Risk evaluation based on vehicle operator behavior

• US 8,954,340 B2
• Filed: 05/20/2013
• Issued: 02/10/2015
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Original Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Inventors: Sanchez, Kenneth J., Chan, Aaron S., Baker, Matthew R., Zettinger, Matthew, Nepomuceno, John A., Fields, Brian
• Primary Examiner(s): Niquette, Robert R
• Application Number:
  US13/897,650
• Publication Number:
  US 20140278569A1
• Time in Patent Office: 631 Days
• Field of Search: None
• US Class Current: 705/4
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A method for ascertaining the risk associated with the driver of a vehicle utilizes three-dimensional (3D) motion sensing data. A server gathers motion sensing data from one or more motion sensing modules and clusters the motion sensing data into movement categories. The server then assigns an indication of risk to at least some of the movement categories and combines the motion sensing data from a plurality of movement categories to generate a collective measure of risk associated with the driver of the vehicle.

Claims

1. A computer-implemented method comprising:

receiving data about vehicle operator behavior via a computer network,

wherein the data about vehicle operator behavior is generated by a motion sensing device adapted to monitor movements of a vehicle operator, and

wherein the data about vehicle operator behavior is stored on a computer-readable medium;

categorizing the data about vehicle operator behavior by one or more processors executing a first specialized computer routine configured to categorize the data about vehicle operator behavior, wherein categorizing the data about vehicle operator behavior includes clustering the data about vehicle operator behavior, generated by the motion sensing device, into a plurality of groups of data, each of the plurality of groups of data representing a type of movement of the vehicle operator;

determining, by the one or more processors, a numerical level of risk corresponding to each of the plurality of groups of data by executing a learning routine, wherein the learning routine is a second specialized computer routine specifically trained to determine the numerical level of risk based on learned correlations between detected movements of vehicle operators and levels of risk, and wherein the learning routine is trained by executing the learning routine with a set of training data about past vehicle operator behavior; and

generating a risk index corresponding to the vehicle operator by the one or more processors executing a third specialized computer routine configured to generate the risk index corresponding to the vehicle operator, the risk index being a collective measure of risk based on the numerical levels of risk corresponding to the plurality of groups of data.

2. The computer-implemented method of claim 1, further comprising:

when it is determined that at least one of the plurality of groups of data represents a particular type of movement corresponding to a relatively high risk, alerting the vehicle operator using at least one or more of an audible alert, a visual alert, or a tactile alert;

analyzing, with one or more processors, the data about vehicle operator behavior to identify recommendations to reduce risk; and

electronically communicating the recommendations to reduce risk to the vehicle operator.

3. The computer-implemented method of claim 2, wherein the recommendations to reduce risk include one or more of:

avoiding operating a vehicle during at least one specific time period;

reducing mobile device use;

reducing use of vehicle features;

or

ceasing vehicle operation.

4. The computer-implemented method of claim 1, wherein clustering the data about vehicle operator behavior into the plurality of groups of data includes comparisons with pre-programmed movement categories.

5. The computer-implemented method of claim 1, wherein clustering the data about vehicle operator behavior into the plurality of groups of data includes comparisons with pre-programmed movement categories and comparisons with newly created movement categories, the newly created movement categories being created for groups of data dissimilar to the pre-programmed movement categories.

6. The computer-implemented method of claim 1, wherein determining, with one or more processors, the level of risk corresponding to the at least one of the plurality of groups of data includes:

determining, by executing a trained learning routine with one or more processors, whether at least some of the one or more groups of data represents a type of behavior associated with relatively high risk in comparison to other types of behavior.

7. The computer implemented method of claim 6, wherein determining whether the at least some of the one or more groups of data represents the type of behavior associated with relatively high risk includes identifying the presence of a particular ones of the plurality of groups of data, wherein the presence of the particular ones of the plurality of groups of data within the whole of the data about vehicle operator behavior is associated with relatively high risk.

8. The method of claim 6, wherein the trained learning routine is updated based on accumulated data about vehicle operator behavior corresponding to a specific vehicle operator.

9. The computer-implemented method of claim 1, further comprising:

causing one or more processors to generate insurance rates for an insurance product consistent with the risk index corresponding to the vehicle operator;

communicating, via the network interface, insurance costs for the insurance product according to the generated insurance rates; and

receiving, via the network interface, payment for the insurance product.

10. The computer-implemented method of claim 9, further comprising:

causing one or more processors to create a risk report for an insurance customer, the risk report including at least one of risk indices, estimated insurance costs, insurance rates, or payment instructions;

communicating, via the network interface, the risk report to the insurance customer.

11. The method of claim 1, wherein the motion sensing device includes at least one of a visible light camera, infrared light camera, visible light emitter, infrared light emitter, depth sensor, microphone, complementary metal-oxide-semiconductor (CMOS) sensor, or charge-coupled device (CCD) image sensor.

12. The method of claim 1, wherein one or more of the plurality of groups of data represents one or more of:

mobile device use;

vehicle feature adjustments;

eating or drinking;

smoking;

grooming and personal hygiene;

reading a map or navigation device;

reaching for objects inside the vehicle;

or

looking at objects or events outside the vehicle.

13. A computer device comprising:

one or more processors; and

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

wherein the one or more memories include specialized computer executable instructions stored therein that, when executed by the one or more processors, cause the one or more processors to;

receive data about vehicle operator behavior via a computer network,

wherein the data about vehicle operator behavior is generated by a motion sensing device adapted to monitor movements of a vehicle operator, and

wherein the data about vehicle operator behavior is stored on a computer-readable medium;

categorize the data about vehicle operator behavior by executing a first set of the specialized computer executable instructions specifically configured to categorize the data about vehicle operator behavior, wherein categorizing the data about vehicle operator behavior includes clustering the data about vehicle operator behavior, generated by the motion sensing device, into a plurality of groups of data, each of the plurality of groups of data representing a type of movement of the vehicle operator;

determine a numerical level of risk corresponding to each of the plurality of groups of data by executing a learning routine, wherein the learning routine includes a second set of the specialized computer executable instructions trained to determine the numerical level of risk based on learned correlations between detected movements of vehicle operators and levels of risk, wherein the learning routine is trained by executing the learning routine with a set of training data about past vehicle operator behavior; and

generate a risk index corresponding to the vehicle operator by executing a third set of the specialized computer executable instructions specifically configured to generate the risk index corresponding to the vehicle operator, the risk index being a collective measure of risk based on the numerical levels of risk corresponding to the plurality of groups of data.

14. The computer device of claim 13, further comprising computer executable instructions stored therein that cause the one or more processors to:

when it is determined that at least one of the plurality of groups of data represents a particular type of movement corresponding to a relatively high risk, alert the vehicle operator using at least one or more of an audible alert, a visual alert, or a tactile alert;

analyze, with one or more processors, the data about vehicle operator behavior to identify recommendations to reduce risk; and

electronically communicate the recommendations to reduce risk to the vehicle operator.

15. The computer device of claim 14, wherein the recommendations to reduce risk include one or more of:

avoiding operating a vehicle during at least one specific time period;

reducing mobile device use;

reducing use of vehicle features;

or

ceasing vehicle operation.

16. The computer device of claim 13, wherein determining, with one or more processors, the level of risk corresponding to the at least one of the plurality of groups of data includes:

determining, by executing a trained learning routine with one or more processors, whether at least some of the one or more groups of data represents a type of behavior associated with relatively high risk compared to other types of behaviors.

17. The computer device of claim 16, wherein the trained learning routine is updated based on accumulated data about vehicle operator behavior corresponding to a specific vehicle operator.

18. The computer device of claim 13, wherein clustering the data about vehicle operator behavior into the plurality of groups of data includes comparisons with pre-programmed movement categories.

19. The computer device of claim 13, wherein the clustering the data about vehicle operator behavior into the plurality of groups of data includes comparisons with pre-programmed movement categories and comparisons with newly created movement categories, the newly created movement categories being created for groups of data dissimilar to the pre-programmed movement categories.

20. A computer readable storage medium comprising non-transitory, specialized computer readable instructions stored thereon, the instructions, when executed on one or more processors, cause the one or more processors to:

receive data about vehicle operator behavior via a computer network,

wherein the data about vehicle operator behavior is generated by a motion sensing device adapted to monitor movements of a vehicle operator, and

wherein the data about vehicle operator behavior is stored on a computer-readable medium;

categorize the data about vehicle operator behavior by executing a first set of the non-transitory, specialized computer readable instructions specifically configured to categorize the data about vehicle operator behavior, wherein categorizing the data about vehicle operator behavior includes clustering the data about vehicle operator behavior, generated by the motion sensing device, into a plurality of groups of data, each of the plurality of groups of data representing a type of movement of the vehicle operator;

determine a numerical level of risk corresponding to each of the plurality of groups of data by executing a learning routine, wherein the learning routine includes a second set of the non-transitory, specialized computer readable instructions trained to determine the numerical level of risk based on learned correlations between detected movements of vehicle operators and levels of risk, wherein the learning routine is trained by executing the learning routine with a set of training data about past vehicle operator behavior; and

generate a risk index corresponding to the vehicle operator by executing a third set of the non-transitory, specialized computer executable instructions specifically configured to generate the risk index corresponding to the vehicle operator, the risk index being a collective measure of risk based on the numerical levels of risk associated with the plurality of groups of data.

21. The computer readable storage medium of claim 20, further comprising:

causing one or more processors to generate insurance rates for an insurance product consistent with the risk index corresponding to the vehicle operator;

communicating, via the network interface, insurance costs for the insurance product according to the generated insurance rates; and

receiving, via the network interface, payment for the insurance product.