The final, formatted version of the article will be published soon.
ORIGINAL RESEARCH article
Front. Comput. Sci.
Sec. Software
Volume 6 - 2024 |
doi: 10.3389/fcomp.2024.1365872
A Comparative Study of Smart Enhancements from Initial Versions to Upgraded Models in Specialized AI Applications in Urban Planning
Provisionally accepted- University of Moratuwa, Moratuwa, Sri Lanka
This study investigates the progression of specialized urban planning Chatbots, with a specific emphasis on the shift from Chatbot 1.0 to Chatbot 2.0. This research comprehensively analyzes the Chatbot concept and its implementation within the domain of urban planning. This study focuses on citizen engagement, information distribution, and data-driven decision-making. This study discusses Chatbot 1.0, encompassing its development methodology, input from stakeholders, significant drawbacks, and ChatGPT API-driven features. The stakeholder engagement feedback indicates that the urban planning Chatbot has received a resounding endorsement, as a substantial majority of respondents expressed contentment and acknowledged its significance. However, the inability to recall previous conversations, perform certain operations, interpret images, and comprehend geographic-based information are identified as limitations. The research subsequently investigates the justification for the creation of Chatbot 2.0, placing particular emphasis on the necessity for a solution that is more capable, adaptable, and economical. The adoption of the Hugging Chat API, the incorporation of real-time web search functionalities, and the training process utilizing authoritative data from Urban Development Authorities (UDA) are all noteworthy advancements in Chatbot 2.0. 'Pro Planning Mode' and a 'user-centric graphical user interface' are two additional features that augment the functionality and user experience of the Chatbot. Thus, this research describes systematically how we developed the specialized urban planning Chatbot from the initial version to evade the restrictions that it had at the beginning.
Keywords: Chatbot 1.0, Chatbot 2.0, Hugging Chat API, real-time web search, Pro Planning Mode
Received: 23 Mar 2024; Accepted: 18 Jul 2024.
Copyright: © 2024 Hasan, Jayasinghe, Sathsarana, Kaveesha and Sankalpa. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Farasath Hasan, University of Moratuwa, Moratuwa, Sri Lanka
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.