Cognitive collaborative moments

• US 10,417,340 B2
• Filed: 10/23/2017
• Issued: 09/17/2019
• Est. Priority Date: 10/23/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Applegate, Katelyn, Blanchflower, Thomas J., Brunn, Jonathan F., Celedonia, Michael A., Chapman, Scott E., Chen, Dennis J., Dewar, Ami H., Dickens, Rachael M. H., Geyer, Ethan A., Jiang, Bo, Vazquez-Rivera, Rogelio
• Primary Examiner(s): Tzeng, Feng-Tzer
• Application Number:
  US15/790,769
• Publication Number:
  US 20190121852A1
• Time in Patent Office: 694 Days
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 17/00 Digital computing or data processing equipment or methods, specially adapted for specific functions information retrieval, database structures or file system structures therefor G06F16/00
• CPC Class Codes: G06F 40/106 Display of layout of documents; Previewing
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 5/043 Distributed expert systems; Blackboards
• CPC Class Codes: H04L 12/1831 Tracking arrangements for later retrieval, e.g. recording contents, participants activities or behavior, network status

Abstract

A method, computer system, and computer program product for cognitively summarizing one or more collaborative moments is provided. An embodiment may include receiving a plurality of communications sent during a collaborative session. The embodiment may also include grouping the plurality of received communications into one or more bursts. The embodiment may further include assigning one or more keywords or one or more entities to each burst. The embodiment may also include generating a summary for each burst using one or more natural language processing techniques based on the assigned one or more keywords or one or more entities. The embodiment may further include transmitting the generated summary to each user participating in the collaborative session.

Claims

1. A processor-implemented method for cognitively summarizing one or more collaborative moments, the method comprising:

receiving, by a processor, a plurality of communications sent during a collaborative session;

grouping the plurality of received communications into one or more bursts based on temporal relatedness of each message by analyzing inter-message time intervals, total elapsed conversation duration, and message topic, wherein the beginning and end of the one or more bursts are computed using an assigned relevance score for each message based on associated keyword, wherein the associated keywords are extracted and assigned to each burst utilizing one or more natural language processing techniques, wherein a burst continues to exist so long as the assigned relevance score for each message remains above a preconfigured threshold value;

generating a summary for each burst using one or more natural language processing techniques to identify key messages based on the assigned one or more keywords or one or more entities, where in the one or more natural language processing techniques include the use of one or more natural language classifiers to select messages to be included in the generated summary; and

transmitting the generated summary to each user participating in the collaborative session.

2. The method of claim 1, wherein the plurality of communications are selected from a group consisting of one or more chat messages, one or more images, one or more videos, one or more emails, and one or more file share actions.

3. The method of claim 1, wherein the collaborative session is selected from a group consisting of a persistent chat, a web conference, an email conversation, and an instant message group chat.

4. The method of claim 1, wherein the one or more bursts are a plurality of temporally related messages within the plurality of received communications.

5. The method of claim 1, wherein the one or more natural language processing techniques comprises selecting one or more key communications from the plurality of received communications.

6. The method of claim 5, wherein selecting the one or more key communications further comprises:

computing an aggregate score for a plurality of summary phrases referenced in a communication relative to a total number of summary phrases in a burst.

7. The method of claim 6, wherein the plurality of summary phrases are selected from a group consisting of one or more keywords, one or more entities, or one or more categories in a taxonomy hierarchy.

8. A computer system for cognitively summarizing one or more collaborative moments, the computer system comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more tangible storage media for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising;

receiving a plurality of communications sent during a collaborative session;

grouping the plurality of received communications into one or more bursts based on temporal relatedness of each message by analyzing inter-message time intervals, total elapsed conversation duration, and message topic, wherein the beginning and end of the one or more bursts are computed using an assigned relevance score for each message based on associated keyword, wherein the associated keywords are extracted and assigned to each burst utilizing one or more natural language processing techniques, wherein a burst continues to exist so long as the assigned relevance score for each message remains above a preconfigured threshold value;

generating a summary for each burst using one or more natural language processing techniques to identify key messages based on the assigned one or more keywords or one or more entities, where in the one or more natural language processing techniques include the use of one or more natural language classifiers to select messages to be included in the generated summary; and

transmitting the generated summary to each user participating in the collaborative session.

9. The computer system of claim 8, wherein the plurality of communications are selected from a group consisting of one or more chat messages, one or more images, one or more videos, one or more emails, and one or more file share actions.

10. The computer system of claim 8, wherein the collaborative session is selected from a group consisting of a persistent chat, a web conference, an email conversation, and an instant message group chat.

11. The computer system of claim 8, wherein the one or more bursts are a plurality of temporally related messages within the plurality of received communications.

12. The computer system of claim 8, wherein the one or more natural language processing techniques comprises selecting one or more key communications from the plurality of received communications.

13. The computer system of claim 12, wherein selecting the one or more key communications further comprises:

computing an aggregate score for a plurality of summary phrases referenced in a communication relative to a total number of summary phrases in a burst.

14. The computer system of claim 13, wherein the plurality of summary phrases are selected from a group consisting of one or more keywords, one or more entities, or one or more categories in a taxonomy hierarchy.

15. A computer program product for cognitively summarizing one or more collaborative moments, the computer program product comprising:

one or more computer-readable tangible storage media and program instructions stored on at least one of the one or more tangible storage media, the program instructions executable by a processor capable of performing a method, the method comprising;

receiving a plurality of communications sent during a collaborative session;

grouping the plurality of received communications into one or more bursts based on temporal relatedness of each message by analyzing inter-message time intervals, total elapsed conversation duration, and message topic, wherein the beginning and end of the one or more bursts are computed using an assigned relevance score for each message based on associated keyword, wherein the associated keywords are extracted and assigned to each burst utilizing one or more natural language processing techniques, wherein a burst continues to exist so long as the assigned relevance score for each message remains above a preconfigured threshold value;

generating a summary for each burst using one or more natural language processing techniques to identify key messages based on the assigned one or more keywords or one or more entities, where in the one or more natural language processing techniques include the use of one or more natural language classifiers to select messages to be included in the generated summary; and

transmitting the generated summary to each user participating in the collaborative session.

16. The computer program product of claim 15, wherein the plurality of communications are selected from a group consisting of one or more chat messages, one or more images, one or more videos, one or more emails, and one or more file share actions.

17. The computer program product of claim 15, wherein the collaborative session is selected from a group consisting of a persistent chat, a web conference, an email conversation, and an instant message group chat.

18. The computer program product of claim 15, wherein the one or more bursts are a plurality of temporally related messages within the plurality of received communications.

19. The computer program product of claim 15, wherein the one or more natural language processing techniques comprises selecting one or more key communications from the plurality of received communications.

20. The computer program product of claim 19, wherein selecting the one or more key communications further comprises:

computing an aggregate score for a plurality of summary phrases referenced in a communication relative to a total number of summary phrases in a burst.