Game push method and device, computer equipment and storage medium

Abstract

The invention provides a game push method. The method comprises the steps of acquiring historical game behavior data; segmenting a time period corresponding to the historical game behavior data to obtain a sub-time period set; acquiring sub-historical game behavior data corresponding to each sub-time period; determining a game behavior sub-vector corresponding to each candidate recommendation game; constructing a game behavior characteristic vector corresponding to the sub-time period according to the game behavior sub-vector; forming a time sequence behavior characteristic matrix corresponding to a user identification according to a time sequence corresponding to the game behavior characteristic vector; inputting the time sequence behavior characteristic matrix to a trained game recommendation model; outputting recommendation parameters corresponding to the candidate recommendation games; and screening a target recommendation game from the candidate recommendation games according to the recommendation parameters for recommendation. With the game push method, the game push accuracy is improved and the recommended resource is saved. In addition, the invention also provides a game push device, computer equipment and a storage medium.

Description

technical field [0001] The present application relates to the field of computer processing technology, and in particular to a game push method, device, computer equipment and storage medium. Background technique [0002] With the improvement of people's living standards and the development of the Internet, more and more people like to play games in their free time. In order to meet people's gaming needs, game developers have continuously proposed various games. Due to the increasing number of games, it is difficult for users to quickly find the games they are interested in. In order to facilitate users to obtain the games they are interested in, many game platforms will actively recommend some games to users. However, traditional game recommendation methods often simply collect user tags, and then make recommendations based on user tags, without considering changes in user interests. This recommendation method does not get good recommendation results, resulting in waste of...

AI Technical Summary

Problems solved by technology

[0003] Based on this, it is necessary to address the above-mentioned waste of recommended resources, and propose a game push method, device, computer equipment and storage medium that can save recommended resources

Images