Method and device to determine rating matrix based on convolutional neural network

Abstract

An embodiment of the invention discloses a method and device to determine a rating matrix based on a convolutional neural network. The method comprises: using a pre-trained convolutional neural network to process acquired document information, and determining a target characteristic vector; establishing an initial rating matrix according users' rating information for a commodity, wherein blank items where users do not make rating may occur in the initial rating matrix; processing the initial rating matrix according to the target characteristic vector and a matrix-decomposition-based latent semantic model, processing the initial rating matrix, and filling the blank items in the initial rating matrix to obtain a target matrix. By using the convolutional neural network, it is possible to recognize context of document information of a commodity, text information of the commodity from users can be better mined, and the influence due to data sparsity problem can be weakened. By substitutingthe target characteristic vector into the matrix-decomposition-based latent semantic model, predicted ratings in the target matrix can be more accurate.

Description

technical field [0001] The present invention relates to the technical field of recommendation systems, in particular to a method and device for determining a scoring matrix based on a convolutional neural network. Background technique [0002] In recent years, with the rapid development of the Internet and the increase of smart mobile devices, human beings have entered the era of information overload. Facing the vast amount of information on the Internet, it has become very difficult for users to find information that really meets their interests. The recommendation system can filter out the information that meets the user's needs from a large amount of information, and is one of the effective technical means to solve the problem of information overload. [0003] In recent years, recommender systems have been extensively developed in both research and application fields. But at the same time, the recommendation system is also facing great challenges, the first challenge is ...

AI Technical Summary

Problems solved by technology

Data sparsity has a great impact on the recommendation effect. Data systems like MovieLens are stored in the form of user-item scoring. When the number of items or users increases, the dimensionality and sparsity will also increase, resulting in the accuracy of the scoring matrix. decline

Since collaborative filtering relies on the scoring matrix, it is greatly affected by this

Images