为更加精准地捕捉用户学习兴趣的动态变化,特别对于C语言等课程,知识点之间有明确的顺序和依赖关系,推荐不仅要考虑用户的兴趣,还要结合知识结构的合理性。对此提出了一种融合用户属性和RippleNet的混合推荐算法。该算法通过引入知识图谱,利用多跳传播机制挖掘学习路径中知识点的潜在关联,同时结合协同过滤算法,从用户的兴趣和知识结构两个维度提供个性化推荐。研究结果表明：通过这种方式,能够在保障兴趣匹配的同时,提升学习路径的逻辑性和连贯性,达到预期效果。
Abstract
In order to more accurately capture the dynamic change of users' learning interests, especially for C language courses, where there is a clear order and dependence between knowledge points, it is recommended to not only consider users' interests, but also combine the rationality of knowledge structure. In this paper, a hybrid recommendation algorithm combining user attributes and RippleNet is proposed. By introducing the knowledge graph, the algorithm uses the multi-hop propagation mechanism to dig the potential correlation of knowledge points in the learning path, and combines the collaborative filtering algorithm to provide personalized recommendation from the two dimensions of user interest and knowledge structure. The research results show that this method can improve the logic and consistency of learning path while ensuring interest matching, and achieve the expected effect.
关键词
知识图谱 /
个性化推荐 /
C语言
Key words
knowledge graph /
personalized recommendation /
C language
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Parameswaran A,Venetis P,Garcia-Molina H.Recommendation systems with complex constraints:A course recommendation perspective[J].ACM Transactions on Information Systems (TOIS),2011,29(4):1-33.
[2] Zhang H,Huang T,Lv Z,et al.MCRS:A course recommendation system for MOOCs[J].Multimedia Tools and Applications,2018,77(6):7051-7069.
[3] Nguyen V A,Nguyen H H,Nguyen D L,et al.A course recommendation model for students based on learning outcome[J].Education and Information Technologies,2021,26(5):5389-5415.
[4] 于延,周国辉,李红宇,等.CDIO模式下C语言程序设计实践教学改革[J].计算机教育,2016(2):122-126.
[5] 于延,李英梅,于龙.程序设计课程游戏化教学模式设计[J].计算机教育,2020(2):68-71+75.
[6] Sun J,Xu C,Tang L,et al.Think-on-graph:Deep and responsible reasoning of large language model on knowledge graph[J].arxiv preprint arxiv:2307.07697,2023.
[7] Chen L,Tong P,et al.Plan-on-graph:Self-correcting adaptive planning of large language model on knowledge graphs[J].Advances in Neural Information Processing Systems,2024,37:37665-37691.
[8] Guo T,Yang Q,Wang C,et al.Knowledgenavigator:Leveraging large language models for enhanced reasoning over knowledge graph[J].Complex & Intelligent Systems,2024,10(5):7063-7076.
[9] Kou Z,Shang L,Zhang Y,et al.Hc-covid:A hierarchical crowdsource knowledge graph approach to explainable covid-19 misinformation detection[J].Proceedings of the ACM on Human-Computer Interaction,2022,6(GROUP):1-25.
[10] 甄好. 基于知识图谱和协同过滤的推荐方法研究[D].天津:天津理工大学,2024.
[11] 彭永梅. 基于知识图谱的多跳路径推荐系统[D].山东:烟台大学,2024.
[12] 沈瑶琦. 基于知识图谱和知识追踪的个性化习题推荐研究[D].上海:上海师范大学,2024.
[13] 杨群峰. 基于知识图谱的可解释图书推荐研究[D].安徽工程大学,2023.
[14] 卢丹,潘旭华.融合教育知识图谱的推荐系统研究进展[J].办公自动化,2025,30(3):112-115,119.
[15] Hrnjica B,Music D,Softic S.Model-based recommender systems[J].Trends in Cloud-based IoT,2020:125-146.
[16] 杨群峰. 基于知识图谱的可解释图书推荐研究[D].安徽工程大学,2023.
[17] 马永娟. 基于智能协同机制的学习路径推荐与评估方法研究[D].陕西:西安理工大学,2023.
