US Patent Issued to Bentley Systems on Feb. 24 for "Classifying elements in an infrastructure model using convolutional graph neural networks" (Canadian Inventors)

ALEXANDRIA, Va., Feb. 24 -- United States Patent no. 12,561,564, issued on Feb. 24, was assigned to Bentley Systems Inc. (Exton, Pa.).

"Classifying elements in an infrastructure model using convolutional graph neural networks" was invented by Marc-Andre Lapointe (Quebec City), Louis-Philippe Asselin (Quebec City), Karl-Alexandre Jahjah (Quebec City) and Evan Rausch-Larouche (Quebec City).

According to the abstract* released by the U.S. Patent & Trademark Office: "In example embodiments, techniques are provided for classifying elements of infrastructure models using a convolutional graph neural network (GNN). Graph-structured data structures are generated from infrastructure models, in which nodes represent elements and edges represent con...