Granted Patent B2

US 12,561,706 · App. 18/790,850 · Granted Feb 24, 2026

Inventor: Kenneth Jason Sanchez (San Francisco, CA)

Assignee: QUANATA, LLC

G06Q30/0201B60W40/09G06N5/04G06Q30/0204B60W2556/55

Abstract

Claims (63)

1 . A computer-implemented method comprising:

receiving personal data sets associated with vehicle operators via at least one mobile application associated with each of the vehicle operators, wherein the at least one mobile application includes a user interface configured to enable the vehicle operators to interact with the at least one mobile application;

receiving, via sensors, sensor data sets associated with the vehicle operators, wherein the sensor data sets are transmitted in response to a triggering event, and wherein the sensors comprise at least one of a Global Positioning Systems (GPS) sensor configured to provide a geographic location, an accelerometer configured to provide at least a linear or angular acceleration, or a gyroscope configured to provide orientation sensor data;

for each vehicle operator of a first plurality of vehicle operators:

generating an operator profile including a personal data set of the personal data sets associated with the vehicle operator;

determining, using a trained model, one or more telematics inferences comprising a predicted relative profitability, based at least in part upon (i) a sensor data set of the sensor data sets associated with the vehicle operator and the personal data set associated with the vehicle operator, and (ii) one or more personal data sets associated with one or more groups of similar vehicle operators and one or more sensor data sets associated with the one or more groups of similar vehicle operators, wherein the one or more groups of similar vehicle operators share at least one common operator characteristic with the vehicle operator, wherein the trained model has a plurality of weights that correspond to each type of sensor data of a sensor data set of the sensor data sets associated with the vehicle operator in determining the predicted relative profitability, wherein the one or more telematics inferences correspond to a characteristic of the vehicle operator relative to the one or more groups of similar vehicle operators sharing the at least one common operator characteristic, wherein the trained model was trained using training data sets comprising the personal data sets and the sensor data sets associated with a second plurality of the vehicle operators to predict a characteristic of a second vehicle operator of the second plurality of the vehicle operators, and wherein the trained model includes a trained machine learning model based at least in part upon the sensor data sets associated with the second plurality of vehicle operators;

generating a data profile including the one or more telematics inferences associated with the vehicle operator; and

listing the data profile on a telematics marketplace to be accessible by marketplace participants;

receiving, from a requesting party of the marketplace participants, an information request for a target operator profile associated with a target data profile selected from the data profiles of the vehicle operators; and

transmitting, in response to the information request, the target operator profile to the requesting party.

2 . The computer-implemented method of claim 1 , wherein the trained machine learning model comprises a convolutional artificial neural network.

3 . The computer-implemented method of claim 1 , wherein the triggering event occurs when at least one of the sensor has acquired measurements greater than a threshold amount.

4 . The computer-implemented method of claim 1 , wherein the trained machine learning model comprises a recurrent artificial neural network.

5 . The computer-implemented method of claim 1 , wherein determining the one or more telematics inferences comprises:

determining and continually updating predicted costs and predicted revenue for each vehicle operator of the vehicle operators based at least in part upon:

the personal data set associated with each vehicle operator and the sensor data set associated with each vehicle operator; and

the one or more personal data sets associated with the one or more groups of similar vehicle operators and the one or more sensor data sets associated with the one or more groups of similar vehicle operators.

6 . The computer-implemented method of claim 1 , wherein determining the one or more telematics inferences comprises:

determining and continually updating predicted losses and predicted expenses for each vehicle operator of the vehicle operators based at least in part upon:

the personal data set associated with each vehicle operator and the sensor data set associated with each vehicle operator; and

the one or more personal data sets associated with the one or more groups of similar vehicle operators and the one or more sensor data sets associated with the one or more groups of similar vehicle operators.

7 . The computer-implemented method of claim 1 , wherein:

the sensors are used by the at least one mobile application of at least one mobile device of at least one of the vehicle operators.

8 . The computer-implemented method of claim 7 , wherein the at least one mobile application comprises at least one system software application, at least one entertainment software application, at least one gaming software application, at least one navigation software application, or at least one environment software application.

9 . The computer-implemented method of claim 1 , wherein the marketplace participants comprise at least one insurance company, at least one car rental company, at least one vehicle manufacturing company, at least one autonomous driving firm, at least one shared ride company, at least one housing firm, a bank, or at least one government agency.

10 . A computing system for data management, the computing system comprising:

one or more processors; and

a memory storing instructions that, upon execution by the one or more processors, cause the computing system to perform one or more processes comprising:

receiving personal data sets associated with vehicle operators via at least one mobile application associated with each of the vehicle operators, wherein the at least one mobile application includes a user interface configured to enable the vehicle operators to interact with the at least one mobile application;

receiving, via sensors, sensor data sets associated with the vehicle operators, wherein the sensor data sets are transmitted in response to a triggering event, and wherein the sensors comprise at least one of a Global Positioning Systems (GPS) sensor configured to provide a geographic location, an accelerometer configured to provide at least a linear or angular acceleration, or a gyroscope configured to provide orientation sensor data;

for each vehicle operator of a first plurality of vehicle operators:

generating an operator profile including a personal data set of the personal data sets associated with the vehicle operator;

determining, using a trained model, one or more telematics inferences comprising a predicted relative profitability, based at least in part upon (i) a sensor data set of the sensor data sets associated with the vehicle operator and the personal data set associated with the vehicle operator, and (ii) one or more personal data sets associated with one or more groups of similar vehicle operators and one or more sensor data sets associated with the one or more groups of similar vehicle operators, wherein the one or more groups of similar vehicle operators share at least one common operator characteristic with the vehicle operator, wherein the trained model has a plurality of weights that correspond to each type of sensor data of a sensor data set of the sensor data sets associated with the vehicle operator in determining the predicted relative profitability, wherein the one or more telematics inferences correspond to a characteristic of the vehicle operator relative to the one or more groups of similar vehicle operators sharing the at least one common operator characteristic, wherein the trained model was trained using training data sets comprising the personal data sets and the sensor data sets associated with a second plurality of the vehicle operators to predict a characteristic of a second vehicle operator of the second plurality of the vehicle operators, and wherein the trained model includes a trained machine learning model based at least in part upon the sensor data sets associated with the second plurality of vehicle operators;

generating a data profile including the one or more telematics inferences associated with the vehicle operator; and

listing the data profile on a telematics marketplace to be accessible by marketplace participants;

receiving, from a requesting party of the marketplace participants, an information request for a target operator profile associated with a target data profile selected from the data profiles of the vehicle operators; and

transmitting, in response to the information request, the target operator profile to the requesting party.

11 . The computer system of claim 10 , wherein the trained machine learning model comprises a convolutional artificial neural network.

12 . The computer system of claim 10 , wherein the triggering event occurs when at least one of the sensor has acquired measurements greater than a threshold amount.

13 . The computer system of claim 10 , wherein the trained machine learning model comprises a recurrent artificial neural network.

14 . The computer system of claim 10 , wherein determining the one or more telematics inferences comprises:

determining and continually updating predicted costs and predicted revenue for each vehicle operator of the vehicle operators based at least in part upon:

the personal data set associated with each vehicle operator and the sensor data set associated with each vehicle operator; and

the one or more personal data sets associated with the one or more groups of similar vehicle operators and the one or more sensor data sets associated with the one or more groups of similar vehicle operators.

15 . The computer system of claim 10 , wherein determining the one or more telematics inferences comprises:

determining and continually updating predicted losses and predicted expenses for each vehicle operator of the vehicle operators based at least in part upon:

the personal data set associated with each vehicle operator and the sensor data set associated with each vehicle operator; and

the one or more personal data sets associated with the one or more groups of similar vehicle operators and the one or more sensor data sets associated with the one or more groups of similar vehicle operators.

16 . The computer system of claim 10 , wherein:

the sensors are used by the at least one mobile application of at least one mobile device of at least one of the vehicle operators.

17 . The computer system of claim 16 , wherein the at least one mobile application comprises at least one system software application, at least one entertainment software application, at least one gaming software application, at least one navigation software application, or at least one environment software application.

18 . The computer system of claim 10 , wherein the marketplace participants comprise at least one insurance company, at least one car rental company, at least one vehicle manufacturing company, at least one autonomous driving firm, at least one shared ride company, at least one housing firm, a bank, or at least one government agency.

19 . The computer system of claim 10 , wherein the predicted relative profitability comprises a relative profitability score.

20 . A non-transitory computer-readable medium storing instructions for data management, the instructions, upon execution by one or more processors of a computing system, cause the computing system to perform one or more processes comprising:

receiving personal data sets associated with vehicle operators via at least one mobile application associated with each of the vehicle operators, wherein the at least one mobile application includes a user interface configured to enable the vehicle operators to interact with the at least one mobile application;

receiving, via sensors, sensor data sets associated with the vehicle operators, wherein the sensor data sets are transmitted in response to a triggering event, and wherein the sensors comprise at least one of a Global Positioning Systems (GPS) sensor configured to provide a geographic location, an accelerometer configured to provide at least a linear or angular acceleration, or a gyroscope configured to provide orientation sensor data;

for each vehicle operator of a first plurality of vehicle operators:

generating an operator profile including a personal data set of the personal data sets associated with the vehicle operator;

determining, using a trained model, one or more telematics inferences comprising a predicted relative profitability, based at least in part upon (i) a sensor data set of the sensor data sets associated with the vehicle operator and the personal data set associated with the vehicle operator, and (ii) one or more personal data sets associated with one or more groups of similar vehicle operators and one or more sensor data sets associated with the one or more groups of similar vehicle operators, wherein the one or more groups of similar vehicle operators share at least one common operator characteristic with the vehicle operator, wherein the trained model has a plurality of weights that correspond to each type of sensor data of a sensor data set of the sensor data sets associated with the vehicle operator in determining the predicted relative profitability, wherein the one or more telematics inferences correspond to a characteristic of the vehicle operator relative to the one or more groups of similar vehicle operators sharing the at least one common operator characteristic, wherein the trained model was trained using training data sets comprising the personal data sets and the sensor data sets associated with a second plurality of the vehicle operators to predict a characteristic of a second vehicle operator of the second plurality of the vehicle operators, and wherein the trained model includes a trained machine learning model based at least in part upon the sensor data sets associated with the second plurality of vehicle operators;

generating a data profile including the one or more telematics inferences associated with the vehicle operator; and

listing the data profile on a telematics marketplace to be accessible by marketplace participants;

receiving, from a requesting party of the marketplace participants, an information request for a target operator profile associated with a target data profile selected from the data profiles of the vehicle operators; and

transmitting, in response to the information request, the target operator profile to the requesting party.

Assignments (2)

Continuity (2)

References Cited (188)