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

Automobile comment text viewpoint mining method and device and storage medium

An opinion mining and text technology, applied in the field of natural language processing, can solve problems such as high complexity and failure to capture the interaction between entities and relationships

Active Publication Date: 2021-05-25
CHINA FIRST AUTOMOBILE
View PDF10 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the current methods adopt the pipeline mode, and the extraction of is treated as two independent subtasks, that is, attribute word / view word entity recognition and relationship extraction; the main disadvantages of adopting the pipeline mode are: (i ) errors in entity recognition will propagate to (affect) the relationship extraction step; (ii) entity recognition and relationship extraction are trained independently, and cannot capture the interaction between entities and relationships; (iii) the relationship extraction step requires attribute words and sentiment words Pairwise matching, high complexity

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
  • Automobile comment text viewpoint mining method and device and storage medium
  • Automobile comment text viewpoint mining method and device and storage medium
  • Automobile comment text viewpoint mining method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] refer to figure 1 , an opinion mining method for car review texts, comprising the following methods:

[0053] Step 1. Preprocessing the data;

[0054] 11) Data cleaning;

[0055]Filters special punctuation in car review text; for example: " / , *+-#￥$@&", etc. The special punctuation marks refer to characters other than common punctuation marks and characters, such as filtering except [, ? . ! English words] and other common punctuation and characters other than characters.

[0056] 12) word segmentation;

[0057] Take the form of a single character, tokenize the car review text, and convert each car review text into a list of characters.

[0058] 13) text character list length specification, the input character list length of all training texts is processed, obtains the fixed-length training input;

[0059] The length is determined according to the character length distribution of the sample data, and the length covers more than 95% of the sample set. For exampl...

Embodiment 2

[0093] The data used in this example is word-of-mouth comment text on automobile forums, and the task is to extract attribute words and opinion words from the comment text, and confirm the comment category and emotional tendency. details as follows:

[0094] "Cheap price and affordable activities" need to extract "attribute words-opinion words-comment category-emotional tendency", as follows:

[0095] price-cheap-price-positive

[0096] Activity-NULL-Price-Forward

[0097] NULL - Affordable - Price - Positive

[0098] The specific implementation process is as follows:

[0099] Step 1. Data preprocessing:

[0100] 11) Filter special punctuation marks in comment text;

[0101] 12) Carry out word segmentation processing to the comment text, and convert each comment text into a list of characters;

[0102]13) Process the character list lengths of all training texts to obtain a training input with a fixed length of 100.

[0103] Step 2. Data enhancement:

[0104] 21) Random...

Embodiment 3

[0125] Figure 8 It is a schematic structural diagram of a computer device in Embodiment 3 of the present invention. Figure 7 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the invention is shown. Figure 7 The computer device 12 shown is only an example, and should not impose any limitation on the functions and scope of use of the embodiments of the present invention.

[0126] Such as Figure 7 As shown, computer device 12 takes the form of a general-purpose computing device. Components of computer device 12 may include, but are not limited to: one or more processors or processing units 16 , system memory 28 , bus 18 connecting various system components including system memory 28 and processing unit 16 .

[0127] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety o...

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 relates to the technical field of natural language processing, in particular to an automobile comment text viewpoint mining method and device and a storage medium. The method comprises the following steps: preprocessing data; enhancing the data; and using a neural network structure composed of a BERT pre-training model, a bidirectional LSTM network, a convolutional neural network and a full connection layer to extract attribute words, viewpoint words, comment categories and emotional tendencies. According to the method, a double-pointer network labeling strategy is adopted, one-time extraction of the attribute words and the viewpoint words can be achieved, the matching complexity of the attribute words and the viewpoint words is reduced, and the extraction accuracy of the attribute words and the viewpoint words is improved; and evaluation category and emotional tendency synchronous prediction is realized, and the emotional tendency prediction accuracy is improved.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a method, device and storage medium for excavating viewpoints of automobile review texts. Background technique [0002] Car forums and car companies have accumulated a large amount of customer comments / complaint texts during the complaint handling process. There is a wealth of valuable information contained in the text content of car reviews / complaints. In-depth analysis of text content and excavation of customer comments can provide guidance for product research, planning, research and development, as well as frequent failure analysis and early warning. Generally, fine-grained sentiment analysis is used for opinion mining of review texts. [0003] The purpose of fine-grained attribute sentiment analysis is to mine user comments from a piece of comment text, and extract attribute words, opinion words, comment categories, and emotional tendencies. ...

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
IPC IPC(8): G06F16/35G06F40/247G06F40/279G06F40/30G06N3/04
CPCG06F16/355G06F40/247G06F40/30G06F40/279G06N3/049
Inventor 付振宫保伟王明月徐海强李涵丁聪敏韩鹏
Owner CHINA FIRST AUTOMOBILE
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