| CPC H04L 43/06 (2013.01) [H04L 41/16 (2013.01); H04L 43/04 (2013.01)] | 14 Claims |
|
1. A network monitoring apparatus comprising:
a memory configured to store a performance management data sample of a network; and
at least one processor configured to:
input both of the performance management data sample and an abnormality probability value to an auto-encoder of an abnormality detection model that is trained based on performance management data of the network, wherein the abnormality probability value is a default value for the abnormality detection model and the abnormality probability value indicates a probability that the performance management data sample is abnormal,
obtain, from the auto-encoder of the abnormality detection model, a reconstructed performance management data sample and an abnormality score value, and
detect an abnormal sample based on the abnormality score value,
wherein the auto-encoder is configured to receive the performance management data sample and the abnormality probability value, and output the reconstructed performance management data sample and the abnormality score value,
wherein the at least one processor is further configured to:
perform one loop of training of the auto-encoder by using auto-encoder training data comprising an initial value of the abnormality probability value and a first number of performance management samples to train the abnormality detection model, and
in a training process, train the abnormality probability value by using the first number of performance management samples, and update the abnormality probability value output from the auto-encoder after an amount of time periods have passed.
|