Key information push method and device based on user behavior data

Abstract

The present invention discloses a key information push method, device, computer equipment and storage medium based on user behavior data, relates to artificial intelligence technology, divides user behavior data sets into fine-grained groups at least three times to obtain multiple second classification result subsets , using it as a data sample to train multiple prediction sub-models, if the current user behavior data uploaded by the client is received, the corresponding target user behavior data, and the corresponding target second classification result subset and target second classification result sub-set are obtained Set the target prediction sub-model corresponding to the set, input the current user behavior data into the target prediction sub-model for calculation, obtain the corresponding current prediction result, obtain the target filtered field factor set corresponding to the second classification result subset of the target, and send it to the corresponding client. It is realized to obtain a prediction model that better matches the current user behavior data, and the obtained prediction result is more accurate, and the data pushed to the client is more accurate.

Description

technical field [0001] The present invention relates to the technical field of intelligent decision-making of artificial intelligence, in particular to a key information push method, device, computer equipment and storage medium based on user behavior data. Background technique [0002] At present, in the field of information recommendation distribution, more and more information recommendation algorithms have emerged. For example, a common information recommendation method is to first obtain the user tags of the target users, and then filter the target data corresponding to the user tags in the database, and then push the target data to the target users. The information recommendation algorithm in the prior art is suitable for scenarios where user tags are easy to obtain. Once the user's user tags are difficult to obtain, data recommendation cannot be performed. [0003] For example, after collecting a large amount of user behavior data and user attribute data, the accurac...

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a method, device, computer equipment, and storage medium for pushing key information based on user behavior data, aiming to solve the problem of Due to the large number of dimensions, the accuracy of obtaining user tags is low, and the efficiency is low, and it is impossible to recommend target data to users more accurately.

Images