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

Merchant multi-view feature extraction and model construction method based on online comment data

A feature extraction and multi-view technology, applied in the field of merchant multi-view feature extraction and model construction based on online review data, can solve the problems of ignoring the differences in different customer evaluations

Active Publication Date: 2020-11-10
HANGZHOU DIANZI UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, few researchers have summarized and extracted various characteristics of these merchants, and built predictive models based on the extracted characteristics.
In addition, although some studies involved semantics in feature extraction, they also ignored the differences between different customer evaluations.

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
  • Merchant multi-view feature extraction and model construction method based on online comment data
  • Merchant multi-view feature extraction and model construction method based on online comment data
  • Merchant multi-view feature extraction and model construction method based on online comment data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0101] The steps in this embodiment are the same as those described above in the specific implementation mode, and will not be repeated here. Part of the implementation process and results are shown below:

[0102] The original data used in this embodiment is the public data set of yelp, and the locations are Las Vegas, USA and Toronto, Canada. According to the statistics of relevant institutions, the contribution of the catering industry to GDP is extremely high, so this embodiment mainly uses restaurants as an example to carry out related experiments. Through preprocessing, correlate the latitude and longitude, comments, check-in, and business attributes of each restaurant; correlate the comment text, comment time, number of comment likes, commenter's historical comment volume, commenter's historical comment like volume, commenter Average rating of historical reviews. So far, many pieces of restaurant data σ have been formed 1 =, and its corresponding comment data σ 2 =....

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 merchant multi-view feature extraction and model construction method based on online comment data. According to the method, firstly, based on comments, sign-in and merchant business attribute data of online comment software, semantic information of customer comments is mined by constructing an emotion classification neural network model, merchant semantic features are generated in combination with customer comment habits, the merchant business features are formed by screening important business attributes, a merchant cluster is generated through density clustering, merchant cluster features of merchants in the cluster are calculated, and finally the three kinds of features are integrated to form multi-view features of the merchants. Then the multi-view features are input into a LightGBM model to realize the prediction of commercial tenant operation conditions. According to the method, the multi-view features of the merchant are extracted from the multi-view perspective based on the online comment data, and the merchant operation state model is constructed based on the features, so that the method has the characteristics of high precision, high expandability and the like, and can provide decision support for merchant operation, commercial investment and the like.

Description

technical field [0001] The invention relates to the fields of feature extraction and model building, in particular to a merchant multi-view feature extraction and model building method based on online review data. Background technique [0002] Online review software such as Yelp, Dianping, and Meituan not only provide a platform for merchants to promote, but also provide a platform for customers to share user experience. The evaluations submitted by these customers provide important references for other customers to choose merchants. Studies have shown that customers' evaluation of merchants on Dianpingsoft closely affects the merchant's business performance. However, few researchers have summarized and extracted various characteristics of these merchants, and built predictive models based on the extracted characteristics. In addition, although some studies involved semantics in feature extraction, they also ignored the differences between different customer evaluations. ...

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): G06F16/33G06F16/35G06K9/62G06F40/289G06F40/30G06Q30/02
CPCG06F16/3344G06F16/35G06F40/289G06F40/30G06Q30/0201G06F18/2321G06F18/24
Inventor 孙笑笑梁平俞东进王欣峰
Owner HANGZHOU DIANZI UNIV
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