Social recommendation method for enhancing influence diffusion based on GCN

Abstract

The invention discloses an enhanced influence diffusion social recommendation method based on GCN, which simulates the process of social recursive dynamic propagation influence based on transitivity and dynamism characteristics of trust, constructs an enhanced influence diffusion model, fuses the trust based on historical interaction records of users and articles into recursive social dynamic modeling, and improves the social recommendation efficiency. The problem that different users recommend different articles due to trust relations is solved. Meanwhile, an attention mechanism is introduced, and different importance is given to users in the social graph, so that the same-order domain weight distribution problem is solved; when the long-distance social relation is calculated in a recursive manner, a residual error connection mode is proposed to reduce the influence of noise; and finally, predicting future behaviors and preferences of the user. According to the method, the user sparsity is reduced by fully utilizing the preferences of neighbors around the user, and a model based on the neural network is designed to simulate the social influence recursive propagation process, so that the recommendation performance is improved.

Description

technical field [0001] The invention relates to the field of recommendation systems based on Internet technology, in particular to a GCN-based social recommendation method for enhanced influence diffusion. Background technique [0002] As a technology to help users obtain needed information from massive data, recommendation system has been widely used in various network applications. Collaborative filtering method is one of the most representative methods in recommendation system. Most of the current collaborative filtering only uses the user's rating information to recommend items, which leads to the problems of rating data sparsity and cold start. At the same time, the traditional collaborative filtering technology only considers the user's rating of the item, and cannot reflect the characteristics of the user and the item itself and the effect of the associated features on the recommendation, resulting in low performance of the recommendation. [0003] With the rapid dev...

AI Technical Summary

Problems solved by technology

Chinese patent document (CN105117422A) discloses that a social recommendation system can use social networks to alleviate the limitations of traditional recommendation algorithms. However, most existing social network recommendation methods simply use local neighbors to develop static models without simulating social networks. Recursive Diffusion Process of Social Relations in Networks

In addition, regarding the trust degree of trusted users, previous methods do not consider the different trust levels of different users when users interact with different items, resulting in poor recommendation results.

Images