Film recommendation method and system of SDDNE model collaborative filtering model, medium and equipment

Abstract

The invention discloses a film recommendation method and system of an SDDNE model collaborative filtering model, a medium and equipment. The method comprises the following steps of acquiring a user film data set required by a test, inputting the data set into a deep belief network for preprocessing, inputting the obtained processed data into an SDDNE model, and performing feature extraction through combination of Laplacian feature mapping and a stacked noise reduction auto-encoder to obtain user and film feature vectors, and splicing the obtained feature vectors to obtain a user-film score matrix, and inputting the obtained matrix into a collaborative filtering model to obtain a final film recommendation result. According to the method, the SDDNE model and the collaborative filtering model are effectively combined together through ensemble learning, so that the accuracy and stability of film recommendation favored by users can be greatly improved.

Description

technical field [0001] The invention belongs to the technical field of movie recommendation, and in particular relates to a movie recommendation method, system, medium and equipment of an SDDNE model collaborative filtering model. Background technique [0002] In the study of existing movie recommendation method models, the initial researchers mainly used the item-based and user-based collaborative filtering (Collaborative Filtering recommendation) recommendation method model. However, with the increase in the number of users and the complexity of the information to be processed, , leading to a gradual decrease in the accuracy of the recommendation results. Afterwards, the researchers adopted content-based (Content-Based Recommendations) recommendation method models, hybrid recommendation method models, and recommendation method models that added association rules, utility and knowledge, but the models proposed by the researchers were unable to deal with the current recommen...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problems existing in the prior art, the present invention proposes a movie recommendation method, system, medium and equipment based on the SDDNE model collaborative filtering model, so as to solve the problem that the current movie recommendation method runs slowly when recommending movies and the accuracy of the recommendation results is relatively low. low problem

Images