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

BiGRU judgment result tendency analysis method based on attention mechanism

A technology of judgment results and analysis methods, applied in the fields of deep learning and natural language processing, can solve problems such as information loss and classification accuracy reduction, and achieve the effects of reducing loss, improving accuracy, and personalization scalability

Pending Publication Date: 2020-04-17
中国科学院沈阳计算技术研究所有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a BiGRU judgment result tendency analysis method based on the attention mechanism, which solves the problem that the classification accuracy rate decreases due to information loss in the judgment result tendency analysis, and improves the judgment result. Efficiency of result propensity analysis calculation

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
  • BiGRU judgment result tendency analysis method based on attention mechanism
  • BiGRU judgment result tendency analysis method based on attention mechanism
  • BiGRU judgment result tendency analysis method based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0078] Judgment text: The plaintiff Qin Moujia and the defendant Cao Mou were allowed to divorce;

[0079] Judgment sequence: (Permit, Plaintiff, Qin Jia, and, Defendant, Cao, Divorce).

[0080] Word vector matrix: (w 1 ,w 2 ,w 3 ,",w n )→S=(s 1 ,s 2 ,s 3 ,",s n ).

[0081] Step 7: Feature vector of word vector: Input the word vector into the BiGRU network for calculation to obtain the feature vector. Such as figure 2 As shown, the word vector sequence S=(s 1 ,s 2 ,...,S n-1 ,s n ) Enter the BiGRU network, which is x in the formula t After the calculation of each unit of the network layer, the feature vector corresponding to the word vector is finally obtained.

[0082] z t =σ(W z ·[H t-1 ,x t ])

[0083] r t =σ(W r ·[H t-1 ,x t ])

[0084]

[0085]

[0086] The specific description is: x t Is the input data, h t Is the output of the current GRU calculation unit, h t-1 Is the calculation output of the previous calculation unit, z t Is the update gate, r t Is the reset gate, z t And r ...

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 a BiGRU judgment result tendency analysis method based on an attention mechanism. The method comprises: extracting party keyword information and judgment result keyword information of a judgment document to be analyzed are extracted; segmenting the judgment result into a plurality of simple sentences, and performing word segmentation and stop word removal processing on each simple sentence to obtain a word sequence; constructing a word vector table, and expressing the word sequence as a corresponding word vector matrix by utilizing the word vector table; performing BiGRU calculation on the word vector matrix to obtain a feature vector of the word vector matrix, and performing attention calculation on the feature vector of the word vector matrix to obtain an outputvector of an attention mechanism; and classifying the output vector of the attention mechanism by utilizing softmax. According to the method, the accuracy of the algorithm is improved, so that the classification result is more accurate, the defect that the text context is ignored based on the unidirectional neural network traditionally is overcome, the accuracy of the emotion classification resultis improved, the key information in the text can be enhanced well, and the accuracy of the algorithm is improved.

Description

Technical field [0001] The present invention relates to the field of deep learning and natural language processing, in particular to a BiGRU decision result tendency analysis method based on an attention mechanism. Background technique [0002] With the development of modern information technology and the deepening of the legal system, with the release of a large number of judgment documents, it becomes more meaningful to dig out knowledge from the massive judgment documents. Text sentiment analysis: also known as opinion mining, tendency analysis, etc., in simple terms, it is the process of analyzing, processing, inducing and reasoning subjective text. Deep learning is the most popular algorithm in the field of text sentiment analysis. [0003] With the development of text sentiment analysis, it is an inevitable trend to apply it to the analysis of judgment results orientation. The current text sentiment analysis algorithm is used in the research of judgment result orientation a...

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): G06F40/279G06F40/30
Inventor 王宁周晓磊李世林刘堂亮张镝祁柏林赵奎
Owner 中国科学院沈阳计算技术研究所有限公司
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