From Dispersed Records to Structured Knowledge: A Graph-based Knowledge Modeling Framework for Archival Resources

Zhaoyang Zhang, Yang Zhang, Quan Z. Sheng, Jia Wu, Yaolin Zhou

Abstract: The effective organization and utilization of dis-persed archival resources remain a significant challenge in archival management services. This paper proposes a structured graph-based knowledge modeling framework to transform dispersed archival records into a structured knowledge system for enhanced analysis and knowledge discovery. The framework uncovers latent knowledge embedded within archival records by applying metadata extraction, semantic annotation, ontology construction, and graph-based visualization methods. Specifically, we first design a metadata schema that integrates both standard and customized elements to maximize the machine-readable representation of archival content. Based on this schema, a domain ontology comprising five core classes is constructed to systematically represent the semantic structure of the archival collection. Secondly, we develop an intelligent processing platform to handle multimodal resources, supporting automatic metadata extraction, manual annotation, and comprehensive data prepro-cessing. Lastly, we take unstructured COVID-19-related archival materials as a case study to demonstrate how the system organizes and links archival knowledge, which significantly improves the retrieval, reuse, and discovery of valuable resources.

External IDs:dblp:conf/icws/ZhangZSWZ25