Behavior data pushing method and device, computer device and storage medium

Abstract

The invention relates to a behavior data pushing method and device based on biological recognition, a computer device and a storage medium. The method comprises the following steps of obtaining multiple frames of face images uploaded by a user terminal, wherein the multiple frames of face images carry a user identifier; identifying a face image according to the plurality of frames of face images,and extracting face features corresponding to the face image; obtaining a preset expression classifier, and classifying the face features through the expression classifier to obtain a corresponding expression category; obtaining corresponding historical behavior data according to the user identifier; obtaining a preset analysis model, analyzing the expression category and the historical behavior data through the analysis model to obtain an analysis result, and the analysis result comprises a behavior label matched with the current expression of the user and the historical behavior habit of theuser; obtaining corresponding behavior data according to the behavior label; and pushing the behavior data to the user terminal. By adopting the method, pushing can be carried out according to user expressions and preferences, and the pushing accuracy of the behavior data is effectively improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a biometric-based behavioral data push method, device, computer equipment and storage medium. Background technique [0002] With the rapid development of artificial intelligence technology, human-computer interaction technology has gradually matured and been applied in various fields. The human face can convey information, and some emotional information of the user can be obtained through the facial expressions of the human face. Expression recognition of facial images has a wide range of applications in real life, including emotional robots, intelligent monitoring, and psychological research-assisted treatment. [0003] At present, there are some ways to push relevant music and other data by recognizing facial expressions of users. Because micro-expressions have the characteristics of low action intensity and fast action behavior, it is difficult to recognize facial...

AI Technical Summary

Problems solved by technology

[0003] At present, there are some ways to push relevant music and other data by recognizing facial expressions of users. Because micro-expressions have the characteristics of low action intensity and fast action behavior, it is difficult to recognize facial expressions.

In the traditional way of pushing data through a single facial expression recognition, the pushed data may not match the user's preferences, resulting in a low accuracy rate of data pushing

Images