ALEXANDRIA, Va., June 18 -- United States Patent no. 12,327,187, issued on June 10, was assigned to ADP Inc. (Roseland, N.J.).

"Time-series anomaly detection via deep learning" was invented by Sheng Zhang (Harrison, N.J.), Warren Douglas Campbell (Hackettstown, N.J.) and Yongmei Jia (Basking Ridge, N.J.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for detecting anomalous data is provided. The method comprises collecting a training dataset comprising a number of transactional time series, wherein the time series comprise non-anomalous data entries for a specified transaction type. The training dataset is fed into a gated recurrent unit (GRU) network, which learns the data distribution for the trans...