Unlock instant, AI-driven research and patent intelligence for your innovation.

A business district discovery method based on gcn embedded spatial clustering model

A technology of spatial clustering and discovery methods, applied in business, neural learning methods, biological neural network models, etc., can solve time-consuming and labor-intensive problems

Active Publication Date: 2022-06-21
ZHEJIANG UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This task is very time-consuming and labor-intensive

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
  • A business district discovery method based on gcn embedded spatial clustering model
  • A business district discovery method based on gcn embedded spatial clustering model
  • A business district discovery method based on gcn embedded spatial clustering model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The present invention will be further described below in conjunction with the example found in Xiaoshan District, Hangzhou.

[0061] The overall framework of the business district discovery method in this example is as follows: figure 1 shown, including the following steps:

[0062] (1) Obtain taxi trajectory data from Hangzhou Taxi Company, and obtain POI and road network information from Beijing Jietai Tianyu Information Technology Co., Ltd., then filter and preprocess the data, and classify parts of Xiaoshan District according to road network data. Divide into n regions. The data set statistics used in the present invention are as follows:

[0063]

[0064] (2) Using the preprocessed data, obtain a matrix representing the geographic similarity of any two regions and a distribution matrix of taxi trajectory points representing the popularity of the region, including the following steps:

[0065] a). Matrix of geographic similarity:

[0066] Take the number of a...

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

A commercial area discovery method based on GCN embedding spatial clustering model, including: 1) Data collection: comprehensively consider multiple data sources, including geographical data, road network data and taxi trajectory data, etc., after screening, extraction and preprocessing, Obtain the data required for the experiment; 2) feature extraction: apply the Pearson correlation coefficient to analyze the similarity between regions, and construct the edge features and node features required by the graph convolutional neural network; 3) embedding space clustering: in the discovery city When considering the functional areas in the functional area, considering geographical similarity and human mobility, the present invention uses a hierarchical clustering algorithm in the embedding space of the graph convolutional neural network; 4) Candidate area identification: the present invention uses Gaussian kernel density estimation to perform functional The evaluation, combined with the results of clustering, finally confirms the candidate business district, which has excellent performance in dealing with similar problems.

Description

technical field [0001] The invention relates to the field of data mining, in particular to a method for discovering commercial functional areas of a city and planning the construction of urban commercial districts. Background technique [0002] With the rapid development of economy and information technology, people's ever-improving modern life has brought about problems such as traffic congestion, environmental pollution, and resource allocation. In the past, it was difficult to solve these problems due to the complex setting of cities. Today, due to the maturity of various sensor technologies and cloud computing services, we have a variety of big data such as traffic flow, taxi trajectory data, and geography. These urban heterogeneous big data provide new possibilities and ideas for solving these problems. Using urban big data and urban computing to provide valuable information for city managers and planners, improve traffic control capabilities, service efficiency, and im...

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): G06F16/9537G06K9/62G06N3/04G06N3/08G06Q30/02G06Q30/06G06Q50/30
CPCG06F16/9537G06Q30/0205G06Q30/0645G06N3/08G06N3/045G06F18/231G06Q50/40
Inventor 沈国江赵振振孔祥杰刘娜利刘志
Owner ZHEJIANG UNIV OF TECH