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

Multi-task network construction and multi-scale charge legal provision joint prediction method

A network construction and multi-task technology, applied in the field of multi-task network construction and multi-scale joint prediction of crimes and laws, can solve problems such as low accuracy and poor prediction diversity, improve accuracy, speed up prediction, reduce The effect of training time

Active Publication Date: 2019-08-30
XIDIAN UNIV
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the shortcomings of low accuracy and poor prediction diversity in the prior art, the purpose of this application is to provide a multi-task network construction and multi-scale Joint Prediction Method of Crime and Law

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
  • Multi-task network construction and multi-scale charge legal provision joint prediction method
  • Multi-task network construction and multi-scale charge legal provision joint prediction method
  • Multi-task network construction and multi-scale charge legal provision joint prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082] CAIL2018 is China's first large-scale data set for legal judgment prediction; each case in the CAIL2018 data set consists of two parts, the factual statement and the corresponding judgment result. Distill the corresponding judgment results of each case into three representative parts, including relevant legal provisions, charges, and sentences. Among them, there are 183 criminal law articles and 202 criminal charges.

[0083] Step 1. This embodiment obtains known criminal legal documents from CAIL2018, preprocesses the text of the case description and facts in the known criminal legal documents, and obtains the preprocessed text; uses the Word2Vec method to preprocess The final text is processed to obtain word vectors of multiple words;

[0084] In this embodiment, the preprocessed text is randomly divided into training set, verification set and test set according to the ratio of 10:1, and the Word2Vec method is used to process the training set, verification set and tes...

Embodiment 2

[0097] A multi-scale joint prediction method for criminal offenses using a multi-task network, specifically comprising the following steps:

[0098] Step 1. In this embodiment, the test set obtained in Embodiment 1 and the word vectors of multiple words corresponding to the test set are used as the preprocessed text and the word vectors of multiple words obtained after processing the criminal documents to be predicted;

[0099] Step 2. Input the preprocessed text and the word vectors of multiple words into the trained multi-task network, and use the shared network in the trained multi-task network to process the preprocessed text and the word vectors of multiple words Process to obtain multiple feature vectors; use the unique network of crime prediction in the trained multi-task network to process multiple feature vectors to obtain the crime prediction probability vector; use the legal provisions predicted in the trained multi-task network The unique network processes multiple...

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 provides a multi-task network construction method, which comprises the following steps: processing a text consisting of case description and facts in a known criminal legal document to obtain a preprocessed text and word vectors of a plurality of words; processing and training the preprocessed text and word vectors of a plurality of words by adopting a multi-task network formed by aspecial network of a shared network, charge prediction and legal provision prediction, and finally obtaining a trained multi-task network. The invention also provides a multi-scale charge legal provision joint prediction method, which comprises the following steps: processing a text consisting of case description and facts in the charge legal document to be predicted to obtain a preprocessed textand word vectors of a plurality of words, processing by adopting the trained multi-task network, and judging to obtain a predicted charge and a predicted legal provision. According to the method, thetwo tasks are combined to extract the features together, the prediction accuracy can be effectively improved, and meanwhile, the coverage rate and diversity of prediction on categories are improved.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to a method for joint prediction of multi-task network construction and multi-scale criminal charges. Background technique [0002] Legal Judgment Prediction (LJP) task is a traditional task combining artificial intelligence and law. Its purpose is to let the machine automatically predict the verdict of a legal case after reading the description of criminal facts, such as crime prediction and recommendation of applicable legal provisions. A good LJP model not only benefits social people who are not familiar with the law, but also assists lawyers, judges and other professionals to make decisions. However, it is not easy to predict based on the facts of the crime: (1) It is necessary to distinguish the slight difference between the two crimes, such as distinguishing between the crime of intentional homicide and the crime of intentional injury to determi...

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): G06F16/35G06F17/27G06K9/66G06N3/04G06Q10/04G06Q50/18
CPCG06F16/35G06Q10/04G06Q50/18G06V30/194G06F40/30G06N3/045
Inventor 马晶晶冯嘉伦公茂果王善峰武越张明阳解宇
Owner XIDIAN UNIV
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