Collaborative filtering optimization method based on condition restricted Boltzmann machine

Abstract

The invention discloses a collaborative filtering optimization method based on a condition restricted Boltzmann machine. In the improved condition restricted Boltzmann machine, item category information is fused to serve as a condition layer, and recommendation accuracy is improved in a personalized recommendation system. The collaborative filtering optimization method has the characteristics that modeling is carried out by user-item grading information and item category information, different influences on user interest preference and forecast grading by the user-item grading information and the item category information are considered, and the user-item grading information and the item category information are applied to the calculation of the improved condition restricted Boltzmann machine. Since the influences on user interest preference and forecast grading by the user-item grading information and the item category information are simultaneously considered, the method weakens the restriction of a recommendation system by a single data source and improves recommendation accuracy, and an experiment result indicates that the recommendation accuracy of the method is obviously higher than the recommendation accuracy of a restricted Boltzmann machine method which only adopts the user-item grading information.

Description

technical field [0001] The invention relates to a collaborative filtering optimization method based on conditionally restricted Boltzmann machines, in particular to a method that considers the influence of user-item rating information and item category information on user interest preferences and final prediction ratings, and is applied to improve The restricted Boltzmann machine method, so as to improve the recommendation accuracy of the recommendation system, is applicable to the collaborative filtering recommendation system, and belongs to the technical field of recommendation system research. Background technique [0002] The purpose of the recommendation system is to fully mine the interests and preferences of users and help users find what they are interested in. In the past two decades, recommender systems have been extensively studied and successfully applied to various Internet commercial systems. However, how to generate more accurate recommendations for users has...

AI Technical Summary

Problems solved by technology

[0004] In the existing collaborative filtering methods based on the restricted Boltzmann machine model, only user-item rating data is used for modeling, and the category information of the items is not fully utilized, and there is no relevant method to combine the item category information Applied to Restricted Boltzmann Machine Model to Improve Recommendation Accuracy

Images