Information pushing method and system fusing knowledge graph structure and path semantics

Abstract

The invention discloses an information pushing method and system fusing a knowledge graph structure and path semantics. The method comprises the following steps: constructing a fusion graph based on a user article behavior graph and an article association knowledge graph; mapping the heterogeneous node representation to a unified semantic space; alternately updating the behavior sub-graphs and the article sub-graphs in the fusion graph layer by layer by using a graph neural network; sampling migration between the user and the article node to obtain a path set, and carrying out weighted fusion to generate a path representation; calculating a matching score by combining user and article node representations and path representations between the user and the article node representations to train a recommendation system model; and pushing interested article information to the user based on the recommendation system model. According to the method, the structure information and the path semantics are comprehensively considered to calculate the similarity between the user and the article to push the article information, a more reasonable information fusion means is provided, and the technology can be applied to article information pushing, especially user article representation learning in a sparse scene.

Description

technical field [0001] The invention relates to a push method, in particular to an information push method and system that integrates knowledge map structure and path semantics, and belongs to the field of information push technology. Background technique [0002] With the explosive growth of Internet information, how to mine user interest points from massive data has become an urgent problem to be solved. In recent years, recommender system technology uses algorithms to analyze users' past behavior patterns to recommend items, and is widely used in shopping and information push websites, which greatly improves the user experience. [0003] Traditional recommendation system methods use collaborative filtering algorithms to mine similarity recommendations based on user behavior records such as clicking on and purchasing items, or learn vector representations of users and items to calculate matching scores, and push (recommend) interested items to users based on the scores. t...

AI Technical Summary

Problems solved by technology

After research, it is found that the correlation method based on node representation lacks the consideration of long-distance path dependence, and the correlation method based on path is difficult to learn accurate item and user characteristics. Room for improvement

Images