Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Data processing method, system, device, medium and data analysis method

A data processing and data technology, applied in electrical digital data processing, natural language data processing, special data processing applications, etc., can solve the problems of survivor principle error, statistical dimension subjective interference, sample deviation, etc., to improve the coverage rate and comprehensiveness, the comprehensive effect of the statistical dimension

Active Publication Date: 2021-08-20
CHENGDU UNION BIG DATA TECH CO LTD
View PDF20 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantages of this approach are: 1. The number of samples taken is very small, which is prone to sample deviation and erroneous conclusions based on the survivor’s principle; 2. The dimension of statistics is easily subject to subjective interference by individual referee documents and statisticians, resulting in one-sided results. in conclusion
3. The sample size is too small, and there is no statistics on other dimensions, such as cross-time concept and regional concept statistics, which leads to the inability to effectively judge the development trend and situation of this type of crime within the preset dimension

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
  • Data processing method, system, device, medium and data analysis method
  • Data processing method, system, device, medium and data analysis method
  • Data processing method, system, device, medium and data analysis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Embodiment 1 of the present invention provides a data processing method based on information of referee documents, such as figure 1 As shown, the method includes:

[0047] Screen out the judgment document data containing preset types of crimes from the judgment document database;

[0048] Extracting the factual data of the case in the data information of the judgment document;

[0049] Establishing a graph neural network, and inputting the case fact data into the graph neural network;

[0050] Extract entity information data, relationship data and event sequence information data between entities at the node positions of the graph neural network, and convert to result data output, the result data including (entity 1, relationship, entity 2) triplet and The type of crime to which the judgment document belongs.

[0051] Wherein, the extracting the case fact data in the judgment document data information includes: dividing the judgment document data into sections to obta...

Embodiment 2

[0075] Embodiment 2 of the present invention provides a data processing system based on the information of referee documents, please refer to figure 2 , the system includes:

[0076] 1 Judgment document screening unit, used to filter out the judgment document data containing preset types of crimes from the judgment document database;

[0077] An extraction unit, configured to extract the case fact data in the judgment document data information;

[0078] A building unit, configured to build a graph neural network, and input the factual data of the case into the graph neural network;

[0079] The processing unit is used to extract entity information data, relationship data between entities and event sequence information data at the node positions of the graph neural network, and convert them into result data output, and the result data includes (entity 1, relation, entity 2 ) triplet and the type of crime to which the judgment document belongs.

Embodiment 3

[0081] Embodiment 3 of the present invention provides a data processing device based on information of referee documents, including a memory, a processor, and a computer program stored in the memory and operable on the processor, and the processor executes the The computer program realizes the steps of the data processing method based on the information of the judgment document.

[0082]Wherein, the processor can be a central processing unit (CPU, Central Processing Unit), and can also be other general processors, digital signal processors (digital signal processors), application specific integrated circuits (Application Specific Integrated Circuits), off-the-shelf programmable Gate array (Field programmable gate array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.

[0083] The memory can be ...

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 data processing method, a system, a device, a medium and a data analysis method, and relates to the field of natural language processing, and the method comprises the steps: screening out judgment document data containing a preset type of crime from a judgment document library; extracting case situation and fact data in the judgment document data information; establishing a graph neural network, and inputting the case situation and fact data into the graph neural network; extracting entity information data, relation data between entities and event sequence information data at node positions of the graph neural network and converted into result data to be output, and the result data comprise a triple (entity 1, relation and entity 2) and crime types to which judgment documents belong; the analysis and statistics result obtained by the method is based on the total judgment document data of the preset crime type in the judgment document library; and heuristic information extraction is carried out through a deep learning method, so that the statistical dimension is more comprehensive and is not easily interfered by people.

Description

technical field [0001] The present invention relates to the field of natural language processing, in particular, to a data processing method, system, device, medium, and data analysis method. Background technique [0002] In recent years, the phenomenon of crime has increased significantly, and the types of crime have shown a trend of diversification. With the continuous progress of our country's social development, the judiciary needs to conduct further analysis and research on the types of crimes and the development trend of diversity. To meet these needs, the analysis and statistics of past judgment documents is particularly important, and the analysis of past cases involved is also very important. [0003] Judgment documents involving certain types of crimes over the years are collected from the existing judgment document database, and then the information in the collected judgment documents is extracted and counted using deep learning methods. At present, the industry...

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): G06F16/332G06F16/35G06F16/36G06F40/279G06N3/04G06N3/08
CPCG06F16/3329G06F16/35G06F16/367G06F40/279G06N3/04G06N3/08
Inventor 翁洋李鑫王竹其他发明人请求不公开姓名
Owner CHENGDU UNION BIG DATA TECH CO LTD
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
Eureka Blog
Learn More
PatSnap group products