IP Library Granted Patent US 12,505,292
Granted Patent B2
US 12,505,292 · App. 17/936,695 · Granted Dec 23, 2025

Apparatuses, methods, and computer program products for generating an abstractive context summary scheduling interface configured for scheduling and outputting abstractive context summaries for multi-party communication channels

Inventors: Vasu Gupta (Delhi, IN); Utkarsh Tyagi (New Delhi, IN); Ayushi Gupta (New Delhi, IN); Aneesh Kundu (Delhi, IN)
Assignees: ATLASSIAN PTY, LTD.; ATLASSIAN US, INC.
G06F40/284G06F16/345G06N20/00
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 12,505,292
App. No.
17/936,695
Granted
Dec 23, 2025
Kind
B2
Abstract

Methods, apparatuses, or computer program products provide for enabling generation of abstractive context summaries for multi-party communication channels. An abstractive context summary scheduling interface associated with a selected multi-party communication channel may be caused to be rendered to a client computing device associated with a member profile identifier. A summary generation parameter set may be received in response to user engagement with the abstractive context summary scheduling interface. A plurality of communication data objects from the selected multi-party communication channel may be extracted based on the summary generation parameter set. An abstractive context summary for the selected multi-party communication channel may be generated based on the plurality of communication data objects and utilizing a text summarization machine learning model. The abstractive context summary may be caused to be rendered for display on the client computing device associated with the member profile identifier.

Claims (35)

1 . An apparatus for enabling generation of abstractive context summaries for multi-party communication channels, the apparatus comprising at least one processor and at least one memory including program code, the at least one memory and the program code configured to, with the at least one processor, cause the apparatus to at least:

cause rendering of an abstractive context summary scheduling interface associated with a selected multi-party communication channel to a client computing device associated with a member profile identifier based at least in part on determining that the selected multi-party communication channel is associated with an incident severity level that exceeds an incident severity threshold;

receive a summary generation parameter set in response to user engagement with the abstractive context summary scheduling interface;

extract a plurality of communication data objects from the selected multi-party communication channel based on the summary generation parameter set;

generate, based on the plurality of communication data objects and utilizing a text summarization machine learning model, an abstractive context summary for the selected multi-party communication channel by (i) preprocessing the plurality of communication data objects to generate input text and (ii) inputting the input text into the text summarization machine learning model to receive the abstractive context summary; and

transmit computer-executable instructions configured to cause rendering of the abstractive context summary for display on the client computing device associated with the member profile identifier.

2 . The apparatus of claim 1 , wherein the selected multi-party communication channel comprises a multi-party communication channel of a plurality of multi-party communication channels that is associated with a priority indicator.

3 . The apparatus of claim 1 , wherein the summary generation parameter set comprises one or more of: (i) a topic data object, (ii) a keyword, or (iii) a date range.

4 . The apparatus of claim 1 , wherein the text summarization machine learning model is an attention-based transformer text summarization machine learning model.

5 . The apparatus of claim 1 , wherein the abstractive context summary scheduling interface is rendered in response to a customized summary request.

6 . The apparatus of claim 5 , wherein the customized summary request is initiated by the client computing device.

7 . The apparatus of claim 1 , wherein the selected multi-party communication channel comprises a multi-party communication channel generated in response to an incident alert.

8 . A computer-implemented method for enabling generation of abstractive context summaries for multi-party communication channels, the computer-implemented method comprising:

causing rendering of an abstractive context summary scheduling interface associated with a selected multi-party communication channel to a client computing device associated with a member profile identifier based at least in part on determining that the selected multi-party communication channel is associated with an incident severity level that exceeds an incident severity threshold;

receiving a summary generation parameter set in response to user engagement with the abstractive context summary scheduling interface;

extracting a plurality of communication data objects from the selected multi-party communication channel based on the summary generation parameter set;

generating, based on the plurality of communication data objects and utilizing a text summarization machine learning model, an abstractive context summary for the selected multi-party communication channel by (i) preprocessing the plurality of communication data objects to generate input text and (ii) inputting the input text into the text summarization machine learning model to receive the abstractive context summary; and

transmitting computer-executable instructions configured to cause rendering of the abstractive context summary for display on the client computing device associated with the member profile identifier.

9 . The computer-implemented method of claim 8 , wherein the selected multi-party communication channel comprises a multi-party communication channel of a plurality of multiparty communication channels that is associated with a priority indicator.

10 . The computer-implemented method of claim 8 , wherein the summary generation parameter set comprises one or more of: (i) a topic data object, (ii) keyword, or (iii) date range.

11 . The computer-implemented method of claim 8 , wherein the text summarization machine learning model is an attention-based transformer text summarization machine learning model.

12 . The computer-implemented method of claim 8 , wherein the abstractive context summary scheduling interface is rendered in response to a customized summary request.

13 . The computer-implemented method of claim 12 , wherein the customized summary request is initiated by the client computing device.

14 . The computer-implemented method of claim 8 , wherein the selected multi-party communication channel comprises a multi-party communication channel generated in response to an incident alert.

15 . A computer program product for enabling generation of abstractive context summaries for multi-party communication channels, the computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions configured to:

cause rendering of an abstractive context summary scheduling interface associated with a selected multi-party communication channel to a client computing device associated with a member profile identifier based at least in part on determining that the selected multi-party communication channel is associated with an incident severity level that exceeds an incident severity threshold;

receive a summary generation parameter set in response to user engagement with the abstractive context summary scheduling interface;

extract a plurality of communication data objects from the selected multi-party communication channel based on the summary generation parameter set;

generate, based on the plurality of communication data objects and utilizing a text summarization machine learning model, an abstractive context summary for the selected multi-party communication channel by (i) preprocessing the plurality of communication data objects to generate input text and (ii) inputting the input text into the text summarization machine learning model to receive the abstractive context summary; and

transmit computer-executable instructions configured to cause rendering of the abstractive context summary for display on the client computing device associated with the member profile identifier.

16 . The computer program product of claim 15 , wherein the selected multi-party communication channel comprises a multi-party communication channel of a plurality of multi-party communication channels that is associated with a priority indicator.

17 . The computer program product of claim 15 , wherein the summary generation parameter set comprises one or more of: (i) a topic data object, (ii) keyword, or (iii) date range.

18 . The computer program product of claim 15 , wherein the text summarization machine learning model is an attention-based transformer text summarization machine learning model.

19 . The computer program product of claim 15 , wherein the abstractive context summary scheduling interface is rendered in response to a customized summary request.

20 . The computer program product of claim 19 , wherein the customized summary request is initiated by the client computing device.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 11, 2024
From: ATLASSIAN (US) LLC
To: ATLASSIAN US, INC.
Reel/Frame 067685/0261 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 20, 2022
From: GUPTA, VASU; TYAGI, UTKARSH; GUPTA, AYUSHI; KUNDU, ANEESH
To: ATLASSIAN PTY LTD.; ATLASSIAN (US) LLC
Reel/Frame 061487/0879 →
Continuity (1)
Related Publication 20240111798A1 · Apr 4, 2024
References Cited (16)
US 7034691B1 · Rapaport et al. · 2006 [cited by applicant]
US 10276031B1 · Ho et al. · 2019 [cited by applicant]
US 10931759B2 · Duran et al. · 2021 [cited by applicant]
US 11710000B1 · Cuan · 2023 [cited by examiner]
US 20140067377A1 · Reiter · 2014 [cited by applicant]
US 20170364588A1 · Bastide et al. · 2017 [cited by applicant]
US 20230069113A1 · Tsuchida et al. · 2023 [cited by applicant]
US 20230259544A1 · Sotudeh et al. · 2023 [cited by applicant]
US 20230376515A1 · Tanikella · 2023 [cited by examiner]
US 20230385556A1 · Ranganathan et al. · 2023 [cited by applicant]
US 20240086461A1 · Varakin · 2024 [cited by applicant]
US 20240111959A1 · Gupta et al. · 2024 [cited by applicant]
US 20240249068A1 · Aldred et al. · 2024 [cited by applicant]
Defensive Publication Series, “Automatic Creation of Communication Channels Around Detected Events”, Technical Disclosure Commons, Dec. 15, 2017 (Year: 2017). [cited by examiner]
Final Rejection Mailed on Nov. 6, 2025 for U.S. Appl. No. 17/936,705, 21 page(s). [cited by applicant]
Non-Final Rejection Mailed on Nov. 6, 2025 for U.S. Appl. No. 18/477,176, 19 page(s). [cited by applicant]