US Patent Issued to Oracle International on Jan. 13 for "Training graph neural network to identify key-value pairs in documents" (Australian Inventors)

ALEXANDRIA, Va., Jan. 13 -- United States Patent no. 12,524,611, issued on Jan. 13, was assigned to Oracle International Corp. (Redwood Shores, Calif.).

"Training graph neural network to identify key-value pairs in documents" was invented by Xu Zhong (Vermont South, Australia), Thanh Long Duong (Point Cook, Australia) and Mark Johnson (Castle Cove, Australia).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques for identifying content in key-value pairs of documents using a graph neural network (GNN) are disclosed. A system trains a GNN to identify key-value pair groupings in documents. The GNN classifies nodes in document graphs as key-type nodes and answer-type nodes. The GNN also classifies edges conn...