Method and device for constructing multi-domain knowledge graph, electronic equipment and storage medium

Abstract

This application provides a method, apparatus, electronic device, and storage medium for constructing a multi-domain knowledge graph, relating to the field of knowledge graph construction technology. The method includes: constructing a text dataset and performing domain filtering based on a pre-selected large language model to obtain domain text datasets for target domains (single-domain, related-domain, and full-domain); further performing sentence segmentation, word segmentation, and part-of-speech tagging; extracting nouns from the segmented word dataset to obtain target entities; performing word segmentation and dependency syntax relation extraction on each sentence in the target domain text dataset, and reconstructing a dictionary list of target dependency syntax relations to extract relationships between different domains; and constructing a multi-domain knowledge graph based on entities and relations. The multi-domain knowledge graph constructed in this application is more comprehensive, accurate, and efficient, requiring no large amounts of data for model training, thus saving significant time, manpower, and computational resources.

Images