IP Library Granted Patent US 12,228,924
Granted Patent B2
US 12,228,924 · App. 18/395,360 · Granted Feb 18, 2025

Social data sources feeding a neural network to predict an emerging condition relevant to a transportation plan of at least one individual

Inventor: Charles Howard Cella (Pembroke, MA)
Assignee: Strong Force TP Portfolio 2022, LLC
G05D1/0022B60W40/08G01C21/3438G01C21/3461G01C21/3469G01C21/3617G05B13/027G05D1/0088G05D1/0212G05D1/0287G05D1/224G05D1/225G05D1/226G05D1/227G05D1/228G05D1/229G05D1/24G05D1/646G05D1/69G05D1/692G06F40/40G06N3/0418G06N3/045G06N3/08G06N3/086G06N20/00G06Q30/0208G06Q50/188G06Q50/40G06V10/764G06V10/82G06V20/56G06V20/59G06V20/597G06V20/64G07C5/006G07C5/008G07C5/02G07C5/08G07C5/0808G07C5/0816G07C5/0866G07C5/0891G10L15/16G10L25/63B60W2040/0881G06N3/02G06Q30/0281G06Q50/01
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 12,228,924
App. No.
18/395,360
Granted
Feb 18, 2025
Kind
B2
Abstract

A system may receive social data from a plurality of social data sources. A system may process the social data using semantic analysis to detect keywords in the social data indicative of a group transportation need. A system may identify a plurality of individuals who share a group transportation need. A system may predict the group transportation need using a neural network trained to predict transportation needs based on the detected keywords. A system may provide a transportation recommendation based on the prediction.

Claims (46)

1. A computer-implemented method of providing a transportation recommendation, the method comprising:

receiving social data from a plurality of social data sources, wherein the social data includes social media posts, discussion threads, chats, or photographs;

processing, using a data processing system, the social data using natural language processing analysis to detect indications of a group transportation need in the social data, wherein the indications of the group transportation need in the social data include transportation need indicative language;

identifying a plurality of individuals who share the group transportation need based on the processed social data;

predicting the group transportation need using a neural network that is trained to predict transportation needs based on the detected indications of the group transportation need and based on the plurality of identified individuals;

providing the transportation recommendation to an expert system that is connected to one or more vehicles, wherein the transportation recommendation is provided based on the predicted group transportation need, and wherein the transportation recommendation includes at least one parameter of configuration for the expert system that controls a routing parameter for the one or more vehicles; and

using the expert system to route the one or more vehicles based on the transportation recommendation provided to the expert system.

2. The method of claim 1 , further comprising:

using the processed social data to determine a preferred mode of transportation for each individual in the plurality of individuals who share the group transportation need; and

incorporating the preferred mode of transportation into the transportation recommendation that is provided to the expert system.

3. The method of claim 1 , wherein the plurality of social data sources includes at least one of social media platforms, online discussion threads, or messaging applications.

4. The method of claim 1 , wherein the neural network that is trained to predict the transportation needs is a deep learning neural network.

5. The method of claim 1 , further comprising:

receiving feedback from the plurality of individuals who share the group transportation need regarding the transportation recommendation; and

using the feedback to train the neural network.

6. The method of claim 1 , wherein the group transportation need that is predicted by the neural network is a shared destination of the plurality of individuals.

7. The method of claim 1 , wherein the group transportation need that is predicted by the neural network is a shared departure time of the plurality of individuals.

8. The method of claim 1 , wherein the group transportation need that is predicted by the neural network is a shared route of the plurality of individuals.

9. The method of claim 1 , wherein the transportation recommendation that is provided to the expert system further includes at least one of a suggested route for the one or more vehicles, a suggested departure time for the one or more vehicles, or a suggested mode of transportation that can be used to transport the plurality of individuals.

10. A computer-implemented method of providing a transportation recommendation, the method comprising:

receiving social data from a plurality of social data sources relating to a group of individuals, wherein the social data includes social media posts, discussion threads, chats, or photographs;

processing, using a data processing system, the social data using natural language processing analysis to detect indications in the social data of a group transportation need of the group of individuals;

predicting the group transportation need using a neural network that is trained to predict transportation needs based on the detected indications of the group transportation need and based on the group of individuals to which the social data sources are related;

providing a group transportation recommendation to an expert system that is connected to a plurality of vehicles, wherein the group transportation recommendation is provided based on the predicted group transportation need;

identifying, using the expert system, one or more vehicles from among the plurality of vehicles with performance characteristics consistent with the group transportation recommendation; and

selecting and routing the one or more vehicles to perform the group transportation need in accordance with the group transportation recommendation.

11. The method of claim 10 , further comprising:

using the processed social data to determine a preferred mode of transportation for the group of individuals; and

incorporating the preferred mode of transportation into the group transportation recommendation that is provided to the expert system.

12. The method of claim 10 , wherein the plurality of social data sources includes at least one of social media platforms, online discussion threads, or messaging applications.

13. The method of claim 10 , wherein the neural network that is trained to predict the transportation needs is a deep learning neural network.

14. The method of claim 10 , further comprising:

receiving feedback from the group of individuals regarding the group transportation recommendation; and

using the feedback to train the neural network.

15. The method of claim 10 , wherein the group transportation recommendation that is provided to the expert system includes at least one of a suggested route for the one or more vehicles or a suggested departure time for the one or more vehicles.

16. The method of claim 10 , wherein the performance characteristics include at least one of fuel efficiency, vehicle capacity, or vehicle speed.

17. The method of claim 10 , wherein the group transportation recommendation that is provided to the expert system is further based on a predicted environmental impact.

18. A system for providing a group transportation recommendation, the system comprising a data processing system and an expert system, wherein the system is configured to:

receive social data from a plurality of social data sources, wherein the social data relates to a group of individuals, and wherein the social data includes social media posts, discussion threads, chats, or photographs;

use the data processing system to process the social data with natural language analysis to detect indications in the social data of a group transportation need of the group of individuals;

predict a group transportation need of the group of individuals using a neural network that is trained to predict transportation needs based on the detected indications of the group transportation need and based on the group of individuals to which the social data sources are related;

provide a group transportation recommendation to an expert system that is connected to a plurality of vehicles, wherein the group transportation recommendation is provided based on the predicted group transportation need;

identify, using the expert system, one or more vehicles form among the plurality of vehicles with performance characteristics consistent with the group transportation recommendation; and

select and route the one or more vehicles from among the plurality of identified vehicles to perform the group transportation need in accordance with the group transportation recommendation.

19. The system of claim 18 , wherein the group transportation recommendation that is provided to the expert system includes at least one of a suggested route for the one or more vehicles, a suggested destination for the one or more vehicles, or a suggested departure time for the one or more vehicles.

20. The system of claim 18 , wherein the performance characteristics include at least one of fuel efficiency, vehicle capacity, or vehicle speed.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 24, 2024
From: CELLA, CHARLES HOWARD
To: STRONG FORCE TP PORTFOLIO 2022, LLC
Reel/Frame 066235/0543 →
Continuity (6)
Continuation 17978093 · Oct 31, 2022
Continuation 16887547 · May 29, 2020
Continuation 16694733 · Nov 25, 2019
Continuation PCTUS2019053857 · Sep 30, 2019
Provisional Application 62739335 · Sep 30, 2018
Related Publication 20240126285A1 · Apr 18, 2024
References Cited (110)
US 5400734A · Doyon · 1995 [cited by applicant]
US 6058352A · Lu et al. · 2000 [cited by applicant]
US 6188945B1 · Graf et al. · 2001 [cited by applicant]
US 6694054B1 · Gardes et al. · 2004 [cited by applicant]
US 9451396B2 · Takatsuji · 2016 [cited by applicant]
US 9493168B1 · Kim et al. · 2016 [cited by applicant]
US 9744363B2 · Grill, Jr. et al. · 2017 [cited by applicant]
US 9849044B1 · Groden et al. · 2017 [cited by applicant]
US 10117109B2 · Madaiah et al. · 2018 [cited by applicant]
US 10122692B2 · Maccarthaigh · 2018 [cited by applicant]
US 10126743B2 · Fukumoto · 2018 [cited by applicant]
US 10152875B2 · Khaligh et al. · 2018 [cited by applicant]
US 10289618B2 · Fink et al. · 2019 [cited by applicant]
US 10346415B1 · Smith et al. · 2019 [cited by applicant]
US 10372130B1 · Kaushansky et al. · 2019 [cited by applicant]
US 10373522B2 · Byron et al. · 2019 [cited by applicant]
US 10387205B2 · Boutnaru · 2019 [cited by applicant]
US 10387417B1 · Hansen et al. · 2019 [cited by applicant]
US 10387429B2 · Smith-Mickelson et al. · 2019 [cited by applicant]
US 10423934B1 · Zanghi et al. · 2019 [cited by applicant]
US 10482333B1 · El Kaliouby et al. · 2019 [cited by applicant]
US 10620631B1 · Abeloe · 2020 [cited by applicant]
US 10696306B1 · Benisch et al. · 2020 [cited by applicant]
US 10769525B2 · Redding et al. · 2020 [cited by applicant]
US 10942520B1 · Copeland et al. · 2021 [cited by applicant]
US 20030145647A1 · Ismail et al. · 2003 [cited by applicant]
US 20050143845A1 · Kaji · 2005 [cited by applicant]
US 20090112334A1 · Grichnik et al. · 2009 [cited by applicant]
US 20090112429A1 · Sah et al. · 2009 [cited by applicant]
US 20110213511A1 · Msconti et al. · 2011 [cited by applicant]
US 20120016551A1 · Krause et al. · 2012 [cited by applicant]
US 20120197504A1 · Sujan et al. · 2012 [cited by applicant]
US 20130057671A1 · Levin et al. · 2013 [cited by applicant]
US 20130204874A1 · Frey · 2013 [cited by applicant]
US 20140201126A1 · Zadeh et al. · 2014 [cited by applicant]
US 20140309806A1 · Ricci · 2014 [cited by examiner]
US 20150271557A1 · Tabe · 2015 [cited by applicant]
US 20150298565A1 · Iwamura et al. · 2015 [cited by applicant]
US 20150317990A1 · Fousek et al. · 2015 [cited by applicant]
US 20150344036A1 · Kristinsson et al. · 2015 [cited by applicant]
US 20160035150A1 · Barfield, Jr. et al. · 2016 [cited by applicant]
US 20160098561A1 · Keller et al. · 2016 [cited by applicant]
US 20160161275A1 · Waltermann et al. · 2016 [cited by applicant]
US 20160189056A1 · Mayhew · 2016 [cited by applicant]
US 20160297309A1 · Kim · 2016 [cited by applicant]
US 20160364823A1 · Cao · 2016 [cited by applicant]
US 20170021282A1 · Comploi · 2017 [cited by applicant]
US 20170025983A1 · Sills et al. · 2017 [cited by applicant]
US 20170057507A1 · Gordon et al. · 2017 [cited by applicant]
US 20170151956A1 · Boesen · 2017 [cited by applicant]
US 20170299399A1 · Yamaguchi et al. · 2017 [cited by applicant]
US 20170316533A1 · Goldman-Shenhar · 2017 [cited by applicant]
US 20170352267A1 · Tzirkel-Hancock et al. · 2017 [cited by applicant]
US 20180027215A1 · Carlson · 2018 [cited by applicant]
US 20180050686A1 · Alturi et al. · 2018 [cited by applicant]
US 20180053413A1 · Patil et al. · 2018 [cited by applicant]
US 20180082501A1 · Kochar et al. · 2018 [cited by applicant]
US 20180086223A1 · Lindemann et al. · 2018 [cited by applicant]
US 20180101800A1 · Lecue · 2018 [cited by examiner]
US 20180120843A1 · Berntorp et al. · 2018 [cited by applicant]
US 20180137593A1 · Djuric · 2018 [cited by examiner]
US 20180143635A1 · Zijderveld · 2018 [cited by examiner]
US 20180157923A1 · El Kaliouby et al. · 2018 [cited by applicant]
US 20180203455A1 · Cronin et al. · 2018 [cited by applicant]
US 20180208211A1 · Chiba · 2018 [cited by applicant]
US 20180238698A1 · Pedersen · 2018 [cited by applicant]
US 20180260414A1 · Gordo Soldevila · 2018 [cited by applicant]
US 20180266834A1 · Cronin et al. · 2018 [cited by applicant]
US 20180303397A1 · Krupat et al. · 2018 [cited by applicant]
US 20180322112A1 · Bellegarda et al. · 2018 [cited by applicant]
US 20180330178A1 · El Kaliouby et al. · 2018 [cited by applicant]
US 20190018067A1 · Kong et al. · 2019 [cited by applicant]
US 20190033085A1 · Ogale et al. · 2019 [cited by applicant]
US 20190047584A1 · Donnelly · 2019 [cited by applicant]
US 20190049267A1 · Huang · 2019 [cited by applicant]
US 20190049957A1 · Healey et al. · 2019 [cited by applicant]
US 20190049969A1 · Qawami et al. · 2019 [cited by applicant]
US 20190050714A1 · Nosko et al. · 2019 [cited by applicant]
US 20190051069A1 · Cooley · 2019 [cited by examiner]
US 20190079659A1 · Adenwala et al. · 2019 [cited by applicant]
US 20190101985A1 · Sajda et al. · 2019 [cited by applicant]
US 20190102840A1 · Perl et al. · 2019 [cited by applicant]
US 20190113362A1 · Kline et al. · 2019 [cited by applicant]
US 20190122544A1 · Schlesinger et al. · 2019 [cited by applicant]
US 20190156596A1 · Followell et al. · 2019 [cited by applicant]
US 20190178678A1 · Rahbari-Asr et al. · 2019 [cited by applicant]
US 20190204840A1 · Park et al. · 2019 [cited by applicant]
US 20190225232A1 · Blau · 2019 [cited by applicant]
US 20190226861A1 · Schimik et al. · 2019 [cited by applicant]
US 20190276037A1 · Ito et al. · 2019 [cited by applicant]
US 20190283762A1 · El Kaliouby et al. · 2019 [cited by applicant]
US 20190294159A1 · Pedersen et al. · 2019 [cited by applicant]
US 20190311614A1 · Yang et al. · 2019 [cited by applicant]
US 20190319477A1 · Manikfan · 2019 [cited by applicant]
US 20190332902A1 · Gallagher et al. · 2019 [cited by applicant]
US 20190370915A1 · Garden et al. · 2019 [cited by applicant]
US 20210091995A1 · Trim · 2021 [cited by examiner]
US 20210197867A1 · Kirk et al. · 2021 [cited by applicant]
US 20210217510A1 · Chakra · 2021 [cited by examiner]
US 20220005291A1 · Konrardy et al. · 2022 [cited by applicant]
US 20220036122A1 · Higa · 2022 [cited by applicant]
KR 1020150050134A · 2015 [cited by applicant]
WO 2009061687A1 · 2009 [cited by applicant]
WO 2011080321A1 · 2011 [cited by applicant]
WO 2018094375A1 · 2018 [cited by applicant]
Villarejo, et al., “A Stress Sensor Based on Galvanic Skin Response (GSR) Controlled by ZigBee Sensors”, Sensors, 12, 6075-6101, 2012. [cited by applicant]
Author Unknown, “The Difference Between Robotic Process Automation and Artificial Intelligence”, CFB Bots, retrieved from https://medium.com/@cfb_bots, 7 pages, Apr. 20, 2018. [cited by applicant]
Gallego, “Stress Level Assessment with Non-Intrusive Sensors, Doctoral Thesis”, Universidad Carlos III De Madrid, accessed at http://www.tsc.uc3m.es/˜fhernando/ research/ ThesisFHG.pdf on Jun. 21, 2021, Apr. 2018. [cited by applicant]
Yang, Carl, et al., “Did You Enjoy the Ride: Understanding Passenger Experience via Heterogeneous Network Embedding”, 2018 IEEE 34th International Conference on Data Engineering, pp. 1392-1403, 2018. [cited by applicant]
Sekar, M., et al., “Carbon fiber based electrochemical sensor for sweat cortisol measurement”, Scientific Reports, 9:403-403, 2019. [cited by applicant]