Granted Patent B2

US 12,210,968 · App. 17/371,721 · Granted Jan 28, 2025

Inventors: Vinay Kumar (Fremont, CA); Kenneth J. Sanchez (San Francisco, CA)

Assignee: QUANATA, LLC

G06N3/08G07C5/008G07C5/0858

Abstract

Claims (67)

1. A method implemented by one or more processors for determining a role of an individual associated with a vehicle, the method comprising:

receiving, by the one or more processors, a set of sensor data associated with an electronic device of the individual, the set of sensor data corresponding to a first set of timing data;

receiving, by the one or more processors, a set of location data corresponding to a second set of timing data;

determining, by the one or more processors, a time of interest that corresponds to when the electronic device is located in proximity to a designated vehicle location based upon the set of location data;

identifying, by the one or more processors, a first portion of the set of sensor data corresponding to the time of interest;

inputting, by the one or more processors, the first portion of the set of sensor data into a trained neural network; and

determining, by the one or more processors using the trained neural network, a probability of the individual being an operator of the vehicle based at least in part upon the first portion of the set of sensor data.

2. The method of claim 1 , further comprising:

determining, by the one or more processors, that the individual is either the operator or a passenger of the vehicle based upon the probability.

3. The method of claim 2 , further comprising:

processing, by the one or more processors, an account of the individual based upon determining that the individual is either the operator or the passenger of the vehicle.

4. The method of claim 1 , wherein the determining, by the one or more processors using the trained neural network, the probability comprises:

inputting a first initial probability representative of a first feature and a second initial probability representative of a second feature into a softmax function,

wherein an output of the softmax function includes a first final probability representative of the first feature and a second final probability representative of the second feature.

5. The method of claim 1 , wherein the determining, by the one or more processors using the trained neural network, the probability comprises:

inputting a first probability representative of a first feature and a second probability representative of a second feature into an affine layer of the trained neural network; and

processing an output of the affine layer by a sigmoid function.

6. The method of claim 1 , further comprising:

identifying, by the one or more processors, a second portion of the set of sensor data that is indicative of a set of movements of the electronic device in association with the vehicle; and

determining, by the one or more processors using the trained neural network, the probability based at least in part upon the second portion of the set of sensor data.

7. The method of claim 1 , further comprising:

detecting an instance of the electronic device connecting to the vehicle based upon the set of sensor data; and

identifying a third portion of the set of sensor data that is in temporal proximity to the instance of the electronic device connecting to the vehicle.

8. The method of claim 7 , further comprising:

determining, by the one or more processors using the trained neural network, the probability based at least in part upon the third portion of the set of sensor data.

9. A computing system for determining a role of an individual associated with a vehicle, the computing system comprising:

a processor; and

a memory storing computer-executable instructions, that when executed by the processor, cause the processor to perform operations comprising:

receiving a set of sensor data associated with an electronic device of the individual, the set of sensor data corresponding to a first set of timing data;

receiving a set of location data corresponding to a second set of timing data;

determining a time of interest that corresponds to when the electronic device is located in proximity to a designated vehicle location based upon the set of location data;

identifying a first portion of the set of sensor data corresponding to the time of interest;

inputting the first portion of the set of sensor data into a trained neural network; and

determining, using the trained neural network, a first probability of the individual being an operator of the vehicle based at least in part upon the first portion of the set of sensor data.

10. The computing system of claim 9 , wherein the operations further comprise:

determining that the individual is either the operator or a passenger of the vehicle based upon the first probability.

11. The computing system of claim 10 , wherein the operations further comprise:

processing an account of the individual based upon determining that the individual is either the operator or the passenger of the vehicle.

12. The computing system of claim 10 , wherein the operations further comprise:

determining a second probability of the individual being the passenger of the vehicle.

13. The computing system of claim 12 , wherein the operations further comprise:

comparing the first probability and the second probability with a threshold value to generate a comparison result; and

determining that the individual is either the operator or the passenger of the vehicle based at least in part upon the comparison result.

14. The computing system of claim 9 , wherein the operations further comprise:

identifying a second portion of the set of sensor data that is indicative of a set of movements of the electronic device in association with the vehicle; and

determining, using the trained neural network, the first probability based at least in part upon the second portion of the set of sensor data.

15. The computing system of claim 9 , wherein the operations further comprise:

detecting an instance of the electronic device connecting to the vehicle based upon the set of sensor data; and

identifying a third portion of the set of sensor data that is in temporal proximity to the instance of the electronic device connecting to the vehicle.

16. The computing system of claim 9 , wherein the operations further comprise:

determining, using the trained neural network, the first probability based at least in part upon the third portion of the set of sensor data.

17. A non-transitory computer-readable storage medium having stored thereon a set of instructions, executable by a processor, for determining a role of an individual associated with a vehicle, the set of instructions comprising instructions for:

receiving a set of sensor data associated with an electronic device of the individual, the set of sensor data corresponding to a first set of timing data;

receiving a set of location data corresponding to a second set of timing data;

determining a time of interest that corresponds to when the electronic device is located in proximity to a designated vehicle location based upon the set of location data;

identifying a first portion of the set of sensor data corresponding to the time of interest;

inputting the first portion of the set of sensor data into a trained neural network; and

determining, by the one or more processors using the trained neural network, a probability of the individual being an operator of the vehicle based at least in part upon the first portion of the set of sensor data.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the set of instructions further comprise:

inputting a first initial probability representative of a first feature and a second initial probability representative of a second feature into a softmax function,

wherein an output of the softmax function includes a first final probability representative of the first feature and a second final probability representative of the second feature.

19. The non-transitory computer-readable storage medium of claim 17 , wherein the set of instructions further comprise:

inputting a first probability representative of a first feature and a second probability representative of a second feature into an affine layer of the trained neural network; and

processing an output of the affine layer by a sigmoid function.

20. The non-transitory computer-readable storage medium of claim 17 , further comprising:

determining a second portion of the set of sensor data that is indicative of a set of movements of the electronic device in association with the vehicle; and

determining, using the trained neural network, the probability based at least in part upon the second portion of the set of sensor data.

Assignments (2)

Continuity (2)

References Cited (9)