Unlock instant, AI-driven research and patent intelligence for your innovation.

A method for identifying malicious users based on e-commerce reviews

A malicious user and user technology, applied in the fields of e-commerce and social computing, can solve problems such as poor stability, achieve stable performance, good robustness, and improve accuracy

Active Publication Date: 2021-04-13
广州拉拉米信息科技股份有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the user's rating distribution is different and does not completely obey a certain distribution, so the stability of this algorithm is poor

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for identifying malicious users based on e-commerce reviews
  • A method for identifying malicious users based on e-commerce reviews
  • A method for identifying malicious users based on e-commerce reviews

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The technical solutions and beneficial effects of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0051] The present invention provides a method for identifying malicious users based on e-commerce reviews, which mainly includes the following four stages:

[0052] First of all, triplets are used to store scoring data; triplets are used to store scoring data, which saves space compared to arrays when the amount of data is large and the scoring data is relatively sparse;

[0053] Secondly, count the size of the weighted group of each product under each rating, and use the user's reputation score as the weight to calculate the proportion of each rating group in each product;

[0054] Then, calculate the user's reputation score based on the average and standard deviation of the proportion of each user's group and the standard deviation of the user's score, and iteratively calculate the user's reputation until the user'...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for identifying malicious users based on e-commerce reviews. The steps are: step 1, construct triplets for storing scoring data; step 2, initialize the reputation of all users; The size of the weighted group; step 4, calculate the proportion matrix of each group in different commodities; step 5, map the proportion matrix to the matrix whose rows and columns correspond to users and commodities respectively; step 6, calculate the The average and standard deviation of the group proportion, and calculate the standard deviation of user ratings; step 7, calculate user reputation based on the data obtained in step 6; step 8, based on the user reputation obtained in step 7, repeat step 3‑7, and then Calculate the difference between the two user reputations, if it is greater than the threshold, continue to iterate until it is less than or equal to the threshold; step 9, regard the L users with the lowest reputation as malicious users. This method can improve the accuracy of filtering malicious users and increase the stability of calculation in the identification process.

Description

technical field [0001] The invention belongs to the fields of electronic commerce and social computing, and in particular relates to a method for screening malicious users based on comments of electronic commerce. Background technique [0002] In the Internet age, user ratings are starting to play an increasingly important role, especially in the field of e-commerce. Therefore, many e-commerce platforms (such as Taobao, JD.com) have launched scoring systems, users can rate products, and the ratings received by products will affect user decision-making. It is particularly important to ensure the authenticity and effectiveness of ratings. However, there are some malicious users in the rating system, whose ratings are unreliable. One type of malicious users is a troll army invited by merchants to give high scores to their own products and low scores to rival products. Another type of malicious users is Malicious users with random ratings. The ratings of these malicious users ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q30/00
CPCG06Q30/012
Inventor 孙宏亮付泉赟卜湛曹杰
Owner 广州拉拉米信息科技股份有限公司