Driver identification among a limited pool of potential drivers

• US 10,676,097 B1
• Filed: 07/19/2017
• Issued: 06/09/2020
• Est. Priority Date: 01/29/2016
• Status: Active Grant

• Current Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Original Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Inventors: Goldfarb, Meghan Sims, Christensen, Scott Thomas, Thiel, Taylor Michael, Dahiya, Anuj
• Primary Examiner(s): Badii, Behrang
• Application Number:
  US15/653,759
• Time in Patent Office: 1,056 Days
• CPC Class Codes: B60W 2040/0809 Driver authorisation; Driver identity check
• CPC Class Codes: B60W 2540/043 Identity of occupants
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 2556/55 using telemetry
• CPC Class Codes: B60W 30/00 Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: G01C 21/34 Route searching; Route guidance
• CPC Class Codes: G02B 27/00 Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
• CPC Class Codes: G02B 27/01 Head-up displays
• CPC Class Codes: G02B 27/0172 characterised by optical features
• CPC Class Codes: G05D 1/00 Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots drive control systems specially adapted for autonomous road vehicles B60W60/00
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 18/24137 Distances to cluster centroïds
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/08 Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
• CPC Class Codes: G06Q 10/083 Shipping
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06V 20/59 inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
• CPC Class Codes: G07B 15/06 Arrangements for road pricing or congestion charging of vehicles or vehicle users, e.g. automatic toll systems
• CPC Class Codes: G07C 5/00 : Registering or indicating the working of vehicles
• CPC Class Codes: G07C 5/008 : communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/085 : using electronic data carriers
• CPC Class Codes: G08G 1/0112 : from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0129 : for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/017 : identifying vehicles G08G1/015, G08G1/054 take precedence
• CPC Class Codes: G08G 1/052 : with provision for determining speed or overspeed speed measuring in general G01P
• CPC Class Codes: G10L 25/48 : specially adapted for particular use
• CPC Class Codes: H04W 4/02 : Services making use of location information
• CPC Class Codes: H04W 4/30 : Services specially adapted for particular environments, situations or purposes
• CPC Class Codes: H04W 4/40 : for vehicles, e.g. vehicle-to-pedestrians [V2P]
• CPC Class Codes: H04W 76/10 : Connection setup

Abstract

Historical vehicle telematics data, corresponding to trips known to have been driven by specific persons within a limited pool of potential drivers, may be processed to generate a statistical model that is customized for those persons. Once generated, the custom statistical model may be used to process vehicle telematics data from trips where it is known that the driver was one of the drivers in the pool of drivers, but the specific identify of the driver is not known. Because the statistical model is specifically optimized or designed to distinguish among the drivers in the pool, the model may be more accurate than universal driver identification models.

Claims

1. A method of identifying a driver in the presence of vehicle telematics data from multiple data collection devices, the method comprising:

receiving, by a server, historical vehicle telematics data including (i) first historical vehicle telematics data corresponding to one or more trips driven by a first person, and (ii) second historical vehicle telematics data corresponding to one or more trips driven by a second person, wherein the first historical vehicle telematics data and the second historical vehicle telematics data are indicative of a plurality of driving behaviors for the first person and the second person, respectively;

generating, by the server and based upon both the first historical vehicle telematics data and the second historical vehicle telematics data, a custom statistical model that defines a driving behavior vector representing a plurality of driving behavior metrics that distinguish the first person from the second person based on vehicle telematics data;

processing the first historical vehicle telematics data corresponding to one or more trips driven by the first person according to the custom statistical model to determine a first centroid of a first cluster of driving behavior vectors for the first person;

processing the second historical vehicle telematics data corresponding to one or more trips driven by the second person according to the custom statistical model to determine a second centroid of a second cluster of driving behavior vectors for the second person;

receiving, at the server, first vehicle telematics data collected by a first data collection device during a first trip in a vehicle, wherein the first person is associated with the first data collection device;

receiving, at the server, second vehicle telematics data collected by a second data collection device during the first trip in the vehicle, wherein the second person is associated with the second data collection device;

identifying the first person and the second person as potential drivers for the first trip based on a comparison of the first vehicle telematics data and the second vehicle telematics data;

when the first person and the second person are both potential drivers for the first trip, determining with the custom statistical model, by the server, a first driving behavior vector representing a first plurality of driving behavior metrics for the first trip;

when the first driving behavior vector is closer to the first centroid than to the second centroid, assigning the first person as the driver of the vehicle for the first trip; and

when the first driving behavior vector is closer to the second centroid than to the first centroid assigning, by the server, the second person as the driver of the vehicle for the first trip.

2. The method of claim 1, wherein the first historical vehicle telematics data and the second historical vehicle telematics data each include at least two of (i) global positioning satellite (GPS) data, (ii) accelerometer data, and (iii) gyroscope data.

3. The method of claim 1, wherein:

the first data collection device includes a first mobile electronic device associated with the first person, and

the second data collection includes a second mobile electronic device associated with the second person.

4. The method of claim 1, further comprising:

receiving, at the server, third vehicle telematics data collected by the first data collection device during a second trip;

receiving, at the server, fourth vehicle telematics data collected by the second data collection device during the second trip;

determining with the custom statistical model, by the server, a second driving behavior vector representing a second plurality of driving behavior metrics for the second trip;

when the second driving behavior vector is not within a threshold distance to the first centroid and not within the threshold distance to the second centroid, assigning, by the server, an unknown driver as the driver of the vehicle for the second trip.

5. The method of claim 1, further comprising:

causing, by the server, an insurance rating associated with an insurance policy of one or both of the first person and the second person to be adjusted based at least in part upon (i) one or both of the first vehicle telematics data and the second vehicle telematics data and (ii) whether the first trip was assigned to the first person or the second person.

6. The method of claim 1, wherein generating the custom statistical model includes generating the custom statistical model using a machine learning algorithm.

7. The method of claim 1, wherein generating the custom statistical model includes (i) generating, based upon the first historical vehicle telematics data, first driving behavior metrics each corresponding to a respective one of potential plurality of driving behaviors, (ii) generating, based upon the second historical vehicle telematics data, second driving behavior metrics each corresponding to a respective one of potential plurality of driving behaviors, and (iii) determining, based upon the first driving behavior metrics and the second driving behavior metrics, a set of key driving behavior metrics of the potential plurality of driving behaviors having relatively high predictive power as the plurality of driving behavior metrics that distinguish the first person from the second person.

8. A server comprising:

one or more processors; and

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

receive historical vehicle telematics data including (i) first historical vehicle telematics data corresponding to one or more trips driven by a first person, and (ii) second historical vehicle telematics data corresponding to one or more trips driven by a second person, wherein the first historical vehicle telematics data and the second historical vehicle telematics data are indicative of a plurality of driving behaviors for the first person and the second person, respectively;

generate, based upon both the first historical vehicle telematics data and the second historical vehicle telematics data, a custom statistical model that defines a vector representing a plurality of driving behavior metrics that distinguish the first person and the second person based on vehicle telematics data;

process the first historical vehicle telematics data corresponding to one or more trips driven by the first person with the custom statistical model to determine a first centroid of a first cluster of vectors for the first person;

process the second historical vehicle telematics data corresponding to one or more trips driven by the second person with the custom statistical model to determine a second centroid of a second cluster of vectors for the second person;

receive first vehicle telematics data collected by a first data collection device during a first trip in a vehicle, wherein the first person is associated with the first data collection device,

receive second vehicle telematics data collected by a second data collection device during the first trip in a vehicle, wherein the second person is associated with the second data collection device,

identify both the first person and the second person as potential drivers for the first trip based on a comparison of the first vehicle telematics data and the second vehicle telematics data;

when the first person and the second person are both potential drivers for the first trip, determine with the custom statistical model a first vector representing a first plurality of driving behavior metrics for the first trip, and

based upon a first comparison of the first vector to the first centroid of the first cluster and a second comparison of the first vector to the second centroid of the second cluster, assign the first person or the second person as the driver of the vehicle for the second trip.

9. The server of claim 8, wherein the first historical vehicle telematics data and the second historical vehicle telematics data each include at least two of (i) global positioning satellite (GPS) data, (ii) accelerometer data, and (iii) gyroscope data.

10. The server of claim 8, wherein the instructions further cause the server to cause an insurance rating associated with an insurance policy of one or both of the first person and the second person to be adjusted based at least in part upon (i) one or both of the first vehicle telematics data and the second vehicle telematics data and (ii) whether the first trip was assigned to the first person or the second person.

11. The server of claim 8, wherein the instructions cause the server to generate the custom statistical model specific to the first person and the second person using a machine learning algorithm.