Credit big data-oriented risk control method and credit big data-oriented risk control system

Abstract

The invention discloses a credit big data-oriented risk control method and a credit big data-oriented risk control system. The credit big data-oriented risk control method comprises the following steps of: finishing data acquisition by terminal equipment, finishing data fusion and cleaning by a server, labeling an attribute label and a main body label and the like to realize data preprocessing; designing a risk control module for native data acquired by the trusted terminal, and dividing the data into different sensitivity levels by performing tagging processing and sensitivity division on thedata to realize first-level risk control; for the initial credit problem of a user of the data storage platform, evaluating the initial credibility and authority of a data visitor by analyzing a mainbody label in the native data, so as to achieve the purpose of secondary risk control; and finally, for the problem that the system and the storage platform need to monitor data visitor behaviors inreal time, dynamically defining the trust degree of the subject according to the visitor behaviors so as to complete three-level risk control for credit big data.

Description

technical field [0001] The invention belongs to the field of security technology, and in particular relates to a credit big data-oriented risk control method and a system thereof. Background technique [0002] With the continuous development of Internet technology, the importance of data credibility issues has gradually become more prominent, and the private information contained in credit big data is also increasing day by day. Due to the wide variety of credit big data and multi-source heterogeneity, the effect of credit big data risk control methods is often unsatisfactory. Therefore, how to design a risk assessment method with high security, reliability and systematic important. [0003] Generally speaking, the reasons for the low risk control effect of credit big data can be roughly divided into the following three aspects: First, because the credit data collected by different terminals is multi-source heterogeneous data, the amount of information is large but the qual...

AI Technical Summary

Problems solved by technology

[0003] Generally speaking, the reasons for the low risk control effect of credit big data can be roughly divided into the following three aspects: First, because the credit data collected by different terminals is multi-source heterogeneous data, the amount of information is large but the quality is not good, which may lead to The validity of the obtained credit data is not high, and it cannot well meet the data requirements of risk control; secondly, the existing risk control system generally has partial control phenomena, which is not systematic, and cannot predict and control risks from an overall perspective ;Finally, due to the malicious falsification of the collected data visitors' data, these data will lead to inaccurate measurement of trust, resulting in non-standard setting of access rights, which will seriously affect the effect of credit big data risk control

Images