Machine learning method of managing conversations in a messaging interface

• US 9,804,752 B1
• Filed: 06/27/2016
• Issued: 10/31/2017
• Est. Priority Date: 06/27/2016
• Status: Active Grant

• Current Assignee: Atlassian Pty Ltd (d/b/a Confluence) (Atlassian Corporation)
• Original Assignee: Atlassian Pty Ltd (d/b/a Confluence) (Atlassian Corporation)
• Inventors: Mall, Orpheus
• Primary Examiner(s): To, Jennifer
• Assistant Examiner(s): Burwell, Joseph R
• Application Number:
  US15/194,400
• Time in Patent Office: 491 Days
• CPC Class Codes: G06F 3/0484 for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]
• CPC Class Codes: H04L 51/212 using filtering or selective blocking
• CPC Class Codes: H04L 51/216 Handling conversation history, e.g. grouping of messages in sessions or threads
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

A method for managing contacts in a messaging application includes receiving a request from relating to obtaining conversations associated with a client device, in response to the request, retrieving data corresponding to the conversations and causing displaying a list of the conversations on the client device, determining, based on a least one conversation attributes, a rating value for each conversation among the conversations, identifying a particular conversation of the conversations wherein the rating value associated with the particular conversation is below a threshold rating value, and in response to identifying the particular conversation, causing updating the list that is displayed on the client device by removing the particular conversation from the list of the conversations that is displayed on the client device.

Claims

1. A method comprising:

receiving, by a server computer that is hosting a messaging application, a request from a client device that is executing a second instance of the messaging application relating to obtaining a plurality of conversations associated with the client device;

by the server computer in response to the request, retrieving data corresponding to the plurality of conversations that are associated with the client device and causing displaying a list of the plurality of conversations on the client device;

determining, by the server computer, an amount of time that the second instance of the messaging application has been in use by the client device;

determining, by the server computer and based on the amount of time and at least one of a plurality of conversation attributes, a rating value for each conversation among the plurality of conversations;

identifying, by the server computer, a particular conversation of the plurality of conversations wherein the rating value associated with the particular conversation is below a threshold rating value;

by the server computer in response to identifying the particular conversation, causing updating the list that is displayed on the client device by removing the particular conversation from the list of the plurality of conversations that is displayed on the client device.

2. The method of claim 1, wherein the plurality of conversation attributes comprise:

a conversation frequency value, a conversation length value, a location value, a time zone value, an amount of links shared, an number of documents shared, invitation data, a distance value specifying a geographical distance between members of a conversation, and a department value specifying an organizational unit that is associated with members of a conversation.

3. The method of claim 1, further comprising, prior to removing the particular conversation from the list, causing displaying the particular conversation in the list in a different appearance.

4. The method of claim 1, further comprising, prior to removing the particular conversation from the list, causing displaying the particular conversation in the list in a faded appearance.

5. The method of claim 1, further comprising:

prior to removing the particular conversation from the list, causing displaying the particular conversation in the list in a faded appearance;

receiving, from the client device, input indicating selection of the particular conversation;

in response to the input, increasing the rating value of the particular conversation and updating the display of the client device to cause displaying the particular conversation in the list in a normal appearance.

6. The method of claim 1, wherein determining the rating value for each of the plurality of conversations comprises:

training a machine learning algorithm using historical data from the messaging application;

processing at least the plurality of conversations using the machine learning algorithm.

7. The method of claim 6, wherein the historical data is from a plurality of tenants, each of the plurality of tenants using an instance of the messaging application.

8. The method of claim 1, wherein the list of the plurality of conversations are displayed according to a ranking of the rating value for each of the plurality of conversations.

9. A computer system comprising:

a server computer comprising one or more processors and electronic digital memory storing one or more sequences of instructions of a messaging application which, when executed by the one or more processors, cause the one or more processors to perform;

receiving a request from a client device that is executing a second instance of the messaging application relating to obtaining a plurality of conversations associated with the client device;

in response to the request, retrieving data corresponding to the plurality of conversations that are associated with the client device and causing displaying a list of the plurality of conversations on the client device;

determining an amount of time that the second instance of the messaging application has been in use by the client device;

determining, based on the amount of time and at least one of a plurality of conversation attributes, a rating value for each conversation among the plurality of conversations;

identifying a particular conversation of the plurality of conversations wherein the rating value associated with the particular conversation is below a threshold rating value;

in response to identifying the particular conversation, causing updating the list that is displayed on the client device by removing the particular conversation from the list of the plurality of conversations that is displayed on the client device;

the client device comprising one or more processors and electronic digital memory storing one or more sequences of instructions for the second instance of the messaging application which, when executed by the one or more processors, cause the one or more processors to perform;

displaying the list of the plurality of conversations;

removing the particular conversation from the list of the plurality of conversations.

10. The computer system of claim 9, wherein the plurality of conversation attributes comprise:

a conversation frequency value, a conversation length value, a location value, a time zone value, an amount of links shared, an number of documents shared, invitation data, a distance value specifying a geographical distance between members of a conversation, and a department value specifying an organizational unit that is associated with members of a conversation.

11. The computer system of claim 9, further comprising, prior to removing the particular conversation from the list, causing displaying the particular conversation in the list in a different appearance.

12. The computer system of claim 9, the one or more sequences of instructions, when executed by the one or more processors, further cause the one or more processors to perform:

prior to removing the particular conversation from the list, causing displaying the particular conversation in the list in a faded appearance.

13. The computer system of claim 9, the one or more sequences of instructions, when executed by the one or more processors, further cause the one or more processors to perform:

prior to removing the particular conversation from the list, causing displaying the particular conversation in the list in a faded appearance;

receiving, from the client device, input indicating selection of the particular conversation;

in response to the input, increasing the rating value of the particular conversation and updating the display of the client device to cause displaying the particular conversation in the list in a normal appearance.

14. The computer system of claim 9, wherein determining the rating value for each of the plurality of conversations comprises:

training a machine learning algorithm using historical data from the messaging application;

processing at least the plurality of conversations using the machine learning algorithm.

15. The computer system of claim 14, wherein the historical data is from a plurality of tenants, each of the plurality of tenants using an instance of the messaging application.

16. The computer system of claim 9, wherein the list of the plurality of conversations are displayed according to a ranking of the rating value for each of the plurality of conversations.

17. A method comprising:

receiving, by a server computer that is hosting a messaging application, a request from a client device that is executing a second instance of the messaging application relating to obtaining a plurality of conversations associated with the client device;

by the server computer in response to the request, retrieving data corresponding to the plurality of conversations that are associated with the client device and causing displaying a list of the plurality of conversations on the client device;

determining, by the second instance of the messaging application, an amount of time that the second instance of the messaging application has been in use by the client device;

determining, by the server computer and based on the amount of time and at least one of a plurality of conversation attributes, a rating value for each conversation among the plurality of conversations;

identifying, by the server computer, a particular conversation of the plurality of conversations wherein the rating value associated with the particular conversation is below a threshold rating value;

by the server computer in response to identifying the particular conversation, causing updating the list that is displayed on the client device by removing the particular conversation from the list of the plurality of conversations that is displayed on the client device.

18. The method of claim 17, wherein the plurality of conversation attributes comprise:

a conversation frequency value, a conversation length value, a location value, a time zone value, an amount of links shared, an number of documents shared, invitation data, a distance value specifying a geographical distance between members of a conversation, and a department value specifying an organizational unit that is associated with members of a conversation.

19. The method of claim 17, further comprising, prior to removing the particular conversation from the list, causing displaying the particular conversation in the list in a faded appearance.

20. The method of claim 17, wherein determining the rating value for each of the plurality of conversations comprises:

training a machine learning algorithm using historical data from the messaging application;

processing at least the plurality of conversations using the machine learning algorithm.