Construction method and system of tumor onset risk prediction model for assisted reproduction of children

The invention discloses a construction method and system of an assisted reproduction child tumor onset risk prediction model, and relates to the technical field of model training, and the method comprises the steps: collecting original related data, and carrying out the regression analysis to screen influence data; preprocessing the influence data to obtain various feature data sets; performing importance analysis on each type of feature data set by adopting a convolutional neural network model, and dividing feature variables in each type of feature data set according to importance; and constructing a hybrid neural network model, performing model training on the hybrid neural network model by taking the main feature variables and the composite feature variables of the various feature data sets in the training set as input feature variables, and using the hybrid neural network model. According to the construction method and system for the assisted reproduction children tumor onset risk prediction model, predic