ALEXANDRIA, Va., Sept. 8 -- United States Patent no. 12,731,034, issued on Sept. 8, was assigned to NEC Corp. (Japan).

"Compact representation and time series segment retrieval through deep learning" was invented by Takehiko Mizoguchi (West Windsor, N.J.), Dongjin Song (Princeton, N.J.), Yuncong Chen (Plainsboro, N.J.), Cristian Lumezanu (Princeton Junction, N.J.) and Haifeng Chen (West Windsor, N.J.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for retrieving similar multivariate time series segments are provided. The systems and methods include extracting a long feature vector and a short feature vector from a time series segment, converting the long feature vector into a long binary c...