US 11,842,533 B2
Predictive search techniques based on image analysis and group feedback
Chia-Lin Simmons, Moraga, CA (US); and Rafael Antonio Saavedra, Sunnyvale, CA (US)
Assigned to Chia-Lin Simmons, Moraga, CA (US)
Filed by Cha-Lin Simmons, Moraga, CA (US)
Filed on Jul. 1, 2020, as Appl. No. 16/918,920.
Application 16/918,920 is a continuation in part of application No. 15/957,596, filed on Apr. 19, 2018, abandoned.
Claims priority of provisional application 62/490,508, filed on Apr. 26, 2017.
Prior Publication US 2022/0004604 A1, Jan. 6, 2022
Int. Cl. G06N 5/04 (2023.01); G06N 20/00 (2019.01); G06F 16/55 (2019.01); G06F 16/538 (2019.01); G06T 7/90 (2017.01); G06V 10/94 (2022.01); G06F 21/31 (2013.01); G06T 7/11 (2017.01); G06F 16/535 (2019.01); G06F 18/24 (2023.01); G06F 18/214 (2023.01); G06V 10/778 (2022.01); G06V 20/30 (2022.01); G06V 40/10 (2022.01)
CPC G06V 10/95 (2022.01) [G06F 16/535 (2019.01); G06F 16/538 (2019.01); G06F 16/55 (2019.01); G06F 18/214 (2023.01); G06F 18/24 (2023.01); G06F 21/31 (2013.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06T 7/11 (2017.01); G06T 7/90 (2017.01); G06V 10/7788 (2022.01); G06V 20/30 (2022.01); G06V 40/103 (2022.01); G06T 2207/10024 (2013.01); G06T 2207/20081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium including instructions for performing a predictive search to compensate for a misclassification that, when executed by at least one processor, causes a system to:
receive a user-defined classification of a physical characteristic of the user, the user-defined classification being input to a user device;
obtain an image captured by a camera device, the image being authorized for access by a plurality of authorized users;
aggregate binary feedback data submitted by the plurality of authorized users, the aggregate binary feedback data indicating a favorability of the image by the plurality of authorized users;
predict a classification for the physical characteristic by processing the image with a machine learning (ML) process, the predicted classification being generated independent of the user-defined classification;
search a database based on a query having criteria that includes an indication of the aggregate binary feedback data and at least one of the user-defined classification or the predicted classification;
identify a search result that satisfies the query, the search result being obtained from the database; and
cause display, on a display device of the user device, a recommendation including at least an indication of the search result.