Account risk evaluation method based on relational network

Abstract

The invention provides an account risk evaluation method based on a relational network. The method comprises the following steps: S1, recognizing a high-risk device with an abnormal user according to the device model, the number of times of device registration, and whether the number of device login accounts is too many, and obtaining a device recognition result; s2, the behavior similarity between the accounts is calculated based on the relation network, and a behavior similarity result is obtained; s3, performing error analysis on the behavior similarity according to a preset risk adjustment threshold, and obtaining a similarity analysis result; and S4, evaluating the account risk according to the equipment recognition result and the similarity analysis result. The account risk evaluation method based on the relational network provided by the invention has the advantages that the account risk can be assessed through the equipment risk recognition result and the account behavior similarity analysis result, so that a more accurate recognition result is obtained, and misjudgment is avoided.

Description

technical field [0001] The invention relates to the technical field of account risk assessment of a relationship network, in particular to an account risk assessment method based on a relationship network. Background technique [0002] Risk assessment refers to the work of quantitatively assessing the impact of the event on people's lives, lives, property and other aspects and the possibility of loss before or after the occurrence of a risk event (but not yet over), that is, risk assessment is Quantitative evaluation of the possible degree of impact or loss caused by an event or thing. From the perspective of information security, risk assessment is the threat and existence of information assets (that is, the information set of an event or thing). Weaknesses, impacts, and the assessment of the possibility of risks brought about by the combined effects of the three are the basis of risk management. Risk assessment is an important way for organizations to determine information...

AI Technical Summary

Problems solved by technology

[0003] But at present, attacks often occur in unnoticed scenes. Real-time identification can realize all-dimensional judgments in one scene. There is no so-called process adaptation. We only understand the occurrence of abnormalities and cannot understand the attack targets of black products. Stacking cannot create a good business security system. In addition, security personnel will encounter many "non-technical" problems, such as: consuming manpower to write rules, updating cannot keep up with the pace of cracking, and not being able to deal with suspicious data, always worrying Mis-sealed, unable to convince operators to believe in the authenticity of data and other issues

Images