Method and device for determining risk behavior generation model

Abstract

One or more embodiments of the invention provide a risk behavior generation model determination method and device, and the method comprises the steps: carrying out the dimension division of the real behavior data of a historical user according to a plurality of preset information dimensions; utilizing a generator in the target adversarial neural network to automatically generate a plurality of simulation sample data based on the real sample data obtained by dimension division, and utilizing a discriminator in the target adversarial neural network to perform risk identification on the simulation sample data and the real sample data; according to risk identification result, judging whether the sample generation level of the generator and the sample discrimination level of the discriminator meet a preset adversarial termination condition or not; and if so, determining the final generator as a risk behavior generation model so as to update the online risk control strategy based on the riskbehavior data generated by the risk behavior generation model, and performing risk prevention and control on the behavior data of the online user based on the updated risk control strategy.

Description

technical field [0001] This document relates to the field of computer technology, in particular to a method and device for determining a risk behavior generation model. Background technique [0002] At present, with the rapid development of Internet technology, there are more and more application scenarios for online transactions. Among them, while online transactions bring convenience to users, there are also certain asset security issues. For example, criminals use certain Criminal methods to defraud users of funds pose a great threat to the asset security of normal users. Correspondingly, it is necessary to pre-set a risk control system that includes risk prevention and control strategies to deal with crimes to realize online user behavior data. Carry out risk identification, and then carry out risk management and control on online risk behaviors, so as to improve the security of users' assets. [0003] At present, the update and supplementary process of the risk control...

AI Technical Summary

Problems solved by technology

[0003] At present, the update and supplementary process of the risk control strategy used to identify risky behaviors in the risk control system in related technologies is mainly that the relevant risk control experts investigate the criminal methods of black industry, and then improve the risk control strategy based on their own experience; , due to the fact that it takes some time to investigate the criminal methods of black industry, the risk control strategy has a certain lag. At the same time, criminal users are constantly changing criminal methods. , Accurately predict the criminal methods that black industry may adopt in the future, and then cannot provide a matching risk control strategy in time to quickly and accurately respond to the changed criminal methods

Images