| CPC H04L 43/08 (2013.01) [H04L 41/145 (2013.01)] | 11 Claims |
|
1. An electronic device comprising:
at least one processor,
wherein the at least one processor is configured to:
determine a representative cause representing a cause of each anomaly sample of a quality indicator indicating a quality of a network,
perform a time-series analysis on an indicator associated with the representative cause,
propose a solution corresponding to the representative cause and a result of the time-series analysis,
determine a first time interval for detecting an anomaly of the quality indicator indicating the quality of the network,
detect one or more anomaly samples of the quality indicator of the network during the first time interval,
determine a representative cause representing a cause of each of the one or more anomaly samples,
perform a time-series analysis on an indicator associated with the representative cause during a second time interval comprising the first time interval,
determine the second time interval comprising the first time interval,
determine the indicator associated with the representative cause,
perform the time-series analysis on the indicator associated with the representative cause during the second time interval, and
determine a time corresponding to a predetermined sample prior to a start time of the first time interval as a start time of the second time interval,
wherein the at least one processor is configured to:
determine a cause of each of one or more anomaly samples, and
determine a representative cause representing causes of the one or more anomaly samples, and
wherein the at least one processor is configured to:
input the one or more anomaly samples to a neural network that is trained based on a plurality of pieces of training data associated with a corresponding relationship between an anomaly sample and a cause, and
determine a cause of each of the one or more anomaly samples from an output of the neural network.
|