Floor Identification via Device Positioning Clustering

Solution Overview

Problem

Emergency response systems face challenges in accurately locating individuals within buildings during emergencies due to outdated location determination technologies, which hinder prompt and effective rescue operations.

Innovation Solution

A computer-implemented method using historical device positioning data and machine learning-based clustering algorithms to identify building boundaries and associate cluster centroids with floors, enabling real-time determination of a device's location within a building.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional location determination technologies are used, then the system is simple to implement, but the accuracy of locating individuals within buildings deteriorates

Engineering Contradiction:

Improvelocation accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces historical device positioning data and machine learning clustering algorithms as intermediaries between traditional location determination and accurate floor identification. The system collects historical positioning data from multiple devices, applies clustering algorithms to identify building boundaries and floor patterns, and uses these learned patterns to accurately determine current device locations without requiring complex infrastructure changes

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary actions by collecting and processing historical device positioning data before emergency situations occur. The machine learning clustering algorithm pre-identifies building boundaries, floor levels, and spatial patterns from historical data, creating a ready-to-use floor identification model that can quickly and accurately locate devices during emergencies without needing complex real-time processing

Inventive Principle:

Principle #10Preliminary action

2Productivity

If traditional location determination technologies are used, then the implementation cost is low, but the speed of emergency response deteriorates

Engineering Contradiction:

Improveemergency response speedVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by collecting and processing historical device positioning data before emergency situations occur. The machine learning clustering algorithm pre-identifies building boundaries, floor levels, and spatial patterns from historical data, creating a ready-to-use floor identification model that can quickly and accurately locate devices during emergencies without needing complex real-time processing

Inventive Principle:

Principle #10Preliminary action

3Reliability

If more time is spent inside buildings during rescue operations, then the thoroughness of rescue improves, but the safety of emergency response personnel deteriorates

Engineering Contradiction:

Improverescue effectivenessVSAvoidresponder safety

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary actions by collecting and processing historical device positioning data before emergency situations occur. The machine learning clustering algorithm pre-identifies building boundaries, floor levels, and spatial patterns from historical data, creating a ready-to-use floor identification model that can quickly and accurately locate devices during emergencies without needing complex real-time processing

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11361247B2Spatial device clustering-based emergency response floor identification

Publication Date: 2022.06.14 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Historical device positioning data captured from one or more devices over a period of time is received. The historical device positioning data includes historical latitude, longitude, and elevation data of the one or more devices. Building boundaries for a give building are identified based upon the historical latitude and longitude data. The historical device positioning data corresponding to locations within the building boundaries of the building is clustered using a machine learning-based clustering algorithm, resulting in clusters with corresponding cluster centroids. The cluster centroids are associated with respective floors within the building. A current floor of the building on which a specific device is located is determined by mapping current device positioning data of the specific device to the closest cluster centroid.