IP Library Granted Patent US 10,832,009
Granted Patent B2
US 10,832,009 · App. 15/859,972 · Granted Nov 10, 2020

Extraction and summarization of decision elements from communications

Inventors: Francesca Bonin (Dublin, IE); Lea Deleris (Paris, FR); Debasis Ganguly (Dublin, IE); Killian Levacher (Dublin, IE); Martin Stephenson (Ballynacargy, IE)
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
G06F40/40G06F16/345G06F40/30G06N5/045G10L15/1815H04L51/04
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,832,009
App. No.
15/859,972
Granted
Nov 10, 2020
Kind
B2
Abstract

Embodiments for extraction and summarization of decision discussions of a communication by a processor. The decision elements may be grouped together according to similar characteristics. The decision elements may be linked, and sentiments of the discussion participants towards each of the decision elements may be analyzed. A summary of the plurality of the decision elements may be provided via an interactive graphical user interface (GUI) on one or more Internet of Things (IoT) devices. The summary of the decision elements may be linked to domain knowledge. The summary may be enhanced using a domain knowledge.

Claims (46)

1. A method for automated extraction and summarization of decision discussions of a communication by a processor, comprising:

receiving a plurality of communications related to a single topic from one or more data sources including document sources, electronic communication sources, audio sources, and video sources;

reducing each of the plurality of communications into a text document; wherein natural language processing (NLP) is utilized to transcribe content received from the electronic communication sources, audio sources, and video sources into text of the text document; and wherein one or more users having authored the plurality of communications is attributed to the text of the text document during the reduction;

identifying and extracting decision elements relating to one or more decisions from the plurality of communications so as to provide a summary of the decision elements; wherein artificial intelligence (AI) is used to aggregate and prioritize the decision elements within the summary; and wherein the AI identifies the decision elements by inference notwithstanding whether or not the decision elements related to the single topic are specifically named or mentioned in the plurality of communications;

grouping, clustering, and organizing the decision elements based on context, similar sentiments, similar concepts, and timestamps of the plurality of communications; wherein the decision elements comprise alternative suggestions and one or more criteria;

mapping the alternative suggestions to the one or more criteria;

automatically recommending, within the summary, one or more of the decisions according to a ranking of alternative suggestions associated with the respective one or more criteria; providing within the summary at least an identified consensus and dissension identified from the extracted decision elements, relating to the one or more decisions by the one or more users involved in the plurality of communications;

displaying the summary of the decision elements via an interactive graphical user interface (GUI) on one or more Internet of Things (IoT) devices; wherein displaying the summary includes displaying the plurality of communications in original form, prior to the reduction into the text document, as an overlay atop respective ones of the decision elements within the summary upon the one or more users performing an input gesture on the respective ones of the decision elements to which the plurality of communications are associated; and

linking the displayed decision elements to external resources associated with a domain knowledge to support the one or more decisions, the alternative suggestions, and the one or more criteria.

2. The method of claim 1 , further including

identifying segments and topics that pertain to the one or more decisions.

3. The method of claim 1 , further including linking together each of the decision elements.

4. The method of claim 1 , further including

enhancing the summary using the domain knowledge.

5. The method of claim 1 , further including analyzing one or more sentiments by the one or more users in relation to the one or more decision elements.

6. A system for automated extraction and summarization of decision discussions of a communication, comprising:

one or more computers with executable instructions that when executed cause the system to:

receive a plurality of communications related to a single topic from one or more data sources including document sources, electronic communication sources, audio sources, and video sources;

reduce each of the plurality of communications into a text document; wherein natural language processing (NLP) is utilized to transcribe content received from the electronic communication sources, audio sources, and video sources into text of the text document; and wherein one or more users having authored the plurality of communications is attributed to the text of the text document during the reduction;

identify and extract decision elements relating to one or more decisions from the plurality of communications so as to provide a summary of the decision elements; wherein artificial intelligence (AI) is used to aggregate and prioritize the decision elements within the summary; and wherein the AI identifies the decision elements by inference notwithstanding whether or not the decision elements related to the single topic are specifically named or mentioned in the plurality of communications;

group, cluster, and organize the decision elements based on context, similar sentiments, similar concepts, and timestamps of the plurality of communications; wherein the decision elements comprise alternative suggestions and one or more criteria;

map the alternative suggestions to the one or more criteria;

automatically recommend, within the summary, one or more of the decisions according to a ranking of alternative suggestions associated with the respective one or more criteria; providing within the summary at least an identified consensus and dissension identified from the extracted decision elements, relating to the one or more decisions by the one or more users involved in the plurality of communications;

display the summary of the decision elements via an interactive graphical user interface (GUI) on one or more Internet of Things (IoT) devices; wherein displaying the summary includes displaying the plurality of communications in original form, prior to the reduction into the text document, as an overlay atop respective ones of the decision elements within the summary upon the one or more users performing an input gesture on the respective ones of the decision elements to which the plurality of communications are associated; and

link the displayed decision elements to external resources associated with a domain knowledge to support the one or more decisions, the alternative suggestions, and the one or more criteria.

7. The system of claim 6 , wherein the executable instructions further

identify segments and topics that pertain to the one or more decisions.

8. The system of claim 6 , wherein the executable instructions further link together each of the decision elements.

9. The system of claim 6 , wherein the executable instructions further

enhance the summary using the domain knowledge.

10. The system of claim 6 , wherein the executable instructions further analyze one or more sentiments by the one or more users in relation to the one or more decision elements.

11. A computer program product for automated extraction and summarization of decision discussions of a communication by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

an executable portion that receives a plurality of communications related to a single topic from one or more data sources including document sources, electronic communication sources, audio sources, and video sources;

an executable portion that reduces each of the plurality of communications into a text document; wherein natural language processing (NLP) is utilized to transcribe content received from the electronic communication sources, audio sources, and video sources into text of the text document; and wherein one or more users having authored the plurality of communications is attributed to the text of the text document during the reduction;

an executable portion that identifies and extracts decision elements relating to one or more decisions from the plurality of communications so as to provide a summary of the decision elements; wherein artificial intelligence (AI) is used to aggregate and prioritize the decision elements within the summary; and wherein the AI identifies the decision elements by inference notwithstanding whether or not the decision elements related to the single topic are specifically named or mentioned in the plurality of communications;

an executable portion that groups, clusters, and organizes the decision elements based on context, similar sentiments, similar concepts, and timestamps of the plurality of communications; wherein the decision elements comprise alternative suggestions and one or more criteria;

an executable portion that maps the alternative suggestions to the one or more criteria;

an executable portion that automatically recommends, within the summary, one or more of the decisions according to a ranking of alternative suggestions associated with the respective one or more criteria; providing within the summary at least an identified consensus and dissension identified from the extracted decision elements, relating to the one or more decisions by the one or more users involved in the plurality of communications;

an executable portion that displays the summary of the decision elements via an interactive graphical user interface (GUI) on one or more Internet of Things (IoT) devices; wherein displaying the summary includes displaying the plurality of communications in original form, prior to the reduction into the text document, as an overlay atop respective ones of the decision elements within the summary upon the one or more users performing an input gesture on the respective ones of the decision elements to which the plurality of communications are associated; and

an executable portion that links the displayed decision elements to external resources associated with a domain knowledge to support the one or more decisions, the alternative suggestions, and the one or more criteria.

12. The computer program product of claim 11 , further including an executable portion that

identifies segments and topics that pertain to the one or more decisions.

13. The computer program product of claim 11 , further including an executable portion that links together each of the decision elements.

14. The computer program product of claim 11 , further including an executable portion that

enhances the summary using the domain knowledge.

15. The computer program product of claim 11 , further including an executable portion that analyzes one or more sentiments by the one or more users in relation to the one or more decision elements.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 12, 2025
From: INTERNATIONAL BUSINESS MACHINES CORPORATION
To: MONDAY.COM LIMITED
Reel/Frame 070477/0799 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 2, 2018
From: BONIN, FRANCESCA; DELERIS, LEA; GANGULY, DEBASIS; LEVACHER, KILLIAN; STEPHENSON, MARTIN
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 044515/0388 →
Continuity (1)
Related Publication 20190205395A1 · Jul 4, 2019
Cited By (2)
US 12,598,270 US 12,641,193