US 12,482,028 B2
Building shoppable video corpus out of a generic video corpus via video meta data link
Arun Kumar Chippada, Bellevue, WA (US); Yucan Zhang, Bothell, WA (US); Marcelo M. De Barros, Redmond, WA (US); and Xulong Zhang, Redmond, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Jun. 16, 2023, as Appl. No. 18/211,076.
Prior Publication US 2024/0420204 A1, Dec. 19, 2024
Int. Cl. G06Q 30/06 (2023.01); G06Q 30/0601 (2023.01)
CPC G06Q 30/0625 (2013.01) [G06Q 30/0601 (2013.01); G06Q 30/0639 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, performed by at least one processor, of providing media comprising:
identifying, by the at least one processor, a product using a machine learning model that receives content from a video corpus, the machine learning model trained to analyze video frames and detect product-related features from a video corpus associated with a product;
extracting, by the at least one processor and from the video corpus, a uniform resource locator (URL) associated with the product;
determining, by the at least one processor, that the product matches an item description in a catalog by parsing the extracted URL;
determining, by the at least one processor and from the extracted URL, a selectable URL associated with the product matching the item description in the catalog;
normalizing, by the at least one processor, the selectable URL by performing a digital alteration that reduces noise in the selectable URL to produce a normalized selectable URL;
determining, by the at least one processor, that the normalized selectable URL corresponds to the product by applying a product category filter to the normalized selectable URL; and
causing, by the at least one processor, display of the normalized selectable URL, such that selection of the normalized selectable URL results in display of corresponding product information.