Optimizing messages to users of a social network using a message that includes a user's performance of a desired activity associated with a link included in the message

Patent metadata

Field	Value
Publication number	US-9363223-B2
Application number	US-201414547066-A
Country	US
Kind code	B2
Filing date	Nov 18, 2014
Priority date	May 31, 2012
Publication date	Jun 7, 2016
Grant date	Jun 7, 2016

Abstract

Techniques to optimize messages sent to a user of a social networking system. In one embodiment, information about the user may be collected by the social networking system. The information may be applied to train a model for determining likelihood of a desired action by the user in response to candidate messages that may be provided for the user. The social networking system may provide to the user a message from the candidate messages with a selected likelihood of causing the desired action.

First claim

What is claimed is:

1. A method comprising:
logging one or more user activities associated with a user of an online system, the user activities including the user's responses to one or more messages sent to the user, time that the user is active on the online system, and a type of activity performed by the user on the online system;
generating at least one message to send to the user when the logged activities indicate that the user's last engagement with the online system occurred more than a predetermined time interval ago, the at least one message including a link associated with a desired activity;
applying attributes of the one or more messages sent to the user and the logged activities to a message response prediction model for the user, the message response prediction model determining a prediction of whether the user's response to receiving the at least one message will include the user's performance of the desired activity associated with the link included in the at least one message; and
determining whether to send the generated message based on the prediction, the message being sent when the prediction indicates more than a threshold likelihood of the user's response including the user's performance of the desired activity.

2. The method of claim 1 , wherein user activities associated with a user of an online system further include activities performed on the online system by other users connected to the user.

3. The method of claim 1 , further comprising:
maintaining a user profile including characteristics of the user; and
wherein the message prediction model uses characteristics of the user to output the prediction of whether the user's response to the one or more candidate messages will elicit the specified user response.

4. The method of claim 3 , wherein characteristics of the user include at least one of user demographics, behavior of the user, and behavior of friends of the user.

5. The method of claim 4 , wherein the behavior of the user includes at least one of date and time of activities of the user, types of activities of the user, extent of activities of the user, and responses of the user to previous messages provided by the online system.

6. The method of claim 4 , wherein the behavior of friends of the user includes at least one of date and time of activities of the friends, types of activities of the friends, and extent of activities of the friends.

7. The method of claim 3 , wherein characteristics of the user are based on user activities that occurred during a selected period of time.

8. The method of claim 1 , wherein attributes of the candidate message comprise a type of content to be included in the message.

9. The method of claim 1 , further comprising determining a likelihood that the user will have the specified user response to the candidate message based at least in part on applying at least one of a day of the week the message is to be sent, and a time the message is to be sent by the online system to the user to the message response prediction model.

10. The method of claim 1 , further comprising updating the message response prediction model for the user with changed information about the user.

11. The method of claim 10 , wherein the updating is performed periodically during a selected interval.

12. The method of claim 10 , wherein the updating is performed continuously during a selected interval.

13. The method of claim 1 , further comprising updating the message response prediction model for the user with action taken by the user in response to the message.

14. The method of claim 1 , further comprising associating each of a plurality of message predictions models with each of a plurality of users of the online system.

15. The method of claim 1 , further comprising generating a message response prediction model for a group of users, including the user, of the online system.

16. The method of claim 1 , further comprising training the message response prediction model using information from the user profile and response information about the user's responses to messages sent by the online system.

17. A non-transitory computer storage medium storing computer-executable instructions that, when executed by a processor, cause a computer system to:
log one or more user activities associated with a user of an online system, the user activities including the user's responses to one or more messages sent to the user, time that the user is active on the online system, and a type of activity performed by the user on the online system;
generate at least one message to send to the user when the logged activities indicate that the user's last engagement with the online system occurred more than a predetermined time interval ago, the at least one message including a link associated with a desired activity;
apply attributes of the one or more messages sent to the user and the logged activities to a message response prediction model for the user, the message response prediction model determine a prediction of whether the user's response to receiving the at least one message will include the user's performance of the desired activity associated with the link included in the at least one message; and
determine whether to send the generated message based on the prediction, the message being sent when the prediction indicates more than a threshold likelihood of the user's response including the user's performance of the desired activity.

18. A system comprising:
at least one processor; and
a memory storing instructions configured to instruct the at least one processor to:
log one or more user activities associated with a user of an online system, the user activities including the user's responses to one or more messages sent to the user, time that the user is active on the online system, and a type of activity performed by the user on the online system;
generate at least one message to send to the user when the logged activities indicate that the user's last engagement with the online system occurred more than a predetermined time interval ago, the at least one message including a link associated with a desired activity;

apply attributes of the one or more messages sent to the user and the logged activities to a message response prediction model for the user, the message response prediction model determining a prediction of whether the user's response to receiving the at least on message will include the user's performance of the desired activity associated with the link included in the at least one message; and
determine whether to send the generated message based on the prediction, the message being sent when the prediction indicates more than a threshold likelihood of the user's response including the user's performance of the desired activity.

Assignees

• Facebook Inc

Inventors

• Arquette Lex
• Chen David Y
• Grewal Emily
• Moreno Denise
• Ratiu Florin
• Shi Yanxin
• Sidhu Kiranjit Singh
• Weng Ching-Chih
• Yang Huan

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06Q30/02 Primary

  Marketing; Price estimation or determination; Fundraising · CPC title

• H04L51/32 Primary

  Electricity · mapped topic

• G06N5/048

  Fuzzy inferencing · CPC title

• H04L51/52 Primary

  for supporting social networking services · CPC title