PROBLEM TO BE SOLVED: To generate a seismic motion evaluation model capable of generating a seismic motion evaluation model for evaluating and predicting a seismic motion considered to occur in the future with high accuracy while making the best use of an increase in the amount of data and an improvement in information processing ability of a computer. I will provide a. SOLUTION: The seismic motion evaluation model generation method is a seismic motion characteristic parameter and seismic motion observation when seismic motion is observed for each combination of a plurality of earthquakes and at least one observation point where the seismic motion caused by the plurality of earthquakes is observed. Acquisition of multiple learning data 12 composed of feature quantities and objective variables from the database 10 that stores records in association with each other, with seismic motion characteristic parameters as feature quantities and seismic motion indicators obtained from seismic motion observation records as objective variables. A process and a generation process of generating a seismic motion evaluation model 13 for each observation point or for each observation point group by learning the correlation between the feature amount and the objective variable by machine learning based on a plurality of learning data 12. including. [Selection diagram] FIG. 13
展开▼