IP Library Granted Patent US 12,423,626
Granted Patent B2
US 12,423,626 · App. 17/694,292 · Granted Sep 23, 2025

Dynamic invitation transmission and presentation mode determination for a network-based service

Inventors: Emre Demiralp (San Francisco, CA); Meisam Vosoughpour (San Francisco, CA); Stephen LePallone (San Francisco, CA); Hamid Nazerzadeh (San Francisco, CA); Mustafa Sahin (San Francisco, CA)
Assignee: Uber Technologies, Inc.
G06Q10/047G01C21/3438H04W4/023H04W4/029G06Q50/40H04W4/02
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 12,423,626
App. No.
17/694,292
Filed
Mar 14, 2022
Granted
Sep 23, 2025
Kind
B2
Art Unit
3664
USPC
701/533
Abstract

A network system can receive a first request for a transport service and a second request for the transport service. The system can identify, from a plurality of service providers, a first set of service providers for the first request, and a second set of service providers for the second request. Based on a first set of predictive parameters for the first set of service providers, the system implements a multi-invite mode by transmitting a first invitation data set to service the first request to a plurality of provider devices of the first set of service providers. Based on a second set of predictive parameters for the second set of service providers, the system implements an exclusive-invite mode by transmitting a second invitation data set to a provider device of a selected service provider of the second set of service providers.

Claims (44)

1. A network system for managing a network-based service, the network system comprising:

one or more processors; and

one or more memory resources storing instructions that, when executed by the one or more processors of the network system, cause the network system to:

during a first time period, receive, over one or more networks, multiple requests for transport from a common geographic region, the multiple requests for transport including a first request for transport from a first user device of a first requesting user, and a second request for transport from a second user device of a second requesting user;

during a second time period following the first time period, match each request for transport to a corresponding service provider of a plurality of service providers, wherein matching each request for transport includes:

for the first request for transport, identifying, by accessing one or more databases, a first set of service providers from the plurality of service providers;

for the second request for transport, identifying, by accessing the one or more databases, a second set of service providers from the plurality of service providers;

based on a first set of predictive parameters for the first set of service providers, implement a multi-invite mode for matching the first request for transport by (i) transmitting a first invitation data set to service the first request for transport to each provider device of a plurality of provider devices of the first set of service providers, and (ii) enabling each provider of the plurality of service providers to provide acceptance data during at least a portion of the second time period; and

based on a second set of predictive parameters for the second set of service providers, implement an exclusive-invite mode for matching the second request by (i) transmitting a second invitation data set to a provider device of a selected service provider of the second set of service providers, and (ii) enabling only the selected service provider to provide acceptance data during at least a portion of the second time period.

2. The network system of claim 1 , wherein the executed instructions cause the network system to implement the multi-invite mode based on each of the first set of predictive parameters not meeting or exceeding a threshold value.

3. The network system of claim 2 , wherein the first set of predictive parameters corresponds to a probability or likelihood that a particular service provider in the first set of service providers will accept the first invitation data set to service the first request.

4. The network system of claim 3 , wherein the first set of predictive parameters are outputted by one or more machine-learned models using context data received from the plurality of provider devices of the first set of service providers.

5. The network system of claim 4 , wherein the context data comprises at least one of (i) input data corresponding to provider interactions with a service application executing on the each provider device of the first set of service providers, (ii) location data indicating current locations of each of the first set of service providers, (iii) an estimated time of arrival of each of the first set of service providers to a service location indicated in the first request, or (iv) sensor data received from each provider device of the first set of service providers.

6. The network system of claim 1 , wherein the executed instructions further cause the network system to:

receive a plurality of acceptance data from multiple provider devices of the plurality of provider devices of the first set of service providers; and

select an optimal service provider from the first set of service providers based on the plurality of acceptance data to service the first request.

7. The network system of claim 6 , wherein the executed instructions cause the network system to select the optimal service provider based on the first set predictive parameters.

8. The network system of claim 1 , wherein the first invitation data set is presented to at least one service provider of the first set of service providers in a job board graphical user interface that comprises a set of active multi-invite invitations.

9. The network system of claim 1 , wherein the executed instructions cause the network system to implement the exclusive-invite mode for the second request based on a predictive parameter of the second set of predictive parameters meeting or exceed a threshold value.

10. The network system of claim 9 , wherein the predictive parameter corresponds to a likelihood or probability that the selected service provider will accept the second invitation data set.

11. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a network system, cause the network system to:

during a first time period, receive, over one or more networks, multiple requests for transport from a common geographic region, the multiple requests for transport including a first request for transport from a first user device of a first requesting user, and a second request for transport from a second user device of a second requesting user;

during a second time period following the first time period, match each request for transport to a corresponding service provider of a plurality of service providers, wherein matching each request for transport includes:

for the first request for transport, identifying, by accessing one or more databases, a first set of service providers from the plurality of service providers;

for the second request for transport, identifying, by accessing the one or more databases, a second set of service providers from the plurality of service providers;

based on a first set of predictive parameters for the first set of service providers, implement a multi-invite mode for matching the first request for transport by (i) transmitting a first invitation data set to service the first request for transport to each provider device of a plurality of provider devices of the first set of service providers, and (ii) enabling each provider of the plurality of service providers to provide acceptance data during at least a portion of the second time period; and

based on a second set of predictive parameters for the second set of service providers, implement an exclusive-invite mode for matching the second request by (i) transmitting a second invitation data set to a provider device of a selected service provider of the second set of service providers, and (ii) enabling only the selected service provider to provide acceptance data during at least a portion of the second time period.

12. The non-transitory computer-readable medium of claim 11 , wherein the executed instructions cause the network system to implement the multi-invite mode based on each of the first set of predictive parameters not meeting or exceeding a threshold value.

13. The non-transitory computer-readable medium of claim 12 , wherein the first set of predictive parameters corresponds to a probability or likelihood that a particular service provider in the first set of service providers will accept the first invitation data set to service the first request.

14. The non-transitory computer-readable medium of claim 13 , wherein the first set of predictive parameters are outputted by one or more machine-learned models using context data received from the plurality of provider devices of the first set of service providers.

15. The non-transitory computer-readable medium of claim 14 , wherein the context data comprises at least one of (i) input data corresponding to provider interactions with a service application executing on the each provider device of the first set of service providers, (ii) location data indicating current locations of each of the first set of service providers, (iii) an estimated time of arrival of each of the first set of service providers to a service location indicated in the first request, or (iv) sensor data received from each provider device of the first set of service providers.

16. The non-transitory computer-readable medium of claim 11 , wherein the executed instructions further cause the network system to:

receive a plurality of acceptance data from multiple provider devices of the plurality of provider devices of the first set of service providers; and

select an optimal service provider based on the plurality of acceptance data to service the first request.

17. The non-transitory computer-readable medium of claim 16 , wherein the executed instructions cause the network system to select the optimal service provider based on the first set predictive parameters.

18. The non-transitory computer-readable medium of claim 11 , wherein the first invitation data set is presented to at least one service provider of the first set of service providers in a job board graphical user interface that comprises a set of active multi-invite invitations.

19. The non-transitory computer-readable medium of claim 11 , wherein the executed instructions cause the network system to implement the exclusive-invite mode for the second request based on a predictive parameter of the second set of predictive parameters meeting or exceed a threshold value.

20. A computer-implemented method of matching requests for service, the method being implemented by one or more processors and comprising:

during a first time period, receive, over one or more networks, multiple requests for transport from a common geographic region, the multiple requests for transport including a first request for transport from a first user device of a first requesting user, and a second request for transport from a second user device of a second requesting user;

during a second time period following the first time period, match each request for transport to a corresponding service provider of a plurality of service providers, wherein matching each request for transport includes:

for the first request for transport, identifying, by accessing one or more databases, a first set of service providers from the plurality of service providers;

for the second request for transport, identifying, by accessing the one or more databases, a second set of service providers from the plurality of service providers;

based on a first set of predictive parameters for the first set of service providers, implementing a multi-invite mode for matching the first request for transport by (i) transmitting a first invitation data set to service the first request for transport to each provider device of a plurality of provider devices of the first set of service providers, and (ii) enabling each provider of the plurality of service providers to provide acceptance data during at least a portion of the second time period; and

based on a second set of predictive parameters for the second set of service providers, implementing an exclusive-invite mode for matching the second request by (i) transmitting a second invitation data set to a provider device of a selected service provider of the second set of service providers, and (ii) enabling only the selected service provider to provide acceptance data during at least a portion of the second time period.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 11, 2025
From: SAHIN, MUSTAFA; DEMIRALP, EMRE; NAZERZADEH, HAMID; LEPALLONE, STEPHEN; VOSOUGHPOUR, MEISAM
To: UBER TECHNOLOGIES, INC.
Reel/Frame 071680/0746 →
Continuity (2)
Provisional Application 63161294 · Mar 15, 2021
Related Publication 20220292414A1 · Sep 15, 2022
References Cited (56)
US 7751315B1 · Pai · 2010 [cited by applicant]
US 10171569B2 · Brinig · 2019 [cited by examiner]
US 10248913B1 · Gururajan · 2019 [cited by applicant]
US 10371539B2 · Broyles · 2019 [cited by examiner]
US 11601511B2 · Yamashita · 2023 [cited by examiner]
US 11674811B2 · Shoval · 2023 [cited by examiner]
US 20060136326A1 · Heckman · 2006 [cited by applicant]
US 20090147698A1 · Potvin · 2009 [cited by applicant]
US 20090216600A1 · Hill · 2009 [cited by applicant]
US 20110099040A1 · Felt · 2011 [cited by applicant]
US 20110313804A1 · Camp · 2011 [cited by applicant]
US 20120131170A1 · Spat · 2012 [cited by applicant]
US 20130132140A1 · Amin · 2013 [cited by applicant]
US 20130246207A1 · Novak · 2013 [cited by applicant]
US 20130268406A1 · Radhakrishnan · 2013 [cited by applicant]
US 20140011522A1 · Lin · 2014 [cited by examiner]
US 20150058148A1 · Grosz · 2015 [cited by applicant]
US 20150074215A1 · Arquette · 2015 [cited by applicant]
US 20150161564A1 · Sweeney · 2015 [cited by applicant]
US 20150339923A1 · Konig · 2015 [cited by applicant]
US 20160092962A1 · Wasserman · 2016 [cited by applicant]
US 20160275638A1 · Korpi · 2016 [cited by applicant]
US 20160279523A1 · Altagar · 2016 [cited by applicant]
US 20160307288A1 · Yehuda · 2016 [cited by applicant]
US 20160335694A1 · Catino · 2016 [cited by applicant]
US 20170046644A1 · Zhang · 2017 [cited by applicant]
US 20170109805A1 · Eisen · 2017 [cited by applicant]
US 20170132540A1 · Haparnas · 2017 [cited by applicant]
US 20170140323A1 · Laird · 2017 [cited by applicant]
US 20170161860A1 · Schultz · 2017 [cited by applicant]
US 20170220966A1 · Wang · 2017 [cited by applicant]
US 20170249847A1 · Marueli · 2017 [cited by applicant]
US 20170284820A1 · Dryjanski · 2017 [cited by applicant]
US 20170352093A1 · Armelin · 2017 [cited by applicant]
US 20180088749A1 · Yamashita · 2018 [cited by examiner]
US 20180159921A1 · Brinig · 2018 [cited by examiner]
US 20190266518A1 · Medina · 2019 [cited by applicant]
US 20190289427A1 · Lin · 2019 [cited by examiner]
US 20190295206A1 · Yamashita · 2019 [cited by examiner]
US 20190318630A1 · Marco · 2019 [cited by applicant]
US 20200075016A1 · Goldstein · 2020 [cited by examiner]
US 20200128101A1 · Meng · 2020 [cited by examiner]
US 20200131932A1 · Sezer et al. · 2020 [cited by applicant]
US 20210082076A1 · Gulati · 2021 [cited by examiner]
US 20210209542A1 · Magazinik · 2021 [cited by applicant]
US 20210276595A1 · Casas · 2021 [cited by examiner]
US 20220164910A1 · Gu · 2022 [cited by applicant]
US 20220292414A1 · Demiralp · 2022 [cited by applicant]
US 20230316155A1 · Wu · 2023 [cited by examiner]
WO WO2018058121A1 · 2018 [cited by examiner]
Operational benefits and challenges of shared-ride automated mobility-on-demand services; Author links open overlay panel Michael Hyland et al., Transportation Research Part A: Policy and Practice; vol. 134, Apr. 2020, … [cited by examiner]
Bian, Zheyong, Xiang Liu, and Yun Bai. “Mechanism design for on-demand first-mile ridesharing.” Transportation research part B: methodological 138: 77-117,. (Year: 2020). [cited by examiner]
Boysen, Nils, Dirk Briskorn, and Stefan Schwerdfeger. “Matching supply and demand in a sharing economy: Classification, computational complexity, and application.” European Journal of Operational Research 278.2 578-595.… [cited by examiner]
Davis, Gerald F., and Aseem Sinha. “Varieties of Uberization: How technology and institutions change the organization (s) of late capitalism.” Organization Theory 2.1 (2021): 2631787721995198. (Year: 2021). [cited by examiner]
Posen, Hannah A. “Ridesharing in the sharing economy: Should regulators impose Uber regulations on Uber.” Iowa L. Rev. 101 (2015): 405. (Year: 2015). [cited by examiner]
Mudrić, Mišo. “Nature of Uber services.” Uber—Brave New Service or Unfair Competition: Legal Analysis of the Nature of Uber Services (2020): 15-55. (Year: 2020). [cited by examiner]