US 12,254,269 B2
Machine learning recommendation engine for content item data entry based on meeting moments and participant activity
Matthew Broussard, San Francisco, CA (US); Emma Highley, Santa Monica, CA (US); Behrooz Khorashadi, Davis, CA (US); Devangi Vivrekar, San Jose, CA (US); Hudson Arnold, Alameda, CA (US); and Shehzad Daredia, San Francisco, CA (US)
Assigned to Dropbox, Inc., San Francisco, CA (US)
Filed by Dropbox, Inc., San Francisco, CA (US)
Filed on Feb. 13, 2024, as Appl. No. 18/440,831.
Application 18/440,831 is a continuation of application No. 17/363,883, filed on Jun. 30, 2021, granted, now 12,050,868.
Prior Publication US 2024/0184987 A1, Jun. 6, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/274 (2020.01); G06N 20/00 (2019.01); H04L 12/18 (2006.01)
CPC G06F 40/274 (2020.01) [G06N 20/00 (2019.01); H04L 12/1831 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining at least a portion of a meeting transcript based on an audio stream of a meeting attended by a plurality of users, the at least the portion of the meeting transcript obtained in an ongoing manner as words are uttered during the meeting;
detecting text entered by a user from the plurality of users during the meeting;
inputting at least a portion of the detected text and at least part of the at least the portion of the meeting transcript associated with the detected text into a trained machine-learning model;
determining, based on output from the trained machine-learning model, a suggested subsequent text; and
adding the suggested subsequent text to a content item.
 
14. A non-transitory computer-readable storage medium storing computer program instructions executable by at least one processor to perform operations, the instructions comprising instructions to:
obtain at least a portion of a meeting transcript based on an audio stream of a meeting attended by a plurality of users, the at least the portion of the meeting transcript obtained in an ongoing manner as words are uttered during the meeting;
detect text entered by a user from the plurality of users during the meeting;
input at least a portion of the detected text and at least part of the at least the portion of the meeting transcript associated with the detected text into a trained machine-learning model;
determine, based on output from the trained machine-learning model, a suggested additional text; and
add the suggested additional text to a content item.
 
19. A system comprising:
at least one processor; and
a non-transitory computer-readable storage medium storing computer program instructions executable by the at least one processor, the instructions when executed causing the at least one processor to perform operations, the operations comprising:
obtaining at least a portion of a meeting transcript based on an audio stream of a meeting attended by a plurality of users, the at least the portion of the meeting transcript obtained in an ongoing manner as words are uttered during the meeting;
detecting text entered by a user from the plurality of users into a content item during the meeting;
inputting at least part of the at least the portion of the meeting transcript associated with the detected text into a trained machine-learning model;
determining, based on output from the trained machine-learning model, a suggested additional text; and
adding the suggested additional text to the content item.