De fotos a lugares: Generación de itinerarios turísticos personalizados con modelos de lenguaje largo y análisis de imágenes
| dc.contributor.advisor | Galpin, Ixent | |
| dc.creator | Bermejo Xiao, Kenny Andres | |
| dc.date.accessioned | 2025-06-12T14:35:19Z | |
| dc.date.available | 2025-06-12T14:35:19Z | |
| dc.date.created | 2025-05-16 | |
| dc.description.abstract | Este artículo presenta el desarrollo de una aplicación orientada a la generación automática de itinerarios de viaje personalizados mediante la integración de dos tecnologías emergentes en el campo de la inteligencia artificial: grandes modelos de lenguaje (LLM) y sistemas de reconocimiento de imágenes. La propuesta captura las preferencias del usuario mediante dos mecanismos: (i) un formulario estructurado para la recopilación explícita de intereses, y (ii) el análisis de una imagen proporcionada por el usuario, de la cual se infieren implícitamente las preferencias. La arquitectura del sistema se basa en la combinación de múltiples servicios de inteligencia artificial a través de API, incluyendo servicios de interpretación de imágenes, servicios basados en la localización para identificar sitios turísticos relevantes y modelos de lenguaje para la generación contextual de descripciones y sugerencias. Esta integración permite la construcción de recomendaciones de viaje que consideran tanto las restricciones logísticas (como la duración del vuelo) como los intereses específicos del usuario, presentando así un itinerario visualmente enriquecido y personalizado. La aplicación se evaluó mediante un cuestionario adaptado de la Escala de Usabilidad del Sistema (SUS), obteniendo una puntuación media de 77,59 sobre 100. Este resultado indica un alto nivel de aceptación y usabilidad por parte de los usuarios, lo que respalda la eficacia del sistema como herramienta inteligente de recomendación de viajes. | spa |
| dc.description.abstractenglish | This paper presents the development of an application aimed at the automatic generation of personalized travel itineraries through the integration of two emerging technologies in the field of artificial intelligence: large language models (LLMs) and image recognition systems. The proposal captures user preferences through two mechanisms: (i) a structured form for the explicit collection of interests, and (ii) the analysis of an image provided by the user, from which preferences are implicitly inferred. The system architecture is based on the combination of multiple artificial intelligence services through APIs, including image interpretation services, location-based services for identifying relevant tourist sites, and language models for the contextual generation of descriptions and suggestions. This integration enables the construction of travel recommendations that consider both logistical constraints (such as flight duration) and the user’s specific interests, ultimately presenting a visually enriched and personalized itinerary. The application was evaluated through a questionnaire adapted from the System Usability Scale (SUS), obtaining an average score of 77.59 out of 100. This result indicates a high level of user acceptance and usability, supporting the effectiveness of the system as an intelligent travel recommendation tool. | spa |
| dc.format.extent | 18 páginas | spa |
| dc.format.mimetype | application/pdf | spa |
| dc.identifier.uri | https://hdl.handle.net/20.500.12010/36826 | |
| dc.language.iso | eng | spa |
| dc.relation.references | P. Fakfare, N. Manosuthi, J.-S. Lee, H. Han, M. Jin, Customer word-of-mouth for generative ai: Innovation and adoption in hospitality and tourism, International Journal of Hospitality Management 126 (2025) 104070. | spa |
| dc.relation.references | Y. Chang, X. Wang, J. Wang, Y. Wu, L. Yang, K. Zhu, H. Chen, X. Yi, C. Wang, Y. Wang, et al., A survey on evaluation of large language models, ACM transactions on intelligent systems and technology 15 (2024) 1–45. | spa |
| dc.relation.references | J. Maurício, I. Domingues, J. Bernardino, Comparing vision transformers and convolutional neural networks for image classification: A literature review, Applied Sciences 13 (2023) 5521. | spa |
| dc.relation.references | D. Alieva, Redes de organizaciones turísticas, itinerarios de viaje y experiencias interculturales de los turistas ruso-hablantes en Andalucía, Ph.D. thesis, Universidad de Sevilla, 2018. | spa |
| dc.relation.references | J. C. Niebles, Inteligencia artificial en todo y para todos, Technical Report, Universidad Na cional Autónoma de México, 2020. doi:http://doi.org/10.22201/codeic.16076079e. 2020.v21n1.a5. | spa |
| dc.relation.references | T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al., Language models are few-shot learners, Advances in neural information processing systems 33 (2020) 1877–1901. | spa |
| dc.relation.references | M. Morales-Chan, Explorando el potencial de Chat GPT: Una clasificación de Prompts efectivos para la enseñanza, Technical Report, GES Department, Galileo University, Guatemala, Guatemala, 2023. | spa |
| dc.relation.references | A. Krizhevsky, I. Sutskever, G. E. Hinton, Imagenet classification with deep convolutional neural networks, Advances in neural information processing systems 25 (2012). | spa |
| dc.relation.references | A. D. Cantero Alonso, E. A. Martínez Jara, Visión por computadora: identificación, clasificación y seguimiento de objetos, Technical Report, Facultad Politécnica, Universidad Nacional del Este, Ciu dad del Este, Paraguay, 2014. 1davidcantero.99@gmail.com, 2eamartinez@fpune.edu.py. | spa |
| dc.relation.references | B. Li, Everywheregpt: An ai travel planning assistant based on chatgpt, in: Proceedings of the 4th International Conference on Artificial Intelligence and Computer Engineering, 2023, pp. 995–1003 | spa |
| dc.relation.references | I. A. Wong, Q. L. Lian, D. Sun, Autonomous travel decision-making: An early glimpse into chatgpt and generative ai, Journal of Hospitality and Tourism Management 56 (2023) 253–263. | spa |
| dc.relation.references | K. Volchek, S. Ivanov, Chatgpt as a travel itinerary planner, in: ENTER e-Tourism Conference, Springer, 2024, pp. 365–370. | spa |
| dc.relation.references | G.Ilieva, T.Yankova, S.Klisarova-Belcheva, Effectsofgenerativeaiintourismindustry, Information 15 (2024) 671. | spa |
| dc.relation.references | A. Kanhed, P. Bhagwat, K. Palande, N. Palav, S. Balpande, K. Deshpande, U. Patil, Destinai: Your personalized travel itinerary planner and chat catalyst using generative ai, in: International Conference on Information and Communication Technology for Intelligent Systems, Springer, 2024, pp. 47–55. | spa |
| dc.relation.references | R. George, J. Atluri, Revolutionizing tourism: The power of generative ai, in: Generative AI for Transformational Management, IGI Global, 2024, pp. 271–302. | spa |
| dc.relation.references | M. Gupta, R. Dias, N. Jain, R. R. Dhamija, R. V. Bidwe, S. Mishra, G. Deshmukh, Travel with generator ai: A novel approach to itinerary creation, in: 2024 8th International Conference on Computing, Communication, Control and Automation (ICCUBEA), IEEE, 2024, pp. 1–6. | spa |
| dc.relation.references | K. Londhe, N. Dharmadhikari, P. Zaveri, U. Sakoglu, Enhanced travel experience using artificial intelligence: a data-driven approach, Procedia Computer Science 235 (2024) 1920–1928. | spa |
| dc.relation.references | E. Aribas, E. Daglarli, Transforming personalized travel recommendations: Integrating generative ai with personality models, Electronics 13 (2024) 4751. | spa |
| dc.relation.references | C. D. Duong, T. H. Nguyen, T. V. N. Ngo, T. T. P. Pham, A. T. Vu, N. S. Dang, Using generative artificial intelligence (chatgpt) for travel purposes: parasocial interaction and tourists’ continuance intention, Tourism Review (2024). | spa |
| dc.relation.references | J. Zhang, D. J. Mills, H.-W. Huang, Enhancing travel planning and experiences with multimodal chatgpt 4.0, in: Proceedings of the 2024 International Conference on Innovation in Artificial Intelligence, 2024, pp. 12–19. | spa |
| dc.relation.references | G. Kalaiarasi, M. Selvi, et al., Personalized travel itinerary generator system, in: 2024 International Conference on Intelligent Systems for Cybersecurity (ISCS), IEEE, 2024, pp. 1–6. | spa |
| dc.relation.references | P. Suanpang, P. Pothipassa, Integrating generative ai and iot for sustainable smart tourism destinations, Sustainability 16 (2024) 7435. | spa |
| dc.relation.references | A. Singh, R. Madhogaria, A. Misra, E. Elakiya, Automated travel planning via multi-agent systems and real-time intelligence, Available at SSRN 5089025 (2024). | spa |
| dc.relation.references | M. Balawardhana, Travel planning with artificial intelligence, The Role of Artificial Intelligence in the Tourism and Hospitality Sector (2025). | spa |
| dc.relation.references | A. Garg, D. Verma, L. Pandey, K. S. Kumar, R. Singh, A. Sharma, Enhancing tailored travel by integrating generative ai with insights driven by personality, in: 2025 International Conference on Intelligent Control, Computing and Communications (IC3), IEEE, 2025, pp. 404–409. | spa |
| dc.relation.references | H. Kumamoto, H. Joho, Exploring the role of large language model in collaborative travel planning task, Information Research an international electronic journal 30 (2025) 1123–1130. | spa |
| dc.relation.references | M. I. Saleh, Generative artificial intelligence in hospitality and tourism: future capabilities, ai prompts and real-world applications, Journal of Hospitality Marketing & Management (2025) 1–32. | spa |
| dc.relation.references | A. Štilić, A. Puška, M. Nicić, et al., The role of artificial intelligence in shaping the future of travel industry: An expert analysis of artificial intelligence-generated travel itineraries, DETUROPE-The Central European Journal of Regional Development and Tourism 16 (2025) 57–79. | spa |
| dc.relation.references | Y. Li, S. O. Lee, Navigating the generative ai travel landscape: The influence of chatgpt on the evolution from new users to loyal adopters, International Journal of Contemporary Hospitality Management 37 (2025) 1421–1447. | spa |
| dc.relation.references | K. Otaki, Y. Baba, Travel itinerary recommendation using interaction-based augmented data, Expert Systems with Applications 269 (2025) 126294. URL: https://www.sciencedirect.com/science/ article/pii/S0957417424031610. doi:https://doi.org/10.1016/j.eswa.2024.126294. | spa |
| dc.relation.references | P. De Silva, Ai-powered travel planner: A smart solution for personalized and efficient travel itineraries. 2. research area specific area artificial intelligence (ai) , software engineering , tourism technology personalization in travel planning , efficiency in travel itinerary generation , integration of ai and tourism , user-centric design , data-driven decision making 3. supervisor(s), 2025. | spa |
| dc.relation.references | S. Mohith S, H. H, K. .K, N. N, S. . R, A Review Paper On AI-Driven Travel Planning, Technical Report, Department of Computer Science and Engineering, BMS Institute of Technology and Management, Bengaluru, Karnataka., 2025. doi:10.5281/zenodo.14591573. | spa |
| dc.relation.references | V. Udandarao, N. A. Tiju, M. Vairamuthu, H. Mistry, D. Kumar, Roamify: Designing and evalu ating an llm based google chrome extension for personalised itinerary planning, arXiv preprint arXiv:2504.10489 (2025). | spa |
| dc.subject | Itinerarios de viaje personalizados | spa |
| dc.subject | Modelos de Lenguaje Largo | spa |
| dc.subject | Reconocimiento de imágenes | spa |
| dc.subject | Sistemas de recomendación | spa |
| dc.subject | Evaluación de usabilidad (SUS) | spa |
| dc.subject.keyword | Personalized travel itineraries | spa |
| dc.subject.keyword | Large Language Models | spa |
| dc.subject.keyword | Image recognition | spa |
| dc.subject.keyword | Recommender systems | spa |
| dc.subject.keyword | Usability evaluation (SUS) | spa |
| dc.subject.lemb | Planificación de viajes - Aplicaciones de inteligencia artificial | |
| dc.subject.lemb | Sistemas de recomendación (Informática) | |
| dc.subject.lemb | Procesamiento de imágenes digitales - Aplicaciones en turismo | |
| dc.title | De fotos a lugares: Generación de itinerarios turísticos personalizados con modelos de lenguaje largo y análisis de imágenes | spa |
| dc.type.coar | http://purl.org/coar/resource_type/c_2df8fbb1 | spa |
Archivos
Bloque original
1 - 1 de 1
Cargando...
- Nombre:
- From Photos to Places-Generating Personalized Tourist Itineraries with Large Language Models and Image Analysis.pdf
- Tamaño:
- 4.19 MB
- Formato:
- Adobe Portable Document Format
- Descripción:
- Documento reservado
