Cloud-based vehicular telematics systems and methods for generating hybrid epoch driver predictions

Patent metadata

Field	Value
Publication number	US-12229836-B2
Application number	US-202418439507-A
Country	US
Kind code	B2
Filing date	Feb 12, 2024
Priority date	Oct 2, 2019
Publication date	Feb 18, 2025
Grant date	Feb 18, 2025

Abstract

A system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations: receiving telematics data from a mobile device during one or more vehicle trips including a previous epoch for a driver and a current epoch for the driver; generating a previous epoch score for the driver based on the telematics data of the previous epoch for the driver; generating, using a trained machine learning model, a predicted epoch score for the driver based on the telematics data of the current epoch for the driver; generating a hybrid epoch score for the driver from at least portions of the previous epoch score for the driver and the predicted epoch score for the driver; and transmitting the hybrid epoch score for the driver. Other embodiments are described.

First claim

The invention claimed is:

1. A system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising:
receiving telematics data from a mobile device during one or more vehicle trips including a previous epoch for a driver and a current epoch for the driver;
generating a previous epoch score for the driver based on the telematics data of the previous epoch for the driver;
generating, using a trained machine learning model, a predicted epoch score for the driver based on the telematics data of the current epoch for the driver;
generating a hybrid epoch score for the driver from at least portions of the previous epoch score for the driver and the predicted epoch score for the driver; and
transmitting the hybrid epoch score for the driver.

2. The system of claim 1 , wherein the previous epoch score is weighted according to a remaining amount of time of the current epoch.

3. The system of claim 2 , wherein the current epoch is associated with multiple time segments.

4. The system of claim 1 , wherein generating the predicted epoch score for the driver comprises:
predicting future driving behavior for one or more future trips of the driver during a remaining time in the current epoch based at least in part upon past driving behavior of the driver corresponding to past telematics data of one or more previous epochs for the driver.

5. The system of claim 1 , wherein the predicted epoch score comprises a simulated score for the current epoch based at least in part upon (i) a weighting of previous epochs and (ii) an amount of elapsed time of the current epoch.

6. The system of claim 1 , wherein the trained machine learning model is configured to:
identify patterns within historic telematics data corresponding to at least a quantity level metric or a quality level metric of the driver, wherein the historic telematics data is from one or more historic epochs for the driver; and
facilitate predictions of future driving behavior for the driver during a remaining time period of the current epoch.

7. The system of claim 1 , wherein the operations further comprise:
generating a discount amount (a) used to determine a reward for the driver based on the hybrid epoch score and (b) for display on the mobile device, wherein the discount amount displayed fluctuates in real-time corresponding to each additional trip completed during the current epoch.

8. A computer-implemented method comprising:
receiving telematics data from a mobile device during one or more vehicle trips including a previous epoch for a driver and a current epoch for the driver;
generating a previous epoch score for the driver based on the telematics data of the previous epoch for the driver;
generating, using a trained machine learning model, a predicted epoch score for the driver based on the telematics data of the current epoch for the driver;
generating a hybrid epoch score for the driver from at least portions of the previous epoch score for the driver and the predicted epoch score for the driver; and
transmitting the hybrid epoch score for the driver.

9. The computer-implemented method of claim 8 , wherein the previous epoch score is weighted according to a remaining amount of time of the current epoch.

10. The computer-implemented method of claim 9 , wherein the current epoch is associated with multiple time segments.

11. The computer-implemented method of claim 8 , wherein generating the predicted epoch score for the driver comprises:
predicting future driving behavior for one or more future trips of the driver during a remaining time in the current epoch based at least in part upon past driving behavior of the driver corresponding to past telematics data of one or more previous epochs for the driver.

12. The computer-implemented method of claim 8 , wherein the predicted epoch score comprises a simulated score for the current epoch based at least in part upon (i) a weighting of previous epochs and (ii) an amount of elapsed time of the current epoch.

13. The computer-implemented method of claim 8 , wherein the trained machine learning model is configured to:
identify patterns within historic telematics data corresponding to at least a quantity level metric or a quality level metric of the driver, wherein the historic telematics data is from one or more historic epochs for the driver; and
facilitate predictions of future driving behavior for the driver during a remaining time period of the current epoch.

14. The computer-implemented method of claim 8 further comprising:
generating a discount amount (a) used to determine a reward for the driver based on the hybrid epoch score and (b) for display on the mobile device wherein the discount amount displayed fluctuates in real-time corresponding to each additional trip completed during the current epoch.

15. One or more non-transitory computer-readable media storing computing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving telematics data from a mobile device during one or more vehicle trips including a previous epoch for a driver and a current epoch for the driver;
generating a previous epoch score for the driver based on the telematics data of the previous epoch for the driver;
generating, using a trained machine learning model, a predicted epoch score for the driver based on the telematics data of the current epoch for the driver;
generating a hybrid epoch score for the driver from at least portions of the previous epoch score for the driver and the predicted epoch score for the driver; and
transmitting the hybrid epoch score for the driver.

16. The one or more non-transitory computer-readable media of claim 15 , the previous epoch score is weighted according to a remaining amount of time of the current epoch, wherein the current epoch is associated with multiple time segments.

17. The one or more non-transitory computer-readable media of claim 15 , wherein generating the predicted epoch score for the driver comprises:
predicting future driving behavior for one or more future trips of the driver during a remaining time in the current epoch based at least in part upon past driving behavior of the driver corresponding to past telematics data of one or more previous epochs for the driver.

18. The one or more non-transitory computer-readable media of claim 15 , wherein the predicted epoch score comprises a simulated score for the current epoch based at least in part upon (i) a weighting of previous epochs and (ii) an amount of elapsed time of the current epoch.

19. The one or more non-transitory computer-readable media of claim 15 , wherein the trained machine learning model is configured to:
identify patterns within historic telematics data corresponding to at least a quantity level metric or a quality level metric of the driver, wherein the historic telematics data is from one or more historic epochs for the driver; and
facilitate predictions of future driving behavior for the driver during a remaining time period of the current epoch.

20. The one or more non-transitory computer-readable media of claim 15 , wherein the operations further comprise:
generating a discount amount (a) used to determine a reward for the driver based on the hybrid epoch score and (b) for display on the mobile device, wherein the discount amount displ

Assignees

• Blueowl Llc
• Quanata Llc

Inventors

• Sanchez Kenneth Jason

Classifications

• G07C5/08

  Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time · CPC title

• G06Q30/0224

  based on user history · CPC title

• B60W40/09

  Driving style or behaviour · CPC title

• B60W2556/55

  using telemetry · CPC title

• B60W2556/10

  Historical data · CPC title