US Patent Issued to Microsoft Technology Licensing on Oct. 28 for "Embedded learning for response prediction in content item relevance" (California Inventors)

ALEXANDRIA, Va., Oct. 28 -- United States Patent no. 12,456,045, issued on Oct. 28, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).

"Embedded learning for response prediction in content item relevance" was invented by Seyedmohsen Jamali (Sunnyvale, Calif.), Samaneh Abbasi Moghaddam (Sunnyvale, Calif.), Revant Kumar (Sunnyvale, Calif.) and Vinay Praneeth Boda (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques are provided for using machine learning techniques to learn embeddings for content items. In one technique, training data is used to learn embeddings for each attribute value of multiple attribute values of multiple content items, embeddings for each att...