Method for identifying malicious users according to negative comments of users

Abstract

The invention discloses a method for identifying the malicious users according to the negative comments of the users. The method comprises the following steps of S1, acquiring the order information of a user in a historical time period; S2, collecting the evaluation information of the user in the historical time period; S3, updating a sensitive word bank in real time and analyzing the negative comment information; S4, judging the risk level of the user by combining the order and the negative comment information; and S5, classifying different users. By utilizing the negative comment records in the specified historical time period of the user and combining the user order dimension attributes to formulate a negative comment risk user level, the blacklist management is carried out on the high-risk risk users; by marking a medium-risk user as a risk, and waiting for the manual checking processing, the low-risk user is not processed and is filtered automatically; meanwhile, in combination with the sensitive word bank, the word bank has the characteristic of dynamic updating, the word segmentation is conducted on the user negative comment data through a word segmentation device, and the weighted calculation is conducted on the user risks through the sensitive words, so that the high-risk user recognition rate is effectively increased.

Description

technical field [0001] The invention relates to the technical field of e-commerce platform monitoring, in particular to a method for identifying malicious users according to user negative reviews. Background technique [0002] With the development of network technology, network servers can provide information services for a large number of access users in parallel by virtue of their powerful processing performance, such as software downloads, online chat, online shopping and so on. However, among the users who access the network server, there are often some malicious users who use technical means to damage the rights and interests of others. For example, malicious negative reviews aimed at merchant stores affect the reputation of merchants and seriously damage the rights and interests of sellers and other consumers. [0003] In order to effectively stop the behavior of malicious users, there are some schemes that can identify malicious users in user groups. For example, in...

AI Technical Summary

Problems solved by technology

[0004] However, the actual effect of the above-mentioned scheme depends heavily on the personal experience and personal ability of the makers of the scoring mechanism, and is inevitably subject to the subjective cognition of the makers, so it is easy to cause misjudgments and missed judgments, and the recognition cannot be achieved. Accuracy requirements for malicious users

Images