US Patent Issued to Oracle International on July 7 for "Techniques for detecting anomalous data points in time series data" (California, Washington Inventors)

ALEXANDRIA, Va., July 7 -- United States Patent no. 12,675,494, issued on July 7, was assigned to Oracle International Corp. (Redwood Shores, Calif.).

"Techniques for detecting anomalous data points in time series data" was invented by Amir Hossein Rezaeian (San Mateo, Calif.) and Hariharan Balasubramanian (Redmond, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques for increasing the precision of machine learning models that are trained to detect anomalous data points in a time series. The techniques including methods and systems for training machine learning models offline, using the trained machine learning models to predict anomalies in an online runtime environment, and updating anomaly det...