Systems and methods for detecting and assessing distracted drivers

1. A system comprising:

a mobile device comprising a plurality of sensors;

a memory; and

a processor coupled to the memory, wherein the processor is configured to perform operations including:

obtaining a plurality of movement measurements over a plurality of time intervals from at least one of the plurality of sensors in the mobile device of a user during a trip in a vehicle;

determining mobile device usage movements from the plurality of movement measurements obtained from the at least one of the plurality of sensors, wherein the mobile device usage movements are movements indicative of the usage of the mobile device by the user based on the plurality of movement measurements;

determining a time series of usage probabilities over the plurality of time intervals based on a comparison of the plurality of movement measurements to known usage measurements, wherein the usage probabilities include probabilities that the user is using the mobile device over the plurality of time intervals;

determining that the mobile device is in a mount in the vehicle during the trip by comparing the plurality of movement measurements to known mount measurements;

determining whether a global positioning system (GPS) application of the mobile device is active;

flagging a first set of time intervals for which the usage probabilities are greater than a first threshold and a determination is made that the GPS application is active and flagging a second set of time intervals for which the usage probabilities are greater than a second threshold and a determination is made that the GPS application is not active, wherein the first threshold is greater than the second threshold; and

consolidating the flagged first set of time intervals and the flagged second set of time intervals within a threshold time period into continuous periods of usage to provide filtered mobile device usage movements; and

outputting the filtered mobile device usage movements.

2. The system of claim 1 , wherein the usage of the mobile device by the user includes interaction with the mobile device by the user.

3. The system of claim 1 , further comprising:

extracting the movement measurements corresponding to the plurality of time intervals in which the usage probabilities exceed at least one of the first threshold or the second threshold.

4. The system of claim 1 , further comprising:

classifying the user of the mobile device as a driver of the vehicle on the trip after determining that the mobile device is in the mount.

5. The system of claim 1 , further comprising:

extracting the mobile device usage movements that occurred while a screen of the mobile device was on.

6. The system of claim 1 , further comprising:

determining whether the user of the mobile device is a driver of the vehicle on the trip by comparing the plurality of movement measurements to known driver usage measurements.

7. The system of claim 1 , further comprising:

calculating a score for at least one of the user or the trip using the filtered mobile device usage movements, wherein the outputting the filtered mobile device usage movements includes outputting the score.

8. A method, comprising:

obtaining a plurality of movement measurements over a plurality of time intervals from at least one of a plurality of sensors in a mobile device of a user during a trip in a vehicle;

determining mobile device usage movements from the plurality of movement measurements obtained from the at least one of the plurality of sensors, wherein the mobile device usage movements are movements indicative of usage of the mobile device by the user based on the plurality of movement measurements;

determining a time series of usage probabilities over the plurality of time intervals based on a comparison of the plurality of movement measurements to known usage measurements, wherein the usage probabilities include probabilities that the user is using the mobile device over the plurality of time intervals;

determining that the mobile device is in a mount in the vehicle during the trip by comparing the plurality of movement measurements to known mount measurements;

determining whether a global positioning system (GPS) application is active on the mobile device by comparing the obtained plurality of movement measurements to known GPS active data;

flagging first time intervals for which the usage probabilities are greater than a first threshold and the GPS application is active and flagging second time intervals for which the usage probabilities are greater than a second threshold and the GPS application is inactive or is not present on the mobile device, wherein the first threshold is greater than the second threshold;

consolidating the flagged first time intervals and the flagged second time intervals within a threshold time period into continuous periods of usage to provide filtered mobile device usage movements; and

outputting the filtered mobile device usage movements.

9. The method of claim 8 , wherein the usage of the mobile device by the user includes interaction with the mobile device by the user.

10. The method of claim 8 , further comprising:

extracting the movement measurements corresponding to the plurality of time intervals in which the usage probabilities exceed at least one of the first threshold or the second threshold.

11. The method of claim 8 , further comprising:

classifying the user of the mobile device as a driver of the vehicle on the trip after determining that the mobile device is in the mount.

12. The method of claim 8 , further comprising:

extracting the mobile device usage movements that occurred while a screen of the mobile device was on.

13. The method of claim 8 , further comprising:

determining whether the user of the mobile device is a driver of the vehicle on the trip by comparing the plurality of movement measurements to known driver usage measurements.

14. The method of claim 8 , further comprising:

calculating a score for at least one of the user or the trip using the filtered mobile device usage movements, wherein the outputting the filtered mobile device usage movements includes outputting the score.

15. A method for identifying a driver of a vehicle using mobile device usage measurements, the method comprising:

operating one or more sensors of a mobile device of a user to obtain a plurality of movement measurements over a plurality of time intervals, the mobile device disposed in the vehicle during a trip;

determining, by a processor of the mobile device, mobile device usage movements from the plurality of movement measurements obtained from the at least one of the one or more sensors, wherein the mobile device usage movements are movements indicative of usage of the mobile device by the user based on the movement measurements;

determining, by the processor, a time series of usage probabilities over the plurality of time intervals based on a comparison of the obtained plurality of movement measurements to known usage measurements, wherein the usage probabilities include probabilities that the user is using the mobile device over the plurality of time intervals;

determining, by the processor, decelerations, stops, and accelerations of the vehicle based on the plurality of movement measurements;

determining, by the processor, whether the mobile device usage movements begin during a deceleration or a stop in movements of the vehicle and end during the stop or an acceleration in the movements of the vehicle; and

in response to determining that the mobile device usage movements begin during the deceleration or the stop in the movements of the vehicle and end during the stop or the acceleration in the movements of the vehicle, classifying, by the processor, the user as the driver of the vehicle.

16. The method of claim 15 , wherein the usage of the mobile device by the user includes interaction with the mobile device by the user.

17. The method of claim 15 , further comprising:

determining, by the processor, whether the user of the mobile device is the driver of the vehicle during the trip by comparing the obtained plurality of movement measurements to known driver usage measurements.