Online commodity reputation value calculation method, network transaction platform and computer

Abstract

The invention belongs to the technical field of e-commerce, and discloses an online commodity reputation value calculation method, a network transaction platform and a computer. The method comprises the steps of malicious evaluation detection, user interestingness evaluation and reputation value calculation. By utilizing a two-phase detection theory, slight change of an evaluation model is detected, so that the conditions when malicious users carry out malicious evaluation on all the commodities can be processed, and the conditions when malicious users only carry out malicious evaluation on target commodities also can be processed. According to the method, weights of different user evaluations are determined through comparing similarities between target items and user evaluation items, sothat the interestingness, to target commodities, of users and reliability of the users can be reflected more correctly.

Description

technical field [0001] The invention belongs to the technical field of electronic commerce, and in particular relates to a method for calculating reputation value of online commodities, a network transaction platform and a computer. Background technique [0002] With the vigorous development of e-commerce (eBay, Amazon, Taobao, Youtube, Netflix and other online trading platforms), according to the report of the E-Commerce Foundation, more than half of the people who use the Internet in most parts of the world have online shopping experience. E-commerce has great potential to drive economic development and bring convenience to people's daily life. As online trading platforms offer more and more goods and services, consumers have more choices. But at the same time, there are profit-driven sellers offering counterfeit goods. Driven by economic interests, a large number of sellers are willing to give their own products abnormally high ratings, while rating their competitors’ p...

AI Technical Summary

Problems solved by technology

[0003] To sum up, the problems existing in the existing technology are: the current reputation value technical method does not take into account how to deal with the situation when malicious users only make malicious evaluations on the target product, rather than all products; Determine the weight of different node evaluations. The weight of evaluation cannot reflect the degree of interest of the user in the target product and the reliability of the user

Images