Messaging system with multiple messaging channels

• US 9,203,796 B2
• Filed: 08/08/2011
• Issued: 12/01/2015
• Est. Priority Date: 11/12/2010
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Hsiao, Daniel, Seligstein, Joel Benjamin, Zuckerberg, Mark E., Lau, Kenneth M., Bayer, Ross David, Zhang, Zheng, Davenport, Benjamin Peter, Deng, Peter Xiu, Gertzfield, Ben, Zhang, Lucy Congyun, Perlow, Jonathan David
• Primary Examiner(s): Hwang, Joon H
• Assistant Examiner(s): ALRIYASHI, ABDULKADER MOHAMED
• Application Number:
  US13/205,194
• Publication Number:
  US 20120124146A1
• Time in Patent Office: 1,576 Days
• Field of Search: 709/206, 709220-222, 709227-229, 709/230, 709/232, 709/234, 709/238, 709/239, 709/241, 709/245, 709/249, 709/250, 706/12, 706/59
• US Class Current: 1/1
• CPC Class Codes: G06F 15/16 Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs coordinating program control therefor G06F9/52; in regulating and control system G05B
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: H04L 51/08 Annexed information, e.g. attachments
• CPC Class Codes: H04L 51/216 Handling conversation history, e.g. grouping of messages in sessions or threads
• CPC Class Codes: H04L 51/56 Unified messaging, e.g. interactions between e-mail, instant messaging or converged IP messaging [CPM]
• CPC Class Codes: H04L 69/14 Multichannel or multilink protocols

Abstract

A messaging system facilitates communication between users through various messaging channels. The messaging system supports multiple communication channels and includes a messaging module that automatically selects one or more of the messaging channels for delivering a message to a recipient of the message using, for example, a set of policy rules or a trained model. The messaging module may also provide, in a user interface for sending and receiving messages, a visual indication of the selected messaging channel to the sender of the message to provide the user with transparency about how the message will be delivered. Additionally, the message may be delivered via multiple messaging channels, where the messaging module may rescind messages from some of the messaging channels upon receiving a reply from the recipient of the message or other confirmation that the recipient has seen the message via one of the communication channels.

Claims

1. A computer-implemented method comprising:

sending a first message to a first message recipient via a plurality of messaging channels;

responsive to sending the first message via the plurality of messaging channels, receiving an indication of a messaging channel of the plurality of messaging channels preferred by the first message recipient for receiving the first message;

sending a second message to a second message recipient via the plurality of messaging channels;

responsive to sending the second message via the plurality of messaging channels, receiving an indication of a messaging channel of the plurality of messaging channels preferred by the second message recipient for receiving the second message;

generating training data based on the messaging channel preferred by the first message recipient and the messaging channel preferred by the second message recipient, the training data describing associations between at least one signal and the messaging channel preferred by the second message recipient and the messaging channel preferred by the first message recipient;

training a predictive model using the associations in the training data describing the associations between the at least one signal and the messaging channel preferred by the second message recipient and the messaging channel preferred by the first message recipient, the predictive model configured to output channel scores for the messaging channels as a function of the at least one signal, wherein the channel scores are indicative of user preferences for the messaging channels; and

storing the predictive model.

2. The method of claim 1, wherein the indication of the messaging channel of the plurality of messaging channels preferred by the first message recipient is a reply to the first message via the messaging channel.

3. The method of claim 1, wherein the indication of the messaging channel of the plurality of message channels preferred by the first message recipient is an indication that first message recipient read the first message using the messaging channel.

4. The method of claim 1, wherein the indication of the messaging channel of the plurality of message channels preferred by the first message recipient is a response to a question about the messaging channel preferred by the first message recipient.

5. The method of claim 1, further comprising:

receiving a new message addressed to a new recipient;

determining the channel scores for the plurality of messaging channels with the predictive model;

selecting one or more of the messaging channels for delivering the new message to the new recipient based at least in part on the determined scores; and

delivering the new message to the new recipient via the one or more selected messaging channels.

6. The method of claim 1, wherein the training data is stored in a co-occurrence table.

7. The method of claim 1, wherein the at least one signal comprises a past messaging activities signal.

8. The method of claim 1, wherein the at least one signal comprises a current status signal.

9. A non-transitory computer readable medium storing instructions, the instructions when executed by a processor cause the processor to implement operations of:

sending a first message to a first message recipient via a plurality of messaging channels;

responsive to sending the first message via the plurality of messaging channels, receiving an indication of a messaging channel of the plurality of messaging channels preferred by the first message recipient for receiving the first message;

sending a second message to a second message recipient via the plurality of messaging channels;

responsive to sending the second message via the plurality of messaging channels, receiving an indication of a messaging channel of the plurality of messaging channels preferred by the second message recipient for receiving the second message;

generating training data based on the messaging channel preferred by the first message recipient and the messaging channel preferred by the second message recipient, the training data describing associations between at least one signal and the messaging channel preferred by the second message recipient and the messaging channel preferred by the first message recipient;

training a predictive model using the associations in the training data describing the associations between the at least one signal and the messaging channel preferred by the second message recipient and the messaging channel preferred by the first message recipient, the predictive model configured to output channel scores for the messaging channels as a function of the at least one signal, wherein the channel scores are indicative of user preferences for the messaging channels; and

storing the predictive model.

10. The non-transitory computer readable medium of claim 9, wherein the indication of the messaging channel of the plurality of messaging channels preferred by the first message recipient is a reply to the first message via the messaging channel.

11. The non-transitory computer readable medium of claim 9, wherein the indication of the messaging channel of the plurality of message channels preferred by the first message recipient is an indication that first message recipient read the first message using the messaging channel.

12. The non-transitory computer readable medium of claim 9, wherein the indication of the messaging channel of the plurality of message channels preferred by the first message recipient is a response to a question about the messaging channel preferred by the first message recipient.

13. The non-transitory computer readable medium of claim 9, the operations further comprising operations of:

receiving a new message addressed to a new recipient;

determining the channel scores for the plurality of messaging channels with the predictive model;

selecting one or more of the messaging channels for delivering the new message to the new recipient based at least in part on the determined scores; and

delivering the new message to the new recipient via the one or more selected messaging channels.

14. The non-transitory computer readable medium of claim 9, wherein the training data is stored in a co-occurrence table.

15. The non-transitory computer readable medium of claim 9, wherein the at least one signal comprises a past messaging activities signal.

16. The non-transitory computer readable medium of claim 9, wherein the at least one signal comprises a current status signal.