Construction method of urban geographic semantic knowledge graph

A construction method and semantic knowledge technology, applied in the construction of urban geographic semantic knowledge graph, can solve the problem of not making full use of cutting-edge methods in the field of natural language processing, and achieve the effect of diversifying data sources

Active Publication Date: 2019-11-19
PEKING UNIV
View PDF6 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These studies have confirmed that the method of accumulating single data analysis results to obtain regional features is feasible, but the data mining methods used have certain limitations and do not make full use of the cutting-edge methods in the field of natural language processing

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
  • Construction method of urban geographic semantic knowledge graph
  • Construction method of urban geographic semantic knowledge graph
  • Construction method of urban geographic semantic knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In the following, the present invention will be further explained through specific embodiments in conjunction with the drawings.

[0041] Such as figure 1 As shown, the method for constructing an urban geographic semantic knowledge graph of this embodiment includes the following steps:

[0042] 1) Manually divide the area within the Fifth Ring Road in Beijing to obtain 201 location entities, using the Weibo corpus with location tags provided by Sina Weibo, a total of 4,591,517 pieces, and divide them into corresponding location entities according to their location tags .

[0043] 2) Using the long and short-term memory (LSTM) model to classify social text data in geographic and semantic related or irrelevant categories, and then multi-categorize the geographic semantics of Weibo texts related to geographic semantics, and calculate each location entity about each The saliency of a geographic semantic topic, as the saliency attribute of the place entity:

[0044] a) Pre-trainin...

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 construction method of an urban geographic semantic knowledge graph. According to the invention, public transport relations between implicit city geographic semantics extracted from social text data and places are integrated, so that a user can form comprehensive cognition of each place in a city, and reference information is provided for decisions such as travel or cityplanning. According to the invention, the conceptual relation is replaced by the public traffic relation in reality, so that the relation network depicted by the knowledge graph is closer to daily life scenes such as place recommendation and place traffic association query; data sources are more diversified, basic information in longitude and latitude, urban areas and other traditional geographicinformation systems is included, and implicit geographic semantics extracted from social text data through the natural language processing technology such as regional function significance and the good reputation rate are further included.

Description

Technical field [0001] The invention relates to the technical field of data mining, in particular to a method for constructing an urban geographic semantic knowledge graph. Background technique [0002] Early geographic information acquisition mainly relied on basic surveying and mapping, satellite remote sensing and other means, emphasizing geometric accuracy. With the development of information technology and the rapid popularization of sensors and smart phones and other devices, geographic information providers and service targets are gradually shifting from professionals to the general public. In addition, the advancement of data mining technology in recent years has made it possible to extract implicit geographic information from a large amount of data such as social texts and information portals on the Internet. According to statistics, 18.78% of web text resources contain geographic location information, and 18.6% of web searches are related to geographic location. This ...

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): G06F16/36G06F16/35G06F16/951G06F16/9537G06F17/27G06Q50/00
CPCG06F16/367G06F16/355G06F16/951G06F16/9537G06Q50/01
Inventor 孙艳春黄罡林刘子轩孙志玉
Owner PEKING UNIV
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