US 12,223,524 B1
Systems and methods for selecting product placement locations and products
Mauricio Alejandro Flores Rios, Seattle, WA (US); Han-Kai Hsu, Seattle, WA (US); Yujia Chen, Bellevue, WA (US); Linda Liu, Seattle, WA (US); and Yash Chaturvedi, Issaquah, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jun. 23, 2022, as Appl. No. 17/847,775.
Int. Cl. G06Q 30/00 (2023.01); G06Q 30/0242 (2023.01); G06V 20/40 (2022.01); H04N 21/81 (2011.01); G05B 19/418 (2006.01)
CPC G06Q 30/0242 (2013.01) [G06V 20/49 (2022.01); H04N 21/812 (2013.01); H04N 21/8146 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
determining, by a computer processor, first, second, and third shot segments of a video;
determining a first segment quality value of the first shot segment, a second segment quality value of the second shot segment, and a third quality value for the third shot segment;
determining the third quality value does not satisfy a quality threshold value;
analyzing the first shot segment and the second shot segment using a first model trained to determine a first product location corresponding to a first position for placement within the first shot segment and a second product location corresponding to a second position for placement within the second shot segment, wherein the first model is a machine learning computer vision model trained to determine locations in shot segments of the digital media for placement of virtual products;
determining the first product location is the same as the second product location;
determining a first product size and a second product size, the first product size based on the first product location and the second product size based on the second product location;
analyzing the first shot segment and the second shot segment using a second model to determine first contextual data corresponding to the first shot segment and second contextual data corresponding to the second shot segment, wherein the second model is a machine learning model trained to automatically determine contextual data in shot segments of the digital media;
determining a first product and a second product based on the first product location, the second product location, the first contextual data, and the second contextual data;
determining a first contextual value corresponding to the first product and a second contextual value corresponding to the second product, each of the first contextual value and the second contextual value based on the first contextual data and second contextual data;
determining the first contextual value exceeds the second contextual value;
determining a first time period corresponding to the first shot segment and the second shot segment;
determining a first revenue value based on the first product, the first product location, the first product size, the second product location, and the first time period; and
determining a first cost value corresponding to digitally incorporating the first product into the first product location and the second product location.