Loan verification method, apparatus, device and medium based on microexpression recognition

Abstract

The invention discloses a loan verification method, apparatus, device and a medium based on micro-expression recognition, comprising the following steps: obtaining a loan request, wherein the loan request comprises a user identification; Acquiring user social information corresponding to the user identification from a big data platform based on the user identification; Based on the social information of the user, according to a preset selection rule ,selecting a true-hearted topic from a true-hearted topic bank; At that same time, starting a camera to shoot the user to obtain the monitor videostream; Calling a pre-created micro-expression recognition model to detect the surveillance video stream and obtain the user sincerity; If the user sincerity degree is greater than a preset sinceritydegree threshold, obtaining the approval result of the loan approval, searching a preset comparison table according to the user sincerity degree, and obtaining a loan amount corresponding to the usersincerity degree. This method does not need manual intervention, can achieve the purpose of intelligent audit and improve the efficiency of loan audit.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a loan review method, device, equipment and medium based on micro-expression recognition. Background technique [0002] The current loan review requires face-to-face communication between the credit reviewer and the lender, and the credit reviewer judges the sincerity of the user during the communication process. The process consumes high labor costs and the review efficiency is low, and the sincerity judgment mainly relies Due to the experience and subjective judgment of the credit reviewer, the result of the credit review is relatively subject to the subjective influence of the credit reviewer, which is not objective enough, so that when the loan review is carried out based on the credit review result, the risk of lending is relatively high. For example, in the process of face-to-face communication, the credit examiner may easily ignore the subtle expression chang...

AI Technical Summary

Problems solved by technology

[0003] Embodiments of the present invention provide a loan review method, device, computer equipment, and storage medium based on micro-expression recognition, so as to solve the problems of high labor cost, low efficiency, and lack of objectivity in current manual loan review.

Images