Personalized recommendation method for mass learning tracks in view of knowledge graph

• Main Authors: MENG TIANHAO, ZHANG HUIJUAN, JIANG HAONAN, WU ZEZHENG, ZHANG JINGWEI, CHEN LIANG
• Format: Patent
• Language: Chinese; English
• Published: 17.03.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a personalized recommendation method for mass learning tracks under a knowledge graph perspective. The method comprises the following steps: constructing a knowledge graph triple after data preprocessing; constructing a knowledge graph: constructing the knowledge graph by taking the course knowledge points as nodes and taking the similarity relationship and the preorder relationship as edges; learning track mining: mining all learning tracks taking the target knowledge point as a starting point; and personalized recommendation of the learning track: recommending the learning track for learning the target knowledge point to the user. According to the method, through a mode of combining the knowledge graph and the recommendation method, the course knowledge points are associated with other knowledge graph attributes, and the problems of sparsity and cold start of the recommendation method are effectively solved. As most users only know the target learning object and do not know the start