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

Class case pushing method and device based on case description

A technology for cases and judgments, applied in text database clustering/classification, biological neural network models, semantic analysis, etc., can solve the problems of reducing accuracy and impact, and achieve the effect of improving results

Pending Publication Date: 2020-08-25
INSPUR QILU SOFTWARE IND
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, similar to the vector space method, this method will also be affected by other types of elements other than the case description when performing vectorized encoding, thereby reducing the accuracy rate
[0012] Among the above four types of methods, the vector space method and the deep learning method are currently the most used methods, and it is a development trend to combine the two methods to push similar cases. Factors of influence

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
  • Class case pushing method and device based on case description
  • Class case pushing method and device based on case description
  • Class case pushing method and device based on case description

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0106] Select 280 judgments from eight provinces and municipalities directly under the central government as an example to demonstrate the processing process of this method, and use several query examples to compare with the query results of the conventional method (using the full text of judgments to construct a latent semantic space), and the indicators include similarity and ranking.

[0107] Executing S11: operations including word segmentation, removing spaces and stop words, etc. First remove spaces, then remove stop words according to the stop word list, and use Stanford NLP for word segmentation;

[0108] Execute S12221: set the word vector dimension of Word2Vec to 100;

[0109] Execute S12222: set the hidden layer dimension of Bi-LSTM to 100;

[0110] Execute S12223: splicing together the output of the forward / backward LSTM terminal, the dimension of the formed vector is 200;

[0111] Execute S1225: set the hidden layer dimension of Bi-LSTM to 200;

[0112] Execut...

example 1

[0141] Example 1: Hu Moutong stole a red motorcycle of a certain brand

[0142] Location: 35 copies of H Province / (2014) Cheng Xing Chu Zi No. 883 Hu Moutong Criminal Judgment for Theft.txt,

[0143] Similarity: 0.38114216172268367->0.9715493492582427

[0144] Rank: 9->1

example 2

[0145] Example 2: Zhang and Liu discussed going to sea at night to steal sea cucumbers

[0146] Location: 35 copies of S Province / Criminal Judgment of the Second Instance of Zhang’s Theft Case.txt

[0147] Similarity: less than 0.49 -> 0.9974174977991768

[0148] Rank: Out of 15 -> 1

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 particularly relates to a class case pushing method and device based on case description. The class case pushing method based on case description comprises the following steps: firstly,hierarchically encoding each paragraph of a decision by means of a deep learning model, forming features according to the context encoding of the paragraph, performing binary classification modeling through a multi-layer perceptron, generating a case description judgment model through training, and extracting case description of a to-be-processed decision by using the model; secondly, constructinga decision-making case description potential semantic space; and finally, mapping a query statement input by the user to a potential semantic space, calculating the similarity between the query statement and all case description vectors, sorting according to the similarity, and recommending a decision corresponding to the TopK case description to the user. According to class case pushing method and device, the influence of other types of elements except the case description is reduced, the class case pushing effect is improved, the case description can be accurately extracted from the decision, and the method and device are suitable for popularization and application.

Description

technical field [0001] The invention relates to the technical fields of text retrieval and neural network, in particular to a method and device for pushing similar cases based on case description. Background technique [0002] Under the background of the intelligent revolution era, the construction of "smart courts" is in full swing, and has achieved phased results. A large number of intelligent auxiliary case handling systems have been built in various places. Among them, the push of similar cases is the basis of these systems. It uses advanced technologies such as natural language processing and artificial intelligence to process massive judgments in the judicial field, find judgments similar to the current case, and push them to relevant users; it can better play The actual value of massive legal documents, thereby improving the efficiency of judicial work. [0003] At present, the commonly used relationship extraction methods include the following four: [0004] (1) Ke...

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): G06F16/33G06F16/35G06F40/30G06Q50/18G06N3/04
CPCG06F16/3344G06F16/35G06F40/30G06Q50/18G06N3/044G06N3/045Y02D10/00
Inventor 王功明谢超王建华张尧臣
Owner INSPUR QILU SOFTWARE IND
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