RESEARCH ON RECOMMENDATION TECHNOLOGY BASED ON KNOWLEDGE GRAPH

Abstract

The recommendation system is of great significance for screening effective information and improving the efficiency of information acquisition. It is widely used in many network scenarios to deal with information overload caused by massive information data, so as to improve user experience. In view of the strong practicability of the recommender system, researchers have conducted extensive research on its methods and applications. In recent years, many works have found that the rich information contained in the knowledge graph can effectively solve a series of key problems in the recommendation system, such as data sparseness, cold start, and recommendation diversity. Therefore, this article first introduces the main personalized recommendation technology and the related content of the knowledge graph, and then uses the knowledge graph to design a model of the fusion of the recommendation system and the knowledge graph. Finally, it is tested according to the data set, and the experiment proves that this model improves the task performance of the recommendation system.