Systems and methods for determining a vehicle is at an elevated risk for an animal collision

Patent metadata

Field	Value
Publication number	US-10166916-B2
Application number	US-201414564960-A
Country	US
Kind code	B2
Filing date	Dec 9, 2014
Priority date	May 30, 2014
Publication date	Jan 1, 2019
Grant date	Jan 1, 2019

Abstract

Methods and systems for analyzing environment data to determine whether a vehicle operator is at an elevated risk for an animal collision are provided. According to certain aspects, an insurance provider may assess elevated risk according to various factors and, if it is determined that the vehicle operator is at an elevated risk for an animal collision, the insurance provider may generate a warning and wirelessly communicate the warning to the vehicle operator. The factors analyzed may include past accident, driver characteristic, weather, calendar, time of day, animal, seasonal, and/or other information. The vehicle operator may be notified of the risk and optionally presented with tips to mitigate the risk. The vehicle operator may be notified of the risk by a mobile device and/or the vehicle, such as from a vehicle communication and control system. Animal collision avoidance functionality may be used to adjust insurance premiums, rates, or rewards.

First claim

What is claimed:

1. A computer-implemented method of processing vehicle collision risk information, the method comprising:
receiving, at a hardware server, vehicle data including an indication of at least a current GPS (Global Positioning System) location of at least one of an automobile or a mobile device located within the automobile;
accessing, by a processor located remotely from the at least one of the automobile or the mobile device, environment data associated with the current GPS location of the at least one of the automobile or the mobile device, the environment data including a historical record of automobile-animal collisions (i) at the current GPS location of the at least one of the automobile or the mobile device, or (ii) in a particular proximity to the current GPS location of the at least one of the automobile or the mobile device;
based on the environment data and the current GPS location, executing a machine learning algorithm to determine, by the processor, that the automobile is at a risk greater than a threshold level for a non-avian animal collision, the threshold level being a level of risk greater than zero risk;
generating, by the processor, a notification indicating the risk greater than the threshold level of collision with a non-avian animal;
communicating, from the processor located remotely from the at least one of the automobile or the mobile device, the notification of the risk greater than the threshold level to the at least one of the automobile or the mobile device via a communications network so as to allow an operator of the automobile to be notified of the risk greater than the threshold level;
receiving, at the hardware server, an animal collision report indicating that the automobile collided with a non-avian animal; and
updating, by the processor, the machine learning algorithm according to the animal collision report.

2. The computer-implemented method of claim 1 , wherein communicating the notification to the at least one of the automobile or the mobile device comprises:
communicating the notification to at least one of an onboard computer of the automobile or an electronic device associated with an operator of the automobile.

3. The computer-implemented method of claim 1 , wherein the vehicle data further includes:
at least one of a speed of the automobile, automobile characteristics, or demographic information associated with an operator of the automobile.

4. The computer-implemented method of claim 1 , wherein the environment data further includes:
at least one of ecological characteristics or roadway characteristics.

5. The computer-implemented method of claim 1 , wherein the environment data includes a first environment factor having a first specific weight and a second environment factor having a second specific weight, and wherein determining that the automobile is at the risk greater than the threshold level comprises:
calculating an overall risk based on combining the first environment factor and the second environment factor.

6. The computer-implemented method of claim 1 , further comprising:
identifying at least one of a time of day or a time of year, wherein determining that the automobile is at the risk greater than the threshold level is further based upon a portion of the environment data corresponding to the at least one of the time of day or the time of year.

7. A system for processing vehicle collision risk information, comprising:
a communication module adapted to communicate data;
a memory adapted to store non-transitory computer executable instructions;
a hardware server to store environment data; and
a processor adapted to interface with the communication module, wherein the processor is configured to execute the non-transitory computer executable instructions to cause the system to:
receive, via the communication module, vehicle data including an indication of at least a current GPS (Global Positioning System) location of at least one of an automobile or a mobile device located within the automobile, the processor being located remotely from the at least one of the automobile or the mobile device,
access, via the processor, at least a portion of the environment data associated with the current GPS location of the at least one of the automobile or the mobile device, the environment data including a historical record of automobile-animal collisions (i) at the current GPS location of the at least one of the automobile or the mobile device, or (ii) in a particular proximity to the current GPS location of the at least one of the automobile or the mobile device,
based on the environment data and the current GPS location, execute a machine learning algorithm to determine, via the processor, that the automobile is at a risk greater than a threshold level for a non-avian animal collision, the threshold level being a level of risk greater than zero risk,
generate, via the processor, a notification indicating the risk greater than the threshold level of collision with a non-avian animal,
communicate, via the communication module and a communications network, the notification of the risk greater than the threshold level to the at least one of the automobile or the mobile device located remotely from the processor so as to allow an operator of the automobile to be notified of the risk greater than the threshold level,
receive, at the hardware server, an animal collision report indicating that the automobile collided with a non-avian animal, and
update, via the processor, the machine learning algorithm according to the animal collision report.

8. The system of claim 7 , wherein to communicate the notification to the at least one of the automobile or the mobile device, the communication module is configured to:
communicate the notification to at least one of an onboard computer of the automobile or an electronic device associated with an operator of the automobile.

9. The system of claim 7 , wherein to receive the vehicle data, the hardware server is configured to:
receive at least one of a speed of the automobile, automobile characteristics, or demographic information associated with an operator of the automobile.

10. The system of claim 7 , wherein to access the environment data, the processor is configured to execute the non-transitory computer executable instructions to cause the processor to:
access at least one of ecological characteristics or roadway characteristics.

11. A computer-implemented method of issuing an alert associated with a vehicle-animal collision, the method comprising:
accessing, via a processor, environment data that includes a historical record of automobile-animal collisions (i) at a current GPS location of at least one of an automobile or a mobile device located within the automobile, or (ii) in a particular proximity to the current GPS location of the at least one of the automobile or the mobile device, the processor being located remotely from the automobile;
predicting, based upon the environment data and using a machine learning algorithm, (1) a geographical scope, (2) a temporal scope, and (3) a seasonal scope of an area at a risk greater than a threshold level of being associated with a collision with a non-avian animal when a non-avian animal is not detected at the automobile, the threshold level being a level of risk greater than zero risk;
monitoring or identifying the current GPS location of the mobile device located within the automobile via the processor;
monitoring or identifying a current time of day via the processor;
monitoring or identifying a current time of year via the processor; and
when, as determined by the processor, (a) the current GPS location of the mobil

Assignees

• State Farm Mutual Automobile Insurance Co

Inventors

• Bernico Michael
• Mowery Milton
• Sanidas Tim G
• Zimmer Christopher

Classifications

• G06Q40/08 Primary

  Insurance · CPC title

• G08G1/096775

  where the origin of the information is a central station · CPC title

• G08G1/0112

  from the vehicle, e.g. floating car data [FCD] · CPC title

• B60Q9/00 Primary

  Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00 {, e.g. haptic signalling} · CPC title

• G08G1/0141

  for traffic information dissemination · CPC title