Ανάπτυξη ψηφιακού βοηθού για την έκδοση ακαδημαϊκής ταυτότητας, με χρήση NLP, LLMs και CPSV-AP
Development of a digital assistant for academic ID issuance using NLP, LLMs, and CPSV-AP

View/ Open
Keywords
CPSV-AP ; LLMs ; Large language models ; Chatbots ; Rasa ; Python ; C# ; NLP ; Ψηφιακός βοηθός ; Έκδοση σκαδημαϊκής ταυτότηταςAbstract
This work focuses on the development of a digital assistant in the form of a chatbot to support the academic ID issuance process in Greek higher education institutions. The system is designed to provide accurate, clear, and personalized responses to user inquiries, leveraging natural language processing (NLP) technologies and large language models (LLMs), such as ChatGPT, in combination with the Rasa framework for dialogue management. Additionally, the system incorporates the CPSV-AP model (Core Public Service Vocabulary), which enables standardized representation and management of information related to public service descriptions, facilitating search, categorization, and personalization of responses.
This approach allows users to interact with the digital assistant in a natural and intuitive way, simulating human communication, while ensuring completeness, clarity, and reliability in the responses. The system also addresses more specialized cases that are often insufficiently handled by traditional websites and FAQ systems, providing a comprehensive solution for enhancing the user experience.
Furthermore, this technology can be extended to support other institutional services, promoting digital service delivery, innovation, and the adoption of advanced technologies within the academic community. The implementation of this system serves as an example of how large language models, NLP technologies, and standardized models such as CPSV-AP can be utilized to improve the daily experience of users in an academic environment.


