A core user mining method and system based on a deep neural network and a graph network

Abstract

The invention provides a core user mining method based on a deep neural network and a graph network. The core user mining method comprises the steps of constructing a user- game history information database; Performing data preprocessing; According to the game historical sequence observation data of the game user after data preprocessing, establishing a directed graph with a game name as a node and a time sequence as an edge, and inputting the directed graph into a graph network embedding method so as to predict a game which is interested in next time; And establishing the directed graph for each game user to obtain an expression of each game, carrying out feature splicing on the obtained expression of each game and the personal information of the corresponding user, and fusing and inputthe expression and the personal information into a deep neural network so as to predict whether the user is a core player of the game or not. According to the invention, the problem of sequence prediction is solved based on the fusion method of graph network embedding and the deep neural network, the time sequence information is fully learned in the form of the graph network, and higher-level interactive expression is learned by fusing the deep learning method, so that the model prediction accuracy is improved.

Description

technical field [0001] The present disclosure relates to the technical fields of artificial intelligence, data mining and recommendation systems, and in particular to a core user mining method and system based on a deep neural network and a graph network. Background technique [0002] With the rapid development and popularization of the Internet and smart phones, a large amount of user log data is recorded every day. [0003] For the field of mobile games, the behavior of logging into the game interface once often has a lot of background information associated with the user, such as user personal information, device information, game behavior information, etc. The complex interaction of these multi-field information often affects The user's behavior on the game has a huge impact. In addition, for the game behaviors on the sequence, that is, the collection of user game behaviors arranged in chronological order within a predetermined period of time, contains rich sequence inf...

AI Technical Summary

Problems solved by technology

However, this method only simply lists the dynamic sequence features, and cannot obtain the dynamic implicit expression well. At the same time, this method only realizes the interaction between low-order features. For more complex high-order interaction features is not good at studying

[0005] In addition, in recent years, there has also been a method of using a recurrent neural network for dynamic sequence prediction, but this method ignores the complex conversion relationship between historical games played by the user in a specific period of time, and cannot learn the user's Preferences for these games

Images