Research on Student Curriculum Selection Recommendation System Based on Graph Convolutional Network

In recent years, the recommendation systems based on knowledge graph have been widely used by researchers, however, existing systems are mostly applied in people’s daily life. This paper proposes a new model of student curriculum selection recommendation system based on graph convolutional network, aiming at providing personalized curriculum selection recommendation for students. In this model, the graph convolution network is used to propagate the embedding from the neighbor of nodes to update the new representation of the nodes, then aggregate the representation of students and curriculums, and output the predicted matching score, so as to realize the personalized curriculum selection recommendation of students.