Intelligent contract state defect detection method and system based on deep learning

The invention relates to an intelligent contract state defect detection method and system based on deep learning. The method comprises the following steps: determining a plurality of smart contracts from a decentralized exchange DApp, and compiling a corresponding Solidiity smart contract source code to generate an abstract syntax tree; determining dependency features corresponding to the state of the smart contract from the abstract syntax tree; traversing the abstract syntax tree, converting each smart contract into a graph, and carrying out graph optimization processing according to dependency features; standardizing the optimized graph and dependency features by using a word vector technology to obtain graph structure data; and inputting the graph structure data into the graph convolutional network, and outputting an intelligent contract state defect prediction result. By fully learning and understanding complex modes and features in the smart contract and learning depth features and modes of graph struct