ALEXANDRIA, Va., June 9 -- United States Patent no. 12,287,835, issued on April 29, was assigned to Ushur Inc. (Santa Clara, Calif.).

"Automatically extracting key-value data included in heterogeneous document types using graph representation learning" was invented by Badri Nath (Edison, N.J.), Vijayendra Mysore Shamanna (Cupertino, Calif.), Yashu Seth (Patna, India), Ravil Kashyap (Bangalore, India), Kaushal Kishore Hebbar (Bangalore, India), Henry Thomas Peter (Mountain House, Calif.) and Simha Sadasiva (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods are disclosed for automatically extracting keys and corresponding values in any type of source document. Extracting desir...