Prediction method and system for patent application authorization success rate and electronic equipment

The invention discloses a prediction method and system for patent application authorization success rate and electronic equipment. The method comprises the steps: obtaining the historical invention data of a public patent applicant and an application company from the State Intellectual Property Office, and constructing a heterogeneous information network; filtering patent text information of historical invention data, reserving only description texts of the abstract and the right part of the specification, carrying out word segmentation and stop word preprocessing on the description texts, andsorting the description texts into a language material set; and respectively training a deep learning model based on a natural language processing technology and a node classification model based ona graph convolutional neural network technology for the corpus set to obtain a document vector and a feature vector; fusing the document vector, the feature vector and the heterogeneous information network, and predicting the