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

Case pre-judgment agent training method and system capable of automatically updating

A technology of automatic update and training method, applied in the field of artificial intelligence, it can solve the problems of re-training update, decrease in accuracy of prediction model, complexity, etc., and achieve the effect of expanding the sample space

Active Publication Date: 2021-08-20
JINAN UNIVERSITY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the technical problems of the decline in the accuracy of the prediction model in the prior art, retraining and updating are relatively complicated, the present invention proposes a case prediction agent training method and system that can be automatically updated

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
  • Case pre-judgment agent training method and system capable of automatically updating
  • Case pre-judgment agent training method and system capable of automatically updating
  • Case pre-judgment agent training method and system capable of automatically updating

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described with reference to the accompanying drawings.

[0031] The most fundamental feature of reinforcement learning is that it requires the agent to explore the environment and update the model parameters for the reward obtained by exploring the environment, which can just make up for the shortcomings of the judicial case prediction system designed using deep learning , that is, to be able to explore situations and states that have not appeared on the basis of existing data sets, and then to be able to adapt to changes in judicial cases caused by social changes, and to avoid the problem that the accuracy of the model decreases with time. Therefore, for judicial The use of reinforcement learning to solve problems in case prediction has high research value.

[0032] The automatically ...

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 case pre-judgment agent training method and system capable of being automatically updated, and the method comprises the steps: obtaining a certain number of judicial case trial books as samples, extracting the key information, such as facts, from the trial books, processing the data, receiving new data labeled by experts, constructing a new data set, carrying out modeling aiming at a judicial trial problem to obtain an accuracy calculation model of key information, extracting parameters required by training from the model, defining a reward function of model training, and carrying out intelligent agent model training according to the parameters and a data set by using a BCQ algorithm. According to the method, the problem of inaccurate judicial case prejudgment is solved by using a reinforcement learning method, meanwhile, improvement and optimization can be performed, and the accuracy of the model is kept for a long time.

Description

technical field [0001] The invention relates to the field of artificial intelligence, and mainly relates to the application of artificial intelligence in the judicial trial process, in particular to a case prediction intelligent agent training method and system capable of automatic updating. Background technique [0002] As the legal system continues to rely on social reality to improve, the number of judicial cases is gradually increasing, resulting in a heavy workload and great pressure on grassroots judges in various places. The majority of civil cases and contract disputes are characterized by simplicity and high repetition. However, due to the large number, they occupy a large amount of judicial case trial resources, resulting in frequent case backlogs all over the country. For problems that are effectively handled, it often takes several months for a case to go to trial, and the work efficiency of the judiciary has also declined as a result. [0003] Most of the commo...

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): G06F16/33G06N3/04G06N3/08G06Q50/18
CPCG06F16/3344G06N3/08G06Q50/18G06N3/045
Inventor 郭洪飞戴源志曾云辉何智慧任亚平张锐
Owner JINAN UNIVERSITY
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