US Patent Issued to SAP on Oct. 20 for "Model-independent data extractor confidence value prediction machine learned model" (German Inventors)

ALEXANDRIA, Va., Oct. 21 -- United States Patent no. 12,770,052, issued on Oct. 20, was assigned to SAP SE (Walldorf, Germany).

"Model-independent data extractor confidence value prediction machine learned model" was invented by Nurzat Rakhmanberdieva (Berlin), Alexey Streltsov (Heidelberg, Germany) and Christian Reisswig (Berlin).

According to the abstract* released by the U.S. Patent & Trademark Office: "In an example embodiment, a confidence score is computed for a predicted label (from a first model) for information extracted from a document. The confidence score is computed using a machine learned model different than the first model which is based on a Sliding-Window method. The Sliding-Window method may be based on convolutional ne...