Driver identification using geospatial information
The system comprises an interface and a processor. The interface is configured to receive vehicle data, comprising data associated with a vehicle over a period of time; and receive driver location data, comprising location data associated with one or more drivers of a roster of drivers. The processor is configured to determine a likely pool of drivers based at least in part on the driver location data and the vehicle data; and process the vehicle data and the likely pool of drivers using a model to determine a most likely driver.
1. A system, comprising:
an interface configured to:
receive vehicle data, comprising data associated with a vehicle over a period of time; and
receive driver location data, comprising location data associated with one or more drivers of a roster of drivers; and
a processor configured to:
determine a likely pool of drivers based at least in part on the driver location data and the vehicle data, comprising to:
determine, within a predefined period of time, whether two similar faces of drivers from completely different locations are included in the driver location data and the vehicle data; and
in the event that the two similar faces of drivers from the completely different locations are included in the driver location data and the vehicle data within the predefined period of time, exclude the drivers having the two similar faces from the likely pool of drivers; and
process the vehicle data and the likely pool of drivers using a model to determine a most likely driver, and wherein the model determines that the most likely driver comprises a driver of the likely pool of drivers that is most likely associated with the vehicle data, wherein the processing of the vehicle data and the likely pool of drivers comprises to:
determine a subset of face data of the vehicle data based on a set of regulation data associated with the driver location data;
select the model based on the subset of face data, wherein the model comprises executing a machine learning algorithm, a neural network algorithm, an artificial intelligence algorithm, or any combination thereof; and
receive the most likely driver from the model based on the subset of face data and the likely pool of drivers.
2. The system of claim 1 , wherein the vehicle data comprises vehicle location data, dynamic maneuver data, static behavior data, face data, vehicle sensor data, and/or historical data.
3. The system of claim 2 , wherein the vehicle location data comprises a GPS point or a GPS path.
4. The system of claim 2 , wherein the dynamic maneuver data comprises turning data, acceleration data, stopping data, and/or lane change data.
5. The system of claim 2 , wherein the static behavior data comprises following distance data, lane position data, and/or parking position data.
6. The system of claim 2 , wherein the face data comprises face image data, facial recognition system data, face parameter data, the face image data captured immediately prior to a time or area with the face data, and/or the face image data captured immediately after the time or area without the face data.
7. The system of claim 2 , wherein the vehicle sensor data comprises accelerometer data, gyroscope data, microphone data, camera data, engine data, brake data, and/or vehicle electrical system data.
8. The system of claim 2 , wherein the historical data comprises a historical driver schedule and/or a historical driver route.
9. The system of claim 1 , wherein the driver location data comprises most recently determined location data associated with the one or more drivers of the roster of drivers and/or historical location data associated with the one or more drivers of the roster of drivers.
10. The system of claim 1 , wherein determining the likely pool of drivers comprises removing from the roster of driver those drivers known to be in locations preventing them from being a driver of the vehicle.
11. The system of claim 1 , wherein the model utilizes the face data of the vehicle data and other data of the vehicle data.
12. The system of claim 1 , wherein the subset of the face data comprises face data captured in regions where performing facial recognition is allowed.
13. The system of claim 12 , wherein the processor is further configured to determine the subset of face data based at least in part on a set of regulation data associated with a set of locations.
14. The system of claim 12 , wherein the processor is further configured to determine the subset of face data based at least in part on a client defined geofence.
15. The system of claim 1 , wherein a determination of the most likely driver is based at least in part on historical traffic data.
16. The system of claim 1 , wherein a determination of the most likely driver comprises an offline process.
17. A method, comprising:
receiving vehicle data comprising data associated with a vehicle over a period of time;
receiving driver location data comprising location data associated with one or more drivers of a roster of drivers;
determining, using a processor, a likely pool of drivers based at least in part on the driver location data and the vehicle data, comprising:
determining, within a predefined period of time, whether two similar faces of drivers from completely different locations are included in the driver location data and the vehicle data; and
in the event that the two similar faces of drivers from the completely different locations are included in the driver location data and the vehicle data within the predefined period of time, excluding the drivers having the two similar faces from the likely pool of drivers; and
processing the vehicle data and the likely pool of drivers using a model to determine a most likely driver, and wherein the model determines that the most likely driver comprises a driver of the likely pool of drivers that is most likely associated with the vehicle data, wherein the processing of the vehicle data and the likely pool of drivers comprises:
determining a subset of face data of the vehicle data based on a set of regulation data associated with the driver location data;
selecting the model based on the subset of face data, wherein the model comprises executing a machine learning algorithm, a neural network algorithm, an artificial intelligence algorithm, or any combination thereof; and
receiving the most likely driver from the model based on the subset of face data and the likely pool of drivers.
18. A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
receiving vehicle data comprising data associated with a vehicle over a period of time;
receiving driver location data comprising location data associated with one or more drivers of a roster of drivers;
determining a likely pool of drivers based at least in part on the driver location data and the vehicle data, comprising:
determining, within a predefined period of time, whether two similar faces of drivers from completely different locations are included in the driver location data and the vehicle data; and
in the event that the two similar faces of drivers from the completely different locations are included in the driver location data and the vehicle data within the predefined period of time, excluding the drivers having the two similar faces from the likely pool of drivers; and
processing the vehicle data and the likely pool of drivers using a model to determine a most likely driver, and wherein the model determines that the most likely driver comprises a driver of the likely pool of drivers that is most likely associated with the vehicle data, wherein the processing of the vehicle data and the likely pool of drivers comprises:
determining a subset of face data of the vehicle data based on a set of regulation data associated with the driver location data;
selecting the model based on the subset of face data, wherein the model comprises executing a machine learning algorithm, a neural network algorithm, an artificial intelligence algorithm, or any combination thereof; and
receiving the most likely driver from the model based on the subset of face data and the likely pool of drivers.