US 11,741,157 B2
Propagating multi-term contextual tags to digital content
Ajinkya Kale, San Jose, CA (US); Baldo Faieta, San Francisco, CA (US); Benjamin Leviant, Mountain View, CA (US); Fengbin Chen, San Jose, CA (US); Francois Guerin, San Francisco, CA (US); Kate Sousa, San Jose, CA (US); Trung Bui, San Jose, CA (US); Venkat Barakam, Cupertino, CA (US); and Zhe Lin, Fremont, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Dec. 7, 2021, as Appl. No. 17/544,689.
Application 17/544,689 is a continuation of application No. 16/525,366, filed on Jul. 29, 2019, granted, now 11,232,147.
Prior Publication US 2022/0100791 A1, Mar. 31, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/40 (2019.01); G06F 16/58 (2019.01); G06F 16/48 (2019.01); G06F 16/2457 (2019.01); G06F 16/43 (2019.01); G06V 20/00 (2022.01); G06F 18/23213 (2023.01)
CPC G06F 16/5866 (2019.01) [G06F 16/24578 (2019.01); G06F 16/43 (2019.01); G06F 16/48 (2019.01); G06F 18/23213 (2023.01); G06V 20/35 (2022.01); G06V 2201/10 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computing device to:
identify one or more tagged digital content items similar to a digital content item utilizing digital content item similarity scores for the one or more tagged digital content items based on similarities between the digital content item and the one or more tagged digital content items;
modify tag scores, identified from a set of multi-term contextual tags corresponding to the one or more tagged digital content items, utilizing the digital content item similarity scores from the one or more tagged digital content items corresponding to the tag scores;
determine aggregated tag scores for the set of multi-term contextual tags corresponding to the one or more tagged digital content items utilizing the modified tag scores for the set of multi-term contextual tags; and
propagate a subset of multi-term contextual tags from the set of multi-term contextual tags to the digital content item based on the aggregated tag scores.