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

Policy text multi-label labeling method and system based on graph neural network

A neural network and multi-label technology, applied in the field of text data processing, can solve problems such as waste of resources, achieve the effect of reducing labor costs, reducing subjective differences, and accurate labeling

Active Publication Date: 2021-06-04
SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN +1
View PDF15 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the deficiencies of the prior art, the present invention provides a policy text multi-label tagging method and system based on a graph neural network; through word semantic understanding of policy files, tagging of policy files and intelligent information extraction, to solve the existing manual tagging There is a lot of waste of resources

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
  • Policy text multi-label labeling method and system based on graph neural network
  • Policy text multi-label labeling method and system based on graph neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] This embodiment provides a policy text multi-label labeling method based on graph neural network;

[0033] Such as figure 1 As shown, the policy text multi-label labeling method based on graph neural network includes:

[0034] S101: Obtain the policy text to be marked;

[0035] S102: Perform preprocessing on the policy text to be marked, and perform word segmentation on the preprocessed policy text;

[0036] S103: Input the word obtained by word segmentation and the pre-obtained weighted word vector into the fully connected neural network after training, and output the multi-label of the policy text to be labeled.

[0037] Further, the weighted word vector obtained in advance is:

[0038] the sum of the first product and the second product;

[0039] Wherein, the first product refers to the product of the first word vector and the first weight;

[0040] The second product refers to the product of the second word vector and the second weight.

[0041] Further, as ...

Embodiment 2

[0093] This embodiment provides a policy text multi-label tagging system based on graph neural network;

[0094] Policy text multi-label tagging system based on graph neural network, including:

[0095] An acquisition module configured to: acquire the policy text to be marked;

[0096] A preprocessing module, which is configured to: preprocess the policy text to be marked, and perform word segmentation on the preprocessed policy text;

[0097] The output module is configured to: input the word obtained by word segmentation and the pre-obtained weighted word vector into the fully connected neural network after training, and output the multi-label of the policy text to be labeled.

[0098] It should be noted here that the above acquisition module, preprocessing module and output module correspond to steps S101 to S103 in the first embodiment, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited...

Embodiment 3

[0102] This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, the processor is connected to the memory, and the one or more computer programs are programmed Stored in the memory, when the electronic device is running, the processor executes one or more computer programs stored in the memory, so that the electronic device executes the method described in Embodiment 1 above.

[0103] It should be understood that in this embodiment, the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA 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, o...

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 policy text multi-label labeling method and system based on a graph neural network. The policy text multi-label labeling method comprises the steps of obtaining a policy text to be labeled; preprocessing the policy text to be labeled, and performing word segmentation on the preprocessed policy text; and inputting words obtained by word segmentation and weighted word vectors obtained in advance into the trained full-connection neural network, and outputting multiple labels of the policy text to be labeled. and in the efficient label labeling process, cheap computing resources are utilized, and a large amount of labor cost is reduced. Compared with manual work, more accurate label labeling is achieved, and mistakes and omissions of label labeling caused by the length of the file information are avoided. And timely policy file multi-label labeling is realized, and the label labeling of the required policy file is quickly carried out. The subjective difference is reduced, and the difference of a large number of labeled labels caused by different subjective judgment of different workers is avoided.

Description

technical field [0001] The invention relates to the technical field of text data processing, in particular to a multi-label tagging method and system for policy text based on a graph neural network. Background technique [0002] The statements in this section merely mention the background technology related to the present invention and do not necessarily constitute the prior art. [0003] With the maturity of Internet technology and information technology, many government departments are more and more inclined to publish policy documents on their official websites, and policy documents are released more frequently, and the number of documents is increasing, but The mass distribution of documents also brings with it the lack of means to use the information efficiently. It is becoming easier for enterprises to obtain a large amount of policy text information, but they urgently need efficient means of policy information processing. The current policy document information is r...

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): G06F40/284G06N3/08
CPCG06F40/284G06N3/08
Inventor 吴晓明石金泽刘祥志汪付强张鹏
Owner SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN
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