US 12,468,761 B2
Product identification in media items
Marco Ziccardi, Basel (CH); Min-hsuan Tsai, San Jose, CA (US); Wei-Hong Chuang, Palo Alto, CA (US); Rahul Sunil Bhalerao, Sunnyvale, CA (US); Ye Xia, Santa Clara, CA (US); Madhuri Shanbhogue, San Jose, CA (US); Mojtaba Seyedhosseini, Foster City, CA (US); Mike Krainin, Arlington, MA (US); Andrei Kapishnikov, Watertown, MA (US); and Yuanzhen Li, Newton, MA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Aug. 1, 2022, as Appl. No. 17/878,845.
Prior Publication US 2024/0037145 A1, Feb. 1, 2024
Int. Cl. G06F 16/783 (2019.01); G06F 16/78 (2019.01); G06F 40/56 (2020.01)
CPC G06F 16/7837 (2019.01) [G06F 16/7867 (2019.01); G06F 40/56 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
obtaining, by a processing device and using a first machine learning model, first data comprising (i) a first identifier of a first product determined in association with a content item based on first metadata of the content item, and (ii) a first confidence value indicating a first likelihood of the first product being associated with the content item;
obtaining, by the processing device and using a second machine learning model, second data comprising (i) a second identifier of the first product determined in association with the content item based on first image data of the content item, and (ii) a second confidence value indicating a second likelihood of the first product being associated with the content item;
providing, by the processing device as input to a third machine learning model, the first data comprising (i) the first identifier of the first product determined based on the first metadata of the content item and (ii) the first confidence value, and the second data comprising (i) the second identifier of the first product determined based on the first image data of the content item, and (ii) the second confidence value;
obtaining an output of the third machine learning model, the output of the third machine learning model comprising a third confidence value associated with the first product; and
adjusting second metadata associated with the content item in view of the third confidence value.