Parameter setting method, data analysis device, data analysis system and program

A data analysis device that can set a parameter, the data analysis device including a computer having an arithmetic device that executes a predetermined process, a storage device that is connected to the arithmetic unit, and a communication interface that is connected to the arithmetic device, the data analysis device comprising:

• a configuration accumulation unit that accumulates a parameter setting configuration for each model corresponding to an analysis target system;
• a data input unit that acquires time-series data including data of a plurality of items from the analysis target system;
• a temporal change feature calculation unit that extracts data of at least one first item from the time series data and calculates a feature of a temporal change of the data of the first item;
• a relevance feature calculation unit that extracts data of at least one second item from the time series data and calculates a feature of at least one of a relevance between the data of the first item and the data of the second item and a relevance between the data of a plurality of the second items;
• a model determination unit that determines a model corresponding to the analysis target system based on the feature of the temporal change and the change of the relevance;
• and
• a parameter setting unit that sets the parameter in the analysis target system by using the parameter setting configuration of the model corresponding to the analysis target system.

A data analysis system that can set a parameter, comprising:

• a unit that accumulates a parameter setting configuration for each of a plurality of models by making an analysis target system in correspondence with the plurality of models;
• a unit that acquires time-series data including data of a plurality of items from the analysis target system;
• a unit that extracts data of at least one first item from the time series data and calculating a feature of a temporal change of the data of the first item;
• a unit that extracts data of at least one second item from the time series data and calculating a feature of at least one of a relevance between the data of the first item and the data of the second item and a relevance between the data of a plurality of the second items;
• a unit that determines a model corresponding to the analysis target system based on the feature of the temporal change and the change of the relevance;
• and
• a unit that sets the parameter in the analysis target system by using the parameter setting configuration of the model corresponding to the analysis target system.