An Intelligent Legal Judgment Method of Numerical Perception Enhanced by Knowledge of Sentencing Standards

A standard and knowledgeable technology, applied in the field of artificial intelligence, can solve the problems of lack of perceived fines, sentence predictions, and inaccuracies in text values

Active Publication Date: 2022-07-08
SOUTHEAST UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a numerically-aware intelligent legal judgment method enhanced by the knowledge of sentencing standards, so as to solve the technical problems of inaccurate fines and sentence predictions caused by the lack of perception of textual values

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
  • An Intelligent Legal Judgment Method of Numerical Perception Enhanced by Knowledge of Sentencing Standards
  • An Intelligent Legal Judgment Method of Numerical Perception Enhanced by Knowledge of Sentencing Standards
  • An Intelligent Legal Judgment Method of Numerical Perception Enhanced by Knowledge of Sentencing Standards

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0060] Embodiment: the technical terms involved in the present invention are explained as follows

[0061] PTLM (Pre-Trained Language Model): Pre-trained language model

[0062] MNP (Masked Numeral Prediction): Masked Numerical Prediction

[0063] JKS (Judicial Knowledge Selection): Judicial Judgment Knowledge Selection

[0064] like figure 1 As shown, the present invention consists of four main modules: a JKS module, a legal digital meaning acquisition module based on MNP tasks, a graph network reasoning module and a judgment prediction module.

[0065] Firstly, a classifier based on contrastive learning is used to select the sentencing standard knowledge corresponding to a given crime fact. This module is the cornerstone of the entire model, which mimics the sentencing practice of judges. Only by using the correct knowledge of sentencing standards can an accurate judgment be made. The model then obtains legal numerical meanings from the knowledge of sentencing criteria...

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 an intelligent legal judgment method with numerical perception enhanced by the knowledge of sentencing standards, which is used to solve the problem that general methods lack numerical perception ability and thus perform poorly on numerical legal judgment tasks. The proposed method includes the following steps: firstly Use PTLM to encode factual descriptions to obtain sentence-level and word-level representations; then; then use Masked Numeric Prediction (MNP) based on a Pre-Trained Language Model (PTLM) to help the model obtain legal numerical meanings ; Then build a graph network from the numerical representation and the selected legal knowledge to perform numerical reasoning; finally, use the representation obtained through the above steps to predict the category. The present invention utilizes the advantages of PTLM in design, incorporates judicial priori, and constructs a graph network for numerical reasoning, which can significantly improve the accuracy of legal judgment.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and in particular relates to an intelligent legal judgment method of numerical perception enhanced by knowledge of sentencing standards. Background technique [0002] In recent years, legal artificial intelligence has attracted extensive attention from academia and industry. Earlier work often utilized mathematical and statistical algorithms to analyze existing legal cases. Inspired by the great success of deep learning, some researchers use knowledge of external legal terms or legal schematics as features to distinguish confusing cases. Some researchers have noticed the dependencies between the subtasks of Legal Judgment Prediction (LJP, Legal Judgment Prediction), and proposed a framework based on multi-task learning, which achieved excellent performance on two subtasks of LJP, namely, the and forecasts of legal terms. However, few methods focus on numerical LJP, the prediction of fine...

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 Patents(China)
IPC IPC(8): G06F40/30G06K9/62G06Q50/18G06F16/35
CPCG06F40/30G06F16/35G06Q50/18G06F18/214
Inventor 毕胜周之遥漆桂林
Owner SOUTHEAST UNIV
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