Predictive risk propensity model for improving high risk driving behaviors

Patent metadata

Field	Value
Publication number	US-12143459-B2
Application number	US-202117644312-A
Country	US
Kind code	B2
Filing date	Dec 14, 2021
Priority date	Oct 3, 2017
Publication date	Nov 12, 2024
Grant date	Nov 12, 2024

Abstract

Systems and methods for providing an aspirational safe driving incentive to drivers having the propensity or ability to improve high risk driving behaviors are provided. Drivers exhibiting high risk driving behaviors may be identified, and initial vehicle telematics data associated with each of the drivers may be collected and analyzed in order to determine which drivers have propensity or ability to improve their high risk driving behaviors. These candidate drivers may receive a probationary safe driving incentive along with feedback configured to improve the drivers' high risk driving behaviors. Updated vehicle telematics data associated with each candidate driver may be collected in order to evaluate an extent to which each candidate driver has improved his or her high risk driving behaviors. Accordingly, a candidate driver's probationary safe driving incentive may be modified or maintained based on the extent to which the candidate has improved upon high risk driving behaviors.

First claim

What is claimed:

1. A method, executed with a computer processor, comprising:
identifying, via the computer processor and based at least in part on first data, a candidate likely to improve a particular technique indicated by the first data, wherein:
the first data is captured by a plurality of sensors disposed at different respective vehicles over a period of time,
each vehicle is associated with a different respective user of a plurality of users,
the candidate is a user of the plurality of users,
the first data comprises a first indication representing that the candidate exhibited a risky driving behavior associated with the particular technique, during the period of time, with a variability that falls below a variability threshold, and
identifying the candidate comprises determining, based on the first indication, that the candidate is likely to improve the particular technique;

receiving, via the computer processor and from an on-board computer disposed at a vehicle operated by the candidate, second data captured by a subset of the plurality of sensors disposed at the vehicle;
transmitting, via the computer processor and based at least in part on the second data, a request to the on-board computer to output, in real time, feedback indicative of the particular technique, wherein outputting the feedback comprises activating a haptic feedback capability of the on-board computer;
receiving, via the computer processor, third data captured by the subset of the plurality of sensors during or after output of the feedback;
determining, via the computer processor and based on the third data, an improvement in the particular technique; and
providing, via the computer processor and based on the improvement, a message to the candidate.

2. The method of claim 1 , wherein the feedback:
is generated based at least in part on personality characteristics of the candidate, and
comprises of at least one of haptic feedback, audible feedback, or visible feedback.

3. The method of claim 1 , wherein the candidate is identified based on information received from at least one of a GPS sensor, an accelerometer, a speedometer, a brake sensor, and an image sensor.

4. The method of claim 1 , wherein the candidate is identified based on information indicative of one or more accidents or tickets.

5. The method of claim 1 , wherein the candidate is identified based on at least one of: (i) performing the particular technique by more or less than at least a minimum amount, (ii) performing the particular technique at a substantially consistent rate, (iii) performing the particular technique at a substantially consistent angle, (iv) a following distance, or (vi) results of one or more personality tests, assessments, surveys, or questionnaires.

6. The method of claim 1 , further comprising:
prior to causing the vehicle to output the feedback, generating the feedback based on a portion of the first data associated with the candidate.

7. The method of claim 1 , wherein determining the improvement in the particular technique comprises:
determining a change in one or both of (i) a frequency, or (ii) a number, of behaviors associated with the candidate.

8. A computer system, comprising:
plurality of sensors disposed at different respective vehicles associated with a plurality of users and configured to capture first data associated with the plurality of users;
one or more processors; and
one or more memories storing instructions that, when executed by the one or more processors, cause the computer system to:
identify, by the one or more processors and based at least in part on the first data, a candidate likely to improve a particular technique indicated by the first data, wherein:
the first data is captured by the plurality of sensors disposed at the different respective vehicles over a period of time,
each vehicle is associated with a different respective user of a plurality of users,
the candidate is a user of the plurality of users,
the first data comprises a first indication representing that the candidate exhibited a risky driving behavior associated with the particular technique, during the period of time, with a variability that falls below a variability threshold, and
identifying the candidate comprises determining, based on the first indication, that the candidate is likely to improve the particular technique;

receive, from an on-board computer disposed at a vehicle operated by the candidate, second data captured buy by a subset of the plurality of sensors disposed at the vehicle operated by the candidate;
transmitting, by the one or more processors and based at least in part on the second data, a request to the on-board computer to output, in real time, feedback indicative of the particular technique, wherein outputting the feedback comprises activating a haptic feedback capability of the on-board computer;
capture, by the subset of the plurality of sensors during or after output of the feedback, third data;
determine, by the one or more processors and based on the third data, an improvement in the particular technique; and
provide, by the one or more processors and based on the improvement, a message to the candidate.

9. The computer system of claim 8 , wherein the first data and the second data each comprise data relating to at least one of:
speed, acceleration, braking, cornering, or following distance.

10. The computer system of claim 8 , wherein the instructions cause the computer system to identify the candidate based on information associated with operation of a vehicle.

11. The computer system of claim 8 , wherein the instructions cause the computer system to identify the candidate based on information indicating a use of at least one of a mobile phone, a smart watch, or an on-board computer.

12. The computer system of claim 8 , wherein the candidate is identified based at least in part on information indicative of performing the particular technique by an amount greater than a threshold amount.

13. The computer system of claim 8 , wherein, the instructions further cause the computer system to, prior to causing the vehicle to output the feedback, generate the feedback based on a portion of the first data associated with the candidate, and wherein the feedback comprises of at least one of haptic feedback, audible feedback, or visible feedback.

14. The computer system of claim 8 , wherein the instructions that cause the computer system to determine the improvement in the particular technique further comprise instructions that cause the computer system to:
determine a change in one or both of (i) a frequency, or (ii) a number, of behavior associated with the candidate.

15. One or more non-transitory computer readable media storing instructions that, when executed, cause a computer processor to perform acts comprising:
identifying, via the computer processor and based at least in part on first data, a candidate likely to improve a particular technique indicated by the first data, wherein:
the first data is captured by a plurality of sensors disposed at different respective vehicles over a period of time,
each vehicle is associated with a different respective user of a plurality of users,
the candidate is a user of the plurality of users,
the first data comprises a first indication representing that the candidate exhibited a risky driving behavior associated with the particular technique, during the period of time, with a variability that falls below a variability threshold, and
identifying the candidate comprises determining, based on the first indication, that the candidate is likely to im

Assignees

• State Farm Mutual Automobile Insurance Co

Inventors

• Fields Brian Mark
• Prevatt Stephen R
• Roberson Steve

Classifications

• H04L67/12

  specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks · CPC title

• G07C5/0841

  Registering performance data (recording measured values G01D; information storage G11B) · CPC title

• G07C5/0833

  using audio means · CPC title

• G07C5/0825

  using optical means · CPC title

• G07C5/0808

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