Construction engineering project risk prediction method based on one-dimensional convolutional neural network

The invention provides a constructional engineering project risk prediction method based on a one-dimensional convolutional neural network. Firstly, risks existing in a constructional engineering project are recognized, and a risk evaluation index system is constructed; a risk value of each risk evaluation index is determined; a one-dimensional convolutional neural network model is constructed totrain and learn the risk value of the constructional engineering project, the construction period risk is selected in the constructional engineering project as an output unit of the convolutional neural network, and the risk of the engineering project is predicted by analyzing the average absolute error value of the predicted value and the actual value of the construction period risk. According tothe invention, the problem of low risk prediction accuracy of a traditional constructional engineering project is solved. 本发明提供了一种基于一维卷积神经网络的建筑工程项目风险预测方法，首先对建筑工程项目存在的风险进行识别并构建风险评价指标系统，然后确定各风险评价指标的风险值，构建一维卷积神经网络模型对建筑工程项目风险值的训练