Malicious registration detection method, device, computer readable medium and electronic device

Abstract

The disclosure provides a malicious registration detection method, device, computer readable medium and electronic equipment, and relates to the technical field. The method includes: obtaining the account number and network environment information in the registration request of the target user, and simultaneously obtaining account characteristic information corresponding to the account and behavior information corresponding to the registration request, the behavior information being the submission frequency of the registration request ; Comparing the behavior information with a preset frequency threshold, and determining a first risk result according to the comparison result; processing the account feature information and the network environment information through a risk model to obtain a second risk result; The first risk result and the second risk result determine a risk value corresponding to the registration request, and judge whether the registration request is a malicious registration according to the risk value. The disclosure can improve the efficiency and accuracy of malicious registration detection, and has high scalability.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, in particular, to a malicious registration detection method, a malicious registration detection device, a computer-readable medium, and an electronic device. Background technique [0002] With the development of e-commerce, more and more users are getting used to online shopping, online reading, online making friends and so on. At present, most Internet-based services require users to register accounts to ensure that users can use the functions of the platform normally. However, there are unavoidable behaviors of gray and black products registering and using malicious accounts, which seriously disrupt the order of the platform and cause serious damage to Internet services. Huge destruction. [0003] At present, the method of identifying malicious registration behaviors is mainly to use user behaviors to conduct audits and to conduct policy optimization and logic optimiza...

AI Technical Summary

Problems solved by technology

At present, most Internet-based services require users to register accounts to ensure that users can use the functions of the platform normally. However, there are unavoidable behaviors of gray and black products registering and using malicious accounts, which seriously disrupt the order of the platform and cause serious damage to Internet services. huge destruction

[0003] At present, the method of identifying malicious registration behaviors is mainly to use user behaviors to conduct audits and to conduct policy optimization and logic optimization based on data judgments. Correspondingly, there will be the following problems. First, user behaviors can only be obtained after malicious behaviors occur. , so due to the post-event audit, it will be impossible to resist the malicious behavior of cheating users beforehand. Secondly, the strategy optimization and logic optimization based on data judgment is an independent business audit mode, and thus it is impossible to comprehensively monitor cheating users.

Images