METHOD AND SYSTEM FOR CONSTRUCTING META MODEL BASED ON MACHINE LEARNING

摘要

Disclosed is a design expert system comprising: a predictive model generation unit for generating a predictive model by using experimental data collected by a design target experiment and keywords describing the experimental data; a data generation unit for generating characteristic data using an approximate model for identifying characteristics of a design object; a data analysis unit for analyzing the generated characteristic data; and a design optimization unit for performing design optimization of the design target according to the optimal design algorithm using various data analysis results based on the prediction model. According to the present invention, it is possible to obtain an optimized performance improvement result only by inputting data in an optimal design and multidimensional data analysis and setting a design target.