US 12,229,839 B2
Expanding semantic classes via user feedback
Michele Banko, San Francisco, CA (US); Alok Puranik, San Francisco, CA (US); and Taylor Rhyne, San Francisco, CA (US)
Assigned to Discord Inc., San Francisco, CA (US)
Filed by Discord Inc., San Francisco, CA (US)
Filed on Aug. 17, 2023, as Appl. No. 18/235,045.
Application 18/235,045 is a continuation of application No. 17/834,218, filed on Jun. 7, 2022, granted, now 11,763,398.
Application 17/834,218 is a continuation of application No. 16/536,043, filed on Aug. 8, 2019, granted, now 11,373,636, issued on Jun. 28, 2022.
Prior Publication US 2023/0394595 A1, Dec. 7, 2023
Int. Cl. G06F 40/20 (2020.01); G06F 18/214 (2023.01); G06F 18/2431 (2023.01); G06Q 50/00 (2012.01); G10L 15/08 (2006.01)
CPC G06Q 50/01 (2013.01) [G06F 18/214 (2023.01); G06F 18/2431 (2023.01); G10L 15/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
accessing an initial semantic class set;
creating a set of labels based on received tags on content items with classifications from the initial semantic class set;
determining a subset of the set of labels is associated with a shared terminology; generating a first new semantic sub-class based on the shared terminology;
providing the first new semantic sub-class as a new tag available for users to tag social media interactions;
receiving an indication for tagging a social media interaction with the new tag; and
performing a predetermined action based on the new tag.