US Patent Issued to Maplebear on April 29 for "Machine learned models for search and recommendations" (Washington, California Inventors)

ALEXANDRIA, Va., June 9 -- United States Patent no. 12,287,819, issued on April 29, was assigned to Maplebear Inc. (San Francisco).

"Machine learned models for search and recommendations" was invented by Haixun Wang (Bellevue, Wash.), Taesik Na (Issaquah, Wash.), Li Tan (Fremont, Calif.), Jian Li (Santa Clara, Calif.) and Xiao Xiao (San Diego).

According to the abstract* released by the U.S. Patent & Trademark Office: "A system may generate a prompt based in part on a search query from a customer client device. The prompt instructs a machine learned model to provide item predictions. And the model was trained by: converting structured data describing items of an online catalog to annotated text data (unstructured data), generating trainin...