Design of Recommendation Algorithm Based on Knowledge Graph

Abstract

The commodity data in the shopping system contains a wealth of feature information, and different commodities are related by these features. Traditional collaborative filtering algorithms represent commodity data in a structured way, but they have issues such as low commodity similarity calculation accuracy, poor recommendation effect, and unfriendly recommendation results. The commodity recommendation algorithm based on the knowledge graph put forward in this paper initially automatically extracts the entities and entity relationships in the commodity data as the vertices and edges of the graph and then stores the commodity data in the Neo4j graph database. Finally, the similarity between commodities is calculated based on the graph’s path similarity, and the list of TOP-K commodities with the highest similarity is chosen for recommendation. The experimental findings indicate that the recommendation algorithm based on the knowledge graph can not only more accurately represent the similarity between commodities, but also that the graph structure can display the recommended path in a more user-friendly manner, and has better recommendation explainability as well as higher recommendation trust.