Similar legal case retrieval method based on self-coding neural network

A neural network and self-encoding technology, applied in the field of natural language processing, can solve problems such as high cost of data labeling and insufficient features extracted

Active Publication Date: 2019-09-24
ZHEJIANG UNIV OF TECH +1
View PDF13 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the problems of high data labeling cost and incomplete extracted features in the prior art, the present invention provides a similar legal case retrieval method based on self-encoded neural network, which saves the high cost of data labeling process by using unsupervised learning method , the codec network structure adopted shares the context semantics, enriches the features of the text, and improves the retrieval efficiency of similar legal cases

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
  • Similar legal case retrieval method based on self-coding neural network
  • Similar legal case retrieval method based on self-coding neural network
  • Similar legal case retrieval method based on self-coding neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0086] The present invention will be further described below in conjunction with specific examples, but the present invention is not limited to these specific implementations. Those skilled in the art will realize that the present invention covers all alternatives, modifications and equivalents as may be included within the scope of the claims.

[0087] refer to Figure 1 ~ Figure 3 , a method for retrieving similar legal cases based on an autoencoded neural network, the method comprising the following steps:

[0088] I) input legal cases to be retrieved;

[0089] II) Using the legal case feature vector model to obtain the legal cases to be retrieved and the feature vectors of the legal cases in the database;

[0090] III) Using the Approximate Nearest Neighbor (ANN) algorithm to calculate the similarity between the legal cases to be retrieved and the legal cases in the database;

[0091] IV) Output the legal cases in the database whose similarity meets the requirements;

...

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 similar legal case retrieval method based on a self-coding neural network. The similar legal case retrieval method constructs a legal case feature vector model, calculates the similarity between a legal case to be retrieved and legal cases in a database by adopting an approximate nearest neighbor ANN algorithm, and outputs similar legal cases, wherein a legal case feature vector model is generated by creating a context triple and adopting a self-attention mechanism and a codec to train and learn a legal case data set. According to the invention, the unsupervised learning method is utilized to save the high cost of the data labeling process, and the adopted coding and decoding network structure shares context semantics, and the characteristics of the text are enriched, and the retrieval efficiency of similar legal cases is improved.

Description

technical field [0001] The invention belongs to the field of natural language processing, and relates to a method for retrieving similar legal cases based on an autoencoding neural network. Background technique [0002] Document similarity calculation is an important part of similar document retrieval, which aims to compare the similarity of document pairs. The research results of document similarity calculation can be applied to many natural language processing tasks, such as information retrieval, machine translation, automatic question answering, rephrasing questions, and dialogue systems. To a certain extent, these natural language processing tasks can be abstracted as document similarity calculation problems. For example, information retrieval can be attributed to the calculation of the similarity between query items and documents in the database. At present, various legal databases have stored a large amount of data in electronic format, but the existing databases ca...

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): G06F16/33G06Q50/18
CPCG06Q50/18G06F16/3335G06F16/3344
Inventor 冯远静金佳佳李建元陈涛吴越王辉
Owner ZHEJIANG UNIV OF TECH
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