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

A Context Reasoning Method Based on Legal Expert Knowledge Base

A technology of expert knowledge base and reasoning method, which is applied in the fields of electrical digital data processing, special data processing application, natural language data processing, etc., and can solve problems such as uncompleted context reasoning methods and unfeasible methods

Active Publication Date: 2021-03-12
南京擎盾信息科技有限公司
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these reasoning methods in the prior art have the following disadvantages, that is, there is no perfect and easy-to-use context reasoning method in the field of legal texts, and the legal field is a professional field, and general methods are not feasible in this field

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
  • A Context Reasoning Method Based on Legal Expert Knowledge Base
  • A Context Reasoning Method Based on Legal Expert Knowledge Base
  • A Context Reasoning Method Based on Legal Expert Knowledge Base

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] see Figure 1~2 , in an embodiment of the present invention, a context reasoning method based on a legal expert knowledge base, which includes the following steps:

[0072] (1) Semantic vector space, which is divided into semantic vector space construction and semantic vector space mapping.

[0073] (1.1) Semantic vector space construction: construct a legal semantic vector library based on the legal text corpus, map text units to vectors in the semantic space, and the semantic similarity between text units can be compared according to the distance of the corresponding vectors in the semantic space , for words with similar semantics, their corresponding semantic vectors will also be very close in space, which overcomes the influence of word deformation, synonym change, and grammatical form change when words are directly compared.

[0074] The training methods of semantic vectors include Word2Vec, ESA (Explicit semantic analysis), LSA (Latent semantic analysis), co-occu...

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 context reasoning method based on a legal expert knowledge base. Based on the expert knowledge base, the invention understands the implicit semantic content in a legal text according to context reasoning through entity recognition and semantic analysis, and uses the New entities and reasoning results not included in the expert knowledge base are added to the expert knowledge base after manual review and arrangement, and the weight of each piece of expert knowledge and each legal entity is obtained from the corresponding corpus. The context reasoning method of the present invention is multi-reasoning Engine-integrated reasoning methods, including PMI-based scoring reasoning, first-order predicate logic reasoning, Bayesian reasoning, neural network reasoning, etc. This method is aimed at contextual reasoning in the field of legal texts, and can effectively solve part of the context in the language understanding of legal texts Reasoning problem: The reasoning method based on the knowledge base of legal experts adopted in the present invention has natural professional advantages in the legal field.

Description

technical field [0001] The invention relates to the technical field of legal text analysis, in particular to a context reasoning method based on a legal expert knowledge base. Background technique [0002] There are a large number of natural language texts in the legal field, and intelligence needs to do a good job in natural language understanding, and context reasoning is a crucial field in NLU. Context reasoning can be intuitively understood as solving the understanding problem of context-based reasoning mechanisms . Only by properly handling the contextual reasoning of legal texts can we truly realize various applications of artificial intelligence in the field of legal texts, such as intelligent question answering and intelligent summarization. At present, in the legal field, there is no substantive technical solution for legal text context reasoning. [0003] Chinese patents CN105808568A and CN 105677671A respectively introduce two general context reasoning methods f...

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): G06F16/36G06F40/295G06F40/30
CPCG06F16/367G06F40/295G06F40/30
Inventor 郑茂盛杜向阳储昭辉
Owner 南京擎盾信息科技有限公司
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