A Large Language Model Driven Knowledge Graph Construction Scheme for Semantic Communication

This study presents a knowledge graph construction scheme leveraging large language models (LLMs) for task-oriented semantic communication systems. The proposed methodology systematically addresses four critical stages: corpus collection, entity extraction and relationship analysis, knowledge base g...

Full description

Saved in:
Bibliographic Details
Main Authors: Chang Guo, Jiaqi Liu, Wei Gao, Zhenhai Lu, Yao Li, Chengyuan Wang, Jungang Yang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/8/4575
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849712366789328896
author Chang Guo
Jiaqi Liu
Wei Gao
Zhenhai Lu
Yao Li
Chengyuan Wang
Jungang Yang
author_facet Chang Guo
Jiaqi Liu
Wei Gao
Zhenhai Lu
Yao Li
Chengyuan Wang
Jungang Yang
author_sort Chang Guo
collection DOAJ
description This study presents a knowledge graph construction scheme leveraging large language models (LLMs) for task-oriented semantic communication systems. The proposed methodology systematically addresses four critical stages: corpus collection, entity extraction and relationship analysis, knowledge base generation, and dynamic updating mechanisms. It is worth noting that prompt engineering is combined with few-shot learning to enhance reliability and accuracy in this methodology. Experimental demonstration showed that this methodology had superior entity extraction performance, achieving 89.7% precision and 92.3% recall rate. This scheme overcomes the demand for domain knowledge and the labor cost of traditional knowledge base construction schemes. It greatly improves the construction efficiency of knowledge graphs. This paper provides an efficient and reliable task knowledge base construction scheme for task-oriented semantic communication, which is expected to promote its wider application.
format Article
id doaj-art-04d65660a1304ff8babc9c2d013c974d
institution DOAJ
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-04d65660a1304ff8babc9c2d013c974d2025-08-20T03:14:17ZengMDPI AGApplied Sciences2076-34172025-04-01158457510.3390/app15084575A Large Language Model Driven Knowledge Graph Construction Scheme for Semantic CommunicationChang Guo0Jiaqi Liu1Wei Gao2Zhenhai Lu3Yao Li4Chengyuan Wang5Jungang Yang6College of Information and Communication, National University of Defense Technology, Wuhan 430030, ChinaCollege of Information and Communication, National University of Defense Technology, Wuhan 430030, ChinaCollege of Information and Communication, National University of Defense Technology, Wuhan 430030, ChinaCollege of Information and Communication, National University of Defense Technology, Wuhan 430030, ChinaCollege of Information and Communication, National University of Defense Technology, Wuhan 430030, ChinaCollege of Information and Communication, National University of Defense Technology, Wuhan 430030, ChinaCollege of Information and Communication, National University of Defense Technology, Wuhan 430030, ChinaThis study presents a knowledge graph construction scheme leveraging large language models (LLMs) for task-oriented semantic communication systems. The proposed methodology systematically addresses four critical stages: corpus collection, entity extraction and relationship analysis, knowledge base generation, and dynamic updating mechanisms. It is worth noting that prompt engineering is combined with few-shot learning to enhance reliability and accuracy in this methodology. Experimental demonstration showed that this methodology had superior entity extraction performance, achieving 89.7% precision and 92.3% recall rate. This scheme overcomes the demand for domain knowledge and the labor cost of traditional knowledge base construction schemes. It greatly improves the construction efficiency of knowledge graphs. This paper provides an efficient and reliable task knowledge base construction scheme for task-oriented semantic communication, which is expected to promote its wider application.https://www.mdpi.com/2076-3417/15/8/4575large language modeltask knowledge basesemantic communication
spellingShingle Chang Guo
Jiaqi Liu
Wei Gao
Zhenhai Lu
Yao Li
Chengyuan Wang
Jungang Yang
A Large Language Model Driven Knowledge Graph Construction Scheme for Semantic Communication
Applied Sciences
large language model
task knowledge base
semantic communication
title A Large Language Model Driven Knowledge Graph Construction Scheme for Semantic Communication
title_full A Large Language Model Driven Knowledge Graph Construction Scheme for Semantic Communication
title_fullStr A Large Language Model Driven Knowledge Graph Construction Scheme for Semantic Communication
title_full_unstemmed A Large Language Model Driven Knowledge Graph Construction Scheme for Semantic Communication
title_short A Large Language Model Driven Knowledge Graph Construction Scheme for Semantic Communication
title_sort large language model driven knowledge graph construction scheme for semantic communication
topic large language model
task knowledge base
semantic communication
url https://www.mdpi.com/2076-3417/15/8/4575
work_keys_str_mv AT changguo alargelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT jiaqiliu alargelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT weigao alargelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT zhenhailu alargelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT yaoli alargelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT chengyuanwang alargelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT jungangyang alargelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT changguo largelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT jiaqiliu largelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT weigao largelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT zhenhailu largelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT yaoli largelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT chengyuanwang largelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication
AT jungangyang largelanguagemodeldrivenknowledgegraphconstructionschemeforsemanticcommunication