Systems and methods for generating location-based group recommendations

• US 10,529,004 B2
• Filed: 08/14/2018
• Issued: 01/07/2020
• 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:
  US16/103,904
• Publication Number:
  US 20190087883A1
• Time in Patent Office: 511 Days
• Field of Search: 4554561, 706 62, 701533
• 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 method comprising:

determining that a first device of a first user is within a threshold distance of a second device of a second user;

including the first user and the second user in a group of users in response to determining that the first device and the second device are within the threshold distance of each other;

accessing first user profile data of the first user and second user profile data of the second user in response to the first user and the second user being included in the group of users;

identifying, from the first user profile data, first online interactions of the first user;

identifying, from the second user profile data, second online interactions of the second user;

identifying, using specialized indexing and retrieval algorithms, one or more common patterns that are common to the first online interactions and the second online interactions; and

generating a common recommendation that is specific to the group of users based on the identified common patterns.

2. The method of claim 1, wherein generating the common recommendation is further based on a geographical area where the first device and the second device are located.

3. The method of claim 1, wherein the first online interactions include first user interactions of the first user with respect to one or more network-based services, and the second online interactions include second user interactions of the second user with respect to the one or more network-based services.

4. The method of claim 3, wherein the recommendation includes consumption of content provided by the one or more network-based services.

5. The method of claim 1, further comprising:

extracting a first feature matrix based on an analysis of the first online interactions; and

extracting a second feature matrix based on an analysis of the second online interactions, wherein identifying the one or more common patterns is based on the first feature matrix and the second feature matrix.

6. The method of claim 5, further comprising:

projecting the first feature matrix onto a geographical area where the first device and the second device are located;

projecting the second feature matrix onto the geographical area where the first device and the second device are located; and

generating a merge place graph using the projection of the first feature matrix and the projection of the second feature matrix, wherein identifying the one or more common patterns is based on the merge graph.

7. One or more non-transitory computer-readable media having instructions stored thereon that, in response to execution by one or more processors, cause a system to perform operations, the operations comprising:

accessing first user profile data of a first user and second user profile data of a second user in response to the first user and the second user being included in a group of users;

identifying, from the first user profile data, first online interactions of the first user;

identifying, from the second user profile data, second online interactions of the second user;

identifying, using specialized indexing and retrieval algorithms, one or more common patterns that are common to the first online interactions and the second online interactions; and

generating a common recommendation that is specific to the group of users based on the identified common patterns.

8. The one or more non-transitory computer readable media of claim 7, wherein the operations further comprise:

determining that a first device of the first user is within a threshold distance of a second device of the second user; and

including the first user and the second user in the group of users in response to determining that the first device and the second device are within the threshold distance of each other.

9. The one or more non-transitory computer readable media of claim 7, wherein generating the common recommendation is further based on a geographical area where a first device of the first user and a second device of the second user are located.

10. The one or more non-transitory computer readable media of claim 7, wherein the first online interactions include first user interactions of the first user with respect to one or more network-based services, and the second online interactions include second user interactions of the second user with respect to the same one or more network-based services.

11. The one or more non-transitory computer readable media of claim 10, wherein the recommendation includes consumption of content provided by the one or more network-based services.

12. The one or more non-transitory computer readable media of claim 7, wherein the operations further comprise:

extracting a first feature matrix based on an analysis of the first online interactions; and

extracting a second feature matrix based on an analysis of the second online interactions, wherein identifying the one or more common patterns is based on the first feature matrix and the second feature matrix.

13. The one or more non-transitory computer readable media of claim 12, wherein the operations further comprise:

projecting the first feature matrix onto a geographical area where a first device of the first user and a second device of the second user are located;

projecting the second feature matrix onto the geographical area where the first device and the second device are located; and

generating a merge place graph using the projection of the first feature matrix and the projection of the second feature matrix, wherein identifying the one or more common patterns is based on the merge graph.

14. A system comprising:

one or more processors; and

one or more non-transitory computer-readable media having instructions stored thereon that, in response to execution by the one or more processors, cause the system to perform operations, the operations comprising;

accessing first user profile data of a first user and second user profile data of a second user in response to the first user and the second user being included in a group of users in response to a determination that the first user and the second user are within a threshold distance of each other;

identifying, using specialized indexing and retrieval algorithms, one or more common patterns that are common to first online interactions of the first user profile data and second online interactions of the second user profile data; and

generating a common recommendation that is specific to the group of users based on the identified common patterns.

15. The system of claim 14, wherein the operations further comprise:

determining that the first user and the second user are within the threshold distance of each other in response to determining that a first device of the first user is within the threshold distance of a second device of the second user.

16. The system of claim 14, wherein the operations further comprise:

identifying, from the first user profile data, the first online interactions of the first user; and

identifying, from the second user profile data, the second online interactions of the second user.

17. The system of claim 14, wherein the first online interactions include first user interactions of the first user with respect to one or more network-based services, and the second online interactions include second user interactions of the second user with respect to the same one or more network-based services.

18. The system of claim 17, wherein the recommendation includes consumption of content provided by the one or more network-based services.

19. The system of claim 14, wherein the operations further comprise:

extracting a first feature matrix based on an analysis of the first user profile data; and

extracting a second feature matrix based on an analysis of the second user profile data, wherein identifying the one or more common patterns is based on the first feature matrix and the second feature matrix.

20. The system of claim 19, wherein the operations further comprise:

projecting the first feature matrix onto a geographical area where a first device of the first user and a second device of the second user are located;

projecting the second feature matrix onto the geographical area where the first device and the second device are located; and

generating a merge place graph using the projection of the first feature matrix and the projection of the second feature matrix, wherein identifying the one or more common patterns is based on the merge graph.