# US 10,246,037 B1 · Vehicle telematics of vehicle crashes > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,246,037 B1 - Document ID: US10246037B1 - Status: Granted - Kind: B1 - Application number: 16/035,861 - Filed: 2018-07-16 - Granted: 2019-04-02 - Earliest claimed: 2018-07-16 - Assignees: Cambridge Mobile Telematics Inc. - Applicants: Cambridge Mobile Telematics Inc. - Inventors: Kimberly Shea; Geronimo Mirano; Jun-geun Park; William Bradley - Web page: https://patentgrep.com/patent/US10246037B1 ## CPC - B60R 21/0132: responsive to vehicle motion parameters {, e.g. to vehicle longitudinal or transversal deceleration or speed value} - G07C 5/008: {communicating information to a remotely located station (transmission systems for measured values G08C)} - B60R 2021/0027: {Post collision measures, e.g. notifying emergency services} - B60R 2021/01088: {wireless} - B60R 2021/01252: {Devices other than bags} - B60R 2021/01325: {Vertical acceleration} - G07C 5/0816: {Indicating performance data, e.g. occurrence of a malfunction} - G07C 5/085: {using electronic data carriers} - B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR - G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE ## Abstract Among other things, a documentation of a crash involving a vehicle is generated automatically. Telematics data is received that has been produced by one or more sensors associated with a telematics device at the vehicle. Based on the telematics data, a vehicle crash period is determined that begins at a start time and ends at an end time of the vehicle crash. Based on the telematics data, one or more metrics are determined associated with the vehicle during the vehicle crash period. Based on one or more metrics, a human-readable documentation of the vehicle crash is generated automatically. ## Claims ### Claim 1 A method for automatically generating a documentation of a crash involving a vehicle, the method comprising: a processor executing instructions for receiving telematics data produced by one or more sensors associated with a telematics device at the vehicle, the sensors including at least one of an accelerometer, a speedometer, a barometer, a gyroscope, a compass, and a position sensor; based on the telematics data, the processor executing instructions for determining a start time of the vehicle crash that is a beginning of a vehicle crash period and an end time of the vehicle crash period, the vehicle crash period including one or more impacts of the vehicle, the start time and the end time being determined based on comparisons of (a) features corresponding to values of telematics data in time segments of the telematics data with (b) predetermined thresholds for the features; the processor executing instructions for determining, based on the telematics data, one or more metrics associated with the vehicle during the vehicle crash period; and the processor automatically generating, based on the one or more metrics, a human-readable prose documentation of the vehicle crash comprising a narrative description of features of the vehicle crash during the vehicle crash period, the narrative description including one or more common phrases and one or more of the determined metrics, and communicating the narrative human-readable prose documentation to a device for presentation in an audible form or a readable form to a user. ### Claim 2 (depends on 1) The method of claim 1, comprising: calculating, by a crash detection component and based on a crash detection model, a probability that the telematics data is associated with a vehicle crash. ### Claim 3 (depends on 1) The method of claim 1, comprising: displaying the human-readable documentation of the vehicle crash. ### Claim 4 (depends on 1) The method of claim 1, comprising: calculating, by a crash metrics component and based on the telematics data, a first rate of altitude change and a second rate of altitude change; calculating, by the crash metrics component, a difference between the first rate of altitude change and the second rate of altitude change; and determining, by the crash metrics component, that an airbag associated with the vehicle was deployed based on the difference satisfying a predetermined threshold. ### Claim 5 (depends on 1) The method of claim 1, comprising: calculating, by a crash metrics component and based on the telematics data, one or more peak acceleration values for at least one axis associated with the telematics device; calculating, by the crash metrics component and based on the one or more peak acceleration values, an acceleration event, wherein the acceleration event includes no more than one peak acceleration value for each of the at least one axis associated with the telematics device; and determining, by the crash metrics component and based on the acceleration event, a qualitative measure of acceleration for each of the at least one axis associated with the telematics device. ### Claim 6 (depends on 5) The method of claim 5, comprising: calculating, based on the acceleration event, a direction of a vehicle impact of the vehicle. ### Claim 7 (depends on 5) The method of claim 5, comprising: calculating, based on the acceleration event, a maneuver of the vehicle before a vehicle impact. ### Claim 8 (depends on 1) The method of claim 1, comprising: calculating, based on the one or more metrics, a severity score of the vehicle crash. ### Claim 9 (depends on 1) The method of claim 1, comprising: the processor executing instructions for identifying, based on the telematics data, a human gait occurring after the start time of the vehicle crash period. ### Claim 10 (depends on 1) The method of claim 1 in which the automatic generation of the human-readable documentation comprises deriving features of the crash from the telematics data. ### Claim 11 (depends on 10) The method of claim 10 in which the features of the crash comprise an event prior to a first impact of the crash. ### Claim 12 (depends on 10) The method of claim 10 in which the features of the crash comprise an event after a final impact of the crash. ### Claim 13 (depends on 10) The method of claim 10 in which the features of the crash comprise vehicle speed. ### Claim 14 (depends on 10) The method of claim 10 in which the features of the crash comprise an event after a first impact of the crash and before a final impact of the crash. ### Claim 15 (depends on 10) The method of claim 10 in which the features of the crash comprise events determined with respect to a largest impact of the crash. ### Claim 16 (depends on 10) The method of claim 10 in which the features of the crash comprise features associated with a position or orientation of the vehicle during the crash. ### Claim 17 (depends on 1) The method of claim 1 in which the human-readable documentation comprises a crash narrative. ### Claim 18 (depends on 1) The method of claim 1 in which generating the human-readable documentation comprises assembling predetermined prose phrases corresponding to the features of the crash. ### Claim 19 (depends on 18) The method of claim 18 in which the prose phrases identify at least one of (a) times, (b) locations or orientations, or (c) speeds. ### Claim 20 A vehicle telematics system for automatically generating a documentation of a vehicle crash, the system comprising: a processor; and storage for instructions executable by the processor to: obtain telematics data from one or more sensors associated with a telematics device; calculate, based on the telematics data, a start time of the vehicle crash that is a beginning of a vehicle crash period and an end time of the vehicle crash period, the vehicle crash period including one or more impacts of the vehicle, the start time and the end time being determined based on comparisons of (a) features corresponding to values of telematics data in time segments of the telematics data with (b) predetermined thresholds for the features; determine, based on the telematics data, one or more metrics associated with a vehicle during the vehicle crash period; automatically provide, based on the one or more metrics, a human-readable prose documentation of the vehicle crash comprising a narrative description of features of the vehicle crash during the vehicle crash period, the narrative description including one or more common phrases and one or more of the determined metrics, and communicate the narrative human-readable prose documentation to a device for presentation in an audible form or a readable form to a user. ### Claim 21 (depends on 20) The system of claim 20, comprising a user interface for displaying the human-readable documentation of the vehicle crash. ### Claim 22 (depends on 20) The system of claim 20, wherein the one or more metrics include at least one of a crash duration, a number of impacts, a mean acceleration, a yaw during the vehicle crash, a direction of vehicle impact, an indication of airbag deployment, an indication of vehicle rollover, an indication of a vehicle maneuver, an indication of whether the vehicle was driven post-crash, and an indication of environmental conditions during the vehicle crash. ### Claim 23 (depends on 20) The system of claim 20, comprising communications circuitry to communicate one or more of the telematics data, the vehicle crash period, the one or more metrics, and the human-readable documentation of the vehicle crash to a remote server. ### Claim 24 (depends on 23) The system of claim 23, wherein the remote server is associated with at least one of an automotive safety organization, an insurance company, an emergency service, a user of the telematics device, or a user of the vehicle. ### Claim 25 (depends on 20) The system of claim 20, wherein the telematics device comprises a mobile device. ### Claim 26 (depends on 20) The system of claim 20, comprising additional instructions executable by the processor to: calculate, by a crash detection component and based on a crash detection model, a probability that the telematics data is associated with a vehicle crash. ### Claim 27 (depends on 20) The system of claim 20, comprising additional instructions executable by the processor to: identify, based on the telematics data, a human gait occurring after the start time of the vehicle crash period.