Risk identification method and system

Abstract

The embodiment of the invention discloses a risk identification method and system, which relates to a risk analysis scheme in online-offline combined scenarios in the field of Internet technologies. The risk identification method comprises the steps of receiving a risk identification request message, determining a user terminal to be detected according to the risk identification request message, and obtaining behavior data of the corresponding user terminal; requesting the acquisition of an algorithm model from an algorithm system according to the behavior data, and requesting the taking of risk feature data matched with the algorithm model from a risk feature library according to the acquired algorithm model; performing risk analysis on the behavior data of the corresponding user terminalaccording to the algorithm model and the risk feature data matched with the algorithm model; and sending the risk analysis result to a service system. The risk identification method and system are applicable to risk identification in online and offline scenarios.

Description

technical field [0001] The present invention relates to the field of Internet technologies, in particular to a risk identification method and system. Background technique [0002] With the application and development of Internet technology, especially the development of mobile Internet technology, hundreds of millions of users use Internet applications in real time every day, and how to ensure the security of various network applications in the process of using them and the risk of users' network behavior control, known as a problem in urgent need of research. [0003] The currently adopted scheme is mainly to accumulate the network behavior data of a large number of users over a period of time to form black samples (such as abnormal network behavior data such as fraud and embezzlement) and white samples (that is, normal network behavior data); and The risk identification model is regularly updated based on black / white samples, and the risk identification of network behavio...

AI Technical Summary

Problems solved by technology

[0004] However, this method requires regular maintenance of the risk identification model. Since the latitude of the rules is relatively single, it can only identify some major risk behaviors. For some special or sudden network behaviors, such as the combination of online and offline scenarios , such as shopping in offline stores through online payment tools, there is a lack of appropriate risk analysis solutions, and misjudgments often occur

Images