RISK IDENTIFICATION METHOD AND APPARATUS BASED ON MULTIPLE CLASSIFIERS, COMPUTER DEVICE, AND STORAGE MEDIUM

摘要

A risk identification method and apparatus based on multiple classifiers, a computer device, and a storage medium, relating to the technical field of intelligent decision making. The method comprises: if an item handling instruction sent by a client is detected, acquiring user video data (S110); acquiring user identity information corresponding to the user video data to determine whether the user identity information passes user identity verification (S120); if yes, acquiring current video data in a current item handling process (S130); extracting emotion information in the current video data, and extracting content information in the current video data (S140); invoking a prebuilt combined classifier consisting of a plurality of nonlinear classifiers and linear classifiers (S150); inputting the emotion information and the content information of the current video data into the combined classifier to obtain a corresponding user risk category (S160); determining whether the user risk category corresponding to the current video data is a high risk category (S170); and if yes, terminating the connection with the client and giving a prompt of terminating item handling (S180). The method achieves the determination of the user risk category of the user video data based on the combined classifier, and improves the identification accuracy.