A state change detection unit obtains the data occurrence probability based on the values of observation data and the value of a parameter of a prior distribution, obtains, based on the data generation probability, a run length probability distribution when the time-series observation data acquired up to the current time point is used as a condition, and detects a change in the state of a facility based on the run length probability distribution. An update unit updates the value of the parameter of the prior distribution using the value of the observation data, to generate the prior distribution for calculating the data occurrence probability at a next time point. In cases when the current time point is determined to be a change point in the state of the facility, the state change detection unit also searches for a change indication point based on the run length probability distribution.