Risk user identification method and device, storage medium and server

Abstract

The invention relates to the technical field of computers, and provides a risk user identification method and device, a storage medium and a server. According to the risk user identification method, before the credit face examination, a certain specific multimedia file is played for a user, and a face image generated when the user appreciates the multimedia file is collected; after the multimediafile is played completely, a first micro-expression feature is identified from the collected face image; then, the first micro-expression feature is compared with a pre-stored reference micro-expression feature, and whether the user is a potential risk user or not is judged according to a comparison result; after the face examination is finished, a second micro-expression feature is identified from the face image collected in the face examination process; and finally, according to whether the user is a potential risk user, different micro-expression fraud recognition models are respectively selected to carry out risk recognition. By adopting the risk user identification method provided by the invention, the risk user identification accuracy can be improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a risk user identification method, device, storage medium and server. Background technique [0002] During the face-to-face review process of credit approval, credit companies will ask various questions for users to answer, and collect facial images of users when answering questions, detect micro-expressions generated in facial images, and input the detected micro-expressions into pre-built The micro-expression fraud detection model to determine whether the user is lying. [0003] However, some illegal users will prepare lies before the interview, and the micro-expression produced when answering questions in the interview is slightly different from that of normal users. At this time, the model may not be able to recognize the small difference, such as a specific expression Although the number of occurrences is high, it has not yet reached the risk judgment threshold. A...

AI Technical Summary

Problems solved by technology

[0003] However, some illegal users will prepare lies before the interview, and the micro-expression produced when answering questions in the interview is slightly different from that of normal users. At this time, the model may not be able to recognize the small difference, such as a specific expression Although the number of occurrences is high, it has not yet reached the risk judgment threshold. At this time, the model will make a wrong judgment and there is a risk

Images