SYSTEMS AND METHODS FOR COMMUNICATION CHANNEL RECOMMENDATIONS USING MACHINE LEARNING

• US 20190319900A1
• Filed: 04/16/2018
• Published: 10/17/2019
• Est. Priority Date: 04/16/2018
• Status: Active Grant

• Current Assignee: Fujifilm Business Innovation Corp. (Fujifilm Holdings Corporation)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: Marlow, Jennifer, Carter, Scott, Denoue, Laurent
• Granted Patent: US 11,228,542 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04L 12/185 with management of multicast group membership
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]

Abstract

Example implementations are directed to a method of controlling contributions to a communication stream. An example implementation includes detecting a request from a user to add a data item to a communication stream of a channel, analyzing the data item in view of the communication stream to determine a relevancy score for the data item; and providing a control interface for the request based on the relevancy score of the data item. For example, the control interface can include an audience report, a notification, a previous post link, an alternative channel recommendation, a private message invitation, or a proceed to post command.

Claims

1. A system comprising:

a memory;

a processor operatively coupled to the memory, the processor configured to;

detect a request from a user to send a data item to a group of recipients via a digital communication channel;

identify one or more alternative digital communication channels associated with two more users of the group;

analyze communication history of the user and the group of recipients to detect similar communications associated to the data item; and

provide a set of controls for the similar communications.

2. The system of claim 1, wherein the controls comprise at least one of identify the alternative digital communication channels, provide a list of subgroup of recipients for the similar communications, and suggest links to the similar communications.

3. The system of claim 1, wherein to analyze the communication history comprises at least one of context analysis, content analysis, and user analysis.

4. The system of claim 1, wherein to analyze the communication history further comprises to:

analyze the data item in view of the communication history to determine a relevancy score for each of the one or more alternative digital communication channels; and

suggest an alternative digital communication channels based on the relevancy score.

5. A non-transitory computer readable medium, comprising instructions that when execute by a processor, the instructions to:

detect a request from a user to send a data item to a group of recipients via a digital communication channel;

identify one or more alternative digital communication channels associated with two more users of the group;

analyze communication history of the user and the group of recipients to detect similar communications associated to the data item; and

provide a set of controls for the similar communications.

6. The non-transitory computer readable medium of claim 5, wherein the controls comprise at least one of identify the alternative digital communication channels, provide a list of subgroup of recipients for the similar communications, and suggest links to the similar communications.

7. The non-transitory computer readable medium of claim 5, wherein to analyze the communication history comprises at least one of context analysis, content analysis, and user analysis.

8. The non-transitory computer readable medium of claim 5, wherein to analyze the communication history further comprises to:

analyze the data item in view of the communication history to determine a relevancy score for each of the one or more alternative digital communication channels; and

suggest an alternative digital communication channels based on the relevancy score.

9. A method comprising:

detecting a request from a user to add a data item to a communication stream of a channel;

analyzing the data item in view of the communication stream to determine a relevancy score for the data item; and

providing a control interface for the request based on the relevancy score of the data item.

10. The method of claim 9, wherein, wherein the control interface comprises at least one of an audience report, a notification, a previous post link, an alternative channel recommendation, a private message invitation, and a proceed to post command.

11. The method of claim 9, wherein to determine the relevancy score for the data item is based at least on other content of the communication stream within a recent time period from the request.

12. The method of claim 11, wherein the relevancy score is further based on determining engagement of other users of the channel within a recent time period from the request.

13. The method of claim 11, wherein the relevancy score is further based at least on a context of the channel.

14. The method of claim 13, wherein the relevancy score is further based at least on other users of the channel within a recent time period from the request.

15. The method of claim 9, wherein the relevancy score is further based on determining engagement of other users of the channel within a recent time period from the request.

16. The method of claim 9, wherein the control interface comprises a duplication alert in response to the relevancy indicating the data item previously posted in the communication stream.

17. The method of claim 16, further comprising determining a content difference between the data item of the request and the data item of the previous post.

18. The method of claim 9, wherein the analyzing the data item in view of the communication stream further comprises:

identifying other user for the channel;

determining one or more alternative channels of the user comprising at least one of the other users; and

determining whether an alternative relevancy based on the one or more alternative channels is greater than the relevancy.

19. The method of claim 18, wherein in response to the alternative relevancy being greater than the relevancy, the control interface provides a command to redirect the request to add the data item to the one or more alternative channels.