Generating event suggestions for users from social information

• US 10,402,426 B2
• Filed: 09/26/2012
• Issued: 09/03/2019
• Est. Priority Date: 09/26/2012
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Baldwin, Robert Michael, Bridge, Henry, Aziz, Omid, Naquin, Devin
• Primary Examiner(s): Mamillapalli, Pavan
• Application Number:
  US13/627,774
• Publication Number:
  US 20140089320A1
• Time in Patent Office: 2,533 Days
• Field of Search: 707736, 707748
• CPC Class Codes: G06F 16/284 Relational databases
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A social networking system suggests events for a target user based on stored data in the social networking system related to the target user and to events. The social networking system may suggest events based on the target user'"'"'s affinity for, connections with, or interactions with objects in the social networking system connected to or otherwise associated with the events. For example, an event is suggested to a target user if users connected to the target user already accepted an invitation to the event. As another example, an event organized by a particular entity is suggested to the target user because of interactions between the target user and other content provided by the entity. Invitations to suggested events may be presented to the target user via a client device, allowing the target user to easily join a suggested event.

Claims

1. A computer-implemented method comprising:

accessing user profile information in a social networking system containing information about a target user, wherein the information comprises information relating to the target user'"'"'s history of attending events;

retrieving data stored in the social networking system related to a plurality of events, each event associated with at least one of a time, a location, and a description;

selecting one or more candidate events based on the user profile information relating to the target user'"'"'s history of attending events and the data related to the plurality of events;

generating, by a processor, a candidate event relevance score for each candidate event based on the user profile information including the target user'"'"'s history of attending events and the data associated with the candidate event, the candidate event relevance score associated with each candidate event comprising an estimate of a probability that the target user will attend the candidate event responsive to a suggestion;

selecting an event from the candidate events based on the candidate event relevance scores; and

suggesting the selected event to the target user by presenting it to the user in a user interface of the social networking system.

2. The computer-implemented method of claim 1, wherein the relevance score associated with each candidate event is based in part on an affinity between the target user and the candidate event.

3. The computer-implemented method of claim 2, wherein the relevance score associated with each candidate event is further based in part on one or more of:

a location associated with the candidate event, a location associated with the target user, a type associated with the candidate event and one or more types of events previously attended by the target user.

4. The computer-implemented method of claim 3, wherein the probability of the target user attending the candidate event is determined at least in part by a comparison between characteristics of the candidate event and characteristics of one or more events previously attended by the target user.

5. The computer-implemented method of claim 1, wherein generating a relevance score associated with each candidate event based on the user profile information and the data associated with the candidate event comprises applying a machine-learned model to the user profile information and to the data associated with the candidate event.

6. The computer-implemented method of claim 5, wherein the machine learned model is trained using historical event data comprising one or more of:

data describing characteristics of past events, data identifying responses from users that received an invitation to at least one of the past events.

7. The computer-implemented method of claim 1, wherein selecting one or more candidate events based on the user profile information and data related to the plurality of events comprises:

selecting an event connected to an object in the social networking system for which the target user has an affinity score equaling or exceeding a threshold value.

8. The computer-implemented method of claim 1, wherein selecting one or more candidate events based on the user profile information and data related to the plurality of events comprises:

selecting an event associated with a location that is within a specified distance of a location associated with the target user.

9. The computer-implemented method of claim 1, wherein selecting one or more candidate events based on the user profile information and data related to the plurality of events comprises:

selecting an event associated with an object that is associated with an additional object with which the target user interacted.

10. The computer-implemented method of claim 9, wherein the additional object comprises media content.

11. The computer-implemented method of claim 1, wherein selecting one or more candidate events based on the user profile information and data related to the plurality of events comprises:

selecting an event associated with a user organizing the event that is connected to an object stored in the social networking system to which the target user is connected.

12. The computer-implemented method of claim 1, wherein selecting one or more candidate events based on the user profile information and data related to the plurality of events comprises:

selecting an event having one or more invited users having a connection to the target user.

13. The computer-implemented method of claim 1, wherein selecting one or more candidate events based on the user profile information and data related to the plurality of events comprises:

selecting an event having one or more invited users, the invited users associated with user profile information having characteristics similar to characteristics of the user profile information of the target user.

14. The computer-implemented method of claim 1, wherein selecting one or more candidate events based on the user profile information and data related to the plurality of events comprises:

selecting an event having characteristics similar to characteristics of additional events that the target user previously attended.

15. A computer-implemented method comprising:

accessing user profile information in a social networking system containing information about a target user, wherein the information comprises information relating to the target user'"'"'s history of attending events;

retrieving data stored in the social networking system describing information about a plurality of events, each event associated with at least one of a time, a location and a description;

selecting one or more candidate events based on the user profile information relating to the target user'"'"'s history of attending events and the information about each of the plurality of events;

generating, by a processor, a candidate event relevance score for each candidate event based on the user profile information including the target user'"'"'s history of attending events and the data describing information about the one or more candidate events, the candidate event relevance score based in part on an affinity between the target user and the candidate event;

selecting one or more suggested events from the candidate events based on the candidate event relevance scores; and

presenting a description of the one or more suggested events to the target user in a user interface of the social networking system.

16. The computer-implemented method of claim 15, wherein a relevance score associated with a candidate event is based in part on information used to select the candidate event.

17. The computer-implemented method of claim 15, wherein information used to select the candidate event includes one or more selected from a group consisting of:

a distance between a location associated with the candidate event and a location associated with the target user, users connected to the candidate event and connected to the target user, characteristics of users attending the candidate event similar to characteristics of the target user, a type associated with the candidate event and keywords associated with the candidate event.

18. The computer-implemented method of claim 15, wherein presenting the description of the one or more suggested events to the target user comprises:

presenting a message describing selection of a suggested event along with a description of the suggested event.