US 12,230,262 B2
Detection and correction of performance issues during online meetings
Ali Mouline, Cupertino, CA (US); Christopher Rowen, Santa Cruz, CA (US); David Guoqing Zhang, Fremont, CA (US); and Francis Anthony Kurupacheril, San Jose, CA (US)
Assigned to CISCO TECHNOLOGY, INC., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on Oct. 19, 2021, as Appl. No. 17/504,726.
Prior Publication US 2023/0117129 A1, Apr. 20, 2023
Int. Cl. G10L 15/22 (2006.01); G10L 15/08 (2006.01); G10L 15/30 (2013.01); H04L 65/401 (2022.01); G06F 40/30 (2020.01); H04L 65/403 (2022.01); H04L 65/80 (2022.01)
CPC G10L 15/22 (2013.01) [G10L 15/08 (2013.01); G10L 15/30 (2013.01); H04L 65/4015 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
detecting a phrase spoken in an online collaboration session between a plurality of users, the phrase being spoken by a first user to one or more second users, the phrase including a name of a user of the one or more second users;
determining that the phrase indicates an issue with a quality of user experience of the online collaboration session;
identifying, from a list that includes phrases, corresponding categories of issues, and corresponding attributes, a category of the issue associated with the phrase and an attribute associated with the phrase, the attribute indicating that the name of the user is included in the phrase;
labeling a log of metrics associated with the online collaboration session with a time stamp corresponding to a time when the phrase was spoken and at least one of an indication of the phrase that was spoken or the category of the issue associated with the phrase that was spoken, to provide a labeled log of metrics that indicates a set of metric values associated with the online collaboration session at the time when the phrase was spoken;
determining one or more actions to perform based on the category of the issue associated with the phrase and the name of the user;
performing the one or more actions to improve the user experience based on detecting the phrase, the one or more actions including transmitting the phrase or the category of the issue to an online collaboration session application associated with the user; and
training a machine learning system using the labeled log of metrics to identify or predict degraded user experiences associated with subsequent online collaboration sessions.