BERT-based film and television work regional knowledge graph construction method and system

Abstract

The invention relates to a BERT-based film and television work regional knowledge graph construction method, and the method comprises the steps of collecting film and television work text data, constructing a regional domain dictionary, carrying out the preprocessing and word segmentation of the text data, and obtaining the regional associated data of the film and television work; defining entities in the regional associated data, and establishing an association relationship between the entities; marking entities and entity relationships in the regional associated data of the film and television works; training the BERT model; extracting the unlabeled film and television works by utilizing a BERT model to obtain an entity relationship of the film and television works; and storing the obtained entity relationship of the film and television works into a graph database to obtain a regional characteristic knowledge graph of the film and television works. The invention further discloses a corresponding knowledge graph construction system. According to the invention, automatic construction of the regional characteristic knowledge graph is realized, and the constructed regional characteristic knowledge graph of the film and television works is beneficial for culture propaganda personnel and researchers to establish visual impressions of regional characteristics of the film and television works and analyze regional differences of the film and television works.

Description

technical field [0001] The invention belongs to the field of intelligent text recognition, and in particular relates to a BERT-based regional knowledge map construction method and system for film and television works. Background technique [0002] The knowledge map was first proposed by Google in 2012, and it was first mainly used in search engines to accurately describe the relationship between people, things, and things. The knowledge graph includes three main elements: entities, relationships, and attributes. The construction of the knowledge map first determines the knowledge representation model, then selects different knowledge acquisition methods according to different knowledge sources and imports relevant knowledge, then builds the corresponding knowledge map based on knowledge reasoning, knowledge fusion and other technologies, and finally designs the knowledge map according to different application scenarios way of expression. As a knowledge storage management m...

AI Technical Summary

Problems solved by technology

At present, domestic research on the construction of knowledge graphs in large fields such as medical care, electricity, finance, and education is relatively rich, but there is relatively little knowledge graph construction in fine fields such as film and television works.

Images