Collaborative filtering recommendation method and system based on decoupling type two-channel hypergraph neural network

Abstract

The invention provides a collaborative filtering recommendation method and system based on a decoupling type two-channel hypergraph neural network, and relates to the technical field of recommendation systems.The method comprises the steps of acquiring a user-article interaction graph and user features and article features by random initialization; constructing a user hypergraph structure and an article hypergraph structure by adopting a dual-channel hypergraph construction method; obtaining a user feature representation and an article feature representation by adopting a feature extraction module of intention perception; obtaining new user features and new article features by adopting a plurality of superposed hypergraph decoupling modules; fusing the new user features and the new article features to obtain a final user feature representation and a final article feature representation; the preference of the user to the article is represented by the click product result of the final feature representation of the user and the final feature representation of the article, and the greater the click product result is, the greater the preference of the user to the article is. Modeling is carried out on various potential intentions existing when the user interacts with the article, and the relation between the user and the article is described more accurately.

Description

technical field [0001] The present application relates to the technical field of recommendation systems, in particular to a collaborative filtering recommendation method and system based on a decoupled dual-channel hypergraph neural network. Background technique [0002] As an effective way to solve the problem of information overload, recommender systems have been widely used in e-commerce and other fields. In recommender systems, collaborative filtering based on user historical behavior information is one of the widely used methods. For collaborative filtering, how to accurately model the relationship between users and items and mine collaborative information is the key issue. In recent years, some researchers have proposed a collaborative filtering algorithm based on hypergraph neural network because hypergraph neural network has demonstrated stronger expressive ability and flexibility when modeling complex data associations. However, the existing methods fail to fully ...

AI Technical Summary

Problems solved by technology

[0004] For this reason, the first purpose of this application is to propose a collaborative filtering recommendation method based on a decoupled dual-channel hypergraph neural network, which solves the problem that existing methods fail to fully consider the relationship between users and items. Different intentions exist in the interaction, it is difficult to accurately describe the technical problems of the relationship between the user and the item, realize the use of multiple probabilistic hypergraphs to model the various potential intentions existing in the interaction between the user and the item, and by proposing a hypergraph The decoupling module makes the hypergraph structure and node characteristics of different intentions as different as possible, so as to focus on the information under different intentions and describe the relationship between users and items more accurately; at the same time, filter the items to be recommended and improve the recommendation quality. item accuracy

Images