Socialized convolution matrix decomposition-based document context sensing recommendation method

Abstract

The invention discloses a socialized convolution matrix decomposition-based document context sensing recommendation method. The method comprises the steps of firstly capturing context information of an article description document by utilizing a convolutional neural network (CNN), and taking obtained context eigenvector and Gaussian noise as potential vectors of a project; secondly, by utilizing acharacteristic that interests and hobbies of users are more easily influenced by trusted friends (having direct link relationships), determining a potential eigenvector of a target user by calculating an average value of potential eigenvectors of the friends; and finally predicting score information of the user for the project according to a joint probability distribution function of the user andthe project. According to the method, the CNN is seamlessly integrated in matrix decomposition technology-based socialized recommendation (SocialMF) from the perspective of a probability, so that thefriends having a trust relationship with the target user and interests relatively close to those of the target user can be further identified in a learning process, and the purpose of optimizing a recommendation result is achieved.

Description

technical field [0001] The invention relates to the technical field of collaborative filtering recommendation. Specifically, it relates to a document context-aware recommendation method based on socialized convolution matrix factorization. Background technique [0002] The recommendation system is one of the important realization technologies of personalized service. Among them, the recommendation algorithm is the core of the whole recommendation system, which determines the performance of the recommendation system. The current mainstream recommendation systems mainly include: content-based recommendation, collaborative filtering recommendation, knowledge-based recommendation and hybrid recommendation. However, with the explosive growth of the number of users and items in e-commerce services, the sparsity of user-item rating data increases. Ultimately, this sparsity reduces the evaluation prediction accuracy of traditional collaborative filtering techniques. In order to i...

AI Technical Summary

Problems solved by technology

However, these methods do not take into account t

Images