US Patent Issued to China UnionPay on July 7 for "Machine learning-based anomaly detection using a multi-layer predictor with hybrid inputs" (Chinese Inventors)

ALEXANDRIA, Va., July 7 -- United States Patent no. 12,675,707, issued on July 7, was assigned to China UnionPay Co. Ltd. (Shanghai).

"Machine learning-based anomaly detection using a multi-layer predictor with hybrid inputs" was invented by Wenqi Li (Shanghai), Gao Lin (Shanghai), Jinjie Liu (Shanghai), Zhenhu Le (Shanghai) and Yang Zhao (Shanghai).

According to the abstract* released by the U.S. Patent & Trademark Office: "Disclosed are a method and an apparatus for real-time data monitoring based on machine learning, the method including: training a multi-layer predictor on actual values of historical indicator data, each layer of the multi-layer predictor including a plurality of predictors of different types; outputting predicted val...