Driving patterns

• US 9,995,584 B1
• Filed: 01/10/2014
• Issued: 06/12/2018
• Est. Priority Date: 01/10/2014
• Status: Active Grant

• Current Assignee: Allstate Insurance Company (Allstate Corporation)
• Original Assignee: Allstate Insurance Company (Allstate Corporation)
• Inventors: Kanevsky, Valery Alexander
• Primary Examiner(s): Olszewski, John
• Assistant Examiner(s): Merlino, David P.
• Application Number:
  US14/152,458
• Time in Patent Office: 1,614 Days
• Field of Search: None
• CPC Class Codes: B60W 2520/105 Longitudinal acceleration
• CPC Class Codes: B60W 2520/125 Lateral acceleration
• CPC Class Codes: B60W 2556/45 External transmission of data to or from the vehicle
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: G01C 21/12 executed aboard the object being navigated; Dead reckoning
• CPC Class Codes: G01C 21/14 by recording the course traversed by the object G01C21/16 takes precedence
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/08 Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
• CPC Class Codes: G07C 5/085 using electronic data carriers

Abstract

One or more devices in a data analysis computing system may be configured to receive and analyze acceleration data corresponding to driving data, analyze the acceleration data, and determine driving patterns and associated drivers based on the data. Acceleration data may be collected by one or more mobile devices, such as smartphones, tablet computers, and/or on-board vehicle systems. Drivers associated with driving trips may be identified based on the acceleration data collected by the mobile devices. In some cases, driving patterns may be determined based on the acceleration data before and after stopping points during driving trips, and the driving patterns may be compared to a set of previously stored driving patterns associated with various different drivers.

Claims

1. A system, comprising:

one or more mobile computing devices; and

a movement data analysis computing device having;

one or more hardware memory units having in combination at least 256 megabytes (MB) of memory, the one or more hardware memory units configured to receive and store acceleration data; and

one or more processors having a bit size of at least 32-bits and a speed of at least 500 megahertz (MHz), the one or more processors configured to analyze acceleration data;

wherein the movement data analysis computing device is configured to access and employ the one or more hardware memory units and the one or more processors to;

transmit a movement data analysis software application, via one or more networking components, to the one or more mobile computing devices; and

wherein each of the one or more mobile computing devices comprises;

at least one processor configured to analyze acceleration data; and

at least one memory configured to receive and store acceleration data;

wherein each of the mobile computing devices is configured to receive, store, and execute the movement data analysis software application, and said movement data analysis software application includes computer-readable instructions that, when executed by the processors of the mobile computing device cause the mobile computing device to;

determine whether a spatial position of one or more acceleration sensors within at least one of the mobile computing devices with respect to a vehicle is known or not known;

responsive to determining that the spatial position of the one or more acceleration sensors within the at least one of the mobile computing devices with respect to the vehicle is not known;

receive acceleration data collected by one or more acceleration sensors during a driving trip;

determine, based on a speed limit associated with the driving trip, one or more time windows corresponding to portions of the driving trip before or after a stopping point;

calculate, based on the acceleration data collected during the one or more time windows, an acceleration vector length; and

use the calculated acceleration vector length to determine a first driving pattern for a driver-vehicle combination;

responsive to determining that the spatial position of the one or more acceleration sensors within the at least one of the mobile computing devices with respect to the vehicle is known;

receive acceleration data collected by one or more acceleration sensors during the driving trip;

determine, based on the speed limit associated with the driving trip, the one or more time windows corresponding to the portions of the driving trip before or after the stopping point; and

determine the first driving pattern for the driver-vehicle combination based on the acceleration data collected during the one or more time windows;

compare the first driving pattern for the driver-vehicle combination to one or more previously stored driving patterns;

determine, based on the comparison, a first driver of the driving trip;

retrieve, from a database, an indication of a plurality of vehicles associated with the first driver;

determine, based on the comparison and from the plurality of vehicles associated with the first driver, a first vehicle of the driving trip; and

output data corresponding to the first driver, the first vehicle and the driving trip.

2. The system of claim 1, wherein calculating the acceleration vector length includes calculating the acceleration vector length as a square root of a sum of squares of acceleration data along multiple different axes.

3. The system of claim 1, wherein the one or more mobile computing devices are one of a smartphone, a tablet computer, or a vehicle-based computer system.

4. The system of claim 1, wherein the one or more mobile computing devices are further configured to access and employ the one or more hardware memory units and processors to:

determine the stopping point within the acceleration data; and

analyze a subset of the acceleration data proximate to the stopping point.

5. The system of claim 4, wherein determining the one or more time windows comprises:

determining that the driving trip comprises a road in a residential neighborhood;

determining, after determining that the driving trip comprises the road in the residential neighborhood, that the speed limit associated with the driving trip is below a predetermined threshold speed limit; and

determining, after determining that the speed limit associated with the driving trip is below the predetermined threshold speed limit, a duration for the one or more time windows that is below a predetermined time window duration.

6. The system of claim 5, wherein determining the first driver and the first vehicle of the driving trip comprises:

calculating the first driving pattern for the driver-vehicle combination based on the analysis of the acceleration data collected during the one or more time windows; and

comparing the first driving pattern for the driver-vehicle combination to a plurality of previously stored driving patterns associated with a plurality of drivers and vehicles including the first driver and the first vehicle.

7. The system of claim 6, wherein comparing the first driving pattern for the driver-vehicle combination comprises:

comparing the first driving pattern for the driver-vehicle combination to a first previously stored driving pattern associated with the first driver and the first vehicle; and

comparing the first driving pattern for the driver-vehicle combination to a second previously stored driving pattern associated with the first driver and a second vehicle.

8. The system of claim 1, wherein the one or more previously stored driving patterns comprises a passenger configuration, a time, a location, a season, and a weather condition, and wherein the first driving pattern comprises a passenger configuration of the driving trip, a time of the driving trip, a location of the driving trip, a season of the driving trip, and a weather condition of the driving trip.

9. The system of claim 1, wherein the outputting the data corresponding to the first driver, the first vehicle and the driving trip comprises:

outputting first data corresponding to the first driver, the first vehicle, and the driving trip to a first entity; and

outputting second data corresponding to the first driver, the first vehicle, and the driving trip to a second entity.

10. One or more non-transitory computer-readable media having computer-executable instructions stored thereon, that, when executed, cause a mobile computing device to:

receive, from a server, a movement data analysis software application, the movement data analysis software application being received via a network interface;

execute the movement data analysis software application, wherein executing the movement data analysis software application includes;

determining whether a spatial position of one or more acceleration sensors within the mobile computing device with respect to a vehicle is known or not known;

responsive to determining that the spatial position of the one or more acceleration sensors within the mobile computing device with respect to the vehicle is not known;

receiving, by the mobile computing device, acceleration data collected by one or more acceleration sensors during a driving trip;

determining, based on a speed limit associated with the driving trip, one or more time windows corresponding to portions of the driving trip before or after a stopping point;

calculating an acceleration vector length based on the acceleration data collected during the one or more time windows; and

using the calculated acceleration vector length to determine a first driving pattern for a driver-vehicle combination;

responsive to determining that the spatial position of the one or more acceleration sensors within the mobile computing device with respect to the vehicle is known;

receiving, by the mobile computing device, the acceleration data collected by the one or more acceleration sensors during the driving trip;

determining, based on the speed limit associated with the driving trip, the one or more time windows corresponding to the portions of the driving trip before or after the stopping point; and

determining, by the mobile computing device, the first driving pattern for the driver-vehicle combination based on the acceleration data collected during the one or more time windows;

comparing, by the mobile computing device, the first driving pattern to one or more previously stored driving patterns;

determining, based on the comparison and by the mobile computing device, a first driver of the driving trip;

determining, based on the comparison, by the mobile computing device, and from a plurality of vehicles associated with the first driver, a first vehicle of the driving trip;

outputting, by the mobile computing device, first data corresponding to the first driver, the first vehicle, and the driving trip to a first entity; and

outputting, by the mobile computing device, second data corresponding to the first driver, the first vehicle, and the driving trip to a second entity.

11. The one or more non-transitory computer-readable media of claim 10, wherein calculating the acceleration vector length further includes calculating the acceleration vector length as a square root of a sum of squares of acceleration data along multiple different axes.

12. The one or more non-transitory computer-readable media of claim 10, further including instructions that, when executed, cause the mobile computing device to:

determine the stopping point within the acceleration data; and

analyze a subset of the acceleration data proximate to the stopping point.

13. The one or more non-transitory computer-readable media of claim 12, wherein determining the one or more time windows comprises:

determining that the driving trip comprises a highway;

determining, after determining that the driving trip comprises the highway, that the speed limit associated with the driving trip is above a predetermined threshold speed limit; and

determining, after determining that the speed limit associated with the driving trip is above the predetermined threshold speed limit, a duration for the one or more time windows that is above a predetermined time window duration.

14. The one or more non-transitory computer-readable media of claim 13, wherein determining the first driver and the first vehicle of the driving trip comprises:

calculating the first driving pattern for the driver-vehicle combination based on the analysis of the acceleration data collected during the one or more time windows; and

comparing the first driving pattern for the driver-vehicle combination to a plurality of previously stored driving patterns associated with a plurality of drivers and vehicles including the first driver and the first vehicle.

15. The one or more non-transitory computer-readable media of claim 14, wherein comparing the first driving pattern for the driver-vehicle combination comprises:

comparing the first driving pattern for the driver-vehicle combination to a first previously stored driving pattern associated with the first driver and the first vehicle; and

comparing the first driving pattern to a second previously stored driving pattern associated with the first driver and a second vehicle.

16. The one or more non-transitory computer-readable media of claim 10, wherein the first data comprises driving data indicating safe driving behavior, wherein the first entity comprises an insurance entity, wherein the second data comprises driving data indicating driver habits, and wherein the second entity comprises a retail entity.

17. The one or more non-transitory computer-readable media of claim 10, further comprising determining a manufacturer and a model of the first vehicle.

18. A system, comprising:

a driving data analysis server; and

one or more mobile computing devices,

wherein the driving data analysis server comprises;

one or more processors having a bit size of at least 32-bits and a speed of at least 500 megahertz (MHz);

one or more nonvolatile hardware memory units having at least 5 gigabytes (GB) of memory; and

one or more networking components,

wherein the driving data analysis server is configured to access and employ the one or more nonvolatile hardware memory units and the one or more processors to;

transmit a movement data analysis software application, via the one or more networking components, to the one or more mobile computing devices; and

receive driving trip data generated by the movement data analysis software application from the one or more mobile computing devices,

wherein each of the one or more mobile computing devices comprises;

one or more nonvolatile hardware memory units having in combination at least 256 megabytes (MB) of memory, the one or more nonvolatile hardware memory units configured to receive and store acceleration data; and

one or more processors having a bit size of at least 32-bits and a speed of at least 500 megahertz (MHz), said processors configured to analyze acceleration data;

wherein each of the mobile computing devices is configured to receive, store, and execute the movement data analysis software application, and said movement data analysis software application includes computer-executable instructions that, when executed by the processors of the mobile computing device, cause the mobile computing device to;

determine whether a spatial position of one or more acceleration sensors within at least one of the mobile computing devices with respect to a vehicle is known or not known;

responsive to determining that the spatial position of the one or more acceleration sensors within the at least one of the mobile computing devices with respect to the vehicle is not known;

receive acceleration data from one or more acceleration sensors during a driving trip;

determine, based on a speed limit associated with the driving trip, one or more time windows corresponding to portions of the driving trip before or after a stopping point;

calculate an acceleration vector length based on the acceleration data collected during the one or more time windows; and

use the calculated acceleration vector length to determine a first driving pattern for a driver-vehicle combination;

responsive to determining that the spatial position of the one or more acceleration sensors within the at least one of the mobile computing devices with respect to the vehicle is known;

receive the acceleration data via the one or more acceleration sensors during the driving trip;

determine, based on the speed limit associated with the driving trip, the one or more time windows corresponding to the portions of the driving trip before or after the stopping point; and

determine the first driving pattern for the driver-vehicle combination of the driving trip based on the acceleration data collected during the one or more time windows;

compare the first driving pattern for the driver-vehicle combination to one or more previously stored driving patterns, wherein the one or more previously stored driving patterns are stored in a first database corresponding to a first driver;

determine, based on the comparison, that the first driving pattern does not correspond to one of the one or more previously stored driving patterns; and

store, responsive to determining that the first driving pattern does not correspond to one of the one or more previously stored driving patterns, the first driving pattern in a second database corresponding to a plurality of drivers.

19. The system of claim 18, wherein the movement data analysis software application is further programmed to access and employ the one or more nonvolatile hardware memory units and processors of the mobile computing device to:

determine the stopping point within the acceleration data.

20. The system of claim 19, wherein the movement data analysis software application is further programmed to access and employ the one or more nonvolatile hardware memory units and processors of the mobile computing device to:

calculate the first driving pattern for the driver-vehicle combination based on the analysis of the acceleration data collected during the one or more time windows; and

compare the first driving pattern for the driver-vehicle combination to a plurality of previously stored driving patterns associated with a plurality of drivers and vehicles including the first driver and a first vehicle to determine the first driver and the first vehicle of the driving trip.