Article recommendation method based on hierarchical multi-granularity matrix decomposition

Abstract

The invention discloses an article recommendation method based on hierarchical multi-granularity matrix decomposition. In a recommendation system, a matrix decomposition algorithm is a recommendationalgorithm for decomposing a scoring matrix into two low-dimensional matrixes, and user preferences and article features can be learned. However, an existing matrix decomposition algorithm and an improved algorithm of the matrix decomposition algorithm only utilize a single feature vector to represent a user and an object, and therefore the problem of low prediction precision exists. In order to solve the technical problem, the invention provides a hierarchical multi-granularity matrix decomposition recommendation method based on deep learning, which can be used for recommending purchased articles with user scores. According to the method, the advantages of feature extraction by deep learning are combined, and the same user or article is represented by utilizing a plurality of different feature vectors, so that the preference representation of the user is more accurate. In addition, the technical problem that an existing recommendation algorithm based on deep learning only uses the lastlayer for prediction, but neglects information loss caused by feature transformation of each layer of the neural network is also solved.

Description

technical field [0001] The invention belongs to the technical field of recommendation, and in particular relates to an item recommendation method based on hierarchical multi-granularity matrix decomposition. Background technique [0002] With the vigorous development of big data, the recommendation technology is becoming more and more mature. The recommended items can be products purchased by users on a certain platform website or mobile terminal applications, such as daily necessities, books, songs, movies, etc. Currently, recommendation schemes for movies mainly have the following deficiencies: [0003] First, the current recommendation algorithm based on matrix factorization requires the user or item to be described by feature vectors of the same dimension, which is obviously not in line with the actual situation. For example, in the recommendation process, some users interact with the system many times, and the recommendation system can collect a large amount of histori...

AI Technical Summary

Problems solved by technology

However, this network structure for extracting features only uses the last layer for prediction, but ignores the information loss problem caused by the feature transformation of each layer of the neural network. Therefore, it is necessary to comprehensively consider the similarities between the recommendation system field and other fields. and difference, setting an improved method applicable to the field of recommender systems

Images