US 12,105,767 B2
Digital content layout encoding for search
Zhaowen Wang, San Jose, CA (US); Yue Bai, Malden, MA (US); and John Philip Collomosse, 18 Abbey Close (GB)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on May 3, 2022, as Appl. No. 17/735,748.
Prior Publication US 2023/0359682 A1, Nov. 9, 2023
Int. Cl. G06F 16/9537 (2019.01); G06F 40/103 (2020.01); G06F 40/30 (2020.01); G06V 30/19 (2022.01); G06K 15/02 (2006.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01); G06V 10/82 (2022.01); G06V 30/412 (2022.01); G06V 30/414 (2022.01)
CPC G06F 16/9537 (2019.01) [G06F 40/103 (2020.01); G06F 40/30 (2020.01); G06V 30/19127 (2022.01); G06K 15/1885 (2013.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06V 10/82 (2022.01); G06V 30/412 (2022.01); G06V 30/414 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method implemented by a processing device, the method comprising:
forming, by the processing device, level data by extracting first and second levels from a hierarchy of elements included within digital content;
encoding, by the processing device, a layout representation of the digital content based on the level data using machine learning, the encoding based on a combination of an encoding of the first level fused with an encoding of the second level; and
outputting, by the processing device, a search result of a digital content search performed using the layout representation.