Vehicle mode determination based on edge-computing

Patent metadata

Field	Value
Publication number	US-12412437-B2
Application number	US-202318142359-A
Country	US
Kind code	B2
Filing date	May 2, 2023
Priority date	Apr 9, 2020
Publication date	Sep 9, 2025
Grant date	Sep 9, 2025

Abstract

Methods, computer-readable media, software, and apparatuses may determine, based upon edge-computing operations, that a vehicular trip has been initiated and cause one or more sensors to collect vehicle data. One or more trip segments for at least a portion of the vehicular trip may be determined. In some aspects, for each trip segment, a first plurality of time features and a second plurality of frequency features may be determined, and may be concatenated with a third plurality of GPS features to form a feature vector. An accuracy measure may be determined based on the feature vector, and a mode for the vehicle may be predicted.

First claim

What is claimed is:

1. A method comprising:
collecting vehicle data associated with a vehicle from one or more sensors based on a determination that a vehicular trip has been initiated;
determining one or more trip segments for at least a portion of the vehicular trip;
determining, using the vehicle data, one or more time domain features and one or more frequency domain features for each trip segment of the one or more trip segments;
generating a first feature vector using the one or more time domain features and the one or more frequency domain features;
after determining that a quantity of features in the first feature vector exceeds a reduced quantity of features that is sufficient for predicting a vehicle mode, generating a second feature vector that comprises the reduced quantity of features, wherein the features in the second feature vector are determined by applying principal component analysis to the features of the first feature vector;
determining an accuracy measure based on the second feature vector;
predicting a mode for the vehicle based on the accuracy measure, the mode for the vehicle includes a type of vehicle; and
ceasing the collection of vehicle data associated with the vehicle from the one or more sensors, and while the vehicle is still traveling, upon a determination that the mode can be predicted.

2. The method of claim 1 , wherein the one or more sensors are associated with one or more of the vehicle, a telematic device, or a mobile computing device.

3. The method of claim 1 , wherein the one or more sensors include one or more of an accelerometer, a gyroscope, or a locational sensor.

4. The method of claim 1 , wherein the vehicle data includes one or more of location data, speed data, direction data, acceleration data, and braking data.

5. The method of claim 1 , wherein the first feature vector is generated based on one or more GPS features.

6. The method of claim 1 , wherein the vehicle is one of an automobile, a motorcycle, scooters, a bus, a recreational vehicle, or a boat.

7. A vehicle mode determination device, comprising:
a processor; and
a memory unit storing computer-executable instructions, which when executed by the processor, cause the processor to:
determine one or more segments for at least a portion of a vehicular trip;
determine, using vehicle data collected via one or more sensors associated with a vehicle, one or more time domain features and one or more frequency domain features for each trip segment of the one or more segments, the vehicle data collected by one or more sensors when the vehicular trip is initiated;
generate a first feature vector by concatenating the one or more time domain features with the one or more frequency domain features;
after determining that a quantity of features in the first feature vector exceeds a reduced quantity of features that is sufficient for predicting a vehicle mode, generating a second feature vector that comprises the reduced quantity of features, wherein the features in the second feature vector are determined by applying principal component analysis to the features of the first feature vector;
determine an accuracy measure based on the second feature vector; and
predict a vehicle mode based on the accuracy measure.

8. The vehicle mode determination device of claim 7 , wherein the computer-executable instructions, when executed by the processor, further cause the processor to:
cease the collection of vehicle data associated with the vehicle from the one or more sensors upon a determination that the vehicle mode can be predicted.

9. The vehicle mode determination device of claim 7 , wherein the one or more sensors are associated with one or more of a vehicle, a telematic device, or the vehicle mode determination device.

10. The vehicle mode determination device of claim 7 , wherein the one or more sensors include one or more of an accelerometer, a gyroscope, or a locational sensor.

11. The vehicle mode determination device of claim 7 , wherein the vehicle data includes one or more of location data, speed data, direction data, acceleration data, and braking data.

12. The vehicle mode determination device of claim 7 , wherein the first feature vector is generated based on one or more GPS features.

13. The vehicle mode determination device of claim 7 , wherein the vehicle mode includes a type of vehicle.

14. One or more non-transitory computer-readable media storing instructions that, when executed by a computing device, cause the computing device to:
collect vehicle data associated with a vehicle from one or more sensors when a vehicular trip has been initiated;
determine one or more trip segments for at least a portion of the vehicular trip;
determine, using the vehicle data, one or more time domain features and one or more frequency domain features for each trip segment of the one or more trip segments;
generate a first feature vector using the one or more time domain features and the one or more frequency domain features;
after determining that a quantity of features in the first feature vector exceeds a reduced quantity of features that is sufficient for predicting a vehicle mode, generate a second feature vector that comprises the reduced quantity of features, wherein the features in the second feature vector are determined by applying principal component analysis to the features of the first feature vector;
determine, based on a machine learning model, a respective weight for one or more components of the second feature vector;
determine an accuracy measure based on the second feature vector; and
predict a mode for the vehicle based on the accuracy measure.

15. The one or more non-transitory computer-readable media storing instructions of claim 14 that, when executed by the computing device, cause the computing device to:
cease the collection of vehicle data associated with the vehicle from the one or more sensors upon a determination that the mode can be predicted.

16. The one or more non-transitory computer-readable media storing instructions of claim 14 , wherein the one or more sensors are associated with one or more of the vehicle, a telematic device, or the computing device.

17. The one or more non-transitory computer-readable media storing instructions of claim 14 , wherein the one or more sensors include one or more of an accelerometer, a gyroscope, or a locational sensor.

18. The one or more non-transitory computer-readable media storing instructions of claim 14 , wherein the vehicle data includes one or more of location data, speed data, direction data, acceleration data, and braking data.

19. The one or more non-transitory computer-readable media storing instructions of claim 14 , wherein the first feature vector is generated based on one or more GPS features.

Assignees

• Allstate Insurance Co

Inventors

• Tammali Venu
• Jeschke Clayton
• Hanna Melanie
• Schmitt Kyle Patrick

Classifications

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title

• G07C5/0808

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

• G08G1/015

  with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles · CPC title

• G08G1/0133

  for classifying traffic situation · CPC title

• G08G1/0112

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