Although interest in indoor space modeling is increasing, the quantity of indoor spatial data available is currently very scarce compared to its demand. Many studies have been carried out to acquire indoor spatial information from floorplan images because they are relatively cheap and easy to access. However, existing studies do not take international standards and usability into consideration, they consider only 2D geometry. This study aims to generate basic data that can be converted to indoor spatial information using IndoorGML (Indoor Geography Markup Language) thick wall model or the CityGML (City Geography Markup Language) level of detail 2 by creating vector-formed data while preserving wall thickness. To achieve this, recent Convolutional Neural Networks are used on floorplan images to detect wall and door pixels. Additionally, centerline and corner detection algorithms were applied to convert wall and door images into vector data. In this manner, we obtained high-quality raster segmentation results and reliable vector data with node-edge structure and thickness attributes that enabled the structures of vertical and horizontal wall segments and diagonal walls to be determined with precision. Some of the vector results were converted into CityGML and IndoorGML form and visualized, demonstrating the validity of our work.

A critical problem in mapping data is the frequent updating of large data sets. To solve this problem, the updating of small-scale data based on large-scale data is very effective. Various map generalization techniques, such as simplification, displacement, typification, elimination, and aggregation, must therefore be applied. In this study, we focused on the elimination and aggregation of the building layer, for which each building in a large scale was classified as “0-eliminated,” “1-retained,” or “2-aggregated.” Machine-learning classification algorithms were then used for classifying the buildings. The data of 1:1000 scale and 1:25,000 scale digital maps obtained from the National Geographic Information Institute were used. We applied to these data various machine-learning classification algorithms, including naive Bayes (NB), decision tree (DT), k-nearest neighbor (k-NN), and support vector machine (SVM). The overall accuracies of each algorithm were satisfactory: DT, 88.96%; k-NN, 88.27%; SVM, 87.57%; and NB, 79.50%. Although elimination is a direct part of the proposed process, generalization operations, such as simplification and aggregation of polygons, must still be performed for buildings classified as retained and aggregated. Thus, these algorithms can be used for building classification and can serve as preparatory steps for building generalization.

In recent years, question answering on knowledge bases (KBQA) has emerged as a promising approach for providing unified, user-friendly access to knowledge bases. Nevertheless, existing KBQA systems struggle to answer spatial-related questions, prompting the introduction of geographic knowledge ba se question answering (GeoKBQA) to address such challenges. Current GeoKBQA systems face three primary issues: (1) the limited scale of questions, restricting the effective application of neural networks; (2) reliance on rule-based approaches dependent on predefined templates, resulting in coverage and scalability challenges; and (3) the assumption of the availability of a golden entity, limiting the practicality of GeoKBQA systems. In this work, we aim to address these three critical issues to develop a practical GeoKBQA system. We construct a large-scale, high-quality GeoKBQA dataset and link mentions in the questions to entities in OpenStreetMap using an end-to-end entity-linking method. Additionally, we develop a query generator that translates natural language questions, along with the entities predicted by entity linking into corresponding GeoSPARQL queries. To the best of our knowledge, this work presents the first purely neural-based GeoKBQA system with potential for real-world application.

Recently, open-domain question-answering systems have achieved tremendous progress because of developments in large language models (LLMs), and have successfully been applied to question-answering (QA) systems, or Chatbots. However, there has been little progress in open-domain question answering in the geographic domain. Existing open-domain question-answering research in the geographic domain relies heavily on rule-based semantic parsing approaches using few data. To develop intelligent GeoQA agents, it is crucial to build QA systems upon datasets that reflect the real users’ needs regarding the geographic domain. Existing studies have analyzed geographic questions using the geographic question corpora Microsoft MAchine Reading Comprehension (MS MARCO), comprising real-world user queries from Bing in terms of structural similarity, which does not discover the users’ interests. Therefore, we aimed to analyze location-related questions in MS MARCO based on semantic similarity, group similar questions into a cluster, and utilize the results to discover the users’ interests in the geographic domain. Using a sentence-embedding-based topic modeling approach to cluster semantically similar questions, we successfully obtained topic models that could gather semantically similar documents into a single cluster. Furthermore, we successfully discovered latent topics within a large collection of questions to guide practical GeoQA systems on relevant questions.

With the diversification of three-dimensional (3D) urban space data sources and data collection methods, the Open Geospatial Consortium published 3D spatial data standards in Geography Markup Language (GML). Among them, IndoorGML is a data model for expressing the topological relationship between indoor spaces with advantages in terms of semantic information storage and navigation applications. Conversion into a suitable binary file must be accomplished to use the IndoorGML documents through integration with other data. This study proposes a method of generating graph database objects from the documents of IndoorGML to promote usability and interoperability. The labeled property graph model is designed to reflect IndoorGML’s multilayered graph concept. Moreover, in the proposed graph model, the geometry of physical indoor spaces is segregated into separate surfaces. All elements from IndoorGML are managed with specific labels in Neo4j, the most dominant graph database. By applying the proposed method, the graph database is constructed using the officially distributed IndoorGML documents of three buildings. The number of generated graph objects is determined to confirm whether the IndoorGML features are accurately converted into graph database objects. Furthermore, the utility of the constructed graph database is verified through two scenario-based routing tests consisting of finding the optimal room with the lowest route cost and allocating indoor spaces for patrolling to outdoor security offices through indoor and outdoor data integration. In conclusion, this study confirms that the utility of IndoorGML can be promoted using a graph database system in data integration, data queries, and pathfinding applications while preserving data topology and interoperability.

With the boom in online information, knowledge graphs like Freebase, Wikidata, and YAGO have emerged, thanks to the introduction of the RDF (Resource Description Framework). As RDF data grew, more and more spatial data was incorporated into it. While we have a lot of 2D data for outdoor spaces, mapping indoor spaces in 3D is challenging because it is expensive and time-consuming. In our research, we turned 2D blueprints into detailed 3D maps and then translated this into RDF format. We used the Jeonju Express Bus Terminal in South Korea as our test case. We made an automated tool that can turn 2D spatial data into 3D data that fits the IndoorGML standard. We also introduced terms like ‘loc’, ‘indoorgml-lite’, and ‘bloc’ to describe indoor spaces in the RDF format. Once we put our data into a GraphDB database, we could easily search for specific details and routes inside buildings. This work fills a significant gap in knowledge graphs concerning indoor spaces. However, the production of large-scale data across varied areas remains a challenge, pointing towards future research directions for more comprehensive indoor spatial information systems.