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

Expert comment induction algorithm based on sentiment classification and SOM clustering

A technology of emotion classification and comments, applied in computing, special data processing applications, instruments, etc., to achieve the effect of improving evaluation efficiency, improving efficiency, and reducing costs

Inactive Publication Date: 2016-11-23
苏州优估营网络科技有限公司
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the bottleneck problem caused by the artificial role of the coordinator in the process of using the Delphi method for online evaluation, the present invention provides a new type of algorithm, which The algorithm can replace the role of the coordinator in the traditional Delphi method process through machine calculation based on artificial intelligence technology, reduce labor costs and improve evaluation efficiency

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
  • Expert comment induction algorithm based on sentiment classification and SOM clustering
  • Expert comment induction algorithm based on sentiment classification and SOM clustering
  • Expert comment induction algorithm based on sentiment classification and SOM clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] exist figure 1 As shown, the specific implementation process of the algorithm involved in the present invention is as follows:

[0023] 1. Text preprocessing:

[0024] The purpose of this step is to generate a structured representation of the comment text, which mainly includes three sub-steps: word segmentation of the text, vectorized representation, and dimensionality reduction:

[0025] a) Using the word segmentation method based on character string matching, combined with general or special thesaurus resources, the comment text is divided into combinations of individual words;

[0026] b) Convert each comment text D i in each word t k frequency of occurrence tf ik As a basic reference, use the commonly used TF-IDF method to determine the weight w of each word ik , forming a vectorized representation D of each document D i =D(t i1 ,w i2 ;...t ik ,w ik ), the weight calculation formula of TF-IDF is as follows:

[0027] w ik ...

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 provides an induction and summarization algorithm which can be conducted on different comments of multiple experts on the basis of artificial intelligence. The algorithm comprises the steps that classification is conducted on the text content of the expert comments according to positive emotions or negative emotions by means of sentiment classification, clustering is conducted on topics related to all the expert comments by means of an SOM (self-organizing feature mapping neural network), and several kinds of comment clusters such as positive opinions of some topics and negative opinions of some topics are summarized from all the expert comments. According to the induction and summarization algorithm, aiming at a specific application scene that a traditional Delphi method is used for online assessment, an artificial intelligent technology is adopted for replacing the time-consuming and high-cost process that induction and summarization are conducted on the expert comments artificially in the traditional Delphi method, the efficiency of conducting online assessment through the traditional Delphi method can be improved, and the labor cost can be reduced.

Description

Technical field [0001] The invention relates to an artificial intelligence-based induction and summary algorithm that can perform different comments from multiple experts. The algorithm adopts emotion classification to first classify the text content of expert comments according to two types of "affirmative emotion" or "negative emotion", and then Using SOM (Self-Organizing Feature Mapping Neural Network) to cluster the topics involved in each expert comment, and summarize several types of comment clusters of "positive opinion on a certain topic" and "negative opinion on a certain topic" from all expert comments. This algorithm is aimed at the specific application scenario of using the traditional Delphi method for online evaluation. Artificial intelligence technology is used to replace the traditional Delphi method, which is time-consuming and costly. It improves the efficiency of traditional Delphi method for online evaluation and reduces labor costs. Background technique ...

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): G06F17/30G06F17/27
Inventor 刘烽刘礼兵
Owner 苏州优估营网络科技有限公司
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