DRIVER PROFILING SYSTEM AND METHOD

• US 20140039749A1
• Filed: 09/20/2011
• Published: 02/06/2014
• Est. Priority Date: 09/20/2010
• Status: Active Grant

• Current Assignee: Generali Jeniot SPA (Assicurazioni Generali SPA)
• Original Assignee: MyDrive Solutions Limited (Assicurazioni Generali SPA)
• Inventors: Jelbert, Richard, Heavyside, Gavin
• Granted Patent: US 9,701,316 B2
• Time in Patent Office: Days
• US Class Current: 701/32.1
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 2552/05 Type of road, e.g. motorways, local streets, paved or unpaved roads
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005
• CPC Class Codes: G07C 5/085 using electronic data carriers

Abstract

A computer-implemented method of profiling a driver comprises: identifying events in data representing motion of a vehicle; for the events, associating an event with a profile index relating at least to a link on which the vehicle was travelling when the respective event occurred; sorting the events into groups, each group corresponding to a different profile index; determining a driver profile from the events; and characterising the driving behaviour of the driver on the basis of the driver profile.

Claims

1. A computer-implemented method of profiling a driver comprising:

identifying events in data representing motion of a vehicle, the events including acceleration events and/or braking events characterised by the speed at which the vehicle was travelling when the respective event occurred;

selecting one or more of the events based on a profile index associated with a respective event and on at least one attribute derived from the respective event, the profile index relating at least to a link on which the vehicle was travelling at a point during the respective event;

determining a driver profile from the selected events; and

characterising the driving behaviour of the driver on the basis of the driver profile.

2. A method as claimed in claim 1 wherein the attribute derived from a respective event includes at least one of:

a start time of the event;

a finish time of the event;

a duration of the event;

a start location of the event;

a finish location of the event;

an intermediate location of the event;

a start speed;

a finish speed;

or a maximum rate of acceleration or braking.

3. A method as claimed in claim 1 wherein a profile index is derived from one or more link indexes relating to feature(s) of the link that influence the behaviour of a driver of a vehicle travelling along that link.

4. A method as claimed in claim 3 wherein a profile index is further derived from one or more indexes that are time-dependent and/or driver-dependent.

5. A method as claimed in claim 1 wherein the events further comprise one or more events selected from the group consisting of:

speed events, cornering events, familiarity events and distance events.

6. A method as claimed in claim 3 wherein the one or more link indexes include at least one index specifying a road classification of the link on which the event occurred, and optionally wherein the road classification includes at least one of road type and road setting.

7. A method as claimed in claim 1 wherein determining the driver profile comprises grouping events by both event type and profile index.

8. A method as claimed in claim 1 and further comprising deriving an analysis profile from the driver profile, the analysis profile having a lower granularity than the driver profile.

9. A method as claimed in claim 8 wherein data points in the driver profile are, for at least one profile index, classified against a plurality of possible values for the profile index, and wherein deriving the analysis profile comprises selecting data points corresponding to a subset of possible values of the profile index.

10. A method as claimed in claim 8 wherein data points in the driver profile are, for at least one profile index, classified against a plurality of possible values for the profile index, and wherein deriving the analysis profile comprises merging two or more possible values of the profile index.

11. A method as claimed in claim 8 and further comprising comparing the analysis profile to a reference profile.

12. A method as claimed in claim 11 wherein the reference profile is a profile for one or more advanced drivers or wherein the reference profile is a profile for one or more drivers of approximately the same age and/or driving experience as the driver.

13. A method as claimed in claim 11 wherein the reference profile is a profile obtained by combining at least a first profile for a first group of drivers and a second profile for a second group of drivers.

17. A computer-readable medium containing instructions that, when executed by a processor, cause the processor to perform a method as defined in claim 1.

14. A device for profiling a driver comprising:

means for generating a network of links from a road map; and

means for generating, for a link, one or more link indexes, at least one link index being associated with an attribute of the link that influences the behaviour of a driver traversing that link.

15. A device as claimed in claim 14 wherein the link indexes include indexes associated with one or more of Road Category, Link Length, Lane Count, Road Density, Junction Category, Road Curvature, Start-or-End-Point-Only.

16. A device as claimed in claim 14 wherein the link indexes include road classification.