Title: Personalised recommendation method for online learning resources in blended learning based on knowledge graph

Authors: Quanzhong Yang; Yu Zhang; Xiaoli Li; Feifei Shen; Xiaoyin Wang; Ruili Zhang; Yongwei Chen

Addresses: College of Medical Technology, Luoyang Polytechnic, Luoyang, 471000, China ' Basic Medical College, Xinxiang Medical College, Xinxiang City, Henan Province, China ' Department of Fundamental Courses, Xinxiang Vocational and Technical College, Xinxiang City, 453000, China ' College of Medical Technology, Luoyang Polytechnic, Luoyang, 471000, China ' Basic Medical College, Xinxiang Medical College, Xinxiang City, Henan Province, China ' Digital Technology School, Sias University, Zhengzhou, 45000, China ' Basic Medical College, Sanquan College of Xinxiang Medical College, Xinxiang City, Henan Province, China

Abstract: To improve the hit rate of personalised learning resource recommendations, this paper proposes a knowledge graph-based personalised recommendation method for online learning resources in blended learning. First, user browsing data on online learning resources is collected through web crawlers to construct a knowledge graph. Then, the self-organising map network and K-means clustering algorithm are used to cluster the learning resource content, while graph neural networks calculate the similarity between users and resources. Finally, the user's rating for recommended resources is predicted, and a time-weighted strategy is introduced to dynamically adjust the ratings, completing the recommendation based on the rating results. Experimental results show that this method consistently maintains a hit rate above 95%, achieves a minimum normalised discounted cumulative gain of 0.92, and reaches a maximum entropy value of 0.75.

Keywords: blended learning; online learning resources; resource recommendation; knowledge graph; self-organising mapping network; K-clustering algorithm.

DOI: 10.1504/IJCEELL.2025.150060

International Journal of Continuing Engineering Education and Life-Long Learning, 2025 Vol.35 No.6, pp.449 - 462

Received: 04 Nov 2024
Accepted: 02 Jun 2025
Published online: 28 Nov 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article