IP Library Granted Patent US 12,499,457
Granted Patent B2
US 12,499,457 · App. 18/507,748 · Granted Dec 16, 2025

System and methods for predicting rental vehicle use preferences

Inventors: Brian N. Harvey (Bloomington, IL); Joseph Robert Brannan (Bloomington, IL); J. Lynn Wilson (Normal, IL); Matthew Eric Riley, Sr. (Heyworth, IL); Ryan Gross (Normal, IL)
Assignee: State Farm Mutual Automobile Insurance Company
G06Q30/0202G06Q30/0645G06Q50/40
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,499,457
App. No.
18/507,748
Granted
Dec 16, 2025
Kind
B2
Abstract

Embodiments described herein generate a first set of prompts, the first set of prompts configured to prompt a vehicle owner for a first set of answers used to learn preferred vehicle renter characteristics; receive the first set of answers; generate, based upon the first set of answers, a second set of prompts, the second set of prompts configured to prompt the owner for a second set of answers used to learn additional preferred vehicle renter characteristics; receive the second set of answers; predict user preference value(s) of a profile of the owner based upon the second set of answers, wherein the user preference value(s) define criteria for sharing a vehicle associated with the profile with vehicle renters who satisfy the criteria; apply the criteria to potential vehicle renters; and cause an indication of the vehicle to be displayed only to the potential vehicle renters who satisfy the criteria.

Claims (111)

1 . A system, comprising:

a processor;

a prediction preference engine comprising a neural network; and

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

receiving, via a vehicle-sharing application, a set of inputs;

executing the prediction preference engine, using the set of inputs as a first input, to generate a predicted preference value as a first output;

executing the prediction preference engine, using the predicted preference value as a second input, to generate a criterion required to share a vehicle as a second output;

mapping the criterion to a prompt for display via the vehicle-sharing application;

executing the prediction preference engine, using the criterion as a third input, to determine a vehicle renter that is registered with the vehicle-sharing application and that satisfies the criterion as a third output;

causing an indication of the vehicle to be displayed together with the prompt, via the vehicle-sharing application to the vehicle renter, wherein receiving a user input via the prompt changes the criterion;

receiving vehicle operation data in real-time from vehicle-mounted sensors configured at the vehicle while the vehicle renter operates the vehicle, the vehicle operation data comprising lateral and longitudinal acceleration data;

generating telematics data at the vehicle-sharing application using the vehicle operation data;

determining a vehicle location based at least in part on geographic location data for the vehicle represented in the vehicle operation data;

determining that the vehicle renter has completed operating the vehicle based at least in part on the vehicle location;

in response to determining that the vehicle renter has completed operating the vehicle, generating one or more metrics associated with the vehicle renter based at least in part on the telematics data;

communicating, via the vehicle-sharing application, the one or more metrics associated with the vehicle renter to a vehicle owner;

receiving, via the vehicle-sharing application, feedback data associated with the vehicle renter from the vehicle owner;

updating the one or more metrics associated with the vehicle renter based at least in part on the feedback data; and

populating a graphical user interface presented via the vehicle-sharing application with the updated one or more metrics.

2 . The system of claim 1 , wherein the prediction preference engine is configured to generate the vehicle renter as the third output by determining that historical data associated with the vehicle renter compromises data associated with the predicted preference value.

3 . The system of claim 1 , wherein:

the operations further comprise generating a score for the vehicle renter based at least in part on at least one of historical data associated with the vehicle renter or vehicle renter telematics data associated with the vehicle renter; and

the prediction preference engine is configured to generate the vehicle renter as the third output determining that the score is greater than or equal to a value indicated by the criterion.

4 . The system of claim 1 , wherein:

the operations further comprise:

accessing historical image data comprising one or more images of the vehicle from a database;

determining contextual data of the vehicle using the historical image data; and

determining vehicle damage data based at least in part on the contextual data, wherein the one or more metrics associated with the vehicle renter is generated based at least in part on the vehicle damage data.

5 . The system of claim 1 , wherein the vehicle operation data further comprises data representing one or more of:

vehicle speed,

a vehicle location, or

vehicle engine RPM.

6 . The system of claim 1 , wherein the prediction preference engine is configured to generate the vehicle renter as the third output by determining that vehicle renter telematics data associated with the vehicle renter compromises data associated with the predicted preference value.

7 . The system of claim 1 , wherein the set of inputs comprises data representing one or more of:

a vehicle renter age range,

a vehicle rental duration,

a length of vehicle renter driving experience,

vehicle renter telematics data associated with the vehicle renter, or historical data associated with the vehicle renter.

8 . A computer-implemented method comprising:

receiving, by a processor via a vehicle-sharing application, a set of inputs;

executing a prediction preference engine comprising a neural network, by the processor, using the set of inputs as a first input, to generate a predicted preference value as a first output;

executing the prediction preference engine, by the processor, using the predicted preference value as a second input, to generate a criterion required to share a vehicle as a second output;

mapping, by the processor, the criterion to a prompt for display via the vehicle-sharing application;

executing the prediction preference engine, by the processor, using the criterion as a third input, to determine a vehicle renter that is registered with the vehicle-sharing application and that satisfies the criterion as a third output;

causing, by the processor, an indication of the vehicle to be displayed together with the prompt, via the vehicle-sharing application to the vehicle renter, wherein receiving a user input via the prompt changes the criterion;

receiving, by the processor, vehicle operation data in real-time from vehicle-mounted sensors configured at the vehicle while the vehicle renter operates the vehicle, the vehicle operation data comprising lateral and longitudinal acceleration data;

generating, by the processor, telematics data at the vehicle-sharing application using the vehicle operation data;

determining, by the processor, a vehicle location based at least in part on geographic location data for the vehicle represented in the vehicle operation data;

determining, by the processor, that the vehicle renter has completed operating the vehicle based at least in part on the vehicle location;

generating, by the processor, one or more metrics associated with the vehicle renter based at least in part on the telematics data;

communicating, by the processor, via the vehicle-sharing application, the one or more metrics associated with the vehicle renter to a vehicle owner;

receiving, by the processor, via the vehicle-sharing application, feedback data associated with the vehicle renter from the vehicle owner;

updating, by the processor, the one or more metrics associated with the vehicle renter based at least in part on the feedback data; and

populating, by the processor, a graphical user interface presented via the vehicle-sharing application with the updated one or more metrics.

9 . The computer-implemented method of claim 8 , further comprising mapping a default criterion to the prompt for display via the vehicle-sharing application.

10 . The computer-implemented method of claim 8 , wherein:

the criterion comprises a first criterion of a plurality of criteria; and

the computer-implemented method further comprises mapping a second criterion of the plurality of criteria to the prompt for display via the vehicle-sharing application.

11 . The computer-implemented method of claim 8 , wherein the set of inputs comprises a first score based at least in part on at least one of preferred vehicle renter historical data or preferred vehicle renter telematics data.

12 . The computer-implemented method of claim 11 , further comprising:

generating a second score for the vehicle renter based at least in part on at least one of historical data associated with the vehicle renter or vehicle renter telematics data associated with the vehicle renter; and

executing the prediction preference engine is configured to generate the vehicle renter as the third output by determining that the second score is greater than or equal to the first score.

13 . The computer-implemented method of claim 8 , wherein the prediction preference engine is configured to generate the vehicle renter as the third output by determining that the vehicle renter satisfies the criterion based at least in part on one or more of:

insurance claims data associated with the vehicle renter,

geographic location data associated with the vehicle renter,

vehicle renter feedback data associated with the vehicle renter, or

driving behavior data associated with the vehicle renter.

14 . The computer-implemented method of claim 8 , wherein the prediction preference engine is configured to generate the vehicle renter by determining that historical data associated with the vehicle renter compromises data represented by the predicted preference value.

15 . A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving, via a vehicle-sharing application, a set of inputs;

executing a prediction preference engine comprising a neural network, using the set of inputs as a first input, to generate a predicted preference value as a first output;

executing the prediction preference engine, using the predicted preference value as a second input, to generate a criterion required to share a vehicle as a second output;

mapping the criterion to a prompt for display via the vehicle-sharing application;

executing the prediction preference engine, using the criterion as a third input, to determine a vehicle renter that is registered with the vehicle-sharing application and that satisfies the criterion as a third output; causing an indication of the vehicle to be displayed together with the prompt, via the vehicle-sharing application to the vehicle renter, wherein receiving a user input via the prompt changes the criterion;

receiving vehicle operation data in real-time from vehicle-mounted sensors configured at the vehicle while the vehicle renter operates the vehicle, the vehicle operation data comprising lateral and longitudinal acceleration data;

generating telematics data at the vehicle-sharing application using the vehicle operation data;

determining a vehicle location based at least in part on geographic location data for the vehicle represented in the vehicle operation data;

determining that the vehicle renter has completed operating the vehicle based at least in part on the vehicle location;

generating one or more metrics associated with the vehicle renter based at least in part on the telematics data;

communicating, via the vehicle-sharing application, the one or more metrics associated with the vehicle renter to a vehicle owner;

receiving, via the vehicle-sharing application, feedback data associated with the vehicle renter from the vehicle owner;

updating the one or more metrics associated with the vehicle renter based at least in part on the feedback data; and

populating a graphical user interface presented via the vehicle-sharing application with the updated one or more metrics.

16 . The non-transitory computer-readable medium of claim 15 , wherein the prediction preference engine is configured to generate the vehicle renter as the third output by:

receiving historical data associated with a plurality of vehicle renters; and

identifying, based at least in part on the historical data, a subset of the plurality of vehicle renters that satisfy the criterion, wherein the subset of the plurality of vehicle renters comprises the vehicle renter.

17 . The non-transitory computer-readable medium of claim 15 , wherein:

the criterion comprises a first criterion of a plurality of criteria; and

receiving the user input via the prompt comprises associating a second criterion of the plurality of criteria with the criterion.

18 . The non-transitory computer-readable medium of claim 17 , wherein receiving the user input via the prompt further comprises disassociating the first criterion from the criterion.

19 . The non-transitory computer-readable medium of claim 15 , wherein the prediction preference engine is configured to generate the vehicle renter by determining that the vehicle renter satisfies the criterion based at least in part on one or more of:

collision repair costs associated with the vehicle renter,

collision location data associated with the vehicle renter,

collision time data associated with the vehicle renter, or

collision date data associated with the vehicle renter.

20 . A system for determining a user preference, the system comprising:

means for receiving, by a processor via a vehicle-sharing application, a set of inputs;

means for executing a prediction preference engine, by the processor, using the set of inputs as a first input, to generate a predicted preference value as a first output;

means for executing the prediction preference engine, by the processor, using the predicted preference value as a second input, to generate a criterion required to share a vehicle as a second output;

means for mapping, by the processor, the criterion to a prompt for display via the vehicle-sharing application;

means for executing the prediction preference engine, by the processor, using the criterion as a third input, to determine a vehicle renter that is registered with the vehicle-sharing application and that satisfies the criterion as a third output;

means for causing, by the processor, an indication of the vehicle to be displayed together with the prompt, via the vehicle-sharing application to the vehicle renter, wherein receiving a user input via the prompt changes the criterion;

means for receiving vehicle operation data in real-time from vehicle-mounted sensors configured at the vehicle while the vehicle renter operates the vehicle, the vehicle operation data comprising lateral and longitudinal acceleration data;

means for generating telematics data at the vehicle-sharing application using the vehicle operation data;

means for determining a vehicle location based at least in part on geographic location data for the vehicle represented in the vehicle operation data;

means for determining that the vehicle renter has completed operating the vehicle based at least in part on the vehicle location;

means for generating one or more metrics associated with the vehicle renter based at least in part on the telematics data;

means for communicating, via the vehicle-sharing application, the one or more metrics associated with the vehicle renter to a vehicle owner;

means for receiving, via the vehicle-sharing application, feedback data associated with the vehicle renter from the vehicle owner;

means for updating the one or more metrics associated with the vehicle renter based at least in part on the feedback data; and

means for populating a graphical user interface presented via the vehicle-sharing application with the updated one or more metrics.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 8, 2024
From: HARVEY, BRIAN N.; BRANNAN, JOSEPH ROBERT; WILSON, J. LYNN; RILEY, MATTHEW ERIC, SR.
To: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
Reel/Frame 066422/0069 →
Continuity (3)
Continuation 17516804 · Nov 2, 2021
Continuation 16266986 · Feb 4, 2019
Related Publication 20240078567A1 · Mar 7, 2024
References Cited (94)
US 7996282B1 · Scott et al. · 2011 [cited by applicant]
US 9087099B2 · Camacho et al. · 2015 [cited by applicant]
US 9311271B2 · Wright · 2016 [cited by applicant]
US 9633487B2 · Wright · 2017 [cited by applicant]
US 9830748B2 · Rosenbaum · 2017 [cited by applicant]
US 9990782B2 · Rosenbaum · 2018 [cited by applicant]
US 10013697B1 · Cote et al. · 2018 [cited by applicant]
US 10026237B1 · Fields et al. · 2018 [cited by applicant]
US 10029696B1 · Ferguson · 2018 [cited by applicant]
US 10192369B2 · Wright · 2019 [cited by applicant]
US 10198879B2 · Wright · 2019 [cited by applicant]
US 10269190B2 · Rosenbaum · 2019 [cited by applicant]
US 10467824B2 · Rosenbaum · 2019 [cited by applicant]
US 10510120B1 · Roll · 2019 [cited by applicant]
US 10664920B1 · Roll et al. · 2020 [cited by applicant]
US 10810504B1 · Fields et al. · 2020 [cited by applicant]
US 10831859B2 · Van Wiemeersch et al. · 2020 [cited by applicant]
US 11227452B2 · Rosenbaum · 2022 [cited by applicant]
US 11257146B1 · Harvey · 2022 [cited by applicant]
US 11407410B2 · Rosenbaum · 2022 [cited by applicant]
US 11524707B2 · Rosenbaum · 2022 [cited by applicant]
US 11594083B1 · Rosenbaum · 2023 [cited by applicant]
US 20070244589A1 · Oku et al. · 2007 [cited by applicant]
US 20090254971A1 · Herz et al. · 2009 [cited by applicant]
US 20100287030A1 · Sinha et al. · 2010 [cited by applicant]
US 20110288891A1 · Zaid et al. · 2011 [cited by applicant]
US 20120330696A1 · Clark · 2012 [cited by examiner]
US 20130321178A1 · Jameel et al. · 2013 [cited by applicant]
US 20130325521A1 · Jameel et al. · 2013 [cited by applicant]
US 20140129301A1 · Van Wiemeersch et al. · 2014 [cited by applicant]
US 20150120489A1 · Edelman · 2015 [cited by applicant]
US 20150149221A1 · Tremblay · 2015 [cited by applicant]
US 20150213420A1 · Krishnamurthy et al. · 2015 [cited by applicant]
US 20150317844A1 · Choi et al. · 2015 [cited by applicant]
US 20150371153A1 · Lohmeier et al. · 2015 [cited by applicant]
US 20160071177A1 · Launay · 2016 [cited by applicant]
US 20160363935A1 · Shuster et al. · 2016 [cited by applicant]
US 20170091856A1 · Canberk et al. · 2017 [cited by applicant]
US 20170098231A1 · Dietrich · 2017 [cited by applicant]
US 20170144671A1 · Memani et al. · 2017 [cited by applicant]
US 20170206717A1 · Kuhnapfel · 2017 [cited by applicant]
US 20180053133A1 · Maheshwari et al. · 2018 [cited by applicant]
US 20180075380A1 · Perl et al. · 2018 [cited by applicant]
US 20190244261A1 · Sakurada et al. · 2019 [cited by applicant]
US 20190351768A1 · Salter et al. · 2019 [cited by applicant]
US 20200118215A1 · Rao et al. · 2020 [cited by applicant]
US 20200164891A1 · Bender et al. · 2020 [cited by applicant]
US 20210215491A1 · Liu et al. · 2021 [cited by applicant]
US 20210358046A1 · Roll · 2021 [cited by applicant]
US 20220058670A1 · Harvey et al. · 2022 [cited by applicant]
US 20220092893A1 · Rosenbaum · 2022 [cited by applicant]
US 20220172280A1 · Harvey et al. · 2022 [cited by applicant]
US 20220258740A1 · Harvey et al. · 2022 [cited by applicant]
US 20220340148A1 · Rosenbaum · 2022 [cited by applicant]
US 20230060300A1 · Rosenbaum · 2023 [cited by applicant]
US 20240087005A1 · Harvey · 2024 [cited by applicant]
US 20240193675A1 · Harvey et al. · 2024 [cited by applicant]
US 20240336270A1 · Harvey et al. · 2024 [cited by applicant]
US 20250182193A1 · Harvey · 2025 [cited by applicant]
EP 3239686 · 2017 [cited by applicant]
EP 3578433A1 · 2019 [cited by applicant]
EP 3730375A1 · 2020 [cited by applicant]
EP 3960576A1 · 2022 [cited by applicant]
EP 4190659 · 2023 [cited by applicant]
EP 4190660A1 · 2023 [cited by applicant]
JP WO2018127968A1 · 2019 [cited by applicant]
WO WO2011139363A1 · 2011 [cited by applicant]
WO WO2017142536 · 2017 [cited by applicant]
WO WO2017192726 · 2017 [cited by applicant]
Eftekhari et al, An inference engine for smartphones to preprocess data and detect stationary and transportation modes, Transportation Research Part C, Apr. 20, 2016, 15 pages. [cited by applicant]
Goodwin, “Policy Incentives to Change Behaviour in Passenger Transport,” OECD International Transport Forum, Leipzig, May 2008, Transport and Energy: The Challenge of Climate Change. 1-34 (May 2008). [cited by applicant]
Griffiths, “Telematics is revolutionising fleet management”, Connected Car, Financial Times. 1-4 (Apr. 18, 2016). [cited by applicant]
Hampshire et al., “Market Analysis and Potential Growth”, Peer-to-Peer Carsharing, Transportation Research Record Journal of the Transportation Research Board. 119-126 (Dec. 2011). [cited by applicant]
Kantor et al., “Design of Algorithms for Payment Telematics Systems Evaluating Driver's Driving Style,” Transactions of Transport Sciences, 7:9-16 (Jan. 2014). [cited by applicant]
Mearian, “Insurers will now be able to track driver behavior via smartphones”, 2014, 13 pgs. [cited by applicant]
Mortimer, et al., “The effect of ‘smart’ financial incentives on driving behaviour of novice drivers,” Accident Analysis and Prevention, 119:68-79 (2018). [cited by applicant]
Office Action for U.S. Appl. No. 17/516,804, mailed on Mar. 1, 2023, Harvey, “System and Methods for Predicting Rental Vehicle Use Preferences”, 13 pages. [cited by applicant]
Office Action for U.S. Appl. No. 16/880,264, mailed on Aug. 4, 2021, Harvey, “System and Methods for Determining Owner's Preferences Based on Vehicle Owners Telematics Data”, 17 Pages. [cited by applicant]
Office Action for U.S. Appl. No. 17/739,730, mailed on Aug. 17, 2023, Harvey, “System and Methods for Determining Owner's Preferences Based On Vehicle Owners Telematics Data”, 11 pages. [cited by applicant]
Non Final Office Action dated Jan. 6, 2021 for U.S. Appl. No. 16/267,023, “System and Methods for Determining Rental Eligibility Based on Contextual Telematics Data”, Harvey, 12 pages. [cited by applicant]
Office Action dated Jan. 7, 2021 for U.S. Appl. No. 16/266,879, “Incentivizing and/or Penalizing Vehicle Renters Based on Telematics Data”, Harvey, 14 pages. [cited by applicant]
Office Action for U.S. Appl. No. 17/673,106, mailed on Oct. 5, 2022, Harvey, “Incentivizing and/or Penalizing Vehicle Renters Based on Telematics Data”, 18 pages. [cited by applicant]
Non Final Office Action dated Oct. 28, 2020 for U.S. Appl. No. 16/266,986, “System and Methods for Predicting Rental Vehicle Use Preferences”, Harvey, 26 pages. [cited by applicant]
Office Action dated Mar. 16, 2021 for U.S. Appl. No. 16/266,986, “System and Methods for Predicting Rental Vehicle Use Preferences”, Harvey, 32 pages. [cited by applicant]
Office Action for U.S. Appl. No. 17/673,106, mailed on May 8, 2023, Incentivizing and/or Penalizing Vehicle Renters Based on Telematics Data, 9 pages. [cited by applicant]
Office Action for U.S. Appl. No. 16/267,023, mailed on Jun. 7, 2023, Harvey, “System and Methods for Determining Rental Eligibility Based on Contextual Telematics Data”, 12 Pages. [cited by applicant]
Office Action for U.S. Appl. No. 16/267,023, mailed on Jul. 20, 2022, Harvey, “System and Methods for Determining Rental Eligibility Based on Contextual Telematics Data”, 11 pages. [cited by applicant]
Office Action for U.S. Appl. No. 16/266,879, mailed on Jul. 21, 2021, Harvey, “Incentivizing and/or Penalizing Vehicle Renters Based on Telematics Data”, 11 pages. [cited by applicant]
Yi et al,“A machine learning based personalized system for driving state recognition”, Transportation Research Part C; Emerging Technologies, vol. 105, year 2019, 27 pages. [cited by applicant]
Final Office Action for related U.S. Appl. No. 18/514,876, dated Feb. 26, 2025 (12 pages). [cited by applicant]
Non-Final Office Action for related U.S. Appl. No. 18/745,397, dated Aug. 6, 2025, to Harvey, entitled “System and Methods for Determining Owner's Preferences Based on Vehicle Owners Telematics Data,” 15 pages. [cited by applicant]
Non-Final Office Action for U.S. Appl. No. 18/514,876, Dated Jun. 4, 2025, Harvey, “Determining Driving Behavior Based on Telematics Data,” 14 pages. [cited by applicant]
Non-Final Office Action mailed Sep. 27, 2024, for related U.S. Appl. No. 18/514,876, to Harvey, entitled “Incentivizing and/or Penalizing Vehicle Renters Based on Telematics Data” (19 Pages). [cited by applicant]
Top Telematics Smartphone Apps, Telematics.com, May 7, 2015, <<https://www.telematics.com/author/telematics-com/)>>, 13 pages. [cited by applicant]