Recommending additional users for an event using a social networking system

Patent metadata

Field	Value
Publication number	US-9576325-B2
Application number	US-201213544197-A
Country	US
Kind code	B2
Filing date	Jul 9, 2012
Priority date	Jul 9, 2012
Publication date	Feb 21, 2017
Grant date	Feb 21, 2017

Abstract

Social networking system users may create events where a group of other users invited to the event meet at a specified time and location. While an inviting user initially specifies the group of users to invite to the event, the social networking system suggests additional users to invite to the event. The social networking system suggests additional users based on a prediction that the users would attend the event if invited. Various factors may be used to make the prediction, such as an affinity between the inviting user and the other users, the availability of the other users at the time of the event and/or the proximity of the other users to the location of the event. Invitations to the suggested additional users may be automatically sent or sent to a set of the additional users selected by the inviting user.

First claim

What is claimed is:

1. A method comprising:
receiving information about an event from an inviting user of a social networking system, the information including one or more of a location, a time, and one or more users of the social networking system who are associated with the event;
accessing user profiles of social networking system users connected to the inviting user and not already associated with the event;
selecting a set of candidate users from the social networking system users connected to the inviting user and not already associated with the event;
for each candidate user, generating a prediction of whether a suggestion to the inviting user to invite a candidate user to the event would lead to the candidate user joining the event based on both (1) an affinity for the inviting user by the candidate user and (2) a history of the candidate user attending events that the inviting user attended, the affinity computed based on scores for edges stored in the social networking system indicating connections between the user and other objects or other users, and based on actions performed by the inviting user in the social networking system with the candidate user;
selecting one or more candidate users from the set based on the prediction by:
assigning a social value to each candidate user from the set;
determining a probability that each candidate user from the set will join the event based on the prediction;
determining an expected value for each candidate user from the set, wherein the expected value of a candidate user is determined based on the candidate user's social value and a probability that the candidate user will join the event;
selecting one or more candidate users having highest expected values; and
sending a suggestion to the inviting user to send an invitation for the event to the selected one or more candidate users.

2. The method of claim 1 , wherein selecting the set of candidate users from the social networking system users connected to the inviting user and not already associated with the event comprises:
selecting users connected to the inviting user and not identified by the information about the event having a location in their user profiles within a specified distance of the location included in the information about the event.

3. The method of claim 1 , wherein selecting a set of candidate users from the social networking system users connected to the inviting user and not already associated with the event comprises:
selecting users having a location in their user profiles within a specified distance of the location included in the information about the event and an availability at the time included in the information about the event.

4. The method of claim 1 , wherein selecting one or more candidate users from the set based on the prediction of whether the suggestion to invite each of the candidate users would lead to the candidate user joining the event comprises:
determining likelihood values indicating whether candidate users would join the event further based on an affinity for the inviting user by a candidate user and a history of the candidate user attending events that the inviting user attended; and
selecting one or more candidate users having highest likelihood value of joining the event.

5. The method of claim 1 , wherein selecting one or more candidate users from the set based on the prediction of whether the suggestion to invite each of the candidate users would lead to the candidate user joining the event comprises:
determining likelihood values indicating whether candidate users would join the event further based on the affinity for the inviting user by a candidate user and a history of the user from the subset attending events that the inviting user attended; and
selecting one or more candidate users having a likelihood value of joining the event equaling or exceeding a threshold likelihood value.

6. The method of claim 1 , wherein selecting one or more candidate users from the set based on the prediction of whether the suggestion to invite each of the candidate users would lead to the candidate user joining the event comprises:
determining likelihood values indicating whether candidate users would join the event further based on an affinity for the inviting user by a candidate user, a history of the candidate user attending events that the inviting user attended and the candidate user's location at the time included in the information about the event; and
selecting one or more candidate users having a likelihood value of joining the event equaling or exceeding a threshold likelihood value.

7. The method of claim 6 , wherein the candidate user's location at the time included in the information about the event is determined from one or more responses to additional events associated with the location identified by the invitation received from the candidate user.

8. The method of claim 1 , further comprising:
receiving a response from the inviting user identifying a candidate user to receive an invitation, sending a notification of the event to an electronic device associated with the identified user.

9. The method of claim 1 , wherein sending the suggestion to the inviting user to send the invitation for the event to the selected one or more candidate users comprises:
including a story identifying the selected one or more candidate users in a news feed sent to an electronic device associated with the inviting user.

10. The method of claim 1 , wherein sending the suggestion to the inviting user to send the invitation for the event to the selected one or more candidate users comprises:
sending a notification identifying the selected one or more candidate users to an electronic device associated with the inviting user.

11. The method of claim 1 , wherein the one or more users of the social networking system who are associated with the event comprise one or more users of the social networking system invited to the event.

12. The method of claim 1 , wherein the one or more users of the social networking system who are associated with the event comprise one or more users of the social networking system attending the event.

13. The method of claim 1 , wherein the prediction of whether the suggestion to invite a candidate user would lead to the candidate user joining the event is further based on the probability of the inviting user inviting the candidate user in response to the inviting user being presented with the suggestion.

14. A method comprising:
receiving information about an event from an inviting user of a social networking system, the information including one or more of a location, a time, and one or more users of the social networking system who are associated with the event;
accessing user profiles of social networking system users connected to the inviting user and not already associated with the event;
selecting a set of candidate users from the social networking system users connected to the inviting user and not already associated with the event;
determining a likelihood value that each of the candidate users from the set would join the event if invited, the likelihood value of a candidate user joining the event based on both (1) an affinity for the inviting user by the candidate user and (2) a history of each of the candidate users attending events that the inviting user attended, the affinity computed based on scores for edges stored in the social networking system indicating connections between the user and other objects or other users, and based on actions performed by the inviting user in the social networking system with the candidate user;
selecting one

Assignees

• Narayanan Srinivas P
• Shaffer Justin Alexander
• Hui Daniel Jeng-Ping
• Bayer Ross David
• Facebook Inc

Inventors

• Narayanan Srinivas P
• Shaffer Justin Alexander
• Hui Daniel Jeng-Ping
• Bayer Ross David

Classifications

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06Q10/10

  Office automation; Time management · CPC title

• G06Q10/06 Primary

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06Q10/1093 Primary

  Calendar-based scheduling for persons or groups · CPC title