Land Use Planning Using Heterogeneous Temporal Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Land-use planners face challenges in distilling vast amounts of heterogeneous temporal data from geographical areas into actionable formats, particularly in capturing multiple dimensions of structured and unstructured data that change over time, to make informed decisions about land-use interventions.

Innovation Solution

A method is provided to summarize heterogeneous data into a machine-processable representation, enabling the computation of recommendations for land-use interventions by identifying similar geographical areas and learning from evolving textual data sources, with a user interface for feedback and explanation of recommendations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If planners manually analyze vast amounts of heterogeneous temporal data, then comprehensive understanding of land-use patterns is achieved, but time consumption and analytical complexity increase significantly

Engineering Contradiction:
Improvecomprehensive understanding of land-use patternsVSAvoidtime consumption for data analysis
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical analysis of heterogeneous temporal data with automated machine learning models and natural language processing systems. These computational systems process satellite imagery, census data, crime statistics, and other temporal datasets automatically, extracting land-use patterns and generating insights without human intervention in the data processing stage, thus resolving the contradiction between comprehensive understanding and time consumption.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates computational representations and models that copy and simulate real-world land-use patterns from heterogeneous data sources. By generating synthetic datasets and virtual models of urban areas, the system enables rapid analysis and planning scenario evaluation without requiring extensive manual processing of original complex datasets, reducing time while maintaining analytical depth.

Inventive Principle:
Principle #26Copying

2Reliability

If multiple dimensions of structured and unstructured data are integrated, then decision-making quality improves, but data processing complexity increases

Engineering Contradiction:
Improvedecision-making qualityVSAvoiddata processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements a universal data processing framework that handles multiple types of structured and unstructured data (satellite imagery, census records, crime data, social media posts) through a single integrated system. This multi-functional platform uses standardized processing pipelines and common machine learning models that can accommodate diverse data formats, reducing overall system complexity while enabling comprehensive multi-dimensional analysis for improved decision-making.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system introduces intermediate data normalization layers and feature extraction modules that act as mediators between heterogeneous data sources and the core analysis engine. These intermediary components standardize diverse data formats into unified representations, simplifying the processing complexity while preserving the rich information from multiple data dimensions, thus improving decision-making quality without proportionally increasing system complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If actionable insights are extracted from evolving textual data sources, then land-use intervention recommendations improve, but computational resources required increase

Engineering Contradiction:
Improveland-use intervention recommendationsVSAvoidcomputational resources
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by focusing computational resources on processing only the most relevant and high-impact textual data sources for land-use planning, rather than analyzing all available text data equally. The system prioritizes processing of officially sanctioned data sources and high-value unstructured data while using sampling and summarization techniques for less critical sources, thereby improving recommendation quality while moderating computational resource consumption.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS11966993B2Land use planning recommendations using heterogeneous temporal datasets
Publication Date: 2024.04.23 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US11966993B2 patent drawing
  • US11966993B2 patent drawing
  • US11966993B2 patent drawing

AI summary

Embodiments for providing intelligent land use planning recommendations using heterogeneous temporal datasets in a computing environment. One or more positive land-use interventions, one or more negative land-use interventions, or a combination thereof may be recommended for a selected geographical region from heterogeneous chronological data.