Ontology-Based Survey Knowledge Modeling to Support The Renovation of Historical Building

Abstract

The renovation of historical buildings requires a comprehensive survey to gather essential data, which is critical for planning effective restoration strategies. However, the typical textual presentation of survey information poses significant challenges for designers to fully consider the information when devising conservation and renovation plans as its unsuitability for knowledge retrieval. There are few effective methods for modeling this survey data, particularly in Chinese. This paper proposes an ontology-based approach for the knowledge modeling of historical building surveys. It begins with the development of a domain-specific ontology, which is followed by the creation of a comprehensive Chinese dataset of historical building survey knowledge. Using the CASREL method, an extractor was trained to retrieve knowledge triples from this dataset, achieving a 78% recall rate. The process concludes with the implementation of a graph database for efficient knowledge extraction and storage. This method provides a robust foundation for enhancing knowledge retrieval in the renovation of historical buildings, ensuring that valuable historical information is reserved and effectively utilized in restoration efforts. The proposed approach aims to bridge the gap in current research by providing a systematic way to manage and retrieve historical building survey data.