SELECTING PREVIOUSLY-PRESENTED CONTENT ITEMS FOR PRESENTATION TO USERS OF A SOCIAL NETWORKING SYSTEM

• US 20150286662A1
• Filed: 04/02/2014
• Published: 10/08/2015
• Est. Priority Date: 04/02/2014
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Marra, Gregory Matthew, Zhang, Li, Guo, Yi, Ruan, Chao
• Granted Patent: US 10,191,927 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2228 Indexing structures
• CPC Class Codes: G06F 16/24578 using ranking

Abstract

A social networking system selects content items previously presented to a user for presentation to the user along with content items that were not previously presented. The social networking system selects candidate content items as previously-presented content items satisfying one or more criteria. One or more indices each associated with one or more attributes are generated that include candidate content items having attributes associated with an index. Candidate content items in an index are ranked based on a likelihood of the user interacting with the candidate content items in the index, and one or more candidate content items are selected from the index for presentation based on the ranking. The candidate content items selected from the index are presented to the user along with additional content items not previously-presented to the user.

Claims

1. A method comprising:

identifying a plurality of content items stored by a social networking system and previously presented to a user of the social networking system, each content item associated with a time when it was presented to the user;

selecting candidate content items from the plurality of content items;

generating one or more indices, each generated index associated with one or more candidate content items having one or more attributes associated with the index;

ranking the candidate content items in an index, the ranking based at least in part on an expected level of interaction by a viewing user with each candidate content item in the index;

selecting one or more candidate content items from the index based at least in part on the ranking; and

generating a feed of content including the selected one or more candidate content items from the set of candidate content items and additional content items for presentation to the viewing user.

2. The method of claim 1, wherein selecting candidate content items from the plurality of content items comprises:

selecting content items satisfying one or more criteria as candidate content items.

3. The method of claim 2, wherein the one or more criteria are selected from a group consisting of:

association with a topic, association with an event occurring within a threshold time from a current time, association with a recurring event, association with a specified time, and any combination thereof.

4. The method of claim 1, wherein the user is the viewing user.

5. The method of claim 1, wherein selecting candidate content items from the plurality of content items comprises:

applying one or more rules to the plurality of content items, the one or more rules excluding content items from the set of content items;

identifying a set of content items from the plurality of content items based at least in part on the one or more rules; and

selecting the candidate content items from the set of content items.

6. The method of claim 5, wherein the one or more rules are selected from a group consisting of:

a rule excluding content items associated with malicious content, a rule excluding content items associated with offensive content, a rule excluding content items associated with negative content, a rule excluding content items associated with one or more specified tags, a rule excluding content items associated with one or more specified users of the social networking system, a rule excluding content items associated with a specified ratio of types of interactions, and any combination thereof.

7. The method of claim 6, wherein the one or more specified users of the social networking system are selected from a group consisting of:

a user associated with a previously removed connection to the viewing user, a user that has not interacted with the social networking system within a threshold period of time, a user that is not currently associated with a user profile maintained by the social networking system, and any combination thereof.

8. The method of claim 1, wherein ranking the candidate content items in the index comprises:

determining values associated with each candidate content item in the index, a value representing a likelihood of the viewing user performing one or more types of interactions with a candidate content item in the index; and

ranking the candidate content items in the index based at least in part on the determined values.

9. The method of claim 8, wherein a type of interaction is selected from a group consisting of:

indicating a preference for the candidate content item in the set of candidate content items, sharing the candidate content item in the set of candidate content items with an additional user of the social networking system, and commenting on the candidate content item in the set of candidate content items.

10. The method of claim 8, wherein ranking the candidate content items in the index based at least in part on the determined values comprises:

modifying values associated with one or more of the candidate content items in the index based on one or more characteristics of the candidate content item; and

ranking the candidate content items in the index based at least in part on the modified values.

11. The method of claim 10, wherein a characteristic of the candidate content item is selected from a group consisting of:

an age of the candidate content item, a type of connection between the viewing user and a user associated with the candidate content item, and a time associated with presentation of the candidate content item.

12. The method of claim 8, wherein the ranking is further based at least in part on a number of content items presented to the viewing user more than once within a threshold time period.

13. The method of claim 1, wherein an attribute of a candidate content item included in the index is selected from a group consisting of:

an event associated with the viewing user, an event associated with an additional user connected to the viewing user, a recurring event, a topic, and a date.

14. A computer program product comprising a computer-readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to:

retrieve a plurality of content items stored by a social networking system and previously presented to a user of the social networking system, each content item associated with a time when it was presented to the user;

select candidate content items from the plurality of content items;

generate one or more indices each including one or more candidate content items having one or more attributes associated with the index;

rank the candidate content items in an index, the ranking based at least in part on an expected level of interaction by a viewing user with each candidate content item in the index;

select one or more candidate content items from the index based at least in part on the ranking; and

generate a feed of content including the selected one or more candidate content items from the set of candidate content items and additional content items for presentation to the viewing user.

15. The computer program product of claim 14, wherein the instructions to select candidate content items from the plurality of content items comprise instructions to:

select content items satisfying one or more criteria as candidate content items.

16. The computer program product of claim 15, wherein the one or more criteria are selected from a group consisting of:

association with a topic, association with an event occurring within a threshold time from a current time, association with a recurring event, association with a specified time, and any combination thereof.

17. The computer program product of claim 14, wherein the instructions to rank the candidate content items in the index comprise instructions to:

determine values associated with each candidate content item in the index, a value representing a likelihood of the viewing user performing one or more types of interactions with a candidate content item in the index; and

rank the candidate content items in the index based at least in part on the determined values.

18. The computer program product of claim 17, wherein a type of interaction is selected from a group consisting of:

indicating a preference for the candidate content item in the set of candidate content items, sharing the candidate content item in the set of candidate content items with an additional user of the social networking system, and commenting on the candidate content item in the set of candidate content items.

19. The computer program product of claim 17, wherein the instructions to rank the candidate content items in the index based at least in part on the determined values comprise instructions to:

modify values associated with one or more of the candidate content items in the index based on one or more characteristics of the candidate content item; and

rank the candidate content items in the index based at least in part on the modified values.

20. The computer program product of claim 19, wherein a characteristic of the candidate content item is selected from a group consisting of:

an age of the candidate content item, a type of connection between the viewing user and a user associated with the candidate content item, and a time associated with presentation of the candidate content item.