Differential evaluation early warning method and system based on current order, and blacklist library establishment method

Abstract

The invention discloses a differential evaluation early warning method based on a current order, and the method comprises the steps: judging whether a to-be-tested buyer and one of differential evaluators in a differential evaluator blacklist library are the same person according to the comparison information, sending differential evaluation early warning if the to-be-tested buyer and one of the differential evaluators are the same person, and otherwise, receiving the transaction of the to-be-tested buyer; a bad evaluator in the bad evaluator blacklist library is mainly composed of malicious bad evaluators judged according to the own information of the historical buyers and the comment information of the historical buyers. if the buyer to be tested and one of the differential evaluators inthe differential evaluator blacklist library are the same person, determining that the buyer to be tested and the differential evaluator are not the same person; according to the differential evaluation early warning method based on the current order, the differential evaluator with the account number replaced can be discriminated, discrimination can be carried out before the differential evaluator gives the differential evaluation, and the interference of malicious differential evaluation on the seller is reduced to the maximum extent. The invention also provides a differential evaluation early warning system based on the current order, a blacklist library establishment method, computer equipment and a storage medium.

Description

technical field [0001] The invention belongs to the field of e-commerce information technology, and in particular relates to a method, a system, a method for establishing a blacklist library, a computer device, and a storage medium based on a current order-based negative evaluation early warning method. Background technique [0002] With the rapid development of the Internet, the position of e-commerce in the commercial field is becoming more and more important. The rapid development of e-commerce also causes some users to seek benefits through abnormal behaviors on e-commerce websites. For example, on an e-commerce website, an abnormal person purchases goods as a buyer, and then gives or does not give a moderate evaluation to the purchased product in the evaluation system, and finally submits a request to Abnormal behavior of shop sellers asking for money. The behavior of these users has greatly affected the normal transaction behavior in the e-commerce field, and these us...

AI Technical Summary

Problems solved by technology

[0003] In view of the above problems, the most primitive specific method for identifying bad reviewers is: when the shop seller receives information for the purpose of extortion and threats sent by the buyer through the client of the e-commerce website, the shop seller or the customer service department personnel rely on experience to conduct Subjectively judge whether it is a bad reviewer, specifically to check the buyer’s past purchase records, evaluation records, registration time and credit. This method of identifying bad reviewers has the following problems: 1) Manual identification is very inefficient; 2) Because the information used to identify bad reviewers is incomplete and the subjective awareness of human identification is relatively strong, the accuracy of recognition is very low; 3) Only when bad reviewers ask for money is identified, which is very passive and brings great harm to sellers. troubled

[0005] However, this method has flaws: 1) It can only be used for those with historical data, and it cannot be recognized after changing the new account; 2) It is still necessary to give negative reviews before screening, which cannot minimize the interference of sellers

Images