Granted Patent B2

US 12,518,199 · App. 17/386,072 · Granted Jan 6, 2026

Inventors: Yuting Qi (Lexington, MA); Sanujit Sahoo (Somerville, MA); Burak Erem (Needham, MA)

Assignee: Cambridge Mobile Telematics Inc.

G06N20/00H04W4/021

Abstract

Claims (49)

1 . A method comprising:

generating an association between a user of a mobile device and the mobile device;

receiving a first set of measurements from one or more sensors of the mobile device while the mobile device is positioned in a first vehicle during a first drive;

training a machine-learning model using the first set of measurements;

receiving a second set of measurements from the one or more sensors of the mobile device while the mobile device is positioned in a vehicle during a second drive that occurs after completion of the first drive, wherein a sampling rate used by at least one sensor of the one or more sensors to collect the second set of measurements is a first sampling rate;

generating, by the machine-learning model based on the second set of measurements, an output indicating that the vehicle used during the second drive is a different vehicle than the first vehicle used during the first drive; and

increasing the sampling rate of the at least one sensor to be a second sampling rate that is higher than the first sampling rate for a remainder of the second drive based on the output from the machine-learning model.

2 . The method of claim 1 , wherein the second set of measurements were received from the one or more sensors of the mobile device while the mobile device was positioned in a second vehicle, and the method further comprises:

training the machine-learning model using the second set of measurements;

receiving a third set of measurements from the one or more sensors of the mobile device; and

determining, by executing the machine-learning model on the third set of measurements, that the mobile device is positioned in the second vehicle.

3 . The method of claim 2 , further comprising transmitting an indication that the mobile device is positioned in the second vehicle to one or more remote devices.

4 . The method of claim 1 , wherein the machine-learning model is trained using unsupervised learning.

5 . The method of claim 1 , wherein the one or more sensors include an accelerometer, a global positioning system (GPS) sensor, and/or a magnetometer.

6 . The method of claim 1 , wherein training the machine-learning model includes generating a training dataset by:

converting the first set of measurements to a frequency domain;

filtering one or more data values of the first set of measurements in the frequency domain; and

generating the training dataset using a remainder of the first set of measurements.

7 . The method of claim 6 , wherein filtering one or more data values of the first set of measurements in the frequency domain includes using a low-pass filter or a band-pass filter.

8 . A system comprising:

one or more processors; and

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

generate an association between a user of a mobile device and the mobile device;

receive a first set of measurements from one or more sensors of the mobile device while the mobile device is positioned in a first vehicle during a first drive;

train a machine-learning model using the first set of measurements;

receive a second set of measurements from the one or more sensors of the mobile device while the mobile device is positioned in a vehicle during a second drive that occurs after completion of the first drive, wherein a sampling rate used by at least one sensor of the one or more sensors to collect the second set of measurements is a first sampling rate;

generate, by the machine-learning model based on the second set of measurements, an output indicating that the vehicle used during the second drive is a different vehicle than the first vehicle used during the first drive; and

increase the sampling rate of the at least one sensor to be a second sampling rate that is higher than the first sampling rate for a remainder of the second drive based on the output from the machine-learning model.

9 . The system of claim 8 , wherein the second set of measurements were received from the one or more sensors of the mobile device while the mobile device was positioned in a second vehicle, and the instructions further configure the system to:

train the machine-learning model using the second set of measurements;

receive a third set of measurements from the one or more sensors of the mobile device; and

determine, by executing the machine-learning model on the third set of measurements, that the mobile device is positioned in the second vehicle.

10 . The system of claim 8 , wherein the machine-learning model is trained using unsupervised learning.

11 . The system of claim 8 , wherein training the machine-learning model includes generating a training dataset by:

converting the first set of measurements to a frequency domain; and

filtering one or more data values of the first set of measurements in the frequency domain; and

generating the training dataset using a remainder of the first set of measurements.

12 . The system of claim 11 , wherein filtering one or more data values of the first set of measurements in the frequency domain includes using a low-pass filter or a band-pass filter.

13 . A method comprising:

receiving a first set of measurements from one or more sensors of a mobile device while the mobile device is positioned in a vehicle during a first drive, wherein a sampling rate used by at least one sensor of the one or more sensors to collect the first set of measurements is a first sampling rate;

generating, by a machine-learning model based on the first set of measurements, an output indicating that the vehicle is a same vehicle as a first vehicle used during a previous drive that was completed prior to a beginning of the first drive, wherein the machine-learning model was trained using a previous set of measurements collected while the mobile device was positioned in the first vehicle during the previous drive; and

reducing the sampling rate of the at least one sensor to be a second sampling rate that is lower than the first sampling rate for a remainder of the first drive based on the output from the machine-learning model.

14 . The method of claim 13 , further comprising transmitting an indication that the mobile device is positioned in the first vehicle to one or more remote devices.

15 . The method of claim 13 , wherein the machine-learning model is trained using unsupervised learning.

16 . The method of claim 13 , wherein the one or more sensors include an accelerometer, a global positioning system sensor, and/or a magnetometer.

17 . The method of claim 13 , wherein training the machine-learning model includes generating a training dataset by:

converting the previous set of measurements to a frequency domain;

filtering one or more data values of the first set of measurements in the frequency domain; and

generating the training dataset using a remainder of the previous set of measurements.

Assignments (1)

Continuity (2)

References Cited (16)