Abnormality detection method and electronic device

Provided is an anomaly detection method capable of minimizing computing resource consumption and time consumption. The anomaly detection method includes: learning a first classifier including an encoder and a decoder using a plurality of training data classified into a plurality of first subsets; calculating a plurality of training data by using an encoder of the learned first classifier, and extracting features from the plurality of training data; clustering the plurality of training data based on the extracted features, and reconstructing the plurality of training data into a plurality of second subsets; learning a plurality of second classifiers corresponding to the plurality of second subsets using the second subsets; and detecting any anomalies in the input data using a plurality of second classifiers. 提供了一种能够最小化计算资源消耗和时间消耗的异常检测方法。该异常检测方法包括：使用被分类成多个第一子集的多个训练数据来学习包括编码器和解码器的第一分类器；通过利用所学习的第一分类器的编码器计算多个训练数据，从多个训练数据中提取特征；通过基于所提取的特征对多个训练数据进行聚类，将多个训练数据重构为多个第二子集；使用第二子集来学习与多个第二子集对应的多个第二分类器；以及使用多个第二分类器来检测输入数据中的任何异