Government affair service item classification method and system

A technology for matters and government affairs, which is applied in the field of government service matters classification methods and systems, can solve the problems of inability to effectively use the guidance data for matters handling, low accuracy of similarity calculation results, poor stability of business capabilities, etc., so as to reduce the workload of manual work. , Guarantee accuracy, guarantee the effect of accuracy and efficiency

Pending Publication Date: 2022-05-20
INSPUR SOFTWARE CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] When the items are classified and grouped, the manual screening method uses the keywords of the item name to filter other regional items, and then judges whether the information of the elements of the filtered item handling guide is the same as the current item, or judges the degree of conformity; this method has a large workload , and the stability of the business ability of the dependent matter classification group personnel is poor
However, the similarity calculation method of the short text similarity calculation method has low accuracy of similarity calculation results, and often matches a large number of irrelevant items, and cannot effectively use the item handling guide data

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
  • Government affair service item classification method and system
  • Government affair service item classification method and system
  • Government affair service item classification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] combined with figure 1 , 2 , this embodiment proposes a method for categorizing government service items, and the categorization process includes:

[0047] Step S1. Extract multiple item elements from the published government affairs guide, including item code, administrative division, item name, item catalog name, item type, industry guidance department, implementation subject, handling result, service object, law Basis, basic code, and whether it is a national catalog code. Among them, the legal basis is based on the laws and regulations database, select national-level laws and regulations, exclude local laws and regulations, and transform the legal basis into standard laws and regulations, based on the extracted multiple event elements Build a model of item characteristics.

[0048] Step S2. Obtain the items to be classified. The item feature model first matches to obtain the name of the relevant government affairs, and then filters the name of the government affai...

Embodiment 2

[0066] combined with image 3 , this embodiment proposes a system for categorizing government service items, the implementation modules of which include: an extraction and construction module 10 , an item feature model 20 , a set processing module 30 , and a comparison and classification module 40 .

[0067] The extraction and construction module 10 extracts a plurality of item elements from the published government affairs guide, and constructs an item feature model 20 based on the extracted plurality of item elements. The extracted item elements include item code, administrative division, item name, item catalog name, item type, industry guidance department, implementation subject, handling result, service object, legal basis, basic code, and whether it is a national catalog code. Among them, the legal basis is as follows: Based on the laws and regulations database, national laws and regulations are selected, local laws and regulations are excluded, and the legal basis is tr...

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 government affair service item classification method and system, and relates to the technical field of data analysis, and the classification process comprises the steps: extracting item elements from a published government affair item handling guide, and constructing an item feature model; to-be-classified items are obtained, the item feature model is firstly matched to obtain related government affair item names, then the government affair item names are filtered according to item types and industry guidance departments to obtain item sets, and then the item sets are weighted according to handling results, national directory codes and legal basis; extracting service object words and behavior feature words from the item directory names and the item names from the filtered item set by using semantic analysis and word segmentation technologies, performing standardization processing, and constructing a service object-management behavior-administrative power model; matching results of the two models are compared, and classification and grouping of the items to be classified are completed according to the matching results. The same item can be quickly positioned, item classification is realized, and item classification accuracy is guaranteed.

Description

technical field [0001] The invention relates to the technical field of data analysis, in particular to a method and system for classifying government service items. Background technique [0002] At present, in the evaluation and evaluation of government services, the classification and grouping of items from different regions is done through manual screening, or by calculation of the similarity of short texts of item names. The manual screening method is to search for items containing keywords through manual continuous query, and then query the service guide to determine whether it is the same item. The short text similarity calculation is to calculate the text similarity of the item name according to different algorithms through the calculation program, and filter the items with high similarity to avoid the process of manual continuous retrieval. [0003] When the items are classified and grouped, the manual screening method uses the keywords of the item name to filter oth...

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): G06F40/289G06F40/216G06F40/30
CPCG06F40/289G06F40/216G06F40/30
Inventor 张峰陈兆亮宁方刚胡芳龙
Owner INSPUR SOFTWARE 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
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