File processing method and device based on graph neural network and storage medium

The invention belongs to the technical field of document processing and retrieval, and aims to solve the technical problems that the semantic relationship among words, sentences and documents cannot be mined and the retrieval effect is poor based on the conventional keyword retrieval technology. The invention discloses a graph neural network-based document processing method and device, an electronic device and a nonvolatile computer storage medium, and the method comprises the steps: enabling a semantic word graph to generate a deep semantic vector through employing a graph neural network technology based on supervised learning, converting the semantic vector into a binary coding mode through employing a binarization encoder technology, further generating a character feature vector, and constructing an inverted index; according to the method, the processed document can be subjected to high-performance retrieval and semantic matching based on the character feature index and the retrieval technology in the retr