Agricultural disease and pest problem intention recognition method and system based on knowledge graph

The invention relates to a crop disease and insect pest problem intention recognition method and system based on a knowledge graph, and the method comprises the steps: 1, collecting crop disease and insect pest data, and constructing a disease and insect pest knowledge graph; step 2, constructing disease and insect pest questions from a peasant household consultation question corpus, and forming a training set and a test set in a certain proportion; and step 3, constructing a neural network identification model, and identifying and responding to the consultation problem intention of the peasant household. According to the invention, the knowledge graph based on diseases and insect pests is constructed, and services are provided for accurate matching and generation of answer sentences of a disease and insect pest knowledge question-answering system; a BERT + TextCNN convolutional neural network model is adopted, and processing, modeling, training and calculation are performed on peasant household consultation