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

Method and device for determining abnormal comment text

A technology for determining methods and texts, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as low efficiency, low accuracy, and difficulty in manual identification, and achieve the effect of improving detection efficiency

Active Publication Date: 2018-08-31
BEIHANG UNIV
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing means of detecting abnormal comments and extreme comments is mainly through manual identification, but manual identification is difficult, the accuracy rate is low, and the efficiency is also very low

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
  • Method and device for determining abnormal comment text
  • Method and device for determining abnormal comment text
  • Method and device for determining abnormal comment text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Such as figure 1 As shown, the embodiment of the present application provides a method for determining abnormal comment text, and the specific steps are as follows S100-S140:

[0055] S100. Obtain multiple comment texts of pending abnormal comments.

[0056] The review texts here include various reviews filled in by users on commodity review websites. In specific implementation, a certain amount of review texts in a certain commodity review website can be obtained.

[0057] S110. Calculate the similarity between any two comment texts among the plurality of comment texts.

[0058] Wherein, in the step S110, calculate the similarity between any two comment texts in the plurality of comment texts, including as figure 2 In the shown method, the specific steps are as follows S200-S220:

[0059] S200. Based on a preset similarity measurement model, perform vector conversion on any piece of comment text to obtain a comment vector of the arbitrary piece of comment text.

...

Embodiment 2

[0100] The embodiment of the present application provides a device for determining abnormal comment text, such as Image 6 shown, including:

[0101] A text acquisition module 601, configured to acquire multiple comment texts to be abnormally commented on.

[0102] The text processing module 602 is configured to calculate the similarity between any two comment texts among the plurality of comment texts; and is configured to classify the plurality of comment texts based on the similarity to obtain a classified comment text set.

[0103] The text execution module 603 is configured to input the comment text corresponding to any classified comment text set into the pre-trained sentiment model to obtain the sentiment score set corresponding to any classified comment text set.

[0104] The text confirmation module 604 is configured to verify the sentiment score sets corresponding to each classified comment text set, obtain an abnormally classified comment text set, and determine th...

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 embodiment of the invention provides a method and a device for determining abnormal comment text. The method comprises the following steps of: obtaining a plurality of to-be -abnormally commentedcomment text; calculating similarity among the comment text; classifying the comment text on the basis of the similarity to obtain a classified comment text set; for any classified comment text set, inputting the comment text corresponding to the classified comment text set into a pre-trained emotion model to obtain an emotion score set corresponding to the classified comment text set; and verifying the emotion score sets corresponding to the classified comment text sets to obtain an abnormal classified comment text set and determining all comment texts in the abnormal classified comment textset as the abnormal comment text. By means of the method provided by the embodiment of the invention, the detection efficiency of abnormal comments is increased.

Description

technical field [0001] The present application relates to the technical field of text detection, in particular, to a method and device for determining abnormal comment text. Background technique [0002] There are a large number of abnormal reviews in commodity review websites. Abnormal comments will affect customer behavior, cause malicious competition among merchants, and form a bad business atmosphere. Abnormal comments mainly include false comments and extreme comments. False reviews refer to malicious advocacy or defamation of merchant products by users. Extreme comments refer to users' comments on products that do not conform to the facts due to personal emotions. Both of these reviews will affect the merchant's credit rating. [0003] The existing means of detecting abnormal comments and extreme comments is mainly through manual identification, but manual identification is difficult, the accuracy rate is low, and the efficiency is also very low. Contents of the ...

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
IPC IPC(8): G06F17/30
CPCG06F16/3344G06F16/355
Inventor 徐振中肖依永苑星龙
Owner BEIHANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com