Urban Land Identification Using Building Forms and Business Big Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current urban land identification methods are inefficient, time-consuming, and prone to errors due to manual surveying and mapping, and non-supervised cluster identification fails to accurately distinguish urban land subclasses.
Innovation Solution
An automatic urban land identification system integrating business big data with building forms, utilizing a supervised classification learning algorithm, spatial calibration, and machine learning models to generate precise urban land usage maps with confidence degrees.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual surveying and mapping is performed on site with reference to topographic maps, then comprehensive determining results can be obtained, but the surveying and mapping time is long and consumption of manpower and material resources is large
Solution Approach 1:
The patent uses remote sensing images and aerial photography to create digital copies of urban land surfaces, replacing manual field surveying. The system extracts building footprint information from these image copies automatically, significantly reducing the time and resources required while maintaining identification accuracy.
Solution Approach 2:
The patent replaces the mechanical manual surveying process with an automated computer-based system that uses image processing algorithms, machine learning models, and digital database operations to extract and identify land usage information, eliminating the need for physical field measurements.
2Measurement precision
If manual surveying and mapping is performed on site, then comprehensive determining results can be obtained, but consumption of manpower and material resources is large
Solution Approach 1:
The system creates digital replicas of urban areas through remote sensing and aerial imaging, allowing multiple analyses to be performed on the same data set without requiring additional field trips or physical resources, thus reducing manpower and material consumption while maintaining comprehensive identification capabilities.
Solution Approach 2:
The automated system performs self-service by automatically processing remote sensing images, extracting building footprint information, and generating land usage identification results without requiring human intervention in the field, thereby eliminating the need for surveyors and reducing material resource consumption.
3Ease of operation
If non-supervised cluster identification based on business points of interest is performed, then identification process is simplified, but identification result has a large error coefficient due to insufficient data dimensions
Solution Approach 1:
The patent merges multiple data sources including remote sensing images, building footprint information, business points of interest, and land parcel data into a unified identification system. This combination of diverse data dimensions improves measurement precision while maintaining ease of operation through automated integration.
Solution Approach 2:
The system creates a composite information model that integrates multiple types of urban data (spatial, functional, and descriptive) similar to how composite materials combine different substances. This multi-layered data structure provides comprehensive coverage for accurate land usage identification while keeping the process simple through automated processing.
4Ease of operation
If non-supervised cluster identification based on business points of interest is performed, then identification process is simplified, but identification result has a large error coefficient
Solution Approach 1:
The patent combines non-supervised cluster identification with supervised classification methods and multiple data validation sources, creating a hybrid system that maintains operational simplicity while improving reliability through cross-verification of results from different identification approaches.
Solution Approach 2:
The system implements feedback mechanisms where identification results are continuously validated against multiple data sources and can be refined through iterative processing. This feedback loop ensures high reliability while keeping the user interface simple and automated.
Data Source
Figure 1
Figure 2~3
Figure 4~5.1
AI summary
The present invention discloses 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 present invention 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.