Abnormal traffic data identification method and device, medium, and electronic equipment

Abstract

The invention relates to the field of information security, and discloses an abnormal traffic data identification method and device, a medium, and electronic equipment. The method comprises the following steps: for a sample set comprising a plurality of traffic data samples, according to independent variables and corresponding dependent variables of the traffic data samples in the sample set, carrying out fitting through a logistic function to obtain a function which is used to obtain the dependent variables from the independent variables; determining weights corresponding to abnormal trafficidentification indicators based on the function obtained through the fitting; determining the weighted sum of abnormal traffic identification indicator values of a candidate negative traffic data sample based on the weights; and if the weighted sum is larger than a weighted sum threshold, identifying the candidate negative traffic data sample as abnormal traffic data. The method disclosed by the invention has the advantages that different importance degrees of the multiple abnormal traffic identification indicators in an abnormal traffic data identification process are fully considered, so that intrusions can be prevented based on network security, and the abnormal traffic identification accuracy can be improved.

Description

technical field [0001] The invention relates to the field of information communication, in particular to a method, device, medium and electronic equipment for identifying abnormal flow data. Background technique [0002] After mankind entered the Internet era, especially the mobile Internet era, with the help of capital, the cost of acquiring customers for Internet companies has increased significantly, and competition has intensified. In the era when traffic is king, Internet companies often adopt promotional methods such as issuing coupons and deducting red envelopes in order to acquire more users. However, these preferential benefits may be exploited by some speculators or illegal industry practitioners by using rule loopholes or technical means "Sweeping wool" not only failed to achieve the promotion effect, but caused losses to related Internet companies. A typical feature of Internet companies being "squeezed" is that there is a large amount of abnormal traffic access...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the technical problem of low accuracy in identifying abnormal flow data existing in related techno

Images