Patent Issued for System and methods for predicting rental vehicle use preferences (USPTO 11836748): State Farm Mutual Automobile Insurance Company

2023 DEC 22 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- State Farm Mutual Automobile Insurance Company (Bloomington, Illinois, United States) has been issued patent number 11836748, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors.

The patent’s inventors are Brannan, Joseph Robert (Bloomington, IL, US), Gross, Ryan (Normal, IL, US), Harvey, Brian N. (Bloomington, IL, US), Riley, Sr., Matthew Eric (Heyworth, IL, US), Wilson, J. Lynn (Normal, IL, US).

This patent was filed on November 2, 2021 and was published online on December 5, 2023.

From the background information supplied by the inventors, news correspondents obtained the following quote: “A peer-to-peer (P2P) car sharing model enables vehicle owners to rent their vehicles to others for short periods of time. Participating vehicle owners typically charge a fee to rent out their vehicles, and participating renters drive the vehicles and pay for the time they need to use them. The participating owners and renters may use a common vehicle-sharing platform, which may be in the form of a website or mobile application, to manage the scheduling of and payment for the vehicles.

“Typically, a participating vehicle owner may use the vehicle-sharing platform to i) describe their vehicle(s), such as the make and model, that are available for rent, ii) set a location for pickup and return of the vehicle(s), and iii) mark available days of the week that their vehicle(s) are available for rent. Participating renters may access the vehicle-sharing platform to search for a vehicle to rent according to their criteria, such as the time period they will need to drive the vehicle, the type of desired vehicle, price, etc. The success of such a vehicle-sharing platform often depends on a sense of trust between the participating vehicle owners and renters. To build trust, vehicle-sharing platforms typically require the participating vehicle owners and renters to verify their identities, such as by entering in their license number and credit card information. Vehicle-sharing platforms may also set general expectations that apply to all participating renters, such as a no smoking policy in the vehicle.

“Despite the high-level trust mechanisms mentioned above that are already in place, conventional vehicle-sharing platforms lack low-level trust mechanisms. For example, participating vehicle owners are unable to set personal preferences to allow only a subset of the verified participating renters to rent their vehicles. In one scenario, although all verified participating renters have approved driving histories, participating vehicle owners may only trust participating renters that have a higher standard of driving etiquette. Existing vehicle-sharing platforms simply do not include a means for generating and enforcing personal preferences onto participating renters.

“Additional challenges in designing a means for generating and enforcing personal preferences are two-fold. First, participating vehicle owners may desire to place varying levels of importance on various aspects of participating renters, which increases the difficulty in designing a standardized means for identifying personal preferences for all participating vehicle owners. For example, one may place more importance on how long participating renters want to rent a vehicle (e.g., only a few hours as opposed to entire days), whereas another may place more importance on how many accidents the participating renters have been involved in.

“Second, given the ubiquitous nature of mobile devices (e.g., smartphones), participating vehicle owners and renters may desire to access vehicle-sharing platforms on their mobile devices that have small screens, which increases the difficulty in designing an interface for a user (e.g., participating vehicle owner). Mobile devices with small screens tend to need data and functionality divided into many layers or views, but as the number of layers or views increases, the efficiency and usability of the user interface decreases. Designing such an interface for mobile devices is therefore a complex human factors problem, especially for mobile devices. The technical problem of effectively designing an interface of a vehicle-sharing platform to enable all participating vehicle owners to identify personalized preferences has to date been inadequately addressed, if at all.”

Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “In one aspect, a computer-implemented method of predicting a user preference may include: (1) generating, by one or more processors, a first set of prompts for display via a vehicle-sharing application, wherein the first set of prompts is configured to prompt a vehicle owner for a first set of answers used to learn preferred vehicle renter characteristics; (2) receiving, by the one or more processors, the first set of answers to the first set of prompts from the vehicle owner via the vehicle-sharing application; (3) generating, by the one or more processors and based upon the first set of answers, a second set of prompts for display via the vehicle-sharing application, wherein the second set of prompts is configured to prompt the vehicle owner for a second set of answers used to learn additional preferred vehicle renter characteristics; (4) receiving, by the one or more processors, the second set of answers to the second set of prompts from the vehicle owner via the vehicle-sharing application; (5) predicting, by the one or more processors, one or more user preference values of a vehicle-sharing platform profile of the vehicle owner based upon the second set of answers, wherein the one or more user preference values define one or more criteria for sharing a vehicle associated with the vehicle-sharing platform profile with vehicle renters who meet the one or more criteria; (6) applying, by the one or more processors, the one or more criteria to potential vehicle renters; and (7) causing, by the one or more processors, an indication of the vehicle of the vehicle owner to be displayed only to the potential vehicle renters who satisfy the one or more criteria.

“In another aspect, a non-transitory, tangible computer-readable medium storing machine-readable instructions that, when executed by one or more processors, may cause the one or more processors to: (1) generate a first set of prompts for display via a vehicle-sharing application, wherein the first set of prompts is configured to prompt a vehicle owner for a first set of answers used to learn preferred vehicle renter characteristics; (2) receive the first set of answers to the first set of prompts from the vehicle owner via the vehicle-sharing application; (3) generate, based upon the first set of answers, a second set of prompts for display via the vehicle-sharing application, wherein the second set of prompts is configured to prompt the vehicle owner for a second set of answers used to learn additional preferred vehicle renter characteristics; (4) receive the second set of answers to the second set of prompts from the vehicle owner via the vehicle-sharing application; (5) predict one or more user preference values of a vehicle-sharing platform profile of the vehicle owner based upon the second set of answers, wherein the one or more user preference values define one or more criteria for sharing a vehicle associated with the vehicle-sharing platform profile with vehicle renters who meet the one or more criteria; (6) apply the one or more criteria to potential vehicle renters; and (7) cause an indication of the vehicle of the vehicle owner to be displayed only to the potential vehicle renters who satisfy the one or more criteria.

“Although the following text sets forth a detailed description of numerous different aspects, it should be understood that the legal scope of the description is defined by the words of the claims set forth at the end of this patent. The detailed description is to be construed as exemplary only and does not describe every possible aspect since describing every possible aspect would be impractical, if not impossible. Numerous alternative aspects may be implemented, using either current technology or technology developed after the filing date of this patent, which would still fall within the scope of the claims.”

The claims supplied by the inventors are:

“1. A computer-implemented method of determining a user preference, comprising: training, by one or more processors, a machine learning model to identify relationships between a) telematics data and b) preference values associated with vehicle rental criteria; receiving, by the one or more processors and in response to a first set of prompts provided by a vehicle-sharing application, a set of inputs from a vehicle owner; determining, by the one or more processors and using the set of inputs, owner preference values; receiving, by the one or more processors, owner telematics data corresponding to a vehicle of the vehicle owner, the owner telematics data indicating driving behavior of the vehicle owner while operating the vehicle; determining, by the one or more processors executing the trained machine learning model using the owner preference values and the owner telematics data, one or more criteria required to share the vehicle of the vehicle owner, wherein the one or more criteria are unique to the vehicle owner; mapping, by the one or more processors, one of the one or more criteria to a prompt for display via the vehicle-sharing application; causing, by the one or more processors, the prompt to be displayed via the vehicle-sharing application, wherein user input received via the prompt causes a change to the one of the one or more criteria; identifying, by the one or more processors, one or more potential vehicle renters from a plurality of potential vehicle renters registered with the vehicle-sharing application and who satisfy the one or more criteria; and causing, by the one or more processors, an indication of the vehicle to be displayed via the vehicle-sharing application to the one or more potential vehicle renters.

“2. The computer-implemented method of claim 1, further comprising: causing, by the one or more processors, the one or more criteria to be displayed via the vehicle-sharing application.

“3. The computer-implemented method of claim 2, further comprising: generating, by the one or more processors, a first graphic user interface (GUI) including a second set of prompts, wherein the second set of prompts request the vehicle owner to confirm the one or more criteria; and causing, by the one or more processors, the first GUI to be displayed via the vehicle-sharing application.

“4. The computer-implemented method of claim 1, further comprising: modifying, by the one or more processors, the one of the one or more criteria based on receiving the user input via the prompt displayed via the vehicle-sharing application from the vehicle owner.

“5. The computer-implemented method of claim 1, wherein the first set of prompts is provided by the vehicle sharing application together with answer choices derived from historical data associated with the vehicle owner.

“6. The computer-implemented method of claim 1, wherein the first set of prompts is provided by the vehicle sharing application together with default answer choices not derived from historical data associated with the vehicle owner.

“7. The computer-implemented method of claim 1, further comprising: receiving, by the one or more processors, historical data associated with the one or more potential vehicle renters; and identifying the one or more potential vehicle renters based at least in part on the historical data.

“8. The computer-implemented method of claim 7, wherein the historical data comprises telematics data indicative of driving behavior of the one or more potential vehicle renters.

“9. The computer-implemented method of claim 7, wherein the historical data comprises evaluation data associated with the one or more potential vehicle renters and determined based on feedback received from other vehicle owners from whom the one or more potential vehicle renters rented vehicles.

“10. A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to: train a machine learning model to identify relationships between a) telematics data and b) preference values associated with vehicle rental criteria; receive, in response to a first set of prompts provided by a vehicle-sharing application, a set of inputs from a vehicle owner; receive owner telematics data corresponding to a vehicle of the vehicle owner, the owner telematics data indicating driving behavior of the vehicle owner while operating the vehicle; determine by executing the trained machine learning model using the set of inputs and the owner telematics data, one or more criteria required to share the vehicle of the vehicle owner, wherein the one or more criteria are unique to the vehicle owner; map one of the one or more criteria to a prompt for display via the vehicle-sharing application; causing the prompt to be displayed via the vehicle-sharing application, wherein user input received via the prompt causes a change to the one of the one or more criteria; identify one or more potential vehicle renters from a plurality of potential vehicle renters registered with the vehicle-sharing application and who satisfy the one or more criteria; and cause an indication of the vehicle to be displayed via the vehicle-sharing application to the one or more potential vehicle renters.

“11. The non-transitory computer-readable medium of claim 10, wherein the instructions when executed by the one or more processors further cause the one or more processors to: generate a first graphic user interface (GUI) including the first set of prompts for display via the vehicle-sharing application; and cause the first GUI to be displayed via the vehicle-sharing application, the first set of inputs being received via the first GUI.

“12. The non-transitory computer-readable medium of claim 10, wherein the instructions when executed by the one or more processors further cause the one or more processors to modify the one of the one or more criteria based on receiving the user input via the prompt displayed via the vehicle-sharing application from the vehicle owner.

“13. The non-transitory, computer-readable medium of claim 10, wherein the instructions, when executed by the one or more processors, further cause the one or more processors to: receive historical data associated with the potential vehicle renters; and identify the one or more potential vehicle renters based at least in part on the historical data.

“14. The non-transitory, computer-readable medium of claim 13, wherein the historical data comprises telematics data indicative of driving behavior of the one or more potential vehicle renters.

“15. The non-transitory, computer-readable medium of claim 13, wherein historical data comprises rental evaluation data associated with the one or more potential vehicle renters and determined based on feedback received from other vehicle owners from whom the one or more potential vehicle renters rented vehicles.

“16. A system, comprising: one or more processors; and memory storing computer-executable instructions that, when executed by the one or more processors, cause the system to perform operations comprising: receiving, in response to a first set of prompts provided by a vehicle-sharing application, a set of inputs from a vehicle owner; receiving owner telematics data corresponding to a vehicle of the vehicle owner, the owner telematics data indicating driving behavior of the vehicle owner while operating the vehicle; determining, by executing a machine learning model using the set of inputs and the owner telematics data, one or more criteria required to share the vehicle of the vehicle owner, wherein the one or more criteria are unique to the vehicle owner; training the machine learning model to identify relationships between a) the owner telematics data and b) the one or more criteria; mapping one of the one or more criteria to a prompt for display via the vehicle-sharing application; causing the prompt to be displayed via the vehicle-sharing application, wherein user input received via the prompt causes a change to the one of the one or more criteria; identifying one or more potential vehicle renters from a plurality of potential vehicle renters registered with the vehicle-sharing application and who satisfy the one or more criteria; and causing an indication of the vehicle to be displayed via the vehicle-sharing application to the one or more potential vehicle renters.

“17. The system of claim 16, the operations further comprising: recording a maximum speed driven by the vehicle owner from the telematics data; and generating, based at least in part on the recorded maximum speed, a first graphic user interface (GUI), the first GUI providing a default user preference to the vehicle owner corresponding to a maximum speed allowed to be driven by the one or more potential vehicle renters.

“18. The system of claim 16, the operations further comprising modifying the one of the one or more criteria based on receiving the user input via the prompt displayed via vehicle-sharing application from the vehicle owner.

“19. The system of claim 16, the operations further comprising: generating a score for a renter of the one or more potential vehicle renters based at least in part on telematics data indicative of driving behavior of the renter and feedback from the vehicle owner.

“20. The system of claim 16, wherein the first set of prompts is accompanied with answer choices derived from historical data associated with the vehicle owner.”

For the URL and additional information on this patent, see: Brannan, Joseph Robert. System and methods for predicting rental vehicle use preferences. U.S. Patent Number 11836748, filed November 2, 2021, and published online on December 5, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11836748)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)