| Summary: | The knowledge graph can make more accurate personalized recommendations for the recommendation system, but it is also interpretative and has traces to follow. The purpose of the recommendation system is to recommend a series of unobserved items for users. At present, recommendation systems based on knowledge graphs are mainly implemented in two ways: Embedding-based and path-based. Embedding methods usually directly use information from the knowledge graph to enrich the representation of an item or user. Still, it failed to introduce multi-hop relations, and it is challenging to use semantic network information. A path-based recommendation algorithm utilizes the knowledge graph to gain multi-hop knowledge and compare the similarity between users or items to improve the recommendation effect. This paper (1) Aiming at the problem of how the recommendation algorithm effectively utilizes the semantically related information of knowledge, a self-attention-based knowledge representation learning model is designed to learn the semantic information of the entity-relationship by using the overall triplet of the entity-relationship to achieve high-quality knowledge features, Which brings more and more helpful information to the recommendation. (2) Constructing a content recommendation model with unified, embedded behavior and knowledge features, using historical user preferences combined with knowledge graphs to dynamically learn knowledge features to bring users more accurate and diverse recommendations. (3) Aiming at the problem of knowledge feature representation learning, a self-attention-based knowledge representation learning model is proposed. Focusing on the difference in the importance of triples for determining entity semantics, the self-attention mechanism is used to learn semantics from triples to improve knowledge features. The quality of the representation provides high-quality auxiliary information for the recommendation system. The model’s performance is demonstrated through link prediction and triple classification experiments to prove the feasibility of the method proposed in this article.
|
|---|
