Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Comment text analysis method and device, model training method and device, equipment and medium

A text analysis and model technology, applied in the field of data processing, can solve problems such as low accuracy of sentiment analysis, inability to deal with the emotional complexity of chat content, and complex discussion content, so as to improve the accuracy of sentiment analysis and avoid inaccurate sentiment analysis Effect

Pending Publication Date: 2022-04-08
BEIJING PERFECT WORLD SOFTWARE TECH DEV CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The related technology uses a single model to predict the emotional tendency of the text. Due to the variety of game users, the discussion content during the game is relatively complicated. A single model cannot cope with the emotional complexity of the chat content, resulting in low accuracy of sentiment analysis.

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
  • Comment text analysis method and device, model training method and device, equipment and medium
  • Comment text analysis method and device, model training method and device, equipment and medium
  • Comment text analysis method and device, model training method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0037] In some implementations, before putting a piece of comment text into M emotion classification models, it also includes: judging whether the word count of the comment text is within the preset word count range; if it is within the preset word count range, putting it into M A sentiment classification model; otherwise, the comment text is discarded or the sentiment classification prediction of the comment text is performed through a separately trained short text classification model.

[0038] For example, the preset range of the number of characters may be: more than 50 characters. Then if the comment text is less than 50 words, you need to use a separately trained short text classification model for sentiment classification prediction.

[0039] S102. Perform sentiment classification prediction on the comment text through M sentiment classification models, and obtain M sub-sentiment classification results of the comment text, wherein, the M sentiment classification models ...

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 comment text analysis method and device, a model training method and device, equipment and a medium, which are applied to the field of data processing, and the method comprises the following steps: obtaining a comment text for a target object; performing sentiment classification prediction on the comment text through M sentiment classification models to obtain M sub-sentiment classification results of the comment text; and processing the M sub-sentiment classification results based on a voting mechanism to obtain the sentiment category of the comment text. Through the technical scheme, the sentiment analysis accuracy of the comment text of the target object can be improved.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a review text analysis method, model training method, device, equipment and medium. Background technique [0002] For game products, such as the popular MMORPG (Massive Multiplayer Online Role-Playing Game, large-scale role-playing online games) or card games, emotional analysis of game users' discussions during the game can help to understand The satisfaction of game users with the game is conducive to timely and accurate adjustment of the version content of the game. The related technology is to use a single model to predict the emotional tendency of the text. Due to the variety of game users, the discussion content during the game is relatively complicated. A single model cannot cope with the emotional complexity of chat content, resulting in low accuracy of sentiment analysis. Contents of the invention [0003] Embodiments of the present invention provide a...

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 Applications(China)
IPC IPC(8): G06F16/35G06N20/00A63F13/87
Inventor 杨辰灏董博
Owner BEIJING PERFECT WORLD SOFTWARE TECH DEV CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com