Data processing device, data processing method, and storage medium

A data processing method comprising:

• extracting time-series data indicating observed values at points in time in an analysis range from a first point in time to a second point in time;
• calculating a gradient of a linear function indicating a trend of change in the observed values in the analysis range to minimize an objective function, the objective function indicating a sum of multiplication values at the points in time within the analysis range, each of the multiplication values being a numerical value obtained by multiplying a square of a difference between a function value of the linear function and each of the observed values at each of the points in time within the analysis range by a weighting coefficient, the weighting coefficient being a numerical value that increases as an elapsed time from the first point in time to each point in time increases;
• calculating a deviation of an input value input from a control target and a target value of the input value as the observed values;
• and
• calculating an output value to be output to the control target on the basis of at least the gradient at a present point in time.

A non-transitory computer-readable storage medium storing a program, which when executed by a computer, causes the computer to:

• extract time-series data indicating observed values at points in time in an analysis range from a first point in time to a second point in time;
• calculate a gradient of a linear function indicating a trend of change in the observed values in the analysis range to minimize an objective function, the objective function indicating a sum of multiplication values at the points in time within the analysis range, each of the multiplication values being a numerical value obtained by multiplying a square of a difference between a function value of the linear function and each of the observed values at each of the points in time within the analysis range by a weighting coefficient, the weighting coefficient being a numerical value that increases as an elapsed time from the first point in time to each point in time increases;
• calculate a deviation of an input value input from a control target and a target value of the input value as the observed values;
• and
• calculate an output value to be output to the control target on the basis of at least the gradient at a present point in time.