Legal document feature extraction method, related device and storage medium

A feature extraction and document technology, applied in the electronic field, can solve problems such as lack of legal logic, difficulty in providing case information, and achieve the effect of improving the efficiency of feature extraction

Pending Publication Date: 2020-02-07
平安直通咨询有限公司
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the existing technology, legal documents are deconstructed, and the elements after deconstruction are simple, which can only realize simple document type classification, lack of complete legal logic, and it is difficult to provide effective case information.

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
  • Legal document feature extraction method, related device and storage medium
  • Legal document feature extraction method, related device and storage medium
  • Legal document feature extraction method, related device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] The embodiment of the present application provides a feature extraction method of legal documents, the feature extraction method of legal documents is applied to an electronic device, and the electronic device can be a smart phone, a tablet computer, a computer and other devices that can install application programs, and the above-mentioned electronic device The operating system may be ios, android, windows system or other operating systems, which are not limited here.

[0044] see figure 1 , the feature extraction method of the legal document mainly includes the following steps:

[0045] 101. Perform pre-identification on legal documents, and determine the paragraph division model and feature extraction model corresponding to the legal documents;

[0046] Pre-identify the legal document, and determine the paragraph division model and feature extraction model corresponding to the legal document; wherein, the feature extraction model includes the corresponding relations...

Embodiment 2

[0065] The embodiment of the present application mainly describes the scheme of extracting document elements through the machine learning model of rule extraction, wherein each document element corresponds to a document element rule, and the document element rule is used to read the features corresponding to the document element in the sentence .

[0066] Step 1. Obtain the document paragraphs after the legal documents are divided into paragraphs, and use the document paragraphs as the input object of the feature extraction model; the feature extraction model includes a plurality of document element rules.

[0067] Step 2, segmenting the document paragraph according to the punctuation marks, and cutting a plurality of sentences obtained to form a sequence of sentences;

[0068] Step 3. According to the document paragraphs after the paragraphs are divided, filter the document element rules corresponding to the document paragraphs in the feature extraction model;

[0069] Step ...

Embodiment 3

[0078] The embodiment of the present application mainly describes the scheme of implementing document element extraction with a supervised neural network model, specifically including:

[0079] First, the training of the neural network model;

[0080] The neural network model of the embodiment of the present application integrates three single models, 1: Based on the TextCNN network, BatchNormal is added, and two layers of fully connected layers are used for classification. Model 2: Based on the TextRNN network, using bidirectional long-term short-term memory (LSTM, Long Short-Term Memory), the hidden vector is classified after K-MaxPooling during classification; Model 3: TextRCNN network. The above three model networks are fused, that is, the outputs of the three networks are added, and then the corresponding legal document samples (marked with document elements) are used for model training.

[0081] The TextCNN network, the three networks of the TextRNN network and the Text...

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 legal instrument feature extraction method, a related device and a storage medium, and the method comprises the steps: carrying out the pre-recognition of a legal instrument,and determining a paragraph partitioning model and a feature extraction model corresponding to the legal instrument; wherein the feature extraction model comprises a corresponding relationship between a document paragraph and a document element; performing document paragraph division on the legal document through the paragraph division model; and extracting document elements corresponding to thedocument paragraphs from the legal documents after the document paragraphs are divided through the feature extraction model, and outputting an extraction result of the document elements.

Description

technical field [0001] The present application relates to the field of electronic technology, and in particular to a feature extraction method of legal documents, a related device and a storage medium. Background technique [0002] With the continuous improvement of my country's legal system, everyone's awareness of rights protection is increasing day by day. Legal services play a pivotal role in daily life. Legal services are an important and necessary part of all walks of life in society. Various Internet + legal platforms It was established and launched like mushrooms after rain. However, as a highly personalized and specialized industry, legal services have higher requirements for Internet+. [0003] Legal documents contain rich legal concepts and legal logic. By deconstructing it, users can quickly grasp the elements of the case. [0004] In the existing technology, legal documents are deconstructed, and the deconstructed elements are simple, which can only realize si...

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): G06K9/00G06K9/46G06F40/295G06F40/30G06N3/04G06N3/08G06Q50/18
CPCG06N3/08G06Q50/18G06V30/40G06V10/40G06N3/045
Inventor 何芳芳邵博
Owner 平安直通咨询有限公司
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