Multi-label labeling method and system for policy text based on graph neural network

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

Active Publication Date: 2022-06-21
SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN +1
View PDF15 Cites 1 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
  • Multi-label labeling method and system for policy text based on graph neural network
  • Multi-label labeling method and system for policy text based on graph neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

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

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

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

[0035] S102: Preprocess the policy text to be labeled, and perform word segmentation on the preprocessed policy text;

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

[0037] Further, the pre-obtained weighted word vector 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 figure 2 As ...

Embodiment 2

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

[0094] A multi-label annotation system for policy text based on graph neural network, including:

[0095] an acquisition module, which is configured to: acquire the policy text to be marked;

[0096] a preprocessing module, which is configured to: preprocess the policy text to be labeled, and segment the preprocessed policy text;

[0097] The output module is configured to: input the word obtained by word segmentation and the weighted word vector obtained in advance 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 a...

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 Stored in the memory, when the electronic device runs, the processor executes one or more computer programs stored in the memory, so that the electronic device executes the method described in the first embodiment.

[0103] It should be understood that, in this embodiment, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors, DSPs, application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), 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 th...

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 tagging method and system based on a graph neural network, comprising: obtaining policy text to be tagged; preprocessing the policy text to be tagged, and performing word segmentation on the preprocessed policy text; The word and the pre-obtained weighted word vector are input into the trained fully connected neural network, and the multi-label of the policy text to be labeled is output. Efficient labeling process, using cheap computing resources, reduces a lot of labor costs. Compared with manual work, more accurate labeling is achieved, and labeling errors and omissions will not occur due to the length of document information. Timely multi-label labeling of policy documents, fast labeling of required policy documents. The subjective difference is reduced, and a large number of labeling differences will not be caused due to different subjective judgments of different workers.

Description

technical field [0001] The invention relates to the technical field of text data processing, in particular to a method and system for multi-label labeling of policy texts based on graph neural networks. Background technique [0002] The statements in this section merely provide background related to the present disclosure and do not necessarily constitute 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 the publication of policy documents is more frequent and the number of documents is increasing, but The mass distribution of documents also creates the problem of a lack of means of efficient use of the information. It is more and more easy 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...

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): 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 Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap