US Patent Issued to Maplebear on June 9 for "Using trained machine-learning model to detect errors based on interactions of users of an online system with physical devices" (Canadian, American Inventors)

ALEXANDRIA, Va., June 9 -- United States Patent no. 12,650,890, issued on June 9, was assigned to Maplebear Inc. (San Francisco).

"Using trained machine-learning model to detect errors based on interactions of users of an online system with physical devices" was invented by Charles Wesley (San Diego), Syed Wasi Hasan Rizvi (Toronto), Brent Scheibelhut (Toronto), Mark Oberemk (Toronto) and Naval Shah (Toronto).

According to the abstract* released by the U.S. Patent & Trademark Office: "An online system uses a trained machine-learning model to detect errors in catalog data based on interactions of users of the online system with physical carts. Upon receiving an interaction signal indicating an interaction by the user with a device in a loc...