Traffic stealing account identification method and device

Abstract

The embodiment of the invention discloses a traffic stealing account identification method and device. The method comprises the steps that the traffic stealing phenomenon is partitioned into a plurality of scenes according to the traffic characteristics of the traffic stealing phenomenon; traffic data of each scene is subjected to corresponding analysis, and suspected accounts which have the traffic stealing phenomenon are identified; the traffic stealing possibilities of the various suspected accounts are calculated according to the traffic values, the bandwidth values, the counting times andthe traffic characteristics of the various suspected accounts; and the target account which has the traffic stealing phenomenon is screened out according to a possibility threshold and the traffic stealing possibilities of the various suspected accounts. According to the traffic stealing account identification method and device, scene partitioning is conducted by analyzing the traffic characteristics, the suspected accounts are identified according to the different scenes, the analysis range of traffic stealing data is narrowed, the target account stealing the traffic is quickly positioned and discovered by means of cooperation of an identification rule, the traffic stealing account is automatically identified in advance, the processing efficiency is high, and the user complaint possibility is decreased.

Description

technical field [0001] The embodiments of the present invention relate to the field of communication technologies, and in particular to a method and device for identifying stolen traffic accounts. Background technique [0002] The access rate of the mobile communication 4G network is improved, and the throughput performance is improved. When the user is using, some special circumstances may cause the user to generate a high amount of Internet traffic in a short period of time without the user's knowledge, causing the user to complain. [0003] In the prior art, passive analysis and active analysis are mainly used to deal with the analysis of sneak traffic phenomena. Passive analysis mainly analyzes user complaints, collects relevant user complaints through the customer service system, and analyzes the behavior of stealing traffic, specifically including: extracting similar user complaints from the customer service system; The occurrence of relevant traffic billing; submit ...

AI Technical Summary

Problems solved by technology

[0005] Due to the fact that the existing method handles the whole process manually, it cannot be discovered in advance, and it can only confirm the events that have occurred, lack of clear classification and judgment rules, lack of screening of suspected accounts, and low processing efficiency. The embodiment of the present invention proposes a Sneak traffic account identification method and device

Images