IP Library Granted Patent US 12,641,193
Granted Patent B2
US 12,641,193 · App. 18/414,996 · Granted May 26, 2026

Generating intelligent meeting insights for upcoming video calls

Inventors: Ameya Bhatawdekar (Issaquah, WA); Geoff Hulten (Lynnwood, WA); Kelsey Glatz (Redondo Beach, CA); Sateesh Srinivasan (Redwood City, CA); Joseph Grillo (San Francisco, CA); Emir Aydin (Vancouver, CA); Ritu Vincent (Alamo, CA); William Adamowicz (Los Angeles, CA)
Assignee: Dropbox, Inc.
H04N7/152G06F3/013G06N5/02G06V20/41G06V40/103G06V40/174G06V40/176G06V40/23G09B19/04G10L25/48H04L12/1822H04L67/306H04N7/147H04N7/155
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 12,641,193
App. No.
18/414,996
Granted
May 26, 2026
Kind
B2
Abstract

The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating and providing intelligent insights for video calls and other virtual meetings. In some embodiments, the disclosed systems analyze stored meeting data from past video calls and other virtual meetings to generate intelligent insights for an upcoming video call. The disclosed systems also generate and provide intelligent insights or coaching tools for ongoing video calls. As part of the intelligent coaching tools for ongoing video calls, the disclosed systems can generate predictions for accomplishing target goals for the video calls. Further, the disclosed systems can generate intelligent insights or coaching tools after video calls take place.

Claims (68)

1 . A method comprising:

generating, from meeting data extracted from past meetings associated with a user account of a content management system, a knowledge graph defining relationships between the past meetings for the user account;

determining, from video call data of a previous video call associated with the user account, a drop-off topic comprising a topic discussed by attendees at termination of the previous video call;

determining, from the video call data of the previous video call, tone data of dialogue corresponding to the drop-off topic;

detecting, for the user account of the content management system, an upcoming video call corresponding to the previous video call based on the knowledge graph defining the relationships between the past meetings; and

generating, utilizing the tone data and in response to initiating the upcoming video call, a suggested phrase corresponding to the drop-off topic for display on a client device of the user account.

2 . The method of claim 1 , wherein generating the knowledge graph comprises:

extracting, from past video calls, video call data comprising one or more of attentiveness data, reaction data, or cross talking data; and

generating, from the video call data, nodes representing the past video calls and edges connecting the nodes to represent relationships between the past video calls.

3 . The method of claim 1 , further comprising determining that the upcoming video call corresponds to the previous video call by determining a distance from a first node representing the previous video call within the knowledge graph to a second node representing the upcoming video call within the knowledge graph.

4 . The method of claim 1 , wherein determining the tone data comprises:

determining a tone of conversation at the termination of the previous video call; and

generating the suggested phrase for the upcoming video call based on the tone of the conversation at the termination of the previous video call.

5 . The method of claim 1 , wherein generating the suggested phrase comprises:

determining a content item modified by an additional user account attending the upcoming video call, wherein the content item is also accessible by the user account; and

generating the suggested phrase to mention the content item modified by the additional user account.

6 . The method of claim 1 , further comprising:

determining a topic of interest associated with an additional user account attending the upcoming video call; and

generating, for display on the client device during the upcoming video call, an insight notification indicating the topic of interest for the additional user account.

7 . The method of claim 1 , further comprising determining a content item to share within the upcoming video call based on the video call data of the previous video call.

8 . A system comprising:

at least one processor; and

a non-transitory computer readable medium comprising instructions that, when executed by the at least one processor, cause the system to:

generate, from meeting data extracted from past meetings associated with a user account of a content management system, a knowledge graph defining relationships between the past meetings for the user account;

determine, from video call data of a previous video call associated with the user account, a drop-off topic comprising a topic discussed by attendees at termination of the previous video call;

determine, from the video call data of the previous video call, tone data of dialogue corresponding to the drop-off topic;

detect, for the user account of the content management system, an upcoming video call associated with the previous video call as indicated by the knowledge graph defining the relationships between the past meetings; and

generate, utilizing the tone data and in response to initiating the upcoming video call, a suggested phrase corresponding to the drop-off topic for display on a client device of the user account.

9 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to determine the drop-off topic by utilizing a topic encoding model to generate a topic embedding from the video call data at the termination of the previous video call.

10 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to:

determine, from the knowledge graph, a topic of a previous video call between the user account and an additional user account attending the upcoming video call; and

generate, for display on the client device during the upcoming video call, an insight notification indicating the topic of the previous video call.

11 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to:

extract, from the video call data of the previous video call, a first set of body language data for a first attendee and a second set of body language data for a second attendee;

determine a first attentiveness score for the first attendee from the first set of body language data and a second attentiveness score for the second attendee from the second set of body language data; and

generate a notification for display on the client device based on the first attentiveness score and the second attentiveness score.

12 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to:

extract, from the video call data of the previous video call, a first set of eye movement data for a first attendee and a second set of eye movement data for a second attendee;

determine a first attentiveness score for the first attendee from the first set of eye movement data and a second attentiveness score for the second attendee from the second set of eye movement data; and

generate the suggested phrase based on the first attentiveness score and the second attentiveness score.

13 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to:

determine, from the video call data of the previous video call, a first attentiveness score for a first attendee whose camera is enabled and a second attentiveness score for a second attendee whose camera is disabled; and

generate the suggested phrase based on the first attentiveness score and the second attentiveness score.

14 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to generate the knowledge graph by:

identifying one or more previous video calls comprising shared attendees; and

determining, from video call data of the one or more previous video calls, a frequency of a topic mentioned by the shared attendees.

15 . A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause the at least one processor to:

generate, from meeting data extracted from past meetings associated with a user account of a content management system, a knowledge graph defining relationships between the past meetings for the user account;

determine, from video call data of a previous video call associated with the user account, a drop-off topic comprising a topic discussed by attendees at termination of the previous video call;

determine, from the video call data of the previous video call, tone data of dialogue corresponding to the drop-off topic;

detect, for the user account of the content management system, an upcoming video call related to the previous video call as indicated by the knowledge graph defining the relationships between the past meetings; and

generate, utilizing the tone data and in response to initiating the upcoming video call, a suggested phrase corresponding to the drop-off topic for display on a client device of the user account.

16 . The non-transitory computer readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to generate the knowledge graph by:

extracting, from the past meetings of the user account, meeting data comprising one or more of attendees of the past meetings, invitees of the past meetings, and calendar data indicating scheduling and location of the past meetings; and

generating, from the meeting data, nodes representing the past meetings and edges connected the nodes to represent relationships between the past meetings.

17 . The non-transitory computer readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to generate the knowledge graph by:

determining digital communications between user accounts comprising mentions of the past meetings;

determining content items stored for user accounts comprising data associated with the past meetings; and

generating, based on the digital communications and the content items, nodes representing the past meetings, the digital communications, and the content items and edges connected the nodes to represent relationships between the past meetings, the digital communications, and the content items.

18 . The non-transitory computer readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to generate the suggested phrase by:

generating a tone embedding by utilizing a tone encoder model to process the tone data, wherein the tone data includes audio information, facial expression information, and body language information; and

generating the suggested phrase based on the tone embedding.

19 . The non-transitory computer readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to:

generate, from the video call data of the previous video call, a reaction score for an attendee of the previous video call based on one or more of body language data or facial expression data; and

generate the suggested phrase based on the reaction score.

20 . The non-transitory computer readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to:

determine, from the knowledge graph, an additional user account associated with the drop-off topic; and

generate, for display on the client device, a notification for inviting the additional user account to attend the upcoming video call.

Assignments (3)
SECURITY INTEREST Recorded Dec 12, 2024
From: DROPBOX, INC.
To: WILMINGTON TRUST, NATIONAL ASSOCIATION, AS COLLATERAL AGENT
Reel/Frame 069604/0611 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 4, 2024
From: GRILLO, JOSEPH; AYDIN, EMIR; VINCENT, RITU; ADAMOWICZ, WILLIAM
To: DROPBOX, INC.
Reel/Frame 068803/0662 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 17, 2024
From: BHATAWDEKAR, AMEYA; HULTEN, GEOFF; GLATZ, KELSEY; SRINIVASAN, SATEESH
To: DROPBOX, INC.
Reel/Frame 066153/0314 →
Continuity (2)
Provisional Application 63611612 · Dec 18, 2023
Related Publication 20250203042A1 · Jun 19, 2025
References Cited (53)
US 6705869B2 · Schwartz · 2004 [cited by applicant]
US 9257115B2 · Waibel · 2016 [cited by applicant]
US 10122848B2 · Sales et al. · 2018 [cited by applicant]
US 10255563B2 · Stickler et al. · 2019 [cited by applicant]
US 10262195B2 · Conway et al. · 2019 [cited by applicant]
US 10832009B2 · Bonin et al. · 2020 [cited by applicant]
US 10956875B2 · Nelson et al. · 2021 [cited by applicant]
US 11024328B2 · Jung et al. · 2021 [cited by applicant]
US 11159767B1 · Kamisetty et al. · 2021 [cited by applicant]
US 11379772B2 · Oberman et al. · 2022 [cited by applicant]
US 11663024B2 · Decrop et al. · 2023 [cited by applicant]
US 11736309B2 · Rey et al. · 2023 [cited by applicant]
US 11798549B2 · Braganza et al. · 2023 [cited by applicant]
US 20020151297A1 · Remboski et al. · 2002 [cited by applicant]
US 20080147706A1 · Anglin et al. · 2008 [cited by applicant]
US 20130144603A1 · Lord et al. · 2013 [cited by applicant]
US 20150181020A1 · Fitzsimmons et al. · 2015 [cited by applicant]
US 20170270822A1 · Cohen · 2017 [cited by applicant]
US 20170272394A1 · Ding et al. · 2017 [cited by applicant]
US 20180101281A1 · Nelson · 2018 [cited by examiner]
US 20180189267A1 · Takiel · 2018 [cited by applicant]
US 20180226069A1 · Fleischman · 2018 [cited by examiner]
US 20190042086A1 · White · 2019 [cited by examiner]
US 20200118010A1 · Lee et al. · 2020 [cited by applicant]
US 20210120206A1 · Liu et al. · 2021 [cited by applicant]
US 20210176427A1 · Sutasirisap et al. · 2021 [cited by applicant]
US 20210314523A1 · Kamisetty et al. · 2021 [cited by applicant]
US 20220086393A1 · Peters · 2022 [cited by examiner]
US 20220113998A1 · Martin · 2022 [cited by applicant]
US 20220139252A1 · Sawyer et al. · 2022 [cited by applicant]
US 20220157189A1 · Harlow et al. · 2022 [cited by applicant]
US 20220182253A1 · Pawar et al. · 2022 [cited by applicant]
US 20220199079A1 · Hanson et al. · 2022 [cited by applicant]
US 20220207392A1 · Hou et al. · 2022 [cited by applicant]
US 20220293107A1 · Leaman et al. · 2022 [cited by applicant]
US 20220407732A1 · Hellman et al. · 2022 [cited by applicant]
US 20230046248A1 · Veyseh et al. · 2023 [cited by applicant]
US 20230177356A1 · Choi et al. · 2023 [cited by applicant]
US 20230385778A1 · Johnson, III · 2023 [cited by examiner]
US 20240021217A1 · Van Rensburg · 2024 [cited by applicant]
US 20240073054A1 · Hong · 2024 [cited by examiner]
US 20240087606A1 · Miller · 2024 [cited by examiner]
US 20240127079A1 · Agley et al. · 2024 [cited by applicant]
US 20240195915A1 · Koneru · 2024 [cited by examiner]
US 20240386015A1 · Crabtree et al. · 2024 [cited by applicant]
US 20240395259A1 · Hilmarsson · 2024 [cited by examiner]
US 20240412720A1 · Vasylyev · 2024 [cited by applicant]
EP 3309731A1 · 2018 [cited by applicant]
Non-Final Office Action from U.S. Appl. No. 18/415,011, mailed Mar. 25, 2025, 15 pages. [cited by applicant]
Final Office Action from U.S. Appl. No. 18/415,011 mailed on Aug. 1, 2025, 19 pages. [cited by applicant]
Non-Final Office Action U.S. Appl. No. 18/415,024 dated Nov. 3, 2025, 16 pages. [cited by applicant]
Notice of Allowance for U.S. Appl. No. 18/415,011 mailed on Nov. 7, 2025, 7 pages. [cited by applicant]
Notice of Allowance from U.S. Appl. No. 18/415,011 mailed Dec. 17, 2025, 7 pages. [cited by applicant]