US Patent Issued to Maplebear on Feb. 17 for "Recommendation method, product, and system using user embeddings having stable long-term component and dynamic short-term session component" (California, Washington Inventors)

ALEXANDRIA, Va., Feb. 17 -- United States Patent no. 12,555,153, issued on Feb. 17, was assigned to Maplebear Inc. (San Francisco).

"Recommendation method, product, and system using user embeddings having stable long-term component and dynamic short-term session component" was invented by Chuanwei Ruan (Sunnyvale, Calif.), Yunzhi Ye (Bothell, Wash.), Han Li (Sunnyvale, Calif.), David Vengerov (San Jose, Calif.), Allan Stewart (Berkeley, Calif.) and Aref Kashani Nejad (Redmond, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "An online system accesses a two-tower model trained to identify candidate items for presentation to users, in which the model includes an item tower trained to compute item embedding...