Raytheon Company secures US patent for unsupervised pattern discovery using dynamic graph embeddings.
The filing
Raytheon Company received a US grant on November 10, 2026 for a method that discovers patterns in data without human supervision by analyzing continuous-time dynamic graphs. The system receives source and destination node embeddings from a graph neural network, clusters the destination embeddings to separate signal from noise, and then identifies patterns based on the remaining signal groups and the source embeddings.
This filing’s full text wasn’t read for this issue, so its claims and the applicant’s background aren’t shown. Both are in the record, under Sources.