Micro-expression recognition financial risk control method and system

Abstract

The invention relates to a micro-expression recognition financial risk control method. The method comprises: obtaining and preprocessing image frames of a video; detecting the preprocessed image frameto obtain a micro-expression frame sequence in the image frame; extracting the detected micro-expression frame sequence to obtain micro-expression features; inputting the obtained micro-expression features into a trained convolutional neural network for classification; and performing psychological analysis on a classification result of the convolutional neural network, and estimating a fraud riskvalue. The invention further relates to a micro-expression recognition financial risk control system. According to the method, the potential fraud risk of the lending user is judged in a mode of combining micro-expression recognition and psychology, a more accurate financial fraud recognition method can be provided for a cash lending company, and the economic loss of the cash lending company is reduced.

Description

technical field [0001] The invention relates to a financial risk control method and system for micro-expression recognition. Background technique [0002] Cash loan, short for small cash loan business, is a consumer loan business that distributes money to applicants. Since 2015, cash loan, as an important branch of consumer finance, has begun to rise in China. The main characteristics of cash loans are: small amount, short cycle, no collateral, fast process, and high interest rate. The review process is: real-name authentication, filling in personal information, selecting the pre-loan amount and term, company review, and lending. However, it is precisely because of the rapid development of cash loans and the immature legal system that the cash loan market is relatively chaotic, and problems such as fraudulent loans, maintenance of cards, and overdue repayments emerge in endlessly. In fact, the risks arising from cash loans are mainly borne by the cash loan company, and th...

AI Technical Summary

Problems solved by technology

[0007] The disadvantages of the HOG algorithm are: First, due to the nature of the gradient, HOG is quite sensitive to noise: in actual use, the light can easily cause a certain point to produce an exposure effect, and HOG is extremely sensitive to such a point, which can easily lead to poor results ; Second, the HOG generation process is lengthy, resulting in slow speed and poor real-time performance

[0008] The disadvantages of the SVM algorithm are: First, the SVM algorithm is difficult to apply to large-scale training samples: because SVM solves the support vector by means of quadratic programming, and solving the quadratic programming will involve the calculation of the m-order matrix (m is the number of samples) , when the number of m is very large, the storage and calculation of the matrix will consume a lot of machine memory and computing time; second, there are difficulties in solving multi-classification problems with SVM: the classic SVM algorithm only gives a binary classification algorithm, and In the application scenario of cash loan micro-expression classification, it is necessary to solve the multi-classification problem. At this time, it must be solved by combining multiple binary classification SVMs, which will also consume a relatively long calculation time.

Images