摘要 |
PROBLEM TO BE SOLVED: To provide a method for detecting a sign of a system failure occurrence with a plurality of various information processing systems as objects.SOLUTION: A system for monitoring a plurality of monitoring object systems receives measurement values about a plurality of indexes, designates from a plurality of prediction models a prediction model for predicting a future measurement value from a measurement value received about a reference index, predicts a prediction value of the reference index on the basis of the designated prediction model, generates or updates a Bayesian network with the reference index and a target index as objects, and calculates a probability that a measurement value of the target index is a prescribed value or value range. |