Systems and methods for determining an actual driver of a vehicle based at least in part upon telematics data

1. A computing device for driver identification, the computing device comprising one or more processors and configured to:

receive a first plurality of measurements collected by a first user device during a vehicle trip, each measurement of the first plurality of measurements including a first measured geographic location and first telematics data corresponding to the first measured geographic location;

receive a second plurality of measurements collected by a second user device during the vehicle trip, each measurement of the second plurality of measurements including a second measured geographic location and second telematics data corresponding to the second measured geographic location;

determine, using deep learning algorithms of a trained machine learning model, patterns in the first and the second telematics data by using pattern recognition;

determine relative positions of the first user device and the second user device in a vehicle using the patterns in the first and the second telematics data;

apply a filter to the first plurality of measurements and the second plurality of measurements to calculate respective geographic locations for the first user device and the second user device;

determine a distance vector between the first user device and the second user device based at least in part on the respective geographic locations;

determine a predicted position of the second user device relative to the first user device based on the relative positions, the respective geographic locations, and with respect to a forward direction of travel of the vehicle based at least in part upon the distance vector; and

identify that the first user device or the second user device corresponds to a user device associated with a driver of the vehicle based at least in part upon the predicted position of the second user device relative to the first user device.

2. The computing device of claim 1 , wherein the computing device is further configured to:

generate an estimated geographic location by integrating an acceleration value from a previous geographic location over a period of time between the previous geographic location and a candidate geographic location; and

calculate the respective geographic locations by calculating a weighted average between the candidate geographic location and the estimated geographic location.

3. The computing device of claim 1 , wherein the computing device is further configured to:

determine a first probability that the first user device corresponds to the user device associated with the driver of the vehicle and a second probability that the second user device corresponds to the user device associated with the driver of the vehicle based at least in part upon the predicted position of the second user device relative to the first user device; and

identify that the first user device or the second user device corresponds to the user device associated with the driver of the vehicle based at least in part upon the first probability and the second probability.

4. The computing device of claim 1 , wherein the computing device is further configured to generate a map indicating a position of the second user device with respect to the first user device based at least in part upon the predicted position of the second user device relative to the first user device.

5. The computing device of claim 1 , wherein the computing device is further configured to:

transmit a confirmation message to the user device associated with the driver of the vehicle;

receive a response message from the user device associated with the driver of the vehicle; and

determine that the driver of the vehicle has been identified based at least in part upon the response message.

6. The computing device of claim 1 , wherein the computing device is further configured to:

receive a third plurality of measurements collected by a third user device during the vehicle trip;

calculate third geographic locations for the third plurality of measurements;

determine a predicted position of the third user device relative to the first user device with respect to the forward direction of travel of the vehicle based at least in part upon the third geographic locations; and

identify that the first user device, the second user device or the third user device corresponds to the user device associated with the driver of the vehicle based at least in part upon the predicted position of the second user device relative to the first user device and the predicted position of the third user device relative to the first user device.

7. The computing device of claim 1 , wherein the filter includes a Kalman filter.

8. A method for driver identification, the method comprising:

receiving, by a computing device from a first user device, a first plurality of measurements collected by the first user device during a vehicle trip, each measurement of the first plurality of measurements including a first measured geographic location and first telematics data corresponding to the first measured geographic location;

receiving, by the computing device from a second user device, a second plurality of measurements collected by the second user device during the vehicle trip, each measurement of the second plurality of measurements including a second measured geographic location and second telematics data corresponding to the second measured geographic location;

determining, using deep learning algorithms of a trained machine learning model, patterns in the first and the second telematics data by using pattern recognition;

determining relative positions of the first user device and the second user device in a vehicle using the patterns in the first and the second telematics data;

applying, by the computing device, a filter to the first plurality of measurements and the second plurality of measurements to calculate respective geographic locations for the first user device and the second user device;

determining, by the computing device, a distance vector between the first user device and the second user device based at least in part on the respective geographic locations;

determining, by the computing device, a predicted position of the second user device relative to the first user device based on the relative positions, the respective geographic locations, and with respect to a forward direction of travel of the vehicle based at least in part upon the distance vector; and

identifying, by the computing device, that the first user device or the second user device corresponds to a user device associated with a driver of the vehicle based at least in part upon the predicted position of the second user device relative to the first user device.

9. The method of claim 8 , further comprising:

generating, by the computing device, an estimated geographic location by integrating an acceleration value from a previous geographic location over a period of time between the previous geographic location and a candidate geographic location; and

calculating, by the computing device, the respective geographic locations by calculating a weighted average between the candidate geographic location and the estimated geographic location.

10. The method of claim 8 , further comprising:

determining, by the computing device, a first probability that the first user device corresponds to the user device associated with the driver of the vehicle and a second probability that the second user device corresponds to the user device associated with the driver of the vehicle based at least in part upon the predicted position of the second user device relative to the first user device; and

identifying, by the computing device, that the first user device or the second user device corresponds to the user device associated with the driver of the vehicle based at least in part upon the first probability and the second probability.

11. The method of claim 8 , further comprising generating a map indicating a position of the second user device with respect to the first user device based at least in part upon the predicted position of the second user device relative to the first user device.

12. The method of claim 8 , further comprising:

transmitting, by the computing device, a confirmation message to the user device associated with the driver of the vehicle;

receiving, by the computing device, a response message from the user device associated with the driver of the vehicle; and

determining, by the computing device, that the driver of the vehicle has been identified based at least in part upon the response message.

13. The method of claim 8 , further comprising:

receiving, by the computing device from a third user device, a third plurality of measurements collected by the third user device during the vehicle trip;

calculating, by the computing device, third geographic locations for the third plurality of measurements;

determining, by the computing device, a predicted position of the third user device relative to the first user device with respect to the forward direction of travel of the vehicle based at least in part upon the third geographic locations; and

identifying, by the computing device, that the first user device, the second user device or the third user device corresponds to the user device associated with the driver of the vehicle based at least in part upon the predicted position of the second user device relative to the first user device and the predicted position of the third user device relative to the first user device.

14. The method of claim 8 , wherein the filter includes a Kalman filter.

15. A non-transitory computer-readable medium storing instructions for driver identification that, when executed by a computing device, cause the computing device to:

receive a first plurality of measurements collected by a first user device during a vehicle trip, each measurement of the first plurality of measurements including a first measured geographic location and first telematics data corresponding to the first measured geographic location;

receive a second plurality of measurements periodically captured by a second user device during the vehicle trip, each measurement of the second plurality of measurements including a second measured geographic location and second telematics data corresponding to the second measured geographic location;

determine, using deep learning algorithms of a trained machine learning model, patterns in the first and the second telematics data by using pattern recognition;

determine relative positions of the first user device and the second user device in a vehicle using the patterns in the first and the second telematics data;

apply a filter to the first plurality of measurements and the second plurality of measurements to calculate respective geographic locations for the first user device and the second user device;

determine a distance vector between the first user device and the second user device based at least in part on the respective geographic locations;

determine a predicted position of the second user device relative to the first user device based on the relative positions, the respective geographic locations, and with respect to a forward direction of travel of the vehicle based at least in part upon the distance vector; and

identify that the first user device or the second user device corresponds to a user device associated with a driver of the vehicle based at least in part upon the predicted position of the second user device relative to the first user device.

16. The non-transitory computer-readable medium of claim 15 , wherein the instructions, when executed by the computing device, further cause the computing device to:

generate an estimated geographic location by integrating an acceleration value from a previous geographic location over a period of time between the previous geographic location and a candidate geographic location; and

calculate the respective geographic locations by calculating a weighted average between the candidate geographic location and the estimated geographic location.

17. The non-transitory computer-readable medium of claim 15 , wherein the instructions, when executed by the computing device, further cause the computing device to:

determine a first probability that the first user device corresponds to the user device associated with the driver of the vehicle and a second probability that the second user device corresponds to the user device associated with the driver of the vehicle based at least in part upon the predicted position of the second user device relative to the first user device; and

identify that the first user device or the second user device corresponds to the user device associated with the driver of the vehicle based at least in part upon the first probability and the second probability.

18. The non-transitory computer-readable medium of claim 15 , wherein the instructions, when executed by the computing device, further cause the computing device to further cause the computing device to:

generate a map indicating a position of the second user device with respect to the first user device based at least in part upon the predicted position of the second user device relative to the first user device.

19. The non-transitory computer-readable medium of claim 15 , wherein the instructions, when executed by the computing device, further cause the computing device to further cause the computing device to:

transmit a confirmation message to the user device associated with the driver of the vehicle;

receive a response message from the user device associated with the driver of the vehicle; and

determine that the driver of the vehicle has been identified based at least in part upon the response message.

20. The non-transitory computer-readable medium of claim 15 , wherein the instructions, when executed by the computing device, further cause the computing device to further cause the computing device to:

receive a third plurality of measurements collected by a third user device during the vehicle trip;

calculate third geographic locations for the third plurality of measurements;

determine a predicted position of the third user device relative to the first user device with respect to the forward direction of travel of the vehicle based at least in part upon the third geographic locations; and

identify that the first user device, the second user device or the third user device corresponds to the user device associated with the driver of the vehicle based at least in part upon the predicted position of the second user device relative to the first user device and the predicted position of the third user device relative to the first user device.