公开(公告)号：US20250068884A1

公开(公告)日：2025-02-27

申请号：US18378665

申请日：2023-10-11

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Kuang Ping Tseng ,  Wen Jen Ho ,  Chia Wei Tsai ,  Kuei Chun Chiang ,  Yung Chieh Hung

IPC: G06N3/045 ,  G06N3/084

Abstract: An anomaly detection model training method, anomaly detection methods, and load detection devices for household electricity are provided. The anomaly detection method is applied to the load detection device, which includes a processing unit and an anomaly detection model. The processing unit trains the anomaly detection model and performs an anomaly detection method. The anomaly detection method includes: extracting user electrical features to obtain feature data; grouping the feature data based on electricity consumption behavior and inputting them into the first and second single classification models respectively to generate detection results corresponding to the first and second single classification models; generating anomaly electricity detection results based on the detection results; differentiating the electricity load data according to unit time to become a plurality segments of sub-electricity load data; and comparing the segments of sub-electricity load data with the historical load data to output a plurality of anomaly electricity consumption periods.