The development and popularization of navigation applications are increasing expectations for their quality and functionality. Users need continuous navigation not only outdoors, but also indoors. In this case, however, the perception of space and movement is somewhat different than it is outside. One potential method of meeting this need may be the use of so-called geo-descriptions—multi-level textual descriptions relating to a point, line or area in a building. Currently, geo-descriptions are created manually. However, this is a rather time-consuming and complex process. Therefore, this study undertook to automate this process as much as possible. The study uses classical methods of spatial analysis from GIS systems and text generation methods based on artificial intelligence (AI) techniques, i.e., large language models (LLM). In this article, special attention will be paid to the second group of methods. As part of the first stage of the research, which was aimed at testing the proposed concept, the possibility of LLMs creating a natural description of space based on a list of features of a given place obtained by other methods (input parameters for AI), such as coordinates and categories of rooms around a given point, etc., was tested. The focus is on interior spaces and a few selected features of a particular place. In the next stages, it is planned to extend the research to spaces outside buildings. In addition, artificial intelligence can be used to provide the input parameters mentioned above.
There are still relatively few applications that serve the function of a traditional tactile map, allowing visually impaired individuals to explore a digital map by sliding their fingers across it. Moreover, existing technological solutions either lack a spatial learning mode or provide only limited functionality, focusing primarily on navigating to a selected destination. To address these gaps, the authors have proposed an original concept for an indoor mobile application that enables map exploration by sliding a finger across the smartphone screen, using audio spatial descriptions as the primary medium for conveying information. The spatial descriptions are hierarchical and contextual, focusing on anchoring them in space and indicating their extent of influence. The basis for data management and analysis is GIS technology. The application is designed to support spatial orientation during user interaction with the digital map. The research emphasis was on creating an effective cartographic communication message, utilizing voice-based delivery of spatial information stored in a virtual building model (within a database) and tags placed in real-world buildings. Techniques such as Text-to-Speech, TalkBack, QRCode technologies were employed to achieve this. Preliminary tests conducted with both blind and sighted people demonstrated the usefulness of the proposed concept. The proposed solution supporting people with disabilities can also be useful and attractive to all users of navigation applications and may affect the development of such applications.
For many years, the number of applications and research related to assisted navigation in buildings has steadily increased. Some of them use textual descriptions of space, called geo-descriptions in short, in navigation. Geodescriptions are specially constructed multi-level textual descriptions associated with a space (a point, a line, an area), which can be displayed on the screen or read, for example, by a speech synthesiser at the appropriate moment in the localisation or navigation process, as well as during spatial analysis of an object. They complement the traditional cartographic transmission of information in graphic form. They can be beneficial in tourism applications, in assisting special services and in assisting people with disabilities (including blind people). An example of a geo-description is: "You are in the Main Building of the University Campus on the second floor in the northern part of the building. You are in the corridor leading to the Main Library. In the opposite direction you can walk to the Main Auditorium and to the elevator adapted for people with disabilities. This part of the building also houses the teaching laboratories of the Department of Geodesy and Cartography and the Center for International Cooperation. The main exit is about 80 meters from where you are." Currently, geo-descriptions are created manually. However, this is a time-consuming and complex process. The research conducted has shown that there are not yet solutions that lead to the results assumed by the authors of this article. It is not enough to use existing Natural Language Processing (NLP) techniques by issuing a command like "Generate geo-description." The paper shows that using NLP techniques, the process of generating geo-descriptions can be partially automated. Therefore, research has been undertaken to automate this process to the extent possible. Automation can involve at least three stages: