Systems and methods for generating location-based group recommendations

• US 9,818,146 B2
• Filed: 01/24/2017
• Issued: 11/14/2017
• Est. Priority Date: 12/07/2011
• Status: Active Grant

• Current Assignee: PayPal, Inc. (PayPal Holdings, Inc.)
• Original Assignee: PayPal, Inc. (PayPal Holdings, Inc.)
• Inventors: Caralis, Jim, Kogan, Nataly, Nakamura, Masumi, Mastroianni, Michael, Sundram, Jason
• Primary Examiner(s): PATEL, MAHENDRA R
• Application Number:
  US15/414,601
• Publication Number:
  US 20170262924A1
• Time in Patent Office: 294 Days
• Field of Search: 455456, 4554561, 4554563, 455561, 4554141, 341 94, 707 69
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

Methods and systems for generating location-aware group recommendations are discussed. For example, a method can include operations for receiving a group recommendation request, accessing user profile data associated with members of the group, and generating a group recommendation. The group recommendation request can be received at a network-based system and include identification of a first and second user as well as information identifying a current location associated with the first and second users. Accessing the user profile information can include accessing user profile information for both the first and second users. The group recommendation can be generated based on the current location data and a combination of at least a portion of the user profile data from the first and second users.

Claims

1. A system comprising:

a non-transitory memory storing instructions; and

a processor configured to execute instructions to cause the system to;

receive, over a network connection with a first device, a group recommendation request and a geographical location of a first user associated with the first device, the group recommendation including a relationship indicator;

generate a first place graph of the first user, the first place graph generated using implicit interactions and explicit interactions of the first user;

generate a second place graph of a second user identified in the group recommendation request, the second place graph generated using implicit interactions and explicit interactions of the second user;

merge the first place graph and the second place graph to generate a merged place graph; and

generate a location aware recommendation based on the merged place graph and the geographical location.

2. The system of claim 1, wherein the first place graph is generated using predictive analysis to project the implicit interactions and explicit interactions of the first user at locations to new first locations.

3. The system of claim 2, wherein the second place graph is generated using predictive analysis to project the implicit interactions and explicit interactions of the second user at locations to new second locations.

4. The system of claim 3, where the location aware recommendation uses a plurality of probabilistic metrics to calculate relationships between the new first locations and the new second location and is generated by traversing the merged place graph including the new first locations and the new second locations.

5. The system of claim 1, wherein the implicit interactions and explicit interactions of the first user are analyzed to extract a feature matrix associated with the first user and wherein the feature matrix is projected onto the geographical location to create the first place graph.

6. The system of claim 1, wherein the group recommendation request comprises historical data, user profile data, location information, and the relationship indicator and wherein the relationship indicator indicates that the second user is part of a social network associated with the first user.

7. The system of claim 1, wherein the first place graph is updated by accessing user profile data for the first user.

8. A method comprising:

receiving, over a network connection with a first device, a group recommendation request and a geographical location of a first user associated with the first device, the group recommendation including a relationship indicator,

generating a first place graph of the first user, the first place graph generated using implicit interactions and explicit interactions of the first user;

generating a second place graph of a second user identified in the group recommendation request, the second place graph generated using implicit interactions and explicit interactions of the second user;

merging the first place graph and the second place graph to generate a merged place graph; and

generating a location aware recommendation based on the merged place graph and the geographical location.

9. The method of claim 8, wherein the first place graph is generated using predictive analysis to project the implicit interactions and explicit interactions of the first user at locations to new first locations.

10. The method of claim 9, wherein the second place graph is generated using predictive analysis to project the implicit interactions and explicit interactions of the second user at locations to new second locations.

11. The method of claim 10, where the location aware recommendation uses a plurality of probabilistic metrics to calculate relationships between the new first locations and the new second location and is generated by traversing the merged place graph including the new first locations and the new second locations.

12. The method of claim 8, wherein the implicit interactions and explicit interactions of the first user are analyzed to extract a feature matrix associated with the first user and wherein the feature matrix is projected onto the geographical location to create the first place graph.

13. The method of claim 8, wherein the group recommendation request comprises historical data, user profile data, location information, and the relationship indicator and wherein the relationship indicator that indicates that the second user is part of a social network associated with the first user.

14. The method of claim 8, wherein the first place graph is updated by accessing user profile data for the first user.

15. A non-transitory machine-readable medium having instructions stored thereon, the instructions executable to cause performance of operating comprising:

receiving, over a network connection with a first device, a group recommendation request and a geographical location of a first user associated with the first device, the group recommendation including a relationship indicator;

generating a first place graph of the first user, the first place graph generated using implicit interactions and explicit interactions of the first user;

generating a second place graph of a second user identified in the group recommendation request, the second place graph generated using implicit interactions and explicit interactions of the second user;

merging the first place graph and the second place graph to generate a merged place graph; and

generating a location aware recommendation based on the merged place graph and the geographical location.

16. The non-transitory machine-readable medium of claim 15, wherein the first place graph is generated using predictive analysis to project the implicit interactions and explicit interactions of the first user at locations to new first locations.

17. The non-transitory machine-readable medium of claim 16, wherein the second place graph is generated using predictive analysis to project the implicit interactions and explicit interactions of the second user at locations to new second locations.

18. The non-transitory machine-readable medium of claim 17, where the location aware recommendation uses a plurality of probabilistic metrics to calculate relationships between the new first locations and the new second location and is generated by traversing the merged place graph including the new first locations and the new second locations.

19. The non-transitory machine-readable medium of claim 15, wherein the implicit interactions and explicit interactions of the first user are analyzed to extract a feature matrix associated with the first user and wherein the feature matrix is projected onto the geographical location to create the first place graph.

20. The non-transitory machine-readable medium of claim 15, wherein the group recommendation request comprises historical data, user profile data, location information, and the relationship indicator and wherein the relationship indicator indicates that the second user is part of a social network associated with the first user.