Skip to Content
ElectronicsElectronics
  • Article
  • Open Access

17 December 2025

19 Pages

Implementing a Knowledge Management System with GraphRAG: A Physical Internet Example

,
and
1
International Maritime Research Center, Kobe University, Kobe 658-0022, Japan
2
Graduate School of Maritime Sciences, Kobe University, Kobe 658-0022, Japan
3
Graduate School of Information Science, University of Hyogo, Kobe 650-0047, Japan
*
Author to whom correspondence should be addressed.

Abstract

The rapid expansion and interdisciplinary nature of Physical Internet (PI) research have resulted in fragmented knowledge, limiting the ability of stakeholders to identify emerging trends, actionable insights and genuine research gaps. This study introduces a novel knowledge management approach that uses Graph Retrieval-Augmented Generation (GraphRAG) to systematically organize and integrate PI-related literature. A comprehensive knowledge graph was constructed by extracting and semantically modeling entities and relationships from 2835 academic papers, conference proceedings and international roadmaps. The developed system incorporates fuzzy semantic search and multiple retrieval strategies, including local, global and hybrid approaches, enabling nuanced, context-aware access to information. Stakeholder-specific prompts, tailored to the needs of industry, government and academia, demonstrate how GraphRAG can support the discovery of business model innovations, policy design and underexplored research areas. A comparative evaluation using cosine similarity and BERTScore confirms that graph-based strategies outperform standard LLM retrieval in providing relevant and comprehensive answers while also revealing connections that would be missed in manual reviews. The results demonstrate that the proposed GraphRAG model is a scalable and extensible framework for addressing knowledge gaps and promoting collaboration in PI research synthesis for sustainable logistics. The model also shows promise for application in other complex domains.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.