
    2 Key Laboratory of Intelligent Finance Collaborative and Trusted Computing Higher Education Institutions in Shaanxi Province,Xi'an 710100,China
  • Received:2025-06-22 Revised:2025-09-12 Published:2026-06-15 Online:2026-06-09
  • About author:ZHAO Lei,born in 1981,Ph.D,associate professor,master's supervisor.Her main research interests include know-ledge graph and recommendation system.
    YANG Yulu,born in 2002,postgra-duate.Her main research interest is knowledge graph.
  • Supported by:
    2024 Graduate Innovation Fund Project of Xi'an University of Finance and Economics(23YC035).

PDF (PC)

77

摘要： 随着在线学习平台数量激增与课程内容的指数级增长,用户在海量信息中面临着严重的选择困境。由于未能充分挖掘用户与课程之间的交互信息,现有推荐模型的推荐结果与用户真实需求存在偏差,严重影响学习体验与资源匹配效率。针对上述问题,提出一种基于增强信息表示的图神经网络推荐模型——IKGCN(Interactive Knowledge Graph Convolutional Network)。该模型通过构建课程知识图谱和用户-课程交互图,借助融合门聚合机制识别并整合两类图结构的互补信息,实现双重信息维度的深度融合,从而有效捕捉用户行为模式的动态特征,显著提升课程语义表征的准确性与推荐系统的智能化水平。实验结果表明,相较于传统基线方法,IKGCN 在多个关键指标上实现了显著突破,在召回率和归一化折扣累积增益(NDCG)等核心评估维度上分别提升了4.84%和9.22%,充分验证了该模型在优化在线教育推荐服务中的有效性与实用性。

关键词: 在线教育, 用户交互信息, 图神经网络, 课程推荐, 知识图谱

Abstract: As online learning platforms and course content multiply,users struggle to choose from a sea of information.Existing recommendation models,failing to fully exploit user-course interaction info,deviate from users' real needs,harming learning experience and resource-matching efficiency.To address this,IKGCN(Interactive Knowledge Graph Convolutional Network),a graph neural network recommendation model based on enhanced info representation,is proposed.It builds a course knowledge graph and a user-course interaction graph.Using a gating mechanism,it identifies and integrates complementary info from these two graph structures,fusing dual info dimensions deeply.This enables effective capture of user behavior dynamics,boosting course semantic representation accuracy and recommendation system intelligence.Experiments show IKGCN outperforms traditional baselines:recall rate and NDCG rise by 4.84% and 9.22% respectively,validating its effectiveness in optimizing online education recommendations.

Key words: Online education, User interaction information, Graph neural network, Course recommendation, Knowledge graph

中图分类号: 

  • TP391
[1]OTERO-CANOP A,PEDRAZA-ALARCÓN E C.Recommen-dation systems in education:A review of recommendation mecha-nisms in e-learning environments[J].Revista Ingenierías Universidad De Medellín,2021,20(38):147-158.
[2]DU M H,CUI X J,JIANG Y M,et al.Research on MOOC Re-commendation Method Based on LDA Topic Model[J].Computer and Digital Engineering,2024,52(12):3616-3622,3760.
[3]TONG J W,LIU Z L.Design of a Personalized Learning Platform for Aesthetic Education Courses Based on the Collaborative Filtering Algorithm[J].Computer Programming Skills & Maintenance,2025(3):50-52.
[4]MAO L.Design and Implementation of an Online Course Re-commendation System[J].Fujian Computer,2024,40(6):95-98.
[5]ZHANG H,SHEN X,YI B,et al.KGAN:Knowledge grouping aggregation network for course recommendation in MOOCs[J].Expert Systems with Applications,2023,211:118344.
[6]DAI J,LI Q S,CHU H,et al.Breaking through Smart Education:A Course Recommendation System Based on Graph Lear-ning[J].Journal of Software,2022,33(10):3656-3672.
[7]TANG S,PETERSON J,PARDOS Z.Predictive modelling ofstudent behaviour using granular large-scale action data[M]//The Handbook of Learning Analytics.2017:223-233.
[8]ZHANG H,HUANG T,LYU Z,et al.MOOCRC:A highly accurate resource recommendation model for use in MOOC environments[J].Mobile Networks and Applications,2019,24:34-46.
[9]HAO H H,YU X Y.Exploration on the Path of Content Supply for College Students' Network Ideological and Political Education－From the Perspective of Content Recommendation Algorithm[J].Journal of Guangxi College of Education,2025,40(3):104-111.
[10]WANG G,ZHANG J M,DONG S H,et al.Content-basedWeighted Granularity Sequence Recommendation Algorithm[J].Computer Engineering and Science,2018,40(3):564-570.
[11]LI Z J,ZHOU Q H,SHUAI Q H.A Recommendation System Model Based on Isomorphic Integration of Content-based and Collaborative Filtering[J].Computer Science,2009,36(12):142-145.
[12]ZHANG J A,YANG K.Collaborative Filtering Recommendation Algorithm Based on User Pseudo-Strong Concepts[J].Control Engineering,2025,32(5):882-890.
[13]ZHANG X,SU K,QIAN F.Collaborative Filtering Algorithm Based on Item Popularity and Dynamic Interest Changes[J].Fire Control & Command Control,2022,47(12):136-144.
[14]MA J H,ZHANG T.Expert Recommendation Algorithm forEnterprise Engineering Problems[J].Computer Science,2022,49(1):159-165.
[15]YU Y H,CHEN X G,GAO Y.An Item Recommendation Algorithm Based on Coupled Object Similarity[J].Computer Science,2014,41(2):33-35,54.
[16]ZHANG F,YUAN N J,LIAN D,et al.Collaborative knowledge base embedding for recommender systems[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2016:353-362.
[17]KOREN Y,BELL R,VOLINSKY C.Matrix factorization techniques for recommender systems[J].Computer,2009,42(8):30-37.
[18]WANG H,ZHAO M,XIE X,et al.Knowledge graph convolutional networks for recommender systems[C]//The World Wide Web Conference.2019:3307-3313.
[19]WANG X,HE X,CAO Y,et al.Kgat:Knowledge graph attention network for recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Disco-very & Data Mining.2019:950-958.
[20]WANG Z,LIN G,TAN H,et al.CKAN:Collaborative know-ledge-aware attentive network for recommender systems[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:219-228.
[21]WANG X,HUANG T,WANG D,et al.Learning intents behind interactions with knowledge graph for recommendation[C]//Proceedings of the Web Conference 2021.2021:878-887.
[22]WANG X,HE X,WANG M,et al.Neural graph collaborative filtering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.2019:165-174.
[23]XU H T,CAI W Y,ZHANG M Y,et al.A Lightweight Convolutional Neural Network Model Based on the Combination of MobileNet and ShuffleNet[J].Journal of Hangzhou Dianzi University(Natural Science Edition),2025,45(3):50-62,72.
[24]MEI S Y.Research on Course Recommendation Methods forMOOCs[D].Hefei:Hefei University of Technology,2023.
[25]HU J T,XIAN G M.Graph Contrastive Learning Recommendation Algorithm Based on Self-Attention Mechanism[J].Computer Science,2025,52(11):82-89.
[26]ZHOU Y T,CHU H,ZHU F F,et al.A Survey of Deep Lear-ning-based Personalized Learning Resource Recommendation[J].Computer Science,2024,51(10):17-32.
[27]LU H Y,LIU X H,HOU W L.Negative Sampling Method Fusing Knowledge Graph[J].Computer Science,2025,52(3):161-168.
[28]YU H,ZHANG W,CHEN Z,et al.MOOCCube:A Large-scale Data Repository for NLP applications in MOOCs[C]//Procee-dings of the 58th Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2020:3135-3140.
[29]RAN J.Research on Knowledge Recommendation Based onUser Interest Topic Model [D].Zhengzhou:Zhengzhou University,2020.
[30]CUI Y.Research on Hybrid Recommendation Algorithm Based on Convolutional Neural Network [D].Changchun:Changchun University of Technology,2020.
[31]DU Y,ZHU X,CHEN L,et al.Metakg:Meta-learning onknowledge graph for cold-start recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2022,35(10):9850-9863.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发