Intelligent identification system based on legal knowledge graph

A knowledge graph, intelligent identification technology, applied in the field of technology and legal integration, can solve problems such as inability to give users answers, consuming a lot of manpower and time, and cumbersome process operations.

Inactive Publication Date: 2019-10-18
天津汇智星源信息技术有限公司
View PDF8 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The existing intelligent recognition system for the legal knowledge graph lacks semantic analysis and semantic understanding of legal common sense, and the process operation is relatively cumbersome, unable to give users a completely accurate answer, and requires a lot of manpower and time to screen and eliminate irrelevant laws technical issues of 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
  • Intelligent identification system based on legal knowledge graph
  • Intelligent identification system based on legal knowledge graph
  • Intelligent identification system based on legal knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0027] A reasoning and precise intelligent question answering method based on the legal knowledge graph, such as Figure 1-3 Shown:

[0028] 1. Word vector representation module:

[0029] 1. Build entity dictionary:

[0030] Extract entity names directly from knowledge graph triples to build entity dictionaries.

[0031] 2. Construct the structure recognition annotation set module:

[0032] The training and testing process of named entity recognition also requires specialized data sets. Unlike general legal data sets, we need to make special annotations for corpus questions and entities. Its algorithm (pseudo-code) flow is shown below.

[0033] Algorithm: entity recognition annotation set construction algorithm;

[0034] Input: training set (question sequence, standard answer), knowledge map;

[0035] Output: entity annotation set;

...

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 relates to an intelligent recognition system based on a legal knowledge graph, which belongs to the field of fusion of technologies such as knowledge graphs and natural language processing and laws, and comprises a word vector representation module, a model training module, a question annotation module, a candidate entity set acquisition module and an emotion recognition module; theword vector representation module is trained by adopting Skip-gram model; the model training module is used for starting to train an entity recognition model by utilizing tensorflow; the question annotation module is used for extracting user question features by utilizing word vectors and inputting the user question features into a trained model to obtain a question sequence annotated by the model; the candidate entity set obtaining module is used for obtaining entity tags marked in a question sequence through the question marking module and obtaining candidate entity names through the entitytags; and the emotion recognition module is used for extracting user emotion from the question description statement of the user. According to the invention, the labor cost can be greatly reduced, andthe intelligent legal semantic recognition speed is increased.

Description

technical field [0001] The invention relates to an intelligent identification system based on a legal knowledge map, and belongs to the technical field of knowledge map and natural language processing and other technology and law fusion. Background technique [0002] Knowledge graph technology is increasingly becoming the basis of artificial intelligence, and it is an important method for machines to understand natural language and build knowledge networks. In recent years, the use of knowledge graphs in the judicial field has quietly emerged. It helps practitioners quickly retrieve relevant legal content online, thereby improving the quality and efficiency of court trials. The existing automatic legal question answering system is based on full-text search technology or deep learning semantic matching technology, which often cannot truly understand the real legal demands of users, cannot solve users' legal problems, and has poor practicability. [0003] In the era of artifi...

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): G06F17/27G06N3/04
CPCG06N3/049G06F40/295G06F40/30
Inventor 余梓飞张程华刘双勇
Owner 天津汇智星源信息技术有限公司
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