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

Fine-grained attribute analysis method in e-commerce comment analysis scene

An attribute analysis and fine-grained technology, which is applied in the field of fine-grained attribute analysis in the e-commerce review analysis scenario, can solve the problems of high cost of labeling data acquisition, achieve the effect of shortening the online cycle, simplifying the complexity, and improving the efficiency of labeling

Pending Publication Date: 2020-05-08
深圳数阔信息技术有限公司
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] To sum up, the problem existing in the existing technology is: in the field of machine learning, the acquisition cost of labeled data is high

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
  • Fine-grained attribute analysis method in e-commerce comment analysis scene
  • Fine-grained attribute analysis method in e-commerce comment analysis scene
  • Fine-grained attribute analysis method in e-commerce comment analysis scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] In order to further understand the content, features and effects of the present invention, the following examples are given, and detailed descriptions are given below with reference to the accompanying drawings.

[0035] Aiming at the problems existing in the prior art, the present invention provides a fine-grained attribute analysis method in the e-commerce comment analysis scenario, and the following is combined with the attached figure 1 The present invention is described in detail.

[0036] A fine-grained attribute analysis method in an e-commerce comment analysis scenario includes:

[0037] S101. Using two isomorphic and independently trained sequence labeling models to extract target attributes and emotions of e-commerce reviews respectively;

[0038] S102. Use a relationship classification model to perform relationship classification on the target attributes and emotions extracted by the model in step 1;

[0039] S103, the training data of the model is carried ...

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 belongs to the technical field of natural language processing, and discloses a fine-grained attribute analysis method in an e-commerce comment analysis scene, which comprises the following steps of: respectively extracting target attributes and emotions of e-commerce comments by using two isomorphic and independently trained sequence labeling models; using a relationship classification model to perform relationship classification on the target attributes and emotion extracted by the model in the step 1; wherein the training data of the model is carried out by using an efficient labeling strategy, and the data labeled by using the strategy is used for training the models in the step 1 and the step 2; the rule matching relation module is used for integrating target attributes and emotions output by all the models; and the post-processing module is used for integrating the output of the rule matching relationship module and the output of the relationship classification model. Through the solution provided by the invention, on the premise of ensuring the accuracy of the fine-grained emotion prediction result, the complexity of the fine-grained emotion annotation task is simplified, and the annotation efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to a fine-grained attribute analysis method in an e-commerce comment analysis scenario. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: With the popularization of the Internet, the logistics industry is becoming more and more perfect, and the e-commerce industry is booming. More and more users choose to purchase various daily necessities, even food and electronic products through online shopping. . Compared with offline channels, e-commerce channels provide a fast and convenient product feedback mechanism - user reviews. E-commerce user reviews have built a high-speed channel connecting users and brands. There are hundreds of thousands or even millions of user reviews for a single product, which undoubtedly has extremely high value for brand and product improvement. Such a huge amount...

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): G06F40/205G06F16/35G06N3/04G06N3/08
CPCG06F16/35G06N3/049G06N3/08G06N3/045
Inventor 刘宝强肖云飞
Owner 深圳数阔信息技术有限公司
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