A method, device and storage medium for identifying malicious users

Abstract

Embodiments of the present invention provide a method, device, and storage medium for identifying malicious users. The method includes: obtaining a training sample set, the training sample set includes features of the training samples and labels corresponding to the training samples, and the training samples correspond to The label is used to identify whether the user is a malicious user; determine the optimal segmentation feature and segmentation threshold from the training sample set; split the training sample set to obtain the first sample set and the second sample set, and the first sample set The average value of each feature in the set and the second sample set is used as the target output value; judge whether the user is a malicious user according to the target output value; judge the label corresponding to the training sample of the malicious user in the first sample set and the second sample set Set as a malicious user, and set the label corresponding to the training sample judged to be a non-malicious user as a non-malicious user. By adopting this scheme, the user's behavior characteristics can be accurately analyzed, and malicious users can be identified according to the behavior characteristics.

Description

technical field [0001] The present invention relates to the technical field of software, in particular to a method, device and storage medium for identifying malicious users. Background technique [0002] During the development of the live broadcast platform, in order to achieve private purposes, some black production groups often register many platform accounts in batches, and use these accounts for malicious activities such as commenting, barrage, and popularity, in an attempt to increase the popularity of a certain live broadcast room. It makes the resources of the entire live broadcast platform unequal and profits from it. The live broadcast platform needs to ban the users of these malicious accounts. However, it is difficult to directly mine the behavior of malicious accounts from massive data. It is a feasible idea to use algorithms to mine malicious users. [0003] Since malicious users operate in batches of illegal products, their behaviors and actions often have c...

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a method, device, and storage medium for identifying malicious users, which are used to solve the problem of low accuracy in mining malicious users in existing mechanisms

Images