Driver risk assessment system and method having calibrating automatic event scoring

Patent metadata

Field	Value
Publication number	US-9317980-B2
Application number	US-201313923130-A
Country	US
Kind code	B2
Filing date	Jun 20, 2013
Priority date	May 9, 2006
Publication date	Apr 19, 2016
Grant date	Apr 19, 2016

Abstract

A Driver Risk Assessment System and Method Having Calibrating Automatic Event Scoring is disclosed. The system and method provide robust and reliable event scoring and reporting, while also optimizing data transmission bandwidth. The system includes onboard vehicular driving event detectors that record data related to detected driving events and selectively store or transfer data related to said detected driving events. If elected, the onboard vehicular system will score a detected driving event, compare the local score to historical values previously stored within the onboard system, and upload selective data or data types to a remote server or user if the system concludes that a serious driving event has occurred. Importantly, the onboard event scoring system, if enabled, will continuously evolve and improve in its reliability by being periodically re-calibrated with the ongoing reliability results of manual human review of automated predictive event reports. The system may further respond to independent user requests by transferring select data to said user at a variety of locations and formats.

First claim

What is claimed is:

1. A system for automated event scoring, comprising:
an automated scoring module for determining an automated score data;
an event detector attached to a vehicle with one or more sensors, wherein the event detector comprises a processor configured for:
receiving data from the one or more sensors;
capturing driving event data associated with a driving event based at least on an event trigger using the one or more sensors;
receiving a manual scoring data related to a previous driving event;
calibrating the automated scoring module using the manual scoring data; and
determining the automated score data for the driving event using the automated scoring module;
determining whether a serious driving event has occurred based at least on the automated score data;
in the event that a serious driving event has occurred, uploading the data to a remote server.

2. A system as in claim 1 , wherein the manual scoring data comprises a risk severity.

3. A system as in claim 1 , wherein the manual scoring data comprises an event type.

4. A system as in claim 1 , wherein the manual scoring data comprises a vehicle type.

5. A system as in claim 1 , wherein the manual scoring data comprises a version identifier.

6. A system as in claim 1 , wherein the event detector is further configured to provide the automated score.

7. A system as in claim 1 , wherein calibrating the automated scoring module comprises comparing a previous automated score related to the previous driving event with the manual scoring data.

8. A system as in claim 1 , wherein determining the automated score data comprises using a risk prediction decision tree data.

9. A system as in claim 8 , wherein calibrating the automated scoring module comprises updating the risk prediction decision tree data.

10. A system as in claim 1 , wherein the processor is further configured to determine a reliability associated with the automated score.

11. A system as in claim 10 , wherein the reliability comprises a reliability in frequency.

12. A system as in claim 10 , wherein the reliability comprises a reliability in severity.

13. A system as in claim 10 , wherein the processor is further configured to determine whether the reliability is sufficient to indicate to a user that data associated with the driving event is available.

14. A system as in claim 1 , wherein calibrating is performed once per day.

15. A system as in claim 1 , wherein calibrating is reviewed for problems or errors.

16. A method for automated event scoring, comprising:
receiving data from one or more data sensors coupled with an event detector attached to a vehicle;
capturing, using a processor coupled to the event detector, driving event data associated with a driving event based at least on an event trigger using the one or more sensors;
receiving a manual scoring data related to a previous driving event;
calibrating an automated scoring module using the manual scoring data;
determining an automated score data for the driving event using the automated scoring module;
determining whether a serious driving event has occurred based at least on the automated score data;
in the event that a serious driving event has occurred, uploading the data to a remote server.

17. A computer program product for automated event scoring, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
receiving data from one or more data sensors coupled with an event detector attached to a vehicle;
capturing driving event data associated with a driving event based at least on an event trigger using the one or more sensors;
receiving a manual scoring data related to a previous driving event;
calibrating an automated scoring module using the manual scoring data; and
determining an automated score data for the driving event using the automated scoring module;
determining whether a serious driving event has occurred based at least on the automated score data;
in the event that a serious driving event has occurred, uploading the data to a remote server.

Assignees

• Drivecam Inc
• Lytx Inc

Inventors

• Cook Bryon
• Gilles Louis

Classifications

• G07C5/0808

  Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005) · CPC title

• G07C5/008

  communicating information to a remotely located station (transmission systems for measured values G08C) · CPC title

• G07C5/085 Primary

  using electronic data carriers · CPC title