Method and device for generating process simulation model

The invention provides a method and a neural network device for generating a simulation model based on simulation data and measurement data of a target. The method comprises the steps that weight parameters included in a pre-learning model based on simulation data learning are classified into a first weight set and a second weight set based on the importance degree; retraining a first weight group of the pre-learning model based on the simulation data; and training a second weight group of a transfer learning model based on the measurement data, the transfer learning model including a first weight group of a pre-learning model retrained based on the simulation data. 提供了一种基于目标的仿真数据和测量数据来生成仿真模型的方法和神经网络装置。该方法包括：基于重要性程度将基于仿真数据学习的预学习模型中所包括的权重参数分类为第一权重组和第二权重组；基于仿真数据来重新训练预学习模型的第一权重组；以及基于测量数据来训练迁移学习模型的第二权重组，其中，迁移学习模型包括基于仿真数据重新训练的预学习模型的第一权重组。