IP Library › Granted Patent US 12,748,929
Granted Patent B2
US 12,748,929 · App. 17/985,958 · Granted Sep 29, 2026

Summarizing collaborative data based on determined user interest and status

Inventors: Harry Hoots (Raleigh, NC); Panav Setia (Southborough, MA); Connor Paul (Raleigh, NC); Jana H. Jenkins (Raleigh, NC)
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
G06F40/40G06F16/345G06F16/355
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 12,748,929
App. No.
17/985,958
Granted
Sep 29, 2026
Kind
B2
Abstract

A method for automatically and electronically generating a communication summary based on communications received on electronic communication systems is provided. The method may include, automatically determining whether new and different communications received on an electronic communication system relates to stored topics of interest to the user. The method may further include, in response to determining that the received new and different communications relate to the stored topics of interest, automatically extracting content from the new and different communications, and associating and storing the extracted content associated with at least one new communication with at least one related topic of interest from the stored topics of interest. The method may further include automatically generating and displaying the communication summary comprising the extracted content from the received new and different communications and presenting and labeling the new and different communications with the at least one related topic of interest.

Claims (56)

1 . A computer-implemented method for automatically and electronically generating a communication summary based on communications received on one or more electronic communication systems, comprising:

automatically determining whether new and different communications received on a plurality of different electronic communication systems relate to one or more stored topics of interest to a user, wherein the one or more stored topics of interest are determined using natural language processing and machine learning algorithms to process received communications for which the user showed interest, identifying and extracting keywords and phrases associated with the received communications, and subsequently determining a topic based on the extracted keywords and phrases by grouping related material and generating a keyword or phrase representative of a topic common to the received communications using similarity algorithms and topic modeling;

in response to determining that the received new and different communications relate to the one or more stored topics of interest, automatically extracting content from the new and different communications, and associating and storing the extracted content with at least one related topic of interest from the one or more stored topics of interest; and

automatically generating and displaying the communication summary, wherein generating the communication summary further comprises generating a user interface window including the extracted content from the received new and different communications from the plurality of different electronic communication systems, and wherein displaying the communication summary further comprises presenting and labeling the new and different communications with the at least one related topic of interest in the user interface window.

2 . The computer-implemented method of claim 1 , wherein automatically determining whether the new and different communications received on the plurality of different electronic communication systems relate to the one or more stored topics of interest to the user further comprises:

automatically determining whether the new and different communications received on the plurality of different electronic communication systems relate electronic to the one or more stored topics of interest to the user in response to detecting a first change to a user status on the plurality of different electronic communication systems, wherein the new and different communications comprise communications received during a time period that the first change in the user status remains in effect.

3 . The computer-implemented method of claim 2 , wherein the first change to the user status comprises a switch in the user status from an active status to an inactive status associated with the user and the plurality of different electronic communication systems.

4 . The computer-implemented method of claim 2 , wherein automatically generating and displaying the communication summary further comprises:

automatically generating and displaying the communication summary in response to detecting a second change to the user status, wherein detecting the second change to the user status comprises detecting a switch in the user status from an inactive status to an active status associated with the user and the plurality of different electronic communication systems.

5 . The computer-implemented method of claim 1 , further comprising:

Tracking the received communications on the plurality of different electronic communication systems;

tracking user activity and interactions with the received communications;

in response to detecting user interest in a communication based on the tracked user activity and interactions, using the natural language processing and the machine learning algorithms on the communication to identify and generate a topic of interest representative of the communication.

6 . The computer-implemented method of claim 5 , further comprising:

in response to determining that the generated topic of interest does not match the one or more stored topics of interest, generating a new entry on a database for the generated topic of interest and assigning an interest percentage to the new entry;

in response to determining that the generated topic of interest does match at least one stored topic of interest from the one or more stored topics of interest, updating the interest percentage for the at least one stored topic of interest matching the generated topic of interest.

7 . The computer-implemented method of claim 1 , further comprising:

ranking the one or more stored topics of interest; and

automatically generating and displaying the new and different communications on the communication summary based on the ranking.

8 . A computer system for automatically and electronically generating a communication summary based on communications received on one or more electronic communication systems, comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage devices, and program instructions stored on at least one of the one or more storage devices 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:

automatically determining whether new and different communications received on a plurality of different electronic communication systems relate to one or more stored topics of interest to a user, wherein the one or more stored topics of interest are determined using natural language processing and machine learning algorithms to process received communications for which the user showed interest, identifying and extracting keywords and phrases associated with the received communications, and subsequently determining a topic based on the extracted keywords and phrases by grouping related material and generating a keyword or phrase representative of a topic common to the received communications using similarity algorithms and topic modeling;

in response to determining that the received new and different communications relate to the one or more stored topics of interest, automatically extracting content from the new and different communications, and associating and storing the extracted content with at least one related topic of interest from the one or more stored topics of interest; and

automatically generating and displaying the communication summary, wherein generating the communication summary further comprises generating a user interface window including the extracted content from the received new and different communications from the plurality of different electronic communication systems, and wherein displaying the communication summary further comprises presenting and labeling the new and different communications with the at least one related topic of interest in the user interface window.

9 . The computer system of claim 8 , wherein automatically determining whether the new and different communications received on the plurality of different electronic communication systems relate to the one or more stored topics of interest to the user further comprises:

automatically determining whether the new and different communications received on the plurality of different electronic communication systems relate to the one or more stored topics of interest to the user in response to detecting a first change to a user status on the plurality of different electronic communication systems, wherein the new and different communications comprise communications received during a time period that the first change in the user status remains in effect.

10 . The computer system of claim 9 , wherein the first change to the user status comprises a switch in the user status from an active status to an inactive status associated with the user and the plurality of different electronic communication systems.

11 . The computer system of claim 9 , wherein automatically generating and displaying the communication summary further comprises:

automatically generating and displaying the communication summary in response to detecting a second change to the user status, wherein detecting the second change to the user status comprises detecting a switch in the user status from an inactive status to an active status associated with the user and the plurality of different electronic communication systems.

12 . The computer system of claim 8 , further comprising:

tracking the received communications on the plurality of different electronic communication systems;

tracking user activity and interactions with the received communications;

in response to detecting user interest in a communication based on the tracked user activity and interactions, using the natural language processing and the machine learning algorithms on the communication to identify and generate a topic of interest representative of the communication.

13 . The computer system of claim 12 , further comprising:

in response to determining that the generated topic of interest does not match the one or more stored topics of interest, generating a new entry on a database for the generated topic of interest and assigning an interest percentage to the new entry;

in response to determining that the generated topic of interest does match at least one stored topic of interest from the one or more stored topics of interest, updating the interest percentage for the at least one stored topic of interest matching the generated topic of interest.

14 . The computer system of claim 8 , further comprising:

ranking the one or more stored topics of interest; and

automatically generating and displaying the new and different communications on the communication summary based on the ranking.

15 . A computer program product for automatically and electronically generating a communication summary based on communications received on one or more electronic communication systems, comprising:

one or more tangible computer-readable storage devices and program instructions stored on at least one of the one or more tangible computer-readable storage devices, the program instructions executable by a processor, the program instructions comprising:

automatically determining whether new and different communications received on a plurality of different electronic communication systems relate to one or more stored topics of interest to a user, wherein the one or more stored topics of interest are determined using natural language processing and machine learning algorithms to process received communications for which the user showed interest, identifying and extracting keywords and phrases associated with the received communications, and subsequently determining a topic based on the extracted keywords and phrases by grouping related material and generating a keyword or phrase representative of a topic common to the received communications using similarity algorithms and topic modeling;

in response to determining that the received new and different communications relate to the one or more stored topics of interest, automatically extracting content from the new and different communications, and associating and storing the extracted content with at least one related topic of interest from the one or more stored topics of interest; and

automatically generating and displaying the communication summary, wherein generating the communication summary further comprises generating a user interface window including the extracted content from the received new and different communications from the plurality of different electronic communication systems, and wherein displaying the communication summary further comprises presenting and labeling the new and different communications with the at least one related topic of interest in the user interface window.

16 . The computer program product of claim 15 , wherein automatically determining whether the new and different communications received on the plurality of different electronic communication systems relate to the one or more stored topics of interest to the user further comprises:

automatically determining whether the new and different communications received on the plurality of different electronic communication systems relate to the one or more stored topics of interest to the user in response to detecting a first change to a user status on the plurality of different electronic communication systems, wherein the new and different communications comprise communications received during a time period that the first change in the user status remains in effect.

17 . The computer program product of claim 16 , wherein the first change to the user status comprises a switch in the user status from an active status to an inactive status associated with the user and the plurality of different electronic communication systems.

18 . The computer program product of claim 16 , wherein automatically generating and displaying the communication summary further comprises:

automatically generating and displaying the communication summary in response to detecting a second change to the user status, wherein detecting the second change to the user status comprises detecting a switch in the user status from an inactive status to an active status associated with the user and the plurality of different electronic communication systems.

19 . The computer program product of claim 15 , further comprising:

tracking the received communications on the plurality of different electronic communication systems;

tracking user activity and interactions with the received communications;

in response to detecting user interest in a communication based on the tracked user activity and interactions, using the natural language processing and the machine learning algorithms on the communication to identify and generate a topic of interest representative of the communication.

20 . The computer program product of claim 19 , further comprising:

in response to determining that the generated topic of interest does not match the one or more stored topics of interest, generating a new entry on a database for the generated topic of interest and assigning an interest percentage to the new entry;

in response to determining that the generated topic of interest does match at least one stored topic of interest from the one or more stored topics of interest, updating the interest percentage for the at least one stored topic of interest matching the generated topic of interest.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 14, 2022
From: HOOTS, HARRY; SETIA, PANAV; PAUL, CONNOR; JENKINS, JANA H.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 061751/0677 →
Continuity (1)
Related Publication 20240160850A1 · May 16, 2024
References Cited (40)
US 6778941B1 · Worrell · 2004 [cited by applicant]
US 7706740B2 · Collins · 2010 [cited by examiner]
US 8332762B2 · Lee · 2012 [cited by applicant]
US 8515336B2 · Collins · 2013 [cited by examiner]
US 9154533B2 · Morrison, III · 2015 [cited by examiner]
US 10574613B2 · Leiba · 2020 [cited by applicant]
US 10977258B1 · Liu · 2021 [cited by applicant]
US 11074284B2 · Cunico · 2021 [cited by applicant]
US 11126796B2 · Chhabra · 2021 [cited by applicant]
US 11145122B2 · Kollencheri Puthenveettil · 2021 [cited by examiner]
US 11630958B2 · Ronen · 2023 [cited by examiner]
US 20020002450A1 · Nunberg · 2002 [cited by examiner]
US 20040153309A1 · Lin · 2004 [cited by examiner]
US 20050235034A1 · Chen et al. · 2005 [cited by applicant]
US 20080126990A1 · Kumar et al. · 2008 [cited by applicant]
US 20100169910A1 · Collins · 2010 [cited by examiner]
US 20110004462A1 · Houghton · 2011 [cited by examiner]
US 20120166179A1 · Tirumalachetty · 2012 [cited by examiner]
US 20120253793A1 · Ghannam · 2012 [cited by examiner]
US 20130179151A1 · Iverson · 2013 [cited by examiner]
US 20150081276A1 · Gerard · 2015 [cited by examiner]
US 20150081277A1 · Behi · 2015 [cited by examiner]
US 20150170646A1 · Fujii · 2015 [cited by examiner]
US 20160048856A1 · Wouhaybi · 2016 [cited by examiner]
US 20160085743A1 · Haley · 2016 [cited by examiner]
US 20160132483A1 · Chelst · 2016 [cited by examiner]
US 20160188573A1 · Tang · 2016 [cited by examiner]
US 20160248716A1 · Chowdhury · 2016 [cited by examiner]
US 20170148050A1 · Montero · 2017 [cited by examiner]
US 20180287981A1 · Leiba · 2018 [cited by examiner]
US 20200273054A1 · Wouhaybi · 2020 [cited by examiner]
US 20230122341A1 · Santo · 2023 [cited by examiner]
US 20230139831A1 · Wang · 2023 [cited by examiner]
US 20230196020A1 · Thoniparambil · 2023 [cited by examiner]
US 20230325606A1 · Mahendravarman · 2023 [cited by examiner]
US 20230401274A1 · Denninghoff · 2023 [cited by examiner]
US 20240160850A1 · Hoots · 2024 [cited by examiner]
Barzilay et al., “Sentence Fusion for Multidocument News Summarization”, Computational Linguistics, vol. 31, No. 3, Mar. 19, 2005, pp. 297-327. [cited by applicant]
Healey et al., “Visual Analytics of Text Conversation Sentiment and Semantics”, Computer Graphics Forum, 2021, 13 pages. [cited by applicant]
Uthus et al., “Plans Toward Automated Chat Summarization”, Proceedings of the Workshop on Automatic Summarization for Different Genres, Media, and Languages, Jun. 23, 2011, pp. 1-7. [cited by applicant]