Granted Patent B2

US 12,651,287 · App. 18/113,879 · Granted Jun 9, 2026

Inventors: Joshua Batie (Frisco, TX); Michael Tripp (Plano, TX); Tyler Brown (Dallas, TX); Brian Kursar (Fairview, TX)

Assignees: Toyota Motor North America, Inc.; Toyota Jidosha Kabushiki Kaisha

G06Q30/0631G06Q30/0278G07C5/06

Abstract

Claims (73)

1 . A method for generating recommendations of a vehicle corresponding to a driver's driving behavior, the method comprising:

receiving, with one or more processors communicatively coupled to a vehicle, driving behavior data of the vehicle generated from vehicle sensors, wherein the driving behavior data is generated from a plurality of drivers that operated the vehicle;

receiving data related to ownership of the vehicle;

receiving vehicle sales market data;

generating, using a trained machine-learning model implemented by the one or more processors, based on the vehicle sales market data, the driving behavior data, and the data related to ownership of the vehicle, an asset valuation;

generating, with the trained machine-learning model, a recommendation to a user based on the asset valuation and the driving behavior data, wherein the recommendation comprises a new or used vehicle for purchase or leasing, and the new or used vehicle is a different vehicle from the vehicle; and

providing the recommendation to a user though a user device.

2 . The method of claim 1 , wherein the recommendation defines whether the new or used vehicle is a truck, an SUV, a sedan, or a hybrid vehicle.

3 . The method of claim 1 , wherein:

the trained machine-learning model is further trained to analyze the driving behavior data and determine a driving behavior score for a plurality of predefined categories, wherein the plurality of predefined categories include an aggressiveness score, a fuel economy score, a service timeliness score, and wherein the recommendation is further based on the driving behavior score.

4 . The method of claim 3 , wherein:

the driving behavior data includes acceleration data,

the acceleration data indicate that the aggressiveness score is above a predetermined threshold, and

the recommendation comprises a recommendation for a purchase of a vehicle with a higher acceleration than a user's current vehicle when the aggressiveness score is above the predetermined threshold.

5 . The method of claim 3 , wherein:

the driving behavior data includes an indication of a number of occupants in a vehicle and a frequency of the number of occupants,

the trained machine-learning model is further trained to predict, based on the driving behavior data and the data related to ownership of the vehicle, a vehicle use type, the vehicle use type indicating that the vehicle is a rideshare vehicle, and

the method further comprising displaying the driving behavior score to a user of the rideshare vehicle.

6 . The method of claim 3 , wherein:

the trained machine-learning model is further configured to generate a valuation of the vehicle based on the vehicle sales market data, the driving behavior data, the data related to ownership of the vehicle, and the driving behavior score, and

the method further comprising providing to the user the valuation with the recommendation though the user device.

7 . The method of claim 1 , further comprising:

generating, using the trained machine-learning model, a vehicle score based on the driving behavior data and the data related to the ownership of the vehicle, and

certifying the vehicle in response to the vehicle score being greater than a predetermined threshold.

8 . The method of claim 1 , wherein the driving behavior data indicates that the vehicle operated outside of a specified set of operational parameters; and the asset valuation is lower when the driving behavior data indicates that the vehicle operated outside of the specified set of operational parameters compared to when the driving behavior data indicates that the vehicle operated within the specified set of operational parameters.

9 . A system comprising:

a computing device having a processor and a non-transitory computer readable memory;

a transceiver unit communicatively coupled to the computing device; and

a machine-readable instruction set stored in the non-transitory computer readable memory that causes the system to perform at least the following when executed by the processor:

receive driving behavior data of a vehicle generated from vehicle sensors, wherein the driving behavior data is generated from a plurality of drivers that operated the vehicle;

receive data related to ownership of the vehicle;

receive vehicle sales market data;

generate, using a trained machine-learning model implemented by the processor, based on the vehicle sales market data, the driving behavior data, and the data related to ownership of the vehicle, an asset valuation;

generate, with the trained machine-learning model, a recommendation to a user based on the asset valuation and the driving behavior data, wherein the recommendation comprises a new or used vehicle for purchase or leasing, and the new or used vehicle is a different vehicle from the vehicle; and

provide the recommendation to a user though a user device.

10 . The system of claim 9 , wherein:

the trained machine-learning model is further trained to analyze the driving behavior data and determine a driving behavior score for a plurality of predefined categories, wherein the plurality of predefined categories include an aggressiveness score, a fuel economy score, a service timeliness score, and wherein the recommendation is further based on the driving behavior score.

11 . The system of claim 10 , wherein:

the driving behavior data includes acceleration data,

the acceleration data indicate that the aggressiveness score is above a predetermined threshold, and

the recommendation comprises a recommendation for a purchase of a vehicle with a higher acceleration than a user's current vehicle when the aggressiveness score is above the predetermined threshold.

12 . The system of claim 10 , wherein:

the driving behavior data includes an indication of a number of occupants in a vehicle and a frequency of the number of occupants,

the trained machine-learning model is further trained to predict, based on the driving behavior data and the data related to ownership of the vehicle, a vehicle use type, the vehicle use type indicating that the vehicle is a rideshare vehicle, and

the machine-readable instruction set, when executed, further causes the system to display the driving behavior score to a user of the rideshare vehicle.

13 . The system of claim 10 , wherein:

the trained machine-learning model is further configured to generate a valuation of the vehicle based on the vehicle sales market data, the driving behavior data, the data related to ownership of the vehicle, and the driving behavior score, and

wherein the machine-readable instruction set, when executed, further causes the system to provide to the user the valuation with the recommendation though the user device.

14 . The system of claim 9 , the machine-readable instruction set, when executed, further causes the system to:

generate, using the trained machine-learning model, a vehicle score based on the driving behavior data and the data related to the ownership of the vehicle, and

certify the vehicle in response to the vehicle score being greater than a predetermined threshold.

15 . A vehicle comprising:

a computing device of a vehicle comprising a processor and a non-transitory computer readable memory;

a transceiver unit communicatively coupled to the computing device; and

a machine-readable instruction set stored in the non-transitory computer readable memory that causes the vehicle to perform at least the following when executed by the processor:

receive driving behavior data of the vehicle generated from vehicle sensors, wherein the driving behavior data is generated from a plurality of drivers that operated the vehicle;

receive data related to ownership of the vehicle;

receive vehicle sales market data;

generate, using a trained machine-learning model implemented by the processor, based on the vehicle sales market data, the driving behavior data, and the data related to ownership of the vehicle, an asset valuation;

generate, with the trained machine-learning model, a recommendation to a user based on the asset valuation and the driving behavior data, wherein the recommendation comprises a new or used vehicle for purchase or leasing, and the new or used vehicle is a different vehicle from the vehicle; and

provide the recommendation to a user though a user device.

16 . The vehicle of claim 15 , wherein,

the trained machine-learning model is further trained to analyze the driving behavior data and determine a driving behavior score for a plurality of predefined categories, wherein the plurality of predefined categories include an aggressiveness score, a fuel economy score, a service timeliness score, and wherein the recommendation is further based on the driving behavior score.

17 . The vehicle of claim 16 , wherein,

the driving behavior data includes an indication of a number of occupants in a vehicle and a frequency of the number of occupants,

the trained machine-learning model is further trained to predict, based on the driving behavior data and the data related to ownership of the vehicle, a vehicle use type, the vehicle use type indicating that the vehicle is a rideshare vehicle, and

the machine-readable instruction set, when executed, further causes display of the driving behavior score to a user of the rideshare vehicle.

18 . The vehicle of claim 16 , wherein,

the trained machine-learning model is further configured to generate a valuation of the vehicle based on the vehicle sales market data, the driving behavior data, the data related to ownership of the vehicle, and the driving behavior score, and

wherein the machine-readable instruction set, when executed, further causes the vehicle to provide to the user the valuation with the recommendation though the user device.

19 . The vehicle of claim 15 , wherein the machine-readable instruction set, when executed, further causes the vehicle to:

generate, using the trained machine-learning model, a vehicle score based on the driving behavior data and the data related to the ownership of the vehicle, and

certify the vehicle in response to the vehicle score being greater than a predetermined threshold.

Assignments (2)

Continuity (1)

References Cited (13)