Abstract: The demand estimation apparatus includes a demand estimation unit that estimate demand for a new component by inputting meta-information of the new component and information regarding use of the new component to a first machine learning model. The first machine learning model is constructed by machine learning using the second machine learning model, meta information of an existent component that is training data for the second machine learning model, and meta information of new component. The second machine learning model predicts demand for existent component using the meta information of the existent component and information regarding use of existent component as input.

Abstract: Reception means 81 receives an estimator learned using measured data up to a point of time in the past, verification data that is measured data from the point of time onward, and an update rule prescribing whether or not the estimator needs to be updated based on an evaluation index. Simulation means 82 simulates at least one of the evaluation index of the estimator and an update result of the estimator in a predetermined period, based on the update rule and an estimation result calculated by applying the verification data of the predetermined period to the estimator in chronological order.

Abstract: Reception means 81 receives an estimator learned using measured data up to a point of time in the past, verification data that is measured data from the point of time onward, and an update rule prescribing whether or not the estimator needs to be updated based on an evaluation index. Simulation means 82 simulates at least one of the evaluation index of the estimator and an update result of the estimator in a predetermined period, based on the update rule and an estimation result calculated by applying the verification data of the predetermined period to the estimator in chronological order.

Abstract: In a production line simulator, an evaluation value of parameter adapted for real data (standard time as a processing period in processing a certain product by a certain production facility through a certain production process) computed at high reliability. From event reported from each production facility in a production line, a process period of the certain product by the certain production facility through the certain production process is derived for deriving the evaluation value on the basis of the derived process period. For deriving the evaluation value, an accumulated data in a is sorted sequential order of values. Then, a first center value is determined on the basis of result of sorting, and data on which an absolute value of a difference with the first center value becomes smaller is detected. A zone where number of the data to be detected exceeds half of all data number, is set.