Virtual prop recommendation method and device and computer readable storage medium

Abstract

The invention discloses a virtual prop recommendation method and device and a computer readable storage medium. The method comprises the following steps: acquiring a heterogeneous network of a targetgame; representing a target user node in the heterogeneous network representation learning model as a user learning vector by using the heterogeneous network representation learning model, and representing each prop node as a prop learning vector; acquiring first preference information of the target game user for each game virtual prop according to the user learning vector and the prop learning vector; acquiring a historical operation sequence of the target game user, and representing the historical operation sequence as a time sequence learning vector through a time sequence model; acquiringsecond preference information of the target game user for each game virtual prop according to the time sequence learning vector and the prop learning vector; and recommending game virtual props to thetarget game user according to the first preference information and the second preference information. Game virtual props can be recommended to game users more accurately.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a virtual item recommendation method, device and computer-readable storage medium. Background technique [0002] With the rapid development of artificial intelligence technology, by deploying intelligent recommendation algorithms on the server, it is possible to make targeted recommendations to users. Taking games as an example, it is possible to recommend game virtual items that users may prefer. [0003] In the existing technology, an intelligent recommendation algorithm based on a graph representation learning model is usually used to learn the user's preference for game items. This intelligent recommendation algorithm represents both the user and the game virtual item as a vector, and finally uses the similarity between the two vectors to To predict the user's preference for a game item. [0004] During the research and practice of the prior art, th...

AI Technical Summary

Problems solved by technology

[0004] During the research and practice of the prior art, the inventors of the present application found that when predicting the user's preference for game props in the prior art, the prediction accuracy rate is low

Images