Sending Notifications About Other Users With Whom A User is Likely to Interact

• US 20130046770A1
• Filed: 08/19/2011
• Published: 02/21/2013
• Est. Priority Date: 08/19/2011
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Tseng, Erick
• Granted Patent: US 8,838,581 B2
• Time in Patent Office: Days
• US Class Current: 707/748
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: H04L 51/52 for supporting social networking services

Abstract

To provide more contextually and temporally relevant information to its users, a social networking system may surface relevant information about a target user with whom an recipient user is likely to interact. The social networking system predicts whether the recipient user is likely to be in contact with a target user, either currently or in the near future. If contact is predicted, the system determines information about the target user that that the recipient user may find of interest for their interaction. To determine what information may be of interest, the system determines a relevance score for information items about that target user. The system can then use the relevance scores to decide whether and which information items to surface to the recipient user, e.g., in the form of notifications.

Claims

1. A method comprising:

maintaining information for a plurality of users of a social networking system, the plurality of users comprising a recipient user and a target user;

predicting an interaction between the recipient user and the target user;

determining a relevance score for each of a plurality of information items, the information items containing information about the target user, wherein a higher relevance score indicates that the information item will assist the recipient user in the interaction with the target user;

ranking the information items according to their relevance scores; and

selecting one or more information items based on the ranking to provide to the recipient user regarding the target user.

2. The method of claim 1, wherein predicting the interaction between the recipient user and the target user comprises:

receiving a current physical location of the recipient user and the target user; and

determining that the recipient user'"'"'s current physical location is within a distance of the target user'"'"'s current physical location.

3. The method of claim 2, wherein the current physical location for a user of the social networking system is received from a user device associated with the user.

4. The method of claim 1, wherein predicting the interaction between the recipient user and the target user comprises:

storing in the social networking system a scheduled activity for the recipient user and the target user, the scheduled activity comprising a starting time; and

determining that a current time is in close proximity to the starting time.

5. The method of claim 1, wherein predicting the interaction between the recipient user and the target user comprises:

storing in the social networking system a scheduled activity for the recipient user comprising a starting time and an activity location;

receiving a current physical location of the target user;

determining that the current physical location of the target user is within a distance of the activity location; and

determining that a current time is in close proximity to the starting time.

6. The method of claim 1, wherein predicting the interaction between the recipient user and the target user comprises:

storing in the social networking system a scheduled activity for the target user comprising a starting time and an activity location;

receiving a current physical location of the recipient user;

determining that the current physical location of the recipient user is within a distance of the activity location; and

determining that a current time is in close proximity to the starting time.

7. The method of claim 1, wherein the relevance score for the information item is determined based on an occurrence type value indicating a general consensus by the social networking system regarding a level of interest in information items of a type.

8. The method of claim 1, wherein the relevance score for the information item is determined based on an affinity value indicating the target user'"'"'s interest in the information item.

9. The method of claim 1, wherein the relevance score for the information item is determined based on an inferred affinity value indicating a commonality of interest in the information item between the target user and the recipient user.

10. The method of claim 9, wherein the inferred affinity value is weighted based on a degree of separation between the recipient user and the target user in the social networking system.

11. The method of claim 1, further comprising filtering one of the information items from the selecting responsive to a determination that the recipient user is already aware of that information item.

12. The method of claim 1, further comprising:

transmitting the selected information items to a user device for display to the recipient user.

13. A method comprising:

maintaining information for a plurality of users of a social networking system, the plurality of users comprising an recipient user and a target user;

predicting an interaction between the recipient user and the target user;

responsive to the predicting, selecting an information item about the target user based on an recipient user'"'"'s expected interest in the selected information item; and

sending a notification to a device associated with the recipient user, the notification comprising the selected information item.

14. The method of claim 13, comprising determining the recipient user'"'"'s expected interest in the selected information item by determining a relevance score for the information item.

15. The method of claim 14, wherein the relevance score for the information item is determined based on an occurrence type value indicating a general consensus by the social networking system regarding a level of interest in information items of a type.

16. The method of claim 14, wherein the relevance score for the information item is determined based on an affinity value indicating the target user'"'"'s interest in the information item.

17. The method of claim 14, wherein the relevance score for the information item is determined based on an inferred affinity value indicating a commonality of interest in the information item between the target user and the recipient user.

18. The method of claim 17, wherein the inferred affinity value is weighted based on a degree of separation between the recipient user and the target user in the social networking system.

19. The method of claim 13, further comprising filtering one of the information items from the selecting responsive to a determination that the recipient user is already aware of that information item.