US 12,321,489 B2
Privacy preserving data labeling
Anh Truong, Champaign, IL (US); Austin Walters, Savoy, IL (US); Jeremy Goodsitt, Champaign, IL (US); Vincent Pham, Seattle, WA (US); Reza Farivar, Champaign, IL (US); and Galen Rafferty, Mahomet, IL (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Nov. 7, 2023, as Appl. No. 18/387,698.
Application 18/387,698 is a continuation of application No. 17/177,822, filed on Feb. 17, 2021, granted, now 11,847,245.
Prior Publication US 2024/0070318 A1, Feb. 29, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 21/00 (2013.01); G06F 18/2132 (2023.01); G06F 21/62 (2013.01); G06N 20/00 (2019.01); G06V 20/62 (2022.01); G06V 30/262 (2022.01)
CPC G06F 21/6245 (2013.01) [G06F 18/2132 (2023.01); G06N 20/00 (2019.01); G06V 20/62 (2022.01); G06V 30/274 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
generating, based on a plurality of confidential data in a document, text embeddings;
inputting the text embeddings into a machine learning model to generate a plurality of synthetic images, wherein each of the plurality of synthetic images corresponds to one of the plurality of confidential data;
receiving, from a first computing device of a data labeler, a label for each of the plurality of synthetic images; and
sending, to a second computing device, the plurality of confidential data and the label for each of the plurality of synthetic images corresponding to the plurality of confidential data.