Abstract: Disclosed is a method and apparatus for detecting anomalies in a system log on the basis of self-supervised learning, using a language model. The method comprises performing preprocessing on the system log, generating a normal token sequence having a preset length by concatenating tokenized log lines of the system log, generating an abnormal token sequence using the normal token sequence, calculating an anomaly score for a determination target token sequence using a sentence classification model, and determining the token sequence as an abnormal system log when the calculated anomaly score is greater than a threshold value.

Abstract: A method of distributedly storing data in a system comprising a plurality of edge nodes communicatively coupled to an end device and a central cloud. The method includes: receiving, by a first edge node, data transmitted by the end device; assigning, by the first edge node, a data tag to received data according to attributes of the received data and duplicating the received data to generate a tagged data copy; and transmitting, by the first edge node, the tagged data copy to at least one second edge node determined by a data distribution policy determined by the central cloud directly or through the central cloud, so that the at least one second edge node store the tagged data copy in a storage.