Event risk prevention and control method, device and equipment

Abstract

The embodiment of the invention discloses an event risk prevention and control method, device and equipment, and the method comprises the steps: obtaining to-be-processed event data of a target event, then determining a risk detection result corresponding to a first risk control model based on the event data and the first risk control model corresponding to the target event, and obtaining a risk detection result corresponding to the first risk control model; the first risk control model is a model constructed by a risk control strategy corresponding to the target event, and finally, initial risk information corresponding to the event data can be determined based on a risk detection result corresponding to the first risk control model. And inputting initial risk information corresponding to the event data and the event data into a second risk control model corresponding to the target event to obtain risk information corresponding to the event data, the second risk control model being a model obtained by performing model training through an event data sample corresponding to the target event.

Description

technical field [0001] This document relates to the field of computer technology, in particular to a method, device and equipment for event risk prevention and control. Background technique [0002] With the continuous development of network technology, handling certain businesses through the network has become an important way of current business handling. Carry out risk prevention and control to avoid user information leakage and even resource loss. [0003] In the risk prevention and control system, risk prevention and control can usually be achieved through risk control strategies and risk control models. However, in the case of the risk control model, the risk control model depends on the training samples. The training samples cannot obtain their real label information. Therefore, during model training, the above training samples will be removed, which will cause the data distribution of the remaining training samples after removal to be the same as the actual data or ...

AI Technical Summary

Problems solved by technology

[0003] In the risk prevention and control system, the risk prevention and control process can usually be realized through risk control strategies and risk control models. However, for the case of the risk control model, the risk control model depends on the training samples. The training samples cannot obtain their real label information. Therefore, during the model training, the above-mentioned training samples will be removed. In this way, the data distribution of the remaining training samples after removal is different from the actual data or the data distribution of the training samples before removal. Inconsistent, and the training samples that are eliminated are often training samples with a high probability of risk, resulting in bias in the training samples for training the risk control model. In addition, the number of positive samples in the above training samples is often relatively small, so that Makes the risk control model difficult to train

In the case of risk control strategies, risk control strategies are the embodiment of the knowledge and experience of risk control experts. Risk control strategies often have low coverage, but their accuracy is high. A risk prevention and control plan with higher control accuracy

Images