Rule-based knowledge graph construction method and system

The invention discloses a rule-based knowledge graph construction method and system, belongs to the technical field of data processing, and aims to solve the technical problem of how to accurately identify entities and relationships and improve the accuracy and integrity of a knowledge graph. Comprising the following steps: carrying out word segmentation, part-of-speech tagging, named entity recognition and entity disambiguation on an input text, and carrying out relation extraction; constructing a feature extraction model based on a CNN algorithm, taking the entity and the relationship as input, and performing feature extraction on the entity and the relationship through the trained feature extraction model; clustering the feature vector matrix into a predetermined number of clusters through a K-means algorithm; and connecting the entities and the relationships in the same cluster to form a graph structure, constructing a rule prediction model based on a graph convolutional neural grid, analyzing rules and a