Systems and methods for determining which mobile device among multiple mobile devices is used by a vehicle driver

1. A computer-implemented method for determining which mobile device among multiple mobile devices in a vehicle is used by a driver of the vehicle, the method comprising:

receiving first telematics data and first device interaction data generated by a first mobile device in the vehicle during a vehicle trip;

receiving second telematics data and second device interaction data generated by a second mobile device in the vehicle during the vehicle trip;

analyzing the first telematics data and the second telematics data to determine one or more driving events of a predetermined type, wherein the predetermined type comprises high attention driving events comprising at least one of: changing lanes, making turns, or passing vehicles;

analyzing the first telematics data and the first device interaction data to determine a first plurality of driving instances at which a first user interacts with the first mobile device during the one or more driving events of the predetermined type during the vehicle trip;

analyzing the second telematics data and the second device interaction data to determine a second plurality of driving instances at which a second user interacts with the second mobile device during the one or more driving events of the predetermined type during the vehicle trip;

by using a classification technique, determining whether or not the first user of the first mobile device is the driver of the vehicle during the vehicle trip based at least in part upon the first plurality of driving instances;

and

calibrating the classification technique based at least in part upon whether or not the first user has been determined to be the driver.

2. The computer-implemented method of claim 1 , wherein determining whether or not the first user of the first mobile device is the driver of the vehicle comprises:

determining a first probability value that the first user of the first mobile device is the driver of the vehicle by using the classification technique.

3. The computer-implemented method of claim 2 , wherein determining whether or not the second user of the second mobile device is the driver of the vehicle comprises:

determining a second probability value that the second user of the second mobile device is the driver of the vehicle by using the classification technique.

4. The computer-implemented method of claim 3 , wherein the calibrating the classification technique comprises:

adjusting the first probability value and the second probability value if both the first probability value and the second probability value are above a threshold value.

5. The computer-implemented method of claim 4 , wherein adjusting the first probability value and the second probability value comprises:

if both the first probability value and the second probability value are above the threshold value, reducing at least one probability value of the first probability value and the second probability value.

6. The computer-implemented method of claim 5 , wherein reducing the at least one probability value of the first probability value and the second probability value comprises:

making the at least one probability value become below the threshold value.

7. The computer-implemented method of claim 5 , wherein reducing the at least one probability value of the first probability value and the second probability value further comprises:

if both the first probability value and the second probability value are above the threshold value, reducing both the first probability value and the second probability value.

8. A computing device for determining which mobile device among multiple mobile devices in a vehicle is used by a driver of the vehicle, the computing device comprising:

one or more processors; and

a memory storing instructions that, when executed by the one or more processors, cause the one or more processors to:

receive first telematics data and first device interaction data generated by a first mobile device in the vehicle during a vehicle trip;

receive second telematics data and second device interaction data generated by a second mobile device in the vehicle during the vehicle trip;

analyze the first telematics data and the second telematics data to determine one or more driving events of a predetermined type, wherein the predetermined type comprises high attention driving events comprising at least one of: changing lanes, making turns, or passing vehicles;

analyze the first telematics data and the first device interaction data to determine a first plurality of driving instances at which a first user interacts with the first mobile device during the one or more driving events of the predetermined type during the vehicle trip;

analyze the second telematics data and the second device interaction data to determine a second plurality of driving instances at which a second user interacts with the second mobile device during the one or more driving events of the predetermined type during the vehicle trip;

by using a classification technique, determine whether or not the first user of the first mobile device is the driver of the vehicle during the vehicle trip based at least in part upon the first plurality of driving instances;

and

calibrate the classification technique based at least in part upon whether or not the first user has been determined to be the driver.

9. The computing device of claim 8 , wherein, the instructions that cause the one or more processors to determine whether or not the first user of the first mobile device is the driver of the vehicle further cause the one or more processors to:

determine a first probability value that the first user of the first mobile device is the driver of the vehicle by using the classification technique.

10. The computing device of claim 9 , wherein, the instructions that cause the one or more processors to determine whether or not the second user of the second mobile device is the driver of the vehicle further cause the one or more processors to:

determine a second probability value that the second user of the second mobile device is the driver of the vehicle by using the classification technique.

11. The computing device of claim 10 , wherein, the instructions that cause the one or more processors to calibrate the classification technique further cause the one or more processors to:

adjust the first probability value and the second probability value if both the first probability value and the second probability value are above a threshold value.

12. The computing device of claim 11 , wherein, the instructions that cause the one or more processors to adjust the first probability value and the second probability value further cause the one or more processors to:

if both the first probability value and the second probability value are above the threshold value, reduce at least one probability value of the first probability value and the second probability value.

13. The computing device of claim 12 , wherein, the instructions that cause the one or more processors to reduce the at least one probability value of the first probability value and the second probability value further cause the one or more processors to:

make the at least one probability value become below the threshold value.

14. The computing device of claim 12 , wherein, the instructions that cause the one or more processors to reduce the at least one probability value of the first probability value and the second probability value further cause the one or more processors to:

if both the first probability value and the second probability value are above the threshold value, reduce both the first probability value and the second probability value.

15. A non-transitory computer-readable medium storing instructions for determining which mobile device among multiple mobile devices in a vehicle is used by a driver of the vehicle, the instructions when executed by one or more processors of a computing device, cause the computing device to:

receive first telematics data and first device interaction data generated by a first mobile device in the vehicle during a vehicle trip;

receive second telematics data and second device interaction data generated by a second mobile device in the vehicle during the vehicle trip;

analyze the first telematics data and the second telematics data to determine one or more driving events of a predetermined type, wherein the predetermined type comprises high attention driving events comprising at least one of: changing lanes, making turns, or passing vehicles;

analyze the first telematics data and the first device interaction data to determine a first plurality of driving instances at which a first user interacts with the first mobile device during the one or more driving events of the predetermined type during the vehicle trip;

analyze the second telematics data and the second device interaction data to determine a second plurality of driving instances at which a second user interacts with the second mobile device during the one or more driving events of the predetermined type during the vehicle trip;

by using a classification technique, determine whether or not the first user of the first mobile device is the driver of the vehicle during the vehicle trip based at least in part upon the first plurality of driving instances;

and

calibrate the classification technique based at least in part upon whether or not the first user has been determined to be the driver.

16. The non-transitory computer-readable medium of claim 15 , wherein, the instructions that cause the computing device to determine whether or not the first user of the first mobile device is the driver of the vehicle further cause the computing device to:

determine a first probability value that the first user of the first mobile device is the driver of the vehicle by using the classification technique.

17. The non-transitory computer-readable medium of claim 16 , wherein, the instructions that cause the computing device to determine whether or not the second user of the second mobile device is the driver of the vehicle further cause the computing device to:

determine a second probability value that the second user of the second mobile device is the driver of the vehicle by using the classification technique.

18. The non-transitory computer-readable medium of claim 17 , wherein, the instructions that cause the computing device to calibrate the classification technique further cause the computing device to:

adjust the first probability value and the second probability value if both the first probability value and the second probability value are above a threshold value.

19. The non-transitory computer-readable medium of claim 18 , wherein, the instructions that cause the computing device to adjust the first probability value and the second probability value further cause the computing device to:

if both the first probability value and the second probability value are above the threshold value, reduce at least one probability value of the first probability value and the second probability value.

20. The non-transitory computer-readable medium of claim 19 , wherein the instructions that cause the computing device to reduce the at least one probability value of the first probability value and the second probability value further cause the computing device to:

if both the first probability value and the second probability value are above the threshold value, reduce both the first probability value and the second probability value.