Recommendation Based on Knowledge Graph and Graph Neural Network

The recommendation system based on knowledge graph assistance has more advantages than the traditional recommendation system, mainly reflected in: accurate, efficient and explainable. Most of the recommendation methods of existing studies use knowledge graph representation learning for information mining of entity features, but some of them ignore the neighborhood information of knowledge graph entities, resulting in the loss of high-order feature information. Considering the above problem, this study proposes a recommendation method based on graph neural network for the problem that the existing recommendation methods ignore the overall information in the process of knowledge graph entity information mining. The graph attention network is introduced to carry out neighborhood information aggregation to make up for the neighborhood information of missing entities in the process of extracting the features of the knowledge graph in existing research. In this study, the prediction experiments of click rate and top-k recommendation scenarios were carried out on the data under the four backgrounds of movies, books, online courses and music, and the influence of some key parameters and structures in the model on the model was analyzed, compared and discussed.