User request detection method and device, computer device and storage medium

Abstract

The embodiment of the invention discloses a user request detection method and device, a computer device and a storage medium, and the method comprises the following steps of obtaining a user request sent by a terminal, the user request comprising terminal equipment data; inputting the equipment data into a plurality of anomaly detection models to obtain a plurality of detection results for judgingwhether the user request is abnormal or not, the anomaly detection models being detection models which are trained to a convergence state by adopting a sample feature set in advance and are used forcarrying out security classification on the terminal through the feature set; and judging the detection result by adopting a preset judgment method so as to determine whether the user request is abnormal or not. The method is simple in judgment method, can identify the diversified abnormal scenes, and can cover more and more complex conditions along with increase of the sample size. In addition, adetection result can be obtained more comprehensively, and the accuracy of anomaly detection is improved.

Description

technical field [0001] The embodiments of the present invention relate to the field of network technology, in particular, a method, device, computer equipment, and storage medium for detecting user requests. Background technique [0002] With the development of Internet technology, the role of the network in people's work, life, and study is becoming more and more important. With the increase of network users, in order to ensure the security of network data, it is necessary to detect user behavior to determine whether it is true user actions. [0003] At present, there are two judgment methods, one is to detect crawlers based on request frequency and request data, and block IP, increase verification, etc. Anti-crawler technical methods; the other is based on user verification code track data, click time, etc. Identify the authenticity of the user. [0004] But both methods have certain problems. Among them, in the solution for crawler detection, it is usually judged wheth...

AI Technical Summary

Problems solved by technology

Crawler developers can develop targeted directional crawlers according to the anti-crawler strategy of the target website, so the security maintenance of the website is more complicated, and the anti-crawler strategy must be updated in real time

For the abnormal user detection method of the verification code, the data such as the click time and the mouse dragging track during the user verification process are collected, and the user type is judged based on this behavior data. This kind of method has a high error rate, and it is easy to distinguish real users as abnormal users. Affect the user experience

And due to the continuous improvement of technical means, automated tools such as button sprites can effectively imitate real user behaviors. Effective classification features need to be mined from behavior data to establish a good detection model. The method is too complicated

Images