# US 10,771,920 B2 · First responder feedback-based emergency response floor identification > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,771,920 B2 - Document ID: US10771920B2 - Status: Granted - Kind: B2 - Application number: 16/681,959 - Filed: 2019-11-13 - Published: 2020-04-02 - Granted: 2020-09-08 - Earliest claimed: 2018-10-01 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Sushain Pandit; Charles D. Wolfson; Brent Gross; Otis Smart; Harikumar Venkatesan; David A. Selby - Web page: https://patentgrep.com/patent/US10771920B2 ## CPC - G06Q 50/265: {Personal security, identity or safety} - G06F 18/23213: with fixed number of clusters, e.g. K-means clustering - G06N 20/00: Machine learning - G08B 27/001: {Signalling to an emergency team, e.g. firemen} - H04W 4/024: Guidance services - H04W 4/025: {using location based information parameters} - H04W 4/33: for indoor environments, e.g. buildings - H04W 4/90: Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS] - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) ## Abstract Known geospatial device coordinates are clustered using a clustering algorithm into device clusters with cluster centroids. Each device cluster corresponds to a geographical location. Each cluster centroid is annotated with a regional floor-height value of the respective geographical location. Current device data of a device, including geographic location and elevation, are received. An approximate current floor upon which the first device is located is determined using the elevation of the first device and the annotated regional floor-height value of a closest cluster centroid, the closest cluster centroid determined based, at least in part, on the geographic location of the first device. An individual is directed to the device's geographic location and approximate current floor. The device clusters are re-computed based upon feedback from the individual regarding the device's actual floor. ## Claims ### Claim 1 A computer-implemented method, comprising: clustering known geospatial device coordinates using a clustering algorithm, resulting in device clusters with corresponding cluster centroids, each device cluster corresponding to a particular geographical location; annotating each cluster centroid with a regional floor-height value of the respective particular geographical location; receiving current device data comprising geographic location and elevation of a first device; determining an approximate current floor upon which the first device is located using the received elevation of the first device and the annotated regional floor-height value of a closest cluster centroid, the closest cluster centroid being determined based, at least in part, on the received geographic location of the first device; directing an individual to the geographic location and the approximate current floor of the first device; re-computing the device clusters based upon feedback received from the individual regarding an actual current floor of the first device; and determining a current floor for a second device based upon the re-computed device clusters. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, where: the feedback comprises the actual current floor of the first device; the actual current floor of the first device is different from the determined approximate current floor of the first device; the actual current floor of the first device is used to determine an inter-floor height of the geographic location of the first device; and re-computing the device clusters based upon the feedback comprises re-clustering the known geospatial device coordinates of the geographic location of the first device into elevation regions based upon the determined inter-floor height. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, where: the feedback comprises a confirmation that the determined approximate current floor upon which the first device is located is the actual current floor upon which the first device is located; and re-computing the device clusters based upon the feedback comprises increasing a confidence measure of the closest cluster centroid associated with the geographic location of the first device. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, where: the known geospatial device coordinates comprise latitude coordinates, longitude coordinates, and elevation coordinates of a plurality of devices; and the regional floor-height value annotated to each cluster centroid comprises one of a publicly known regional floor-height value or an approximate regional floor-height value of the respective particular geographical location. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, where the clustering algorithm is a machine learning-based clustering algorithm and comprises one of vector quantization-based k-means clustering or density-based spatial clustering of applications with noise (DBSCAN). ### Claim 6 (depends on 1) The computer-implemented method of claim 1, where the individual comprises an emergency first responder, and where determining the approximate current floor upon which the first device is located comprises determining the approximate current floor upon which the first device is located during an emergency response situation. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, where software programmed according to the computer-implemented method is provided as a service in a cloud environment. ### Claim 8 A system, comprising: a memory; and a processor programmed to: cluster, within the memory, known geospatial device coordinates using a clustering algorithm, resulting in device clusters with corresponding cluster centroids, each device cluster corresponding to a particular geographical location; annotate each cluster centroid with a regional floor-height value of the respective particular geographical location; receive current device data comprising geographic location and elevation of a first device; determine an approximate current floor upon which the first device is located using the received elevation of the first device and the annotated regional floor-height value of a closest cluster centroid, the closest cluster centroid being determined based, at least in part, on the received geographic location of the first device; direct an individual to the geographic location and the approximate current floor of the first device; re-compute the device clusters based upon feedback received from the individual regarding an actual current floor of the first device; and determine a current floor for a second device based upon the re-computed device clusters. ### Claim 9 (depends on 8) The system of claim 8, where: the feedback comprises the actual current floor of the first device; the actual current floor of the first device is different from the determined approximate current floor of the first device; the actual current floor of the first device is used to determine an inter-floor height of the geographic location of the first device; and in being programmed to re-compute the device clusters based upon the feedback, the processor is programmed to re-cluster the known geospatial device coordinates of the geographic location of the first device into elevation regions based upon the determined inter-floor height. ### Claim 10 (depends on 8) The system of claim 8, where: the feedback comprises a confirmation that the determined approximate current floor upon which the first device is located is the actual current floor upon which the first device is located; and in being programmed to re-compute the device clusters based upon the feedback, the processor is programmed to increase a confidence measure of the closest cluster centroid associated with the geographic location of the first device. ### Claim 11 (depends on 8) The system of claim 8, where: the known geospatial device coordinates comprise latitude coordinates, longitude coordinates, and elevation coordinates of a plurality of devices; and the regional floor-height value annotated to each cluster centroid comprises one of a publicly known regional floor-height value or an approximate regional floor-height value of the respective particular geographical location. ### Claim 12 (depends on 8) The system of claim 8, where the clustering algorithm is a machine learning-based clustering algorithm and comprises one of vector quantization-based k-means clustering or density-based spatial clustering of applications with noise (DBSCAN). ### Claim 13 (depends on 8) The system of claim 8, where the individual comprises an emergency first responder, and where in being programmed to determine the approximate current floor upon which the first device is located, the processor is programmed to determine the approximate current floor upon which the first device is located during an emergency response situation. ### Claim 14 A computer program product, comprising: a computer readable storage medium having computer readable program code embodied therewith, where the computer readable storage medium is not a transitory signal per se and where the computer readable program code when executed on a computer causes the computer to: cluster known geospatial device coordinates using a clustering algorithm, resulting in device clusters with corresponding cluster centroids, each device cluster corresponding to a particular geographical location; annotate each cluster centroid with a regional floor-height value of the respective particular geographical location; receive current device data comprising geographic location and elevation of a first device; determine an approximate current floor upon which the first device is located using the received elevation of the first device and the annotated regional floor-height value of a closest cluster centroid, the closest cluster centroid being determined based, at least in part, on the received geographic location of the first device; direct an individual to the geographic location and the approximate current floor of the first device; re-compute the device clusters based upon feedback received from the individual regarding an actual current floor of the first device; and determine a current floor for a second device based upon the re-computed device clusters. ### Claim 15 (depends on 14) The computer program product of claim 14, where: the feedback comprises the actual current floor of the first device; the actual current floor of the first device is different from the determined approximate current floor of the first device; the actual current floor of the first device is used to determine an inter-floor height of the geographic location of the first device; and in causing the computer to re-compute the device clusters based upon the feedback, the computer readable program code when executed on the computer causes the computer to re-cluster the known geospatial device coordinates of the geographic location of the first device into elevation regions based upon the determined inter-floor height. ### Claim 16 (depends on 14) The computer program product of claim 14, where: the feedback comprises a confirmation that the determined approximate current floor upon which the first device is located is the actual current floor upon which the first device is located; and in causing the computer to re-compute the device clusters based upon the feedback, the computer readable program code when executed on the computer causes the computer to increase a confidence measure of the closest cluster centroid associated with the geographic location of the first device. ### Claim 17 (depends on 14) The computer program product of claim 14, where: the known geospatial device coordinates comprise latitude coordinates, longitude coordinates, and elevation coordinates of a plurality of devices; and the regional floor-height value annotated to each cluster centroid comprises one of a publicly known regional floor-height value or an approximate regional floor-height value of the respective particular geographical location. ### Claim 18 (depends on 14) The computer program product of claim 14, where the clustering algorithm is a machine learning-based clustering algorithm and comprises one of vector quantization-based k-means clustering or density-based spatial clustering of applications with noise (DBSCAN). ### Claim 19 (depends on 14) The computer program product of claim 14, where the individual comprises an emergency first responder, and where in causing the computer to determine the approximate current floor upon which the first device is located, the computer readable program code when executed on the computer causes the computer to determine the approximate current floor upon which the first device is located during an emergency response situation. ### Claim 20 (depends on 14) The computer program product of claim 14, where software programmed according to the computer is provided as a service in a cloud environment.