A public opinion monitoring method and system based on commodity comments

A product review and public opinion technology, applied in the field of public opinion monitoring methods and systems based on product reviews, can solve problems such as difficulties for enterprises, difficulty in obtaining labeled data, and failure of models to obtain effective results, and achieve the effect of maintaining corporate image

Active Publication Date: 2018-12-11
南京新贝金服科技有限公司 +1
View PDF9 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the emotional classification methods based on neural networks all target a small field, and the same model cannot achieve effective results in other fields.
For enterprises, it is difficult to obtain labeled data, and labeling data is a huge project, and it is difficult for ordinary enterprises to achieve such a goal

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 public opinion monitoring method and system based on commodity comments
  • A public opinion monitoring method and system based on commodity comments
  • A public opinion monitoring method and system based on commodity comments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described below in conjunction with accompanying drawing and exemplary embodiment:

[0041] Such as figure 1 Shown, the technical scheme that the present invention adopts comprises the following steps:

[0042] Step 101, use Wikipedia and public comment data to form a corpus Corpus, which includes n documents such as D1, D2, ..., Dn. Perform word segmentation operations on all documents, and Corpus can obtain a set Σ consisting of m words consisting of W1, W2, ..., Wm. Then create a dictionary dict, the key and value in the dict are respectively {Wi:Vi}. Where Vi is a vector consisting of K random numbers uniformly distributed between [0,1]. In order to carry out the next step of training, a hyperparameter Window needs to be set.

[0043] In step 102, a neural network is constructed. According to the above parameters and variables, the input layer has Window*2*k nodes, and the output layer has k nodes.

[0044] Step 102, the tr...

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 public opinion monitoring method based on commodity comments, which is characterized in that the method comprises the steps of word vector embedding, comment data collectionand preprocessing, comment data indexing, neural network training and automatic classification and alarm. The invention combines a plurality of deep learning algorithms and an innovative data processing method, discriminates the negative comment and detects the negative comment point, so that the enterprise can maintain the enterprise image even if it finds the negative comment information and intervenes pertinently. The unstructured review data can be effectively transformed into the structured data that the business needs and can analyze.

Description

technical field [0001] The invention relates to the field of electronic commerce, in particular to a public opinion monitoring method and system based on commodity reviews. Background technique [0002] With a large amount of retail shifting from offline to online, the biggest problem in online retail is the lack of physical information, especially for experiential products. It is difficult for users to determine and evaluate the quality of experiential products through product indicators and data, so after-sales reviews of products have become an important factor affecting users' purchase decisions. Whether an enterprise can provide timely and effective feedback on negative reviews will greatly affect users' impression of the enterprise. For e-commerce enterprises with large sales volume, tens of thousands of comments are formed every day, and manual inspection is a huge task. For boring work, automated detection and commenting can effectively reduce the labor cost 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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06N3/04G06N3/08
CPCG06N3/084G06F2216/03G06N3/045
Inventor 黄文明李莉林雨蓝邹苇夏静徐丽萍
Owner 南京新贝金服科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap