Method for mobile device-based cooperative data capture

Patent metadata

Field	Value
Publication number	US-11659368-B2
Application number	US-202016814444-A
Country	US
Kind code	B2
Filing date	Mar 10, 2020
Priority date	Sep 12, 2016
Publication date	May 23, 2023
Grant date	May 23, 2023

Abstract

Embodiments of a method for improving movement characteristic determination using a plurality of mobile devices associated with a vehicle can include: collecting a first movement dataset corresponding to at least one of a first location sensor and a first motion sensor of a first mobile device of the plurality of mobile devices; collecting a second movement dataset corresponding to at least one of a second location sensor and a second motion sensor of a second mobile device of the plurality of mobile devices; determining satisfaction of a device association condition indicative of the first and the second mobile devices as associated with the vehicle, based on the first and the second movement datasets; and after determining the satisfaction of the device association condition, determining a vehicle movement characteristic based on the first and the second movement datasets.

First claim

We claim:

1. A method for improving movement characteristic determination using a plurality of mobile devices in a vehicle, the method comprising:
receiving at least a portion of a first movement dataset corresponding to a first sensor of a first mobile device of the plurality of mobile devices;
receiving at least a portion of a second movement dataset corresponding to a second sensor of a second mobile device of the plurality of mobile devices;
detecting satisfaction of a device association condition indicative of the first and the second mobile devices residing in the vehicle, based on the first and the second movement datasets, wherein detecting the satisfaction of the device association condition comprises determining an overlap between the first and second movement datasets;
selecting a multi-device-based vehicle movement model from a set of stored vehicle movement models comprising the multi-device-based vehicle movement model and a single-device-based vehicle movement model, wherein each of the set of stored vehicle movement models comprises a deep learning algorithm, based on detecting the satisfaction of the device association condition; and
determining a vehicle movement characteristic based on the multi-device-based vehicle movement model and the first and the second movement datasets, wherein the vehicle movement characteristic is associated with movement of the vehicle.

2. The method of claim 1 , wherein the first sensor of the first mobile device comprises at least one of a first location sensor and a first motion sensor of the first mobile device, and wherein the second sensor of the second mobile device comprises at least one of a second location sensor and a second motion sensor of the second mobile device.

3. The method of claim 1 , wherein the vehicle movement characteristic is further determined based on the overlap.

4. The method of claim 1 , wherein detecting the satisfaction of the device association condition comprises determining a mobile device location proximity between the first and second mobile devices based on the first and second sensors.

5. The method of claim 4 , wherein the first sensor comprises a first motion sensor and the second sensor comprises a second motion sensor, wherein the satisfaction of the device association condition is further detected based on motion datasets corresponding to the first and second motion sensors.

6. The method of claim 1 , wherein the first movement dataset is associated with a first time period and the second movement dataset is associated with a second time period, wherein the second time period is at least partially overlapping with the first time period.

7. The method of claim 1 , wherein determining the vehicle movement characteristic comprises combining the first and second movement datasets for improving accuracy of the vehicle movement characteristic.

8. The method of claim 7 , wherein the vehicle movement characteristic comprises an acceleration.

9. The method of claim 8 , wherein determining the acceleration comprises determining an overlap between a first set of acceleration values and a second set of acceleration values, wherein the first set of acceleration values is determined based on the first movement dataset and the second set of acceleration values is determined based on the second movement dataset.

10. The method of claim 1 , further comprising, after detecting the satisfaction condition:
collecting a second portion of the first movement dataset, wherein the second portion of the first movement dataset is collected later in time than the first portion of the first movement dataset;
collecting a second portion of the second movement dataset, wherein the second portion of the second movement dataset is collected later in time than the first portion of the second movement dataset;
wherein the vehicle movement characteristic is determined based on the second portions of the first and second movement datasets.

11. A method for improving movement characteristic determination using a plurality of mobile devices in a vehicle, the method comprising:
receiving a first dataset associated with a first time period from a first mobile device of the plurality of mobile devices, the first dataset collected from a first sensor of the first mobile device, wherein the first sensor comprises at least one of a first motion sensor and a first location sensor;
receiving a second dataset associated with a second time period, from a second mobile device of the plurality of mobile devices, the second dataset collected from a second sensor of the second mobile device, wherein the second sensor comprises at least one of a second motion sensor and a second location sensor;
detecting satisfaction of a device association condition indicative of the first and the second mobile devices residing in the vehicle based on the first and second datasets, wherein the first and second time periods are at least partially overlapping, wherein detecting the satisfaction of the device association condition comprises determining a mobile device location proximity between the first and second mobile devices based on the first and second sensors;
selecting a multi-device-based vehicle movement model from a set of stored vehicle movement models comprising the multi-device-based vehicle movement model and a single-device-based vehicle movement model, wherein each of the set of stored vehicle movement models comprises a deep learning algorithm, based on detecting the satisfaction of the device association condition; and
determining a vehicle movement characteristic based on the multi-device-based vehicle movement model and the first and the second datasets, wherein the vehicle movement characteristic is associated with movement of the vehicle.

12. The method of claim 11 , wherein the first dataset is associated with a first user and wherein the second dataset is associated with a second user, and wherein the method further comprises updating a score associated with at least one of the first and second users based on the vehicle movement characteristic.

13. The method of claim 12 , further comprising identifying which of the first and second users is a driver of the vehicle, wherein the score comprises a driver score, wherein the driver score associated with the driver of the vehicle is updated.

14. The method of claim 11 , wherein determining the vehicle movement characteristic comprises combining the first and second datasets for improving accuracy of the vehicle movement characteristic.

15. The method of claim 14 , wherein the vehicle movement characteristic comprises an acceleration.

16. The method of claim 15 , wherein determining the acceleration comprises determining an overlap between a first set of acceleration values and a second set of acceleration values, wherein the first set of acceleration values is determined based on the first dataset and the second set of acceleration values is determined based on the second dataset.

Assignees

• Zendrive Inc

Inventors

• Matus Jonathan
• Risbood Pankaj
• Karnik Aditya
• Sachdev Manish

Classifications

• G08B21/04

  responsive to non-activity, e.g. of elderly persons (G08B21/06 takes precedence) · CPC title

• G08G1/205

  Indicating the location of the monitored vehicles as destination, e.g. accidents, stolen, rental · CPC title

• G08G1/162

  event-triggered · CPC title

• H04W4/027

  using movement velocity, acceleration information · CPC title

• G08B25/016

  Personal emergency signalling and security systems (emergency non-personal manually actuated alarm activators G08B25/12) · CPC title