Real-time fraud detection method and device based on complex network and electronic equipment

Abstract

The embodiment of the invention provides a real-time fraud detection method and device based on a complex network, and electronic equipment. A large-scale image storage database is created based on user data; based on a large-scale image storage database and a preset scoring model, a multi-hop query mechanism is adopted and information is associated with fraud characteristics, user fraud detectionis carried out, the problem that data is too much, the model operation is slow and detection efficiency is low is solved, real-time anti-fraud detection is realized; real-time defense is realized, the fraud detection efficiency is improved; a single-entity knowledge graph network and a multi-entity knowledge graph network are constructed based on a large-scale graph storage database; based on a single-entity knowledge graph network and a multi-entity knowledge graph network, a graph propagation algorithm is adopted, and community mining is performed according to information with fraud characteristics, so that the fraud gang identification range is quickly expanded, fraud gangs are deeply mined, and the fraud detection efficiency is improved.

Description

Technical field [0001] This application relates to the field of information processing technology, in particular to a real-time fraud detection method, device and electronic equipment based on a complex network. Background technique [0002] With the rapid development of network technology, network fraud has gradually emerged. Scammers with security risks such as black production and black intermediaries have evolved from a single individual behavior to a well-organized black industry chain. Fraud groups use illegal means to arbitrage and disrupt Internet information security. In order to improve the security of network information, fraud gangs need to be dealt with in a timely manner. [0003] The traditional method of processing is mainly to construct a dimensional knowledge graph to check the information associated with it. In the event of fraud, passive defense and remedial processing are performed based on the individual characteristics of the current dimension. This processi...

AI Technical Summary

Problems solved by technology

[0003] The traditional processing method is mainly to build a dimensional knowledge map to check the information associated with it. When fraudulent, passive defense and remedial processing are carried out based on the individual characteristics of the current dimension. This processing method is very easy to be discovered by fraud gangs, and Bypassing the fraud detection system by updating dimension values, etc., there is a lack of early risk assessment, and it is impossible to predict the risk in advance before the fraud occurs, and it is impossible to dig deep into fraudulent gangs, and it is impossible to detect and defend in real time, and the detection efficiency is low.

In addition, when there is too much data, the model operation is slow, resulting in low detection efficiency

In short, the traditional processing methods have limited data and identification capabilities, and cannot quickly identify potential fraudulent gangs with strong camouflage, and cannot effectively monitor and process risks

Images