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

Graph-based judgment document case similarity calculation and retrieval method and system

A retrieval system and case technology, applied in the field of data processing, can solve the problems of low precision of search results and difficult tree representation.

Active Publication Date: 2018-05-15
江西思贤数据科技有限公司
View PDF6 Cites 55 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Moreover, in the actual trial process, the characteristics of the case are often intertwined, which is difficult to express in the form of a tree
[0007] Therefore, those skilled in the art are devoting themselves to developing a graph-based judgment document case similarity calculation and retrieval method and system, so as to solve the problem of low accuracy of search results caused by ignoring legal expertise and judicial logic in existing methods

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
  • Graph-based judgment document case similarity calculation and retrieval method and system
  • Graph-based judgment document case similarity calculation and retrieval method and system
  • Graph-based judgment document case similarity calculation and retrieval method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 As shown, a schematic flow chart of a graph-based judgment document case similarity calculation and retrieval method proposed by the present invention, a graph-based judgment document case similarity calculation and retrieval method includes the following steps:

[0041] Step S101: The server collects referee documents.

[0042] Step S102: Identify and locate the reasoning part in the judgment document, which part contains the key elements of the case and the trial result of the court.

[0043] Step S103: Cut the reasoning part of the judgment document into several text fragments according to the described content, semantics, and situation to form text clusters, and analyze the case elements for each text cluster.

[0044] Step S104: Form a matter map based on the case elements extracted in step 103.

[0045] Step S105: The user inputs search information, which may be the text of the complaint, the text of the trial transcript, or keywords, etc., and ...

Embodiment 2

[0050] Such as Figure 4 As shown, taking "Shanghai NTN XXX Co., Ltd. and Yang XX Labor Contract Dispute First Instance Civil Judgment" as an example, it specifically illustrates the implementation process of the similarity calculation and retrieval method based on the graph.

[0051]In this specific implementation, the more referee documents collected by the server, the more fact graphs that can be used for graph similarity calculation when retrieving similar referee documents, and the better the retrieval effect. Judgment documents record the trial process and results of the people's courts, and are the carrier of the results of litigation activities. Judgment documents include judgments, rulings, and mediation documents.

[0052] In this specific implementation, step S102 includes: finding similar phrases such as "this court believes" as the beginning of the reasoning part, and "this court supports" and "this court does not support" and other similar phrases expressing the...

Embodiment 3

[0074] Such as figure 2 Shown is a schematic diagram of the structure of a graph-based judgment document case similarity calculation device adopted by the graph-based judgment document case similarity calculation and retrieval system in a preferred embodiment of the present invention. Devices include:

[0075] Reasoning part identification module 201: used to identify the reasoning part in the judgment document or the search information input by the user.

[0076] Case element analysis module 202: used to semantically segment the reasoning part identified by the reasoning part identification module 201, form text fragments to form text clusters, and then perform element analysis to form a mapping between text and elements.

[0077] Affair map module 203: used to form an event map from the case elements analyzed by the case element analysis module 202.

[0078] Case element mapping module 204: used to extract or map the case elements that the user searches for case informati...

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 graph-based judgment document case similarity calculation and retrieval method. The method includes the following main steps that 1, judgment documents are collected; 2, thereasoning parts of the judgment documents are identified; 3, the case elements of the reasoning parts are analyzed; 4, case reason atlases are generated; 5, a client receives the retrieval information; 6, the case elements are extracted or mapped; 7, the reason atlases of the case elements are matched and calculated; 8, cases similar to retrieval content are returned. Meanwhile, the invention further discloses a graph-based judgment document case similarity calculation and retrieval system. The system is characterized by including a judgment document case similarity calculation device and a similar case document retrieval device. The method and the system fully consider the professional knowledge of the judgment documents, and the generated case reason atlases show the most critical elements and internal logical relations of the cases in a compressed but intuitive mode; therefore, the method and the system provide convenience for relevant persons to intuitively look over the main points of the cases, and meanwhile enable the relevant persons to accurately retrieve the relevant cases from a document library.

Description

technical field [0001] The present invention relates to the technical field of data processing, and in particular to a method and system for similarity calculation and retrieval of cases of judgment documents. Background technique [0002] Similar case retrieval is to use big data technology to mine and analyze public judgment documents, and to push directly related guiding or reference similar cases for judges, parties, and lawyers handling the case. Accurate and efficient retrieval of similar cases will greatly improve the quality and efficiency of case handling, and make the public feel fair and just. [0003] In the prior art, the matching of keywords or keyword combinations is usually used to retrieve similar judgment documents, and at the same time, the retrieval results are filtered in combination with preset conditions such as cause of action, court name, trial procedure, and judgment date. If exact matching is used for keyword retrieval, there will be few matching ...

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): G06F17/22G06F17/30
CPCG06F16/3328G06F40/194
Inventor 金耀辉姜华李慧王永坤
Owner 江西思贤数据科技有限公司
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