Automatic urban land identification system integrating business big data with building form

Patent metadata

Field	Value
Publication number	US-11270397-B2
Application number	US-202016963506-A
Country	US
Kind code	B2
Filing date	Jan 14, 2020
Priority date	Jan 25, 2019
Publication date	Mar 8, 2022
Grant date	Mar 8, 2022

Abstract

An automatic urban land identification system integrating business big data with building forms, including a data acquiring and inputting module, a database construction module, a machine learning training module, an automatic identification module, and a data outputting module. The system automatically identifies an urban land by extracting a data distribution feature of an urban business site and a multi-dimensional form feature of an urban spatial three-dimensional entity. The system can be used for the determining of land usage of an urban plot in the field of urban planning and design, to achieve efficient and automatic refined identification of land usages of cities of different scales based on an artificial intelligence system, providing an efficient and convenient surveying and mapping approach and reference for surveying and mapping of the current urban construction land, and effectively saving time costs of manual surveying and mapping.

First claim

What is claimed is:

1. An automatic urban land identification system integrating business big data with building forms, the automatic urban land identification system comprising:
a data acquiring and inputting module configured to acquire and store spatial vector data and business site data within a plurality of constructed regions of a plurality of case cities of a plurality of different scales and a target city, and input the spatial vector data and the business site data into a geographic information system, wherein the plurality of case cities of the plurality of different scales are classified into five types: a super mega city, a mega city, a large city, a medium-sized city, and a small city, one database and one machine learning classification model being correspondingly generated for each type of city, and the business site data comprises a business site name, a plurality of geographic coordinates, and business feature type information, wherein the business feature type information is information about an industry, wherein a business site belongs to the industry, functional information of the business site, or classification information of the business site;
a database construction module configured to calibrate and associate data through the geographic information system according to a set automatic spatial calibration method to obtain a plot database associated with the business site, a weight, according to a business feature importance, the plot database associated with the business site, automatically calculate a plurality of indicators of a maximum height, an average height, an average base area, and a floor area ratio of all buildings in each plot according to a plurality of set building form feature indicators, associate the plurality of indicators with the each plot, and generate and store the plot database comprising a plurality of weighted business features and a plurality of form features, the plot database comprising a database of the target city and a plurality of databases of the plurality of case cities of the plurality of different scales;
a machine learning training module configured to input land usage standard data of the plurality of case cities of the plurality of different scales, the land usage standard data being classified according to a plurality of land subclasses and being used as a plurality of machine learning labels; and perform, by using a supervised classification learning algorithm, a machine learning training on the plurality of databases of the plurality of case cities of the plurality of different scales comprising the plurality of weighted business features and the plurality of form features and obtained by the database construction module, to generate a plurality of machine learning classification models corresponding to a plurality of different city scales, and combine the plurality of machine learning classification models to form an automatic urban land identification model cluster;
an automatic identification module configured to automatically identify, by using a trained automatic urban land identification model cluster, an urban land usage and a confidence degree corresponding to the each plot in a constructed region of the plurality of constructed regions of the target city according to the database of the target city comprising the plurality of weighted business features and the plurality of form features and generated in the database construction module; and
a data outputting module configured to input, into a plot vector file, a plurality of land usages according to the plurality of land subclasses corresponding to a plurality of different color blocks, and annotate a plurality of data confidence degrees to obtain a current urban land usage map.

2. The automatic urban land identification system integrating business big data with building forms according to claim 1 , wherein the spatial vector data within an urban constructed region comprises a polygonal block with a closed outline, wherein the polygonal block comprises more than one polygonal plot with the closed outline, the each plot comprising more than one polygonal building with the closed outline, a building having information about a number of floors or a height.

3. The automatic urban land identification system integrating business big data with building forms according to claim 1 , wherein the set automatic spatial calibration method comprises: spatially calibrating the business site and an urban block, spatially calibrating the business site and a land plot, associating the business site with a plurality of attributes of the land plot and the urban block, wherein the business site is located at the urban block, and first performing an expansion on the urban plot and then spatially joining the business site data.

4. The automatic urban land identification system integrating business big data with building forms according to claim 1 , wherein the geographic information system is configured to process the spatial vector data and comprising: Aeronautical reconnaissance coverage Geographic Information System (ArcGIS) and Computer Aided Design (CAD).

5. The automatic urban land identification system integrating business big data with building forms according to claim 1 , wherein weighting the plot database associated with the business site is implemented in the following manner:
processing the plot database associated with the business site by using a TF-IDF algorithm according to the following formula:

n

i
,
j

∑
K

⁢

n

i
,
j

·
log

⁢


D


{

j
⁢

:

⁢

t
i

∈

D
j

}

wherein i is a plot number, j is a business feature number, n i,j is a frequency of a j th business feature of an i th plot, K is a number of dimensions of the business feature, |D| is a total number of plots in a city, and {j:t i ∈D j } is a number of plots of the city wherein the frequency of the j th business feature is not 0.

6. The automatic urban land identification system integrating business big data with building forms according to claim 1 , wherein the indicator of the plurality of indicators of the maximum height of all the buildings within the each plot is a maximum value of heights of all the buildings in the each plot; the indicator of the plurality of indicators of the average height of all the buildings within the each plot is an average value of the heights of all the building in the each plot; the indicator of the plurality of indicators of the average base area of

Assignees

• Univ Southeast

Inventors

• Yang Junyan
• Shao Dian
• Wang Qiao
• Liu Zhicheng

Classifications

• G06V20/176

  Urban or other man-made structures · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06F18/2431

  Multiple classes · CPC title

• G06Q50/16

  Real estate · CPC title

• G06Q50/26 Primary

  Government or public services (business processes related to the transportation industry G06Q50/40) · CPC title