Selecting users to receive a recommendation to establish connection to an object in a social networking system

• US 10,210,458 B2
• Filed: 11/19/2013
• Issued: 02/19/2019
• Est. Priority Date: 11/19/2013
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Chakrabarti, Deepayan
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): Seck, Ababacar
• Application Number:
  US14/083,582
• Publication Number:
  US 20150142721A1
• Time in Patent Office: 1,918 Days
• Field of Search: 706 52
• CPC Class Codes: G06N 7/00 Computing arrangements based on specific mathematical models
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A social networking system identifies users to receive a recommendation to establish a connection to an object maintained by the social networking system. The social networking system determines one or more classifiers identifying attributes of users to receive the recommendation based on attributes of users connected to the object and additional users connected to those users. The attributes of an additional user may be weighted by a factor that provides a measure of the overlap between the attributes of the additional user and a user connected to the object.

Claims

1. A method comprising:

identifying a brand page within a social networking system that is maintained by the social networking system and is established by an entity, the brand page having less than a threshold number of connections to it by users of the social networking system, wherein connections to the brand page result in users receiving within the social networking system content posted to the brand page by the entity over a period of time;

identifying a plurality of users of the social networking system connected to the brand page;

responsive to identifying the users connected to the brand page, for each user;

identifying one or more additional users of the social networking system that are connected to the user within the social networking system,

retrieving information describing one or more attributes of the user connected to the brand page, and

retrieving information describing one or more attributes associated with the one or more additional users,

for each of the one or more additional users;

determining a relationship factor between the user connected to the brand page and an additional user connected to the user, the determined relationship factor describing a number of attributes of the user connected to the brand page matching a number of attributes of the additional user,

weighting the one or more attributes of the additional user based on the relationship factor, and

selecting at least one of the one or more weighted attributes as classifiers for the brand page based on the weighting;

identifying one or more of the additional users to receive a recommendation to establish a connection with the brand page based at least in part on the determined relationship factor having at least a threshold value;

sending the recommendation to the one or more identified users;

receiving, by the social networking system, a response to the recommendation from at least one of the plurality of identified users requesting to establish a connection to the brand page, that was recommended;

connecting the responding user to the brand page by forming an edge in the social networking system between the responding user and the brand page, the edge representing an interaction between the responding user and the brand page, the edge stored by the social networking system in an edge store; and

based on the edge stored within the social networking system, sending by the social networking system to the responding user a content posted to the brand page over a period of time.

2. The method of claim 1, wherein the one or more of the additional users to receive the recommendation to establish the connection with the brand page comprise one or more additional users having a determined value having at least a threshold value.

3. The method of claim 1, further comprising:

determining one or more attributes associated with users of the social networking system having a threshold likelihood of having an interest in the brand page.

4. The method of claim 3, further comprising:

identifying one or more users of the social networking system associated with at least a threshold number of the determined one or more attributes.

5. The method of claim 3, further comprising:

identifying one or more users of the social networking system associated with at least a threshold percentage of attributes matching the determined one or more attributes.

6. The method of claim 3, wherein determining the one or more attributes associated with users of the social networking system having the threshold likelihood of having the interest in the brand page comprises:

determining scores for each attribute associated with at least one additional user, a score for an attribute based at least in part on the weight associated with the attribute; and

selecting attributes associated with the one or more additional users based at least in part on the determined scores.

7. The method of claim 3, wherein determining the one or more attributes associated with users of the social networking system having the threshold likelihood of having the interest in the brand page comprises:

receiving responses to the recommendations from a set of the one or more identified users;

modifying values describing the number of attributes associated with the one or more users from which responses were received matching attributes associated with the user based at least in part on the received responses;

determining scores for each attribute associated with at least one additional user, a score for an attribute based at least in part on a value associated with a user associated with the attribute; and

selecting attributes associated with one or more additional users based at least in part on the determined scores.

8. A method comprising:

identifying a page within a social networking system that is maintained by the social networking system and is established by an entity, the page having less than a threshold number of connections to it by users of the social networking system, wherein connections to the page result in users receiving within the social networking system content posted to the page by the entity over a period of time;

identifying a plurality of users of the social networking system connected to the page;

responsive to identifying the users connected to the page, for each user;

identifying one or more additional users of the social networking system connected to the user,

retrieving information describing one or more attributes of the user connected to the page, and

retrieving information describing one or more attributes associated with the one or more additional users;

identifying one or more attributes associated with users of the social networking system, the users having an interest in the page based at least in part on the one or more attributes of the user connected to the page matching one of the one or more attributes of the additional users;

weighting the one or more attributes of the additional user based on the relationship factor;

selecting at least one of the one or more weighted attributes as classifiers for the page based on the weighting;

identifying one or more users of the additional users connected to the user having one or more of the identified one or more attributes to receive a recommendation associated with the page;

sending the recommendation associated with the page to the identified one or more users;

receiving, by the social networking system, a response to the recommendation from at least one of the plurality of identified users requesting to establish a connection to the page, that was recommended;

connecting the responding user to the page by forming an edge in the social networking system between the responding user and the page, the edge representing an interaction between the responding user and the page, the edge stored by the social networking system in an edge store; and

based on the edge stored within the social networking system, sending by the social networking system to the responding user a content posted to the page over a period of time.

9. The method of claim 8, wherein identifying one or more attributes associated with users of the social networking system having the interest in the page based at least in part on the one or more attributes of the user connected to the page and the one or more attributes of the additional users comprises:

determining a value for each of the one or more additional users, the value for an additional user describing an amount of overlap between a number of attributes associated with the user connected to the page and an additional user connected to the user.

10. The method of claim 9, wherein identifying one or more users of the additional users connected to the user having one or more of the identified one or more attributes to receive a recommendation associated with the page comprises:

identifying one or more additional users associated with a value having at least a threshold value.

11. The method of claim 9, wherein identifying one or more attributes associated with users of the social networking system having the interest in the page comprises:

determining scores for each attribute associated with at least one additional user, a score for an attribute based at least in part on the weight associated with the attribute; and

selecting attributes associated with one or more additional users based at least in part on the determined scores.

12. The method of claim 9, wherein identifying one or more attributes associated with users of the social networking system having the interest the page comprises:

receiving responses to the recommendations from a set of the one or more identified users;

modifying values describing the number of attributes associated with the one or more users from which responses were received matching attributes associated with the user based at least in part on the received responses;

determining scores for each attribute associated with at least one additional user, a score for an attribute based at least in part on a value associated with a user associated with the attribute; and

selecting attributes associated with one or more additional users based at least in part on the determined scores.

13. The method of claim 8, wherein identifying one or more users of the additional users connected to the user having one or more of the identified one or more attributes to receive a recommendation associated with the page comprises:

identifying one or more additional users associated with at least a threshold number of the identified one or more attributes.

14. The method of claim 8, wherein identifying one or more users of the additional users connected to the user having one or more of the identified one or more attributes to receive a recommendation associated with the page comprises:

identifying one or more additional users associated with at least a threshold percentage of attributes matching the identified one or more attributes.

15. The method of claim 8, wherein the page is connected to less than a threshold number of users of the social networking system.

16. A system comprising:

a processor; and

a computer-readable storage medium coupled to the processor, the computer-readable storage medium having instructions encoded thereon that, when executed by the processor, cause the processor to;

identify a brand page within a social networking system that is maintained by the social networking system and is established by an entity, the brand page having less than a threshold number of connections to it by users of the social networking system, wherein connections to the brand page result in users receiving within the social networking system content posted to the brand page by the entity over a period of time,

identify a plurality of users of the social networking system connected to the brand page,

responsive to identifying the users connected to the brand page, for each user;

identify one or more additional users of the social networking system that are connected to the user within the social networking system,

retrieve information describing one or more attributes of the user connected to the brand page,

retrieve information describing one or more attributes associated with the one or more additional users, and

for each of the one or more additional users,

determine a relationship factor between the user connected to the brand page and an additional user connected to the user, the determined relationship factor describing a number of attributes of the user connected to the brand page matching a number of attributes of additional user,

weighting the one or more attributes of the additional user based on the relationship factor, and

selecting at least one of the one or more weighted attributes as classifiers for the brand page based on the weighting;

identify one or more of the additional users to receive a recommendation to establish a connection with the brand page based at least in part on the determined relationship factor having at a threshold value;

send the recommendation to the one or more identified users;

receive, by the social networking system, a response to the recommendation from at least one of the plurality of identified users requesting to establish a connection to the brand page, that was recommended;

connect the responding user to the brand page by forming an edge in the social networking system between the responding user and the brand page, the edge representing an interaction between the responding user and the brand page, the edge stored by the social networking system in an edge store; and

based on the edge stored within the social networking system, send by the social networking system to the responding user a content posted to the brand page over a period of time.

17. The system of claim 16, wherein the computer-readable storage medium further has instructions encoded thereon that, when executed by the processor, cause the processor to:

determine one or more attributes associated with users of the social networking system having a threshold likelihood of having an interest in the brand page.

18. The system of claim 17, wherein the instructions that cause the processor to determine one or more attributes associated with users of the social networking system having the threshold likelihood of having an interest in the page comprises instructions that, when executed by the processor, cause the processor to:

determine scores for each attribute associated with at least one additional user, a score for an attribute based at least in part on the weight associated with the attribute; and

select attributes associated with one or more additional users based at least in part on the determined scores.