Abnormal object identification method and device

Abstract

The embodiment of the invention provides an abnormal object recognition method and device, and the method comprises the steps: obtaining an object sample which comprises a sample object and an abnormal object feature corresponding to the sample object; according to the sample object and the abnormal object features, determining a first verification function and a sample frequency of the first verification function meeting a preset condition; determining an identification association object corresponding to a to-be-identified object, and determining an actual frequency and a critical frequency of the to-be-identified object according to the identification association object and the sample frequency; and according to the actual frequency and the critical frequency, performing anomaly identification on the to-be-identified object. Specifically, the abnormal object recognition method performs abnormal recognition on the to-be-recognized object by performing statistical analysis on the frequency of occurrence of abnormal object features under the same to-be-recognized object, so that the false alarm rate is reduced while the hit rate of the abnormal object is improved.

Description

technical field [0001] The embodiments of this specification relate to the field of computer technologies, and in particular, to an exception object method. Background technique [0002] Network black and gray production is one of the major problems that endanger the ecological security of the Internet. In the black and gray production team, there are often some common features (such as equipment and account mismatch) or common resources (such as using the same device). However, these characteristics The aggregation of these resources may exist in normal users or abnormal users. If these common features or common resources are used to make abnormal judgments, it will lead to great false positives. [0003] Therefore, how to improve the identification of abnormal users while reducing the false alarm rate is a technical problem that needs to be solved. SUMMARY OF THE INVENTION [0004] In view of this, the embodiments of the present specification provide a method for identi...

AI Technical Summary

Problems solved by technology

[0002] Network black and gray production is one of the major problems that endanger the ecological security of the Internet. In the black and gray production team, there are often some common characteristics (such as equipment and account mismatch) or shared resources (such as using the same device), but these characteristics The aggregation of these resources may exist in normal users or in abnormal users. If these common characteristics or common resources are used to make abnormal judgments, it will lead to great false positives

Images