Chinese POI matching method based on natural language understanding

A technology of natural language understanding and matching method, applied in the field of Chinese POI matching based on natural language understanding, can solve the problems of inconsistent expression of Chinese characters, polysemy, and low matching accuracy of Chinese POI, etc. matching effect

Inactive Publication Date: 2021-03-19
安徽迪科数金科技有限公司
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that Chinese POI data has incomplete Chinese addresses, inconsistent Chinese text expressions and polysemy, which lead to low matching accuracy of Chinese POIs, and proposes a method based on natural language understanding. Chinese POI matching method

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
  • Chinese POI matching method based on natural language understanding
  • Chinese POI matching method based on natural language understanding
  • Chinese POI matching method based on natural language understanding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0054] see Figure 1-9 As shown, the Chinese POI matching method based on natural language understanding includes the following steps:

[0055] S1: collect POI data, POI data is the address of Baidu map and Gaode map collected by web crawler;

[0056] S2: Preprocessing the POI data, the specific steps are:

[0057] S21: uniformly transform the POI data into the same data structure and spatial coordinate system, clean the POI data, and retain the ID, name, spatial coordinates, address and category label in the POI data;

...

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 Chinese POI (Point Of Interest) matching method based on natural language understanding, which is used for solving the problem of low Chinese POI matching precision caused byfrequent incomplete Chinese addresses, inconsistent Chinese character expressions and one-word polysemy of multi-source Chinese POI data. According to the method, six similarity measurement characteristics of geometric positions, category structures, POI names and address attributes are integrated and input into the deep neural network to calculate the matching probability, so that the influenceof subjective factors caused by artificial weight allocation is avoided; a natural language understanding technology is introduced to fully consider the semantic relationship between address attributes and name attributes in the similarity calculation process of the six attribute characteristics to overcome the defects of a traditional algorithm; short text similarity calculation is improved by using a neural network of a twin attention mechanism, and POI data accurate matching is achieved in combination with grammar, semantics and spatial similarity calculation.

Description

technical field [0001] The invention relates to the technical field of POI matching, in particular to a Chinese POI matching method based on natural language understanding. Background technique [0002] POI is a kind of point data representing real geography. POI generally includes basic information such as name, category, latitude and longitude, address, etc. It can represent entities of interest to people such as hotels and scenic spots. With the development of big data and electronic maps based on location services, POI data on the Internet has also grown rapidly, and spatial data represented by points of interest has gradually attracted attention. POI is of great significance to the user-oriented research on the relationship between people and land. As an important part of the place name and address database, it provides services for the development of smart cities; [0003] Geographical information data collected from different sources usually have problems such as red...

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): G06F16/29G06F16/33G06F16/35G06F40/289G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06F16/29G06F16/3344G06F16/35G06F40/289G06F40/30G06N3/049G06N3/084G06N3/047G06N3/045G06F18/2415G06F18/241
Inventor 张先荣
Owner 安徽迪科数金科技有限公司
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