基于数据融合的水利工程质量风险评估研究OA

With the development of water conservancy informatization and the proposal of strong supervision in the water conservancy industry,mining the massive data accumulated in business systems and building a precise and intelligent water conservancy engineering supervision system is a key issue that urgently needs to be overcome for the digital transformation of the water conservancy industry.This study combines engineering quality risks,applies natural language processing technology and deep learning technology,and uses various data such as quality supervision text,engineering information,and project participants information,to construct a water conservancy project quality risk assessment model based on multi-input long short-term memory neural network(LSTM).The results show that the accuracy of the model proposed in this study reaches 88.61%,which has higher accuracy and robustness compared to single input LSTM that only uses quality supervision text as features.It can assist relevant departments in implementing differentiated supervision and realize automatic advance warning of water conservancy project quality risks.