Granted Patent B2

US 12,515,602 · App. 17/374,684 · Granted Jan 6, 2026

Inventors: Yuting Qi (Lexington, MA); Cornelius Young (Needham, MA); Rizki Syarif (Lexington, MA); Burak Erem (Lexington, MA)

Assignee: Cambridge Mobile Telematics Inc.

B60R21/013G06N5/04G06N20/00G06Q30/0278G06Q40/08G07C5/008H04W4/40G06Q10/20

Abstract

Claims (74)

1 . A method comprising:

operating, by an application executing on a mobile device, one or more sensors of the mobile device while the mobile device is positioned within a vehicle during a drive to collect movement measurements indicative of movements of the vehicle;

detecting, by the application using the movement measurements as the movement measurements are collected, a change in the movements of the vehicle that exceeds a predefined threshold indicative of an occurrence of a vehicle collision;

identifying, by the application in response to detecting the change in the movements of the vehicle that exceeds the predefined threshold, a first set of data from the movement measurements, wherein the first set of data includes a portion of the movement measurements collected over a time interval that begins at a first time before the change in the movements and ends at a second time after the change in the movements;

generating, by the application, a first feature vector using the first set of data and vehicle data, wherein the vehicle data includes an identifier of the vehicle;

generating, by the application, a second feature vector using the first feature vector and a first predefined value for an additional data type of one or more additional data types;

generating, by the application, a third feature vector using the second feature vector, the third feature vector including a second predefined value for the additional data type that is different from the first predefined value;

executing, by the application, a first machine-learning model on the first feature vector to generate a first confidence value;

executing, by the application, a second machine-learning model on the second feature vector to generate a second confidence value;

executing, by the application, the second machine-learning model on the third feature vector to generate a third confidence value;

determining, by the application, that a conflict exists between the first confidence value, the second confidence value, and the third confidence value;

obtaining, by the application, and in response to determining that the conflict exists, an actual value for the additional data type from a user of the mobile device or an external device;

executing, by the application, the second machine-learning model with the actual value for the additional data type to generate a confidence of a total loss event; and

presenting, by the application, the confidence of the total loss event to the user of the mobile device or a remote computing system.

2 . The method of claim 1 , wherein generating the first feature vector comprises:

extracting a set of crash features from the first set of data, wherein the set of crash features represent sensor data of the vehicle at a time when the change in the movements of the vehicle occurred;

extracting a set of vehicle features from the vehicle data; and

combining the set of crash features and the set of vehicle features.

3 . The method of claim 1 , wherein the total loss event is associated with a determination that the vehicle sustained a damage level during the crash event the change in the movements of the vehicle that is greater than a value of the vehicle.

4 . The method of claim 1 , wherein the one or more additional data types include an airbag activation data type.

5 . The method of claim 1 wherein the one or more additional data types includes a fluid leakage indicator.

6 . The method of claim 1 , wherein obtaining the actual value for the additional data type comprises:

outputting, via a user interface of the mobile device, a request for the actual value; and

receiving, via the user interface, and in response to the request, one or more inputs including the actual value.

7 . A mobile device comprising:

one or more sensors;

one or more processors; and

a non-transitory computer-readable medium storing instructions which, when executed by the one or more processors, cause the mobile device to:

operate the one or more sensors while the mobile device is positioned within a vehicle during a drive to collect movement measurements indicative of movements of the vehicle;

detect, using the movement measurements, and as the movement measurements are collected, a change in the movements of the vehicle that exceeds a predefined threshold indicative of an occurrence of a vehicle collision;

identify, in response to detecting the change in the movements of the vehicle that exceeds the predefined threshold, a first set of data from the movement measurements, wherein the first set of data includes a portion of the movement measurements collected over a time interval that begins at a first time before the change in the movements and ends at a second time after the change in the movements;

generate a first feature vector using the first set of data and vehicle data, wherein the vehicle data includes an identifier of the vehicle;

generate a second feature vector using the first feature vector and a first predefined value for an additional data type of one or more additional data types;

generate a third feature vector using the second feature vector, the third feature vector including a second predefined value for the additional data type that is different from the first predefined value;

execute a first machine-learning model on the first feature vector to generate a first confidence value;

execute a second machine-learning model on the second feature vector to generate a second confidence value;

execute the second machine-learning model on the third feature vector to generate a third confidence value;

determine that a conflict exists between the first confidence value, the second confidence value, and the third confidence value;

obtain, in response to determining that the conflict exists, an actual value for the additional data type from a user of the mobile device or an external device;

execute the second machine-learning model with the actual value for the additional data type to generate a confidence of a total loss event; and

present the confidence of the total loss event to the user of the mobile device or a remote computing system.

8 . The system of claim 7 , wherein generating the first feature vector further comprises:

extracting a set of crash features from the first set of data, wherein the set of crash features represent sensor data of the vehicle at a time when the crash event the change in the movements of the vehicle occurred;

extracting a set of vehicle features from the vehicle data; and

combining the set of crash features and the set of vehicle features.

9 . The system of claim 7 , wherein the total loss event is associated with a determination that the vehicle sustained a damage level during the change in the movements of the vehicle that is greater than a value of the vehicle.

10 . The system of claim 7 , wherein the one or more additional data types include an airbag activation data type.

11 . The system of claim 7 , wherein the one or more additional data types include a fluid leakage indicator.

12 . The system of claim 7 , wherein the instructions further cause the mobile device to obtain the actual value for the additional data type by:

outputting, via a user interface of the mobile device, a request for the actual value; and

receiving, via the user interface, and in response to the request, one or more inputs including the actual value.

13 . A non-transitory computer-readable medium storing instructions which, when executed by one or more processors of a mobile device, cause the one or more processors to perform operations comprising:

operating one or more sensors of the mobile device while the mobile device is positioned within a vehicle during a drive to collect movement measurements indicative of movements of the vehicle;

detecting, using the movement measurements, and as the movement measurements are collected, a change in the movements of the vehicle that exceeds a predefined threshold indicative of an occurrence of a vehicle collision;

identifying, in response to detecting the change in the movements of the vehicle that exceeds the predefined threshold, a first set of data from the movement measurements, wherein the first set of data includes a portion of the movement measurements collected over a time interval that begins at a first time before the change in the movements and ends at a second time after the change in the movements;

generating a first feature vector using the first set of data and vehicle data, wherein the vehicle data includes an identifier of the vehicle;

generating a second feature vector using the first feature vector and a first predefined value for an additional data type of one or more additional data types;

generating a third feature vector using the second feature vector, the third feature vector including a second predefined value for the additional data type that is different from the first predefined value;

executing a first machine-learning model on the first feature vector to generate a first confidence value;

executing a second machine-learning model on the second feature vector to generate a second confidence value;

executing the second machine-learning model on the third feature vector to generate a third confidence value;

determining that a conflict exists between the first confidence value, the second confidence value, and the third confidence value;

obtaining, in response to determining that the conflict exists, an actual value for the additional data type from a user of the mobile device or an external device;

executing the second machine-learning model with the actual value for the additional data type to generate a confidence of a total loss event; and

presenting the confidence of the total loss event to the user of the mobile device or a remote computing system.

14 . The non-transitory computer-readable medium of claim 13 , wherein generating the first feature vector comprises:

extracting a set of crash features from the first set of data, wherein the set of crash features represent sensor data of the vehicle at a time when the change in the movements of the vehicle occurred;

extracting a set of vehicle features from the vehicle data; and

combining the set of crash features and the set of vehicle features.

15 . The non-transitory computer-readable medium of claim 13 , wherein the one or more additional data types include an airbag activation data type.

16 . The non-transitory computer-readable medium of claim 13 , wherein the one or more additional data types include a fluid leakage indicator.

17 . The non-transitory computer-readable medium of claim 13 , wherein obtaining the actual value for the additional data type comprises:

outputting, via a user interface of the mobile device, a request for the actual value; and

receiving, via the user interface, and in response to the request, one or more inputs including the actual value.

Assignments (1)

Continuity (2)

References Cited (24)