Method and system for risk determination of a route

Patent metadata

Field	Value
Publication number	US-11175152-B2
Application number	US-202017111299-A
Country	US
Kind code	B2
Filing date	Dec 3, 2020
Priority date	Dec 3, 2019
Publication date	Nov 16, 2021
Grant date	Nov 16, 2021

Abstract

A method for risk determination of a route includes collecting a set of inputs and determining a set of risk scores. Additionally, the method can include any or all of: processing the set of inputs; organizing the set of inputs; determining a model based on the set of inputs; determining a set of risk scores; producing an outputs based on the set of risk scores; and/or any other suitable processes.

First claim

We claim:

1. A method for route selection for a driver, the method comprising:
receiving a starting point and a destination;
determining a first series of route segments from a predetermined set of route segments based on a 1 st route from the starting point to the destination;
determining a second series of route segments from the predetermined set of route segments based on a 2 nd route from the starting point to the destination;
determining a 1 st route risk score and a 2 nd route risk score, wherein determining the 1 st route risk score and the 2 nd route risk score comprises:
with a model comprising a plurality of model parameters, determining a segment risk score associated with each of the first and second series of route segments, wherein determining the segment risk score comprises:
receiving motion information from a set of mobile user devices associated with a set of drivers driving a set of vehicles, the motion information comprising: location information generated by a mobile user device of the set of mobile user devices and device handling information associated with the driver handling the mobile user device;
receiving collision information from a database;
based on the motion information, determining a set of potential collision events comprising a set of near-miss events; and
determining a set of collision events based on the collision information, wherein the plurality of model parameters comprises a first parameter associated with the set of near-miss events and a second parameter associated with the set of collision events;

for the 1 st route, aggregating the first series of segment risk scores to determine the 1 st route risk score;
for the 2 nd route, aggregating the second series of segment risk scores to determine the 2 nd route risk score;
selecting a route from the 1 st route and the 2 nd route based on the 1 st and 2 nd route risk scores; and
at a mobile user device, providing navigation instructions to the driver based on the selected route.

2. The method of claim 1 , wherein the motion information further comprises positional information collected with the mobile user device of the driver during a traversal of the selected route, wherein the mobile user device comprises an inertial sensor, further comprising transforming a set of inertial measurements of the inertial sensor into the positional information.

3. The method of claim 2 , further comprising updating the plurality of model parameters of the model based on the motion information.

4. The method of claim 3 , wherein the motion information further comprises location information associated with a second set of mobile user devices associated with a second set of drivers.

5. The method of claim 1 , further comprising presenting the 1 st and 2 nd route risk scores to the driver, wherein the selected route is further determined based on a driver input in response presenting the 1 st and 2 nd route risk scores to the driver.

6. The method of claim 1 , further comprising receiving a time of day of associated with a position of the driver at the starting point, wherein each of the segment risk scores is further determined based on the time of day.

7. The method of claim 1 , wherein determining the segment risk score further comprising receiving information from a second database, the second database separate and distinct from the first database.

8. The method of claim 7 , wherein the second database comprises a collision frequency associated with a region, wherein the region comprises the 1 st route and the 2 n d route.

9. The method of claim 1 , further comprising transmitting a selected route risk score to an entity.

10. The method of claim 9 , wherein the entity is an insurance company associated with the driver.

11. The method of claim 1 , wherein the set of drivers comprises at least 1,000 drivers.

12. The method of claim 1 , wherein the set of collision events is further determined based on the motion information.

13. The method of claim 1 , wherein the set of potential collision events comprises:
an acceleration parameter above a predetermined threshold of a vehicle of the set of vehicles;
a braking parameter below a predetermined time threshold of a vehicle of the set of vehicles; and
a mobile device usage above a predetermined threshold of a driver of the set of drivers.

14. The method of claim 1 , wherein the motion information further comprises an arrangement of the mobile user device within a vehicle of the set of vehicles during driving.

15. The method of claim 1 , wherein determining the set of potential collision events based on the sensor information comprises:
determining satisfaction of a vehicle acceleration threshold;
determining a driver behavior based on the device handling information; and
based on the driver behavior and the satisfaction of the vehicle acceleration threshold, determining a near-miss event.

16. A method for determining a route risk score associated with a route, the method comprising:
determining a series of route segments making up the route based on a predetermined set of route segments from a 1 st database;
receiving the predetermined set of route segments from the 1 st database;
receiving a motion dataset from a set of mobile user devices associated with a set of multiple drivers, the motion dataset comprising: an inertial dataset and a location dataset;
based on the motion dataset, determining vehicle movement features and mobile device motion features, the mobile device motion features comprising device handling information;
determining a set of collision events based on a set of collision identifiers and a corresponding set of locations, each received from a 2 nd database;
with a model, based on the vehicle movement features and the mobile device motion features dataset, determining a set of potential collision events comprising near-collision events;
determining a segment risk score associated with each of the series of route segments, thereby determining a series of segment risk scores;
aggregating the series of segment risk scores to determine the route risk score; and
at a mobile user device, triggering an action based on the route risk score.

17. The method of claim 16 , wherein the 2 nd database is separate and distinct from the 1 st database.

18. The method of claim 16 , wherein the action comprises providing a set of navigation instructions to a driver based on the route risk score.

19. The method of claim 18 , wherein the set of multiple drivers comprises the driver.

20. The method of claim 16 , wherein the set of collision events is further determined based on the vehicle movement features.

21. The method of claim 16 , wherein the model comprises a statistical model.

22. The method of claim 21 , wherein the statistical model is a generalized linear model.

Assignees

• Zendrive Inc

Inventors

• Pal Jayanta Kumar
• Verma Vishal
• Singh Shivam
• Risbood Pankaj
• Matus Jonathan

Classifications

• G06Q40/08 Primary

  Insurance · CPC title

• G01C21/3691

  Retrieval, searching and output of information related to real-time traffic, weather, or environmental conditions (arrangements for giving variable traffic instructions G08G1/09) · CPC title

• G01C21/3484

  Personalized, e.g. from learned user behaviour or user-defined profiles · CPC title

• G01C21/3453

  Special cost functions, i.e. other than distance or default speed limit of road segments · CPC title

• G01C21/3461 Primary

  Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types or segments such as motorways, toll roads or ferries · CPC title