System and method for determining driving patterns using telematics data

• US 9,786,103 B2
• Filed: 05/15/2014
• Issued: 10/10/2017
• Est. Priority Date: 05/15/2014
• Status: Active Grant

• Current Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Original Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Inventors: Menon, Sunish Shreenarayan, Dosher, David James, Christensen, Scott Thomas
• Primary Examiner(s): Merchant, Shahid
• Assistant Examiner(s): Alladin, Ambreen A
• Application Number:
  US14/277,939
• Publication Number:
  US 20150332518A1
• Time in Patent Office: 1,244 Days
• Field of Search: 705 44, 705 4
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/0825 using optical means
• CPC Class Codes: G07C 5/085 using electronic data carriers

Abstract

A computer implemented method for determining a yaw angle estimate or vehicle heading direction is presented. A data server may receive a plurality of telematics data originating from a client computing device and determine a first primary movement window from the telematics data. The data server may also determine a potential range of yaw angles from the plurality of telematics data from the first primary movement window and generate an equality that evaluates the potential range of yaw angles. The data server may further maximize the count of acceleration events of the telematics data from the first primary movement window to further generate one or more refined yaw angle estimates. The data server stores the one or more yaw angle estimates on a memory.

Claims

1. A computer implemented method for determining a driving pattern from raw telematics data, the method comprising:

receiving, via a computer network, a plurality of telematics data corresponding to a trip of a vehicle, wherein the plurality of telematics data originates from a client computing device and includes a gravitational data component, a longitudinal data component and a latitudinal data component, wherein each of the longitudinal data component and the latitudinal data component has two acceleration effects;

identifying, by one or more processors, a first primary movement window of the vehicle trip from secondary movement data in the plurality of telematics data, wherein the primary movement window is indicative of the client computing device being static with respect to movement of the vehicle, and wherein the secondary movement data is indicative of the client computing device moving with respect to the moving vehicle;

removing, by the one or more processors, the gravitational data component from the telematics data in the first primary movement window of the vehicle trip leaving a vector defined by the longitudinal data component and the latitudinal data component in a longitudinal-latitudinal plane;

combining, by the one or more processors, the longitudinal data component and the latitudinal data component to create an angular average of four times the directions of all vectors in the longitudinal-latitudinal plane such that all four acceleration effects of the plurality telematics data are in one direction;

generating, by the one or more processors, one or more yaw angle estimates from the first primary movement window of the vehicle trip using the angular average; and

determining, by the one or more processors, a driving pattern based on at least one of the yaw angle estimates.

2. The method of claim 1 further comprising:

determining, by the one or more processors, a driving pattern using at least one of;

a constant speed time, an idling time, an acceleration event, a braking event, a turning event GPS data, gyroscope data and magnetometer data.

3. The method of claim 1 further comprising:

summarizing, by the one or more processors, the driving pattern from the first primary movement windows at one or more of;

a trip, a day, a month or a year level.

4. The method of claim 1 further comprising:

receiving, via the computer network, a plurality of GPS data corresponding to a trip of a vehicle, wherein the plurality of telematics data originates from a client computing device and includes a GPS speed data;

analyzing, by the one or more processors, the plurality of GPS data;

determining, by the one or more processors, that the plurality of GPS data is accurate;

and

combining, by the one or more processors, the plurality of GPS data with the plurality of telematics data.

5. The method of claim 1 further comprising:

generating, by the one or more processors, a pitch and a roll angle from the first primary movement window of the vehicle trip;

determining, by the one or more processors, a driving pattern using at least one of;

the pitch and roll angles; and

determining, by the one or more processors, that using at least the pitch and roll angles is indicative of at least one of;

an acceleration data of an acceleration event, a braking event, a left turn event or a right turn event.

6. The method of claim 1 further comprising:

analyzing, by the one or more processors, the one or more yaw angle estimates; and

determining, at the one or more processors, a final yaw angle from the one or more yaw angle estimates that best aligns the acceleration data with the plurality of telematics data.

7. A computer device for determining a driving pattern from raw telematics data, the device comprising:

one or more processors; and

one or more memories coupled to the one or more processors;

the one or more memories including non-transitory computer executable instructions stored therein that, when executed by the one or more processors, cause the one or more processors to;

receive a plurality of telematics data corresponding to a trip of a vehicle, wherein the plurality of telematics data originates from a client computing device and the plurality of telematics data includes a gravitational data component, a longitudinal data component and a latitudinal data component, wherein each of the longitudinal data component and the latitudinal data component has two acceleration effects;

identify a first primary movement of the vehicle trip from secondary movement data in the plurality of telematics data, wherein the primary movement window is indicative of the client computing device being static with respect to movement of the vehicle, and wherein the secondary movement data is indicative of the client computing device moving with respect to the moving vehicle;

remove the gravitational constant from the telematics data in the first primary movement window of the vehicle trip leaving a vector defined by the longitudinal data component and the latitudinal data component in a longitudinal-latitudinal plane;

combine the longitudinal data component and the latitudinal data component to create an angular average of four times the directions of all vectors in the longitudinal-latitudinal plane such that all four acceleration effects of the plurality telematics data are in one direction;

generate, using the angular average, one or more yaw angle estimates from the first primary movement window of the vehicle trip; and

determine a driving pattern based on at least one of the yaw angle estimates.

8. The computer device of claim 7, wherein the non-transitory computer executable instructions further cause the one or more processors to:

summarize, the driving pattern from the first primary movement windows at one or more of;

a trip, a day, a month and a year level and relating that with an insurance account to determine driving risk.

9. The computer device of claim 7, wherein the non-transitory computer executable instructions further cause the one or more processors to:

receive a plurality of GPS data corresponding to a trip of a vehicle, wherein the plurality of telematics data originates from a client computing device and includes a GPS speed data;

analyze the plurality of GPS data;

determine that the plurality of GPS data is accurate; and

combine the plurality of GPS data with the plurality of telematics data.

10. The computer device of claim 7, wherein the non-transitory computer executable instructions further cause the one or more processors to:

analyze the one or more yaw angle estimates; and

determine a final yaw angle from the one or more yaw angle estimates that best aligns the acceleration data with the plurality of telematics data.

11. The computer device of claim 7, wherein the non-transitory computer executable instructions further cause the one or more processors to:

generate a pitch and a roll angle from the first primary movement window of the vehicle trip;

determine a driving pattern using at least one of;

the pitch and roll angles; and

determine that using at least the pitch and roll angles is indicative of at least one of;

an acceleration of an acceleration event, a braking event, a left turn event or a right turn event.

12. A non-transitory computer readable storage medium having instructions stored thereon for determining a driving pattern from raw telematics data, the instructions when executed on one or more processors cause the one or more processors to:

receive a plurality of telematics data corresponding to a trip of a vehicle, wherein the plurality of telematics data originates from a client computing device and the plurality of telematics data includes a gravitational data component, a longitudinal data component and a latitudinal data component, wherein each of the longitudinal data component and the latitudinal data component has two acceleration effects;

identify a first primary movement window of the vehicle trip from secondary movement data in the plurality of telematics data, wherein the primary movement window is indicative of the client computing device being static with respect to movement of the vehicle, and wherein the secondary movement data is indicative of the client computing device moving with respect to the moving vehicle;

remove the gravitational data component from the telematics data in the first primary movement window of the vehicle trip leaving a vector defined by the longitudinal data component and the latitudinal data component in a longitudinal-latitudinal plane;

combine the longitudinal data component and the latitudinal data component to create an angular average of four times the directions of all vectors in the longitudinal-latitudinal plane such that all four acceleration effects of the plurality telematics data are in one direction;

generate, using the angular average, one or more yaw angle estimates from the first primary movement window of the vehicle trip using the created function without determining which data component corresponds with which acceleration effect; and

determine a driving pattern based on at least one of the yaw angle estimates.

13. The non-transitory computer readable storage medium of claim 12, wherein the further comprising instructions stored thereon that cause the one or more processors to:

summarize, the driving pattern from the first primary movement windows at one or more of;

a trip, a day, a month and a year level.

14. The non-transitory computer readable storage medium of claim 12, wherein the further comprising instructions stored thereon that cause the one or more processors to:

receive a plurality of GPS data corresponding to a trip of a vehicle, wherein the plurality of telematics data originates from a client computing device and includes a GPS speed data;

analyze the plurality of GPS data;

determine that the plurality of GPS data is accurate; and

combine the plurality of GPS data with the plurality of telematics data.

15. The non-transitory computer readable storage medium of claim 12, further comprising instructions stored thereon that cause the one or more processors to:

analyze the one or more yaw angle estimates; and

determine a final yaw angle from the one or more yaw angle estimates that best aligns the acceleration data with the plurality of telematics data.

16. The non-transitory computer readable storage medium of claim 12, further comprising instructions stored thereon that cause the one or more processors to:

generate a pitch and a roll angle from the first primary movement window of the vehicle trip;

determine a driving pattern using at least one of;

the pitch and roll angles; and

determine that using at least the pitch and roll angles is indicative of at least one of;

an acceleration of an acceleration event, a braking event, a left turn event or a right turn event.

17. The non-transitory computer readable storage medium of claim 12, further comprising instructions stored thereon that cause the one or more processors to:

determine a driving pattern using at least one of;

a constant speed time, an idling time, an acceleration event, a braking event, a turning event GPS data, gyroscope data and magnetometer data.