Forecasting model building, pre-loading method of application program, device, medium and terminal

Abstract

The embodiment of the application discloses a forecasting model building and pre-loading method of an application program, a device, a medium and a terminal. The forecasting model building method of the application program includes steps of acquiring a user behavior sample in a preset time section, wherein the user behavior sample comprises use time sequence association records of two applicationprograms; extracting state information of the corresponding terminal of the use time sequence association records of the application programs; training a set forecasting model according to the use time sequence association records and the state information, and generating the forecasting model of the application program. Through adopting the technical scheme, the use time sequence association records of the application programs and corresponding terminal state information can be really reflected through sufficient use, the pre-loading mechanism of the application program is optimized, and theforecasting accuracy of the application program to be started is effectively improved; moreover, the power consumption and the memory share rate of the terminal system are further reduced.

Description

technical field [0001] The embodiments of the present application relate to the technical field of machine learning, and in particular, relate to application program prediction model building, preloading methods, devices, media, and terminals. Background technique [0002] With the rapid development of electronic technology and the improvement of people's living standards, terminals such as smart phones and tablet computers have become an indispensable part of people's lives. [0003] Various applications (Application Software, APP) are set on the terminal. In order to make the application run more smoothly, the terminal usually prepares the loading resources of some applications in advance, that is, advances the loading resources of some applications. to preload. [0004] However, the application cannot be preloaded at will, because if too many resources are preloaded, too much memory will be occupied, and the power consumption will increase, which will seriously affect th...

AI Technical Summary

Problems solved by technology

[0004] However, the application cannot be preloaded at will, because if too many resources are preloaded, it will occupy too much memory, and at the same time, the power consumption will increase, which will seriously affect the smoothness of terminal use.

Images