SYSTEMS AND METHODS FOR RECOMMENDING PAGES

• US 20170185685A1
• Filed: 12/28/2015
• Published: 06/29/2017
• Est. Priority Date: 12/28/2015
• Status: Abandoned Application

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Kapoor, Komal, Brewer, Jason, Green, Bradley Ray, Yao, Jinyi
• Application Number:
  US14/980,669
• Publication Number:
  US 20170185685A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Abstract

Systems, methods, and non-transitory computer-readable media can determine respective geographic locations of a set of users associated with a page that is accessible through a social network. At least one centroid for the page can be generated based at least in part on the respective geographic locations of the set of users. At least one area of influence of the page can be determined based at least in part on the centroid. At least one page recommendation can be presented to one or more users in the set of users based at least in part on the area of influence of the

Claims

1. A computer-implemented method comprising:

determining, by a computing system, respective geographic locations of a set of users associated with a page that is accessible through a social network;

generating, by the computing system, at least one centroid for the page based at least in part on the respective geographic locations of the set of users;

determining, by the computing system, at least one area of influence of the page based at least in part on the centroid; and

determining, by the computing system, at least one page recommendation to be presented to one or more users in the set of users based at least in part on the area of influence of the page.

2. The computer-implemented method of claim 1, wherein determining the respective geographic locations corresponding to the set of users further comprises:

determining, by the computing system, the geographic location of a user based on an address referenced in a social network profile of the user;

determining, by the computing system, the geographic location of the user based on a centroid of geographic locations that correspond to check-ins performed by the user through the social network;

or

determining, by the computing system, the geographic location of the user based on a centroid of geographic locations that correspond to social connections of the user in the social network.

3. The computer-implemented method of claim 1, wherein the respective geographic locations of the set of users are each represented as latitude-longitude coordinates, and wherein generating at least one centroid for the page further comprises:

determining, by the computing system, a mean of the respective latitude-longitude coordinates corresponding to each user in the set of users; and

determining, by the computing system, the centroid for the page based on the mean.

4. The computer-implemented method of claim 1, wherein generating at least one centroid for the page further comprises:

determining, by the computing system, that a number of the users associated with the page satisfy a large page threshold;

determining, by the computing system, a sample of the set of users;

determining, by the computing system, a mean of the respective latitude-longitude coordinates corresponding to each user in the sample; and

determining, by the computing system, the centroid for the page based on the mean.

5. The computer-implemented method of claim 1, wherein generating at least one centroid for the page further comprises:

determining, by the computing system, that a number of the users associated with the page satisfy a small page threshold;

generating, by the computing system, a preliminary centroid for the page using a first sample of the set of users;

determining, by the computing system, a second sample of users by discarding at least one user from the first sample having a geographic distance from the preliminary centroid that satisfies a threshold number of standard deviations; and

generating, by the computing system, the centroid for the page using the second sample of the set of users.

6. The computer-implemented method of claim 1, wherein determining at least one centroid for the page further comprises:

determining, by the computing system, that the set of users associated with the page has a multi-modal distribution;

clustering, by the computing system, the set of users into at least a first cluster corresponding to a first geographic region and a second cluster corresponding to a second geographic region;

generating, by the computing system, at least a first centroid based at least in part on the first cluster of users; and

generating, by the computing system, at least a second centroid based at least in part on the second cluster of users.

7. The computer-implemented method of claim 1, wherein determining at least one area of influence of the page based at least in part on the centroid further comprises:

determining, by the computing system, one or more areas of influence in which a respective threshold percentage of users associated with the page are geographically located.

8. The computer-implemented method of claim 1, wherein determining at least one page recommendation further comprises:

determining, by the computing system, a threshold similarity between an area of influence of at least one candidate page and the area of influence of the page.

9. The computer-implemented method of claim 1, wherein determining at least one page recommendation further comprises:

determining, by the computing system, a threshold similarity between an area of influence of at least one candidate page and the area of influence of the page; and

determining, by the computing system, that a geographic reach category for the candidate page matches a geographic reach category for the page.

10. The computer-implemented method of claim 9, wherein the geographic reach category categorizes a page as having a local, regional, or country-wide area of influence.

11. A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform;

determining respective geographic locations of a set of users associated with a page that is accessible through a social network;

generating at least one centroid for the page based at least in part on the respective geographic locations of the set of users;

determining at least one area of influence of the page based at least in part on the centroid; and

determining at least one page recommendation to be presented to one or more users in the set of users based at least in part on the area of influence of the page.

12. The system of claim 11, wherein determining the respective geographic locations corresponding to the set of users further causes the system to perform:

determining the geographic location of a user based on an address referenced in a social network profile of the user;

determining the geographic location of the user based on a centroid of geographic locations that correspond to check-ins performed by the user through the social network;

or

determining the geographic location of the user based on a centroid of geographic locations that correspond to social connections of the user in the social network.

13. The system of claim 11, wherein the respective geographic locations of the set of users are each represented as latitude-longitude coordinates, and wherein generating at least one centroid for the page further causes the system to perform:

determining a mean of the respective latitude-longitude coordinates corresponding to each user in the set of users; and

determining the centroid for the page based on the mean.

14. The system of claim 11, wherein generating at least one centroid for the page further causes the system to perform:

determining that a number of the users associated with the page satisfy a large page threshold;

determining a sample of the set of users;

determining a mean of the respective latitude-longitude coordinates corresponding to each user in the sample; and

determining the centroid for the page based on the mean.

15. The system of claim 11, wherein generating at least one centroid for the page further causes the system to perform:

determining that a number of the users associated with the page satisfy a small page threshold;

generating a preliminary centroid for the page using a first sample of the set of users;

determining a second sample of users by discarding at least one user from the first sample having a geographic distance from the preliminary centroid that satisfies a threshold number of standard deviations; and

generating the centroid for the page using the second sample of the set of users.

16. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:

determining respective geographic locations of a set of users associated with a page that is accessible through a social network;

generating at least one centroid for the page based at least in part on the respective geographic locations of the set of users;

determining at least one area of influence of the page based at least in part on the centroid; and

determining at least one page recommendation to be presented to one or more users in the set of users based at least in part on the area of influence of the page.

17. The non-transitory computer-readable storage medium of claim 16, wherein determining the respective geographic locations corresponding to the set of users further causes the computing system to perform:

determining the geographic location of a user based on an address referenced in a social network profile of the user;

determining the geographic location of the user based on a centroid of geographic locations that correspond to check-ins performed by the user through the social network;

or

determining the geographic location of the user based on a centroid of geographic locations that correspond to social connections of the user in the social network.

18. The non-transitory computer-readable storage medium of claim 16, wherein the respective geographic locations of the set of users are each represented as latitude-longitude coordinates, and wherein generating at least one centroid for the page further causes the computing system to perform:

determining a mean of the respective latitude-longitude coordinates corresponding to each user in the set of users; and

determining the centroid for the page based on the mean.

19. The non-transitory computer-readable storage medium of claim 16, wherein generating at least one centroid for the page further causes the computing system to perform:

determining that a number of the users associated with the page satisfy a large page threshold;

determining a sample of the set of users;

determining a mean of the respective latitude-longitude coordinates corresponding to each user in the sample; and

determining the centroid for the page based on the mean.

20. The non-transitory computer-readable storage medium of claim 16, wherein generating at least one centroid for the page further causes the computing system to perform:

determining that a number of the users associated with the page satisfy a small page threshold;

generating a preliminary centroid for the page using a first sample of the set of users;

determining a second sample of users by discarding at least one user from the first sample having a geographic distance from the preliminary centroid that satisfies a threshold number of standard deviations; and

generating the centroid for the page using the second sample of the set of users.