ALEXANDRIA, Va., Aug. 20 -- United States Patent no. 12,394,191, issued on Aug. 19, was assigned to Google LLC (Mountain View, Calif.).
"Neural networks based multimodal transformer for multi-task user interface modeling" was invented by Yang Li (Palo Alto, Calif.), Xin Zhou (Mountain View, Calif.), Gang Li (Mountain View, Calif.), Mostafa Dehghani (Amsterdam) and Alexey Alexeevich Gritsenko (Amsterdam).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving, via a computing device, a screenshot of a display provided by a graphical user interface of the computing device. The method also includes generating, by an image-structure transformer of a neural network, a representation by fusing a ...