This study presents the development of a web-based map, referred to as the "Mochi Map," designed to visualize the cultural significance of Mochis across various regions of Japan and to provide a deeper understanding of the relationship between regional identities and local cuisines. Existing systems have shown limitations in systematically organizing detailed information about Mochi components, production methods, and their cultural contexts. Moreover, a comprehensive ontology capturing the diverse aspects of Mochi culture remains incomplete. To address these gaps, this study focuses on constructing a foundational ontology for specific types of Mochis, systematically organizing elements such as ingredients, production techniques, applications, regional characteristics, and historical contexts, while structuring the interrelations among these factors. This framework aims to support future iterations of the "Mochi Map," enhancing its functionality and cultural representation.

To reduce development time, we are creating a chatbot system using Retrieval-Augmented Generation (RAG) to handle specialized inquiries. Challenges include the unfamiliarity of Large Language Model (LLM) with specific terms and the handling of ambiguous queries. We propose using a knowledge graph to supplement terms with explanations, synonyms, and hierarchical concepts. We developed a method using LLM to construct knowledge graphs for RAG more efficiently, maintaining accuracy while significantly reducing processing time compared to traditional methods. This paper details the methods for automating synonym and hierarchical relationship estimation using LLM.

The Genji Monogatari (Tale of Genji), written during the Heian period, is often referred to as the "world's oldest long romance novel" and features around 400 characters. However, due to the cultural practice of referring to characters by their roles or titles rather than by specific names, this creates challenges in the analysis of characters and content in Japanese classical literature. Therefore, this study aims to comprehensively identify the conditions for addressing each character and proposes a knowledge graph. Additionally, the relationships between characters, based on the knowledge graph, will be represented, and the usefulness of this approach will be evaluated.

The folk tools(Min-Goo) held in many local folklore museums are important materials for understanding the culture and history of the region. Managing these folk tools requires various metadata, such as regional characteristics, usage, and historical context. However, due to challenges like a small management team, lack of expertise in information science, and insufficient technical staff, efficient management has been difficult. This paper aims to construct an ontology for the preservation and management of folk tools held in folklore museums, with the goal of facilitating more efficient preservation, management for a digital archive.

Many life science data have been published in RDF. In general, life science data are diverse and store knowledge about various relevant concepts and relationships among them. These concepts include proteins, genes, compounds, and diseases, and are represented by identifiers in databases. To understand biological phenomena, it is crucial to extensively investigate their characteristics and relationships among them, and it is ideal to use one and only identifier for a concept over the databases, but in reality, multiple identifiers are often used for a concept. The Database Center for Life Sciences (DBCLS) has gathered life science RDF data and published them at RDF Portal. Here, we have investigated the synonym URIs in it and examined the challenges and future works.