Recommendation method based on deep learning

Abstract

The invention discloses a recommendation method based on deep learning, belongs to the technical field of data mining, and solves the problems of an existing recommendation method that the potential factor vector of a project can not be predicted from text content information which contains the project descriptions and metadata so as to cause recommendation inaccuracy. The method comprises the following steps that: carrying out modeling on the implicit feedback characteristics of the historical behavior data of a user, and learning to obtain the implicit factor vectors of the user and the project after modeling; taking the implicit factor vector of the project as tag training to carry out modeling on the time sequence information of project text contents and deeply mine a network model; and for a new project which does not appear in the historical behavior data of the user, predicting the network model obtained through S(2) in the text content information of the project to obtain the implicit factor vector of the project, directly matching the implicit factor vector of the project with the implicit factor vector, which is obtained in S(1), of the user, and sorting matching degreesto obtain the new project recommendation list of each user. The method is used for recommending new projects.

Description

technical field [0001] A deep learning-based recommendation method is used for the recommendation of new items, and belongs to the technical fields of data mining, natural language processing, and personalized recommendation. Background technique [0002] Content-based recommendation usually predicts user preferences from content information such as item descriptions and metadata. The most basic recommendation algorithm is to make recommendations based on the available metadata of the item. For example, in movie recommendation, the metadata of the movie may include the category attribute of the movie, the actors involved, the director of the production, the public rating of the movie, and so on. However, this will lead to predictable recommendations. For example recommending movies with actors that the user already knows well, usually this will not be a valid recommendation. Another recommendation algorithm is to make recommendations based on the description information of...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem that the existing recommendation method cannot effectively predict the latent factor vector of the item from the text content information containing the description and metadata of the item, resulting in inaccurate recommendation; the present invention provides A Recommendation Method Based on Deep Learning

Images