Information recommendation method, device, electronic device, and computer-readable storage medium

Abstract

An embodiment of the present invention provides an information recommendation method, device, electronic equipment, and computer-readable storage medium. The method includes: extracting behavior characteristic information of current behavior information; obtaining hidden layer characteristics at the current moment according to the behavior characteristic information at the current moment Information, and cached in the cache module; according to the behavioral feature information at the current moment and the historical feature information stored in the storage module, determine the information to be recommended at the next moment; when the number of hidden layer feature information cached in the cache module is equal to When the value is preset, information is updated for each storage area based on the preset number of hidden layer feature information corresponding to each storage area and corresponding to the time sequence of the information stored in each storage area. In this solution, the hidden layer feature information is cached in the cache module, and the historical feature information in the storage module is only updated once when the number of cached hidden layer feature information is equal to a preset value, which can improve data processing efficiency.

Description

technical field [0001] The present invention relates to the technical field of information processing, in particular, the present invention relates to an information recommendation method, device, electronic equipment and computer-readable storage medium. Background technique [0002] In the existing information recommendation method, it is usually based on the current behavior information of the user at the current moment and the historical behavior information of a period of time before the current moment to predict the information recommended to the user at the next moment, and then update the information based on the current behavior information. The historical information before the current moment is based on the method in the prior art. Every time the behavior information of the user is obtained, the historical information before the corresponding moment will be updated based on the behavior information at each moment. The amount of information is limited, which may no...

AI Technical Summary

Problems solved by technology

[0002] In the existing information recommendation method, it is usually based on the current behavior information of the user at the current moment and the historical behavior information of a period of time before the current moment to predict the information recommended to the user at the next moment, and then update the information based on the current behavior information. The historical information before the current moment is based on the method in the prior art. Every time the behavior information of the user is obtained, the historical information before the corresponding moment will be updated based on the behavior information at each moment. The amount of information is limited, which may not accurately reflect changes in user interests. Therefore, if the corresponding historical information is updated every moment, the number of updates will be frequent and the efficiency of data processing will be reduced.

Images