Mobile application use prediction method based on time sequence mode

Abstract

The invention discloses a mobile application use prediction method based on a time sequence mode, and the method comprises the steps: obtaining the label data of a mobile application, and constructinga bipartite graph of a user and the mobile application according to the attribute information of the mobile application and the use sequence of the mobile application; then modeling a relationship between the user and the mobile application by using a graph neural network model to obtain node vector representation of the mobile application; then respectively embedding the node vector of the mobile application and the position, time, usage amount and the like of the mobile application used by the user to obtain corresponding embedded vectors; inputting the embedded vector into an RNN (Recurrent Neural Network) model based on an attention mechanism to obtain use preference of the user; and finally, constructing a DNN model, and outputting whether the user uses the label of the current mobile application or not at the next moment. According to the invention, the smart phone use data can be more comprehensively utilized, so that the user operation becomes simple and efficient, and the battery energy consumption and the mobile application search time can be planned and optimized in advance.

Description

Technical field [0001] The invention relates to the field of mobile application data analysis, in particular to a method for predicting the usage of mobile applications based on a time sequence mode. Background technique [0002] With the rapid development of wireless communication and mobile technology, smart phones have become an important tool for people to communicate and communicate with each other in daily life. Existing research shows that the number of apps installed on users' smart phones ranges from 10 to 90, or even more than 90, with an average of about 50. This huge number makes it not easy to find a specific APP on a smartphone. The prediction of the use of mobile apps refers to the prediction of the next most likely to be used. When the user uses a smart phone, the user’s operation becomes very simple and efficient, and the battery energy consumption and application search time can also be planned in advance. optimization. Due to the many factors involved in for...

AI Technical Summary

Problems solved by technology

Because there are many factors involved in the prediction, the prediction method is complex and uncertain, and the error of the prediction result is relatively large.

At present, there is no effective forecasting method

Images