LinkQuest
Your AI Travel Patner
Learn More
The intersection of artificial intelligence (AI) and tourism has sparked significant scholarly interest, particularly concerning the customization of travel experiences. Fernando et al. demonstrate the efficacy of machine learning algorithms in tailoring travel itineraries to individual preferences in Sri Lanka. Their research indicates a marked enhancement in user satisfaction, attributing this improvement to the nuanced understanding of traveler behavior facilitated by AI [4]. This is further supported by the findings of Kaushik et who emphasize the role of predictive analytics in understanding tourist preferences and optimizing travel plans accordingly [5]
The convergence of AI with mobile technologies represents a critical evolution in the domain of personalized travel services. Jayawardena and Weerasinghe investigate a mobile application that employs AI to deliver real-time, contextual travel advice. Their study focused on the Sri Lankan tourism market—a substantial contributor to the national economy—confirms that such technological interventions refine the personalization of travel experiences and optimize logistical aspects like route and schedule planning [6]. Similarly, Chen et al. highlight the benefits of integrating AI with mobile apps, noting improvements in user engagement and satisfaction through real-time data processing and personalized content delivery [7] The role of data analytics emerges as fundamental in the realm of personalized travel. Perera and Silva analyze extensive datasets on traveler preferences and behaviors, revealing that AI-driven systems significantly influence tourist decision-making processes. This study corroborates.read the full paper
Following areas are the research gaps found in most of the recent researches.
This model addresses the research gap in personalized travel planning by finding optimal locations in Sri Lanka based on seasonal variations and user preferences. Current systems often overlook the impact of local climate conditions and cultural events on travel decisions. By integrating these factors, the model can enhance the user experience, allowing travelers to select destinations that align with their specific interests and the best seasonal conditions. This approach promotes informed decision-making, ultimately leading to more satisfying travel experiences tailored to the unique environment of Sri Lanka.
The proposed system seeks to fill the research gap in effectively recommending promotions tailored to user calendars. Many platforms fail to consider users’ available free time, which is crucial for maximizing engagement with promotional offers. By incorporating natural language processing (NLP) capabilities, the system aims to enhance interaction with users, streamlining the booking process and providing timely notifications about relevant promotions. This integration will facilitate a more seamless experience, ultimately increasing user satisfaction and the likelihood of booking.
This model addresses the research gap in leveraging sentiment analysis to filter and categorize reviews for travel recommendations. Current methods often ignore the subtleties of user feedback, limiting the ability to identify the most appealing destinations. By employing aspect-based sentiment analysis, the system can enhance user experiences by providing insights into specific attributes of places. Furthermore, integrating augmented reality (AR) features for travel guidance can create an immersive experience, helping users make informed choices based on filtered sentiment data and enhancing their overall travel planning.
Sri Lanka’s tourism industry is currently underutilized, with some destinations experiencing overcrowding while others remain overlooked. Additionally, varying seasonal conditions across different regions complicate travelers’ ability to plan their trips effectively.
Product Demonstration - Solution
This research proposes an AI-driven travel planning solution tailored for Sri Lanka’s tourism sector, divided into four key components: optimal route planning based on budget, time constraints, and seasonal preferences; targeted promotions aligned with individual seasonal preferences and personal calendars; knowledge base development with AR tour guides for enhanced destination insights; and personalized comment analysis to align hotel feedback with users’ preferences. The system integrates machine learning, NLP, and AR technologies to offer personalized recommendations, efficient route planning via algorithms like KNN and Ant Colony Optimization, calendar-based promotions, immersive AR experiences, and sentiment-based feedback insights to enrich user experiences and tourism management.
The objective is to create an algorithm that optimizes travel routes based on user preferences, time and seasonal activities in Sri Lanka. By leveraging machine learning models like KNN and Ant Colony Optimization, the system will generate personalized travel itineraries that maximize user convenience, suggesting the best paths and destinations.
This objective focuses on designing a recommendation system that analyzes user calendars and seasonal patterns to offer tailored promotions. The goal is to provide discounts, special offers, and personalized suggestions that align with the user’s travel plans and preferences, enhancing both the user experience and local business engagement.
This research aims to integrate AR technology into the travel planning app to provide immersive, interactive experiences at tourist destinations. AR-powered virtual guides and visualizations will allow users to explore cultural landmarks, attractions, and historical sites more deeply, enriching their travel experience and encouraging exploration of lesser-known destinations.
The objective here is to use NLP techniques to analyze hotel reviews and comments, generating insights that match users’ preferences. By identifying patterns in user feedback, the system will recommend accommodations that align with individual expectations, such as family-friendly, budget, or luxury options, thus ensuring a more satisfying travel experience.
Figure 1. High Level Architecture of the system.
The proposed travel planning solution is structured into four key components to address the challenges in Sri Lanka’s tourism sector:
1. Optimal Route Planning Based on Budget, Time Constraints, and Seasonal Preferences
This component implements data collection, processing, and machine learning techniques to offer personalized travel recommendations. It starts with data scraping from various sources such as travel sites and user reviews, followed by cleaning and augmentation. The K-Nearest Neighbor (KNN) algorithm is trained on this data to predict ideal destinations based on user inputs like budget and travel dates. The integration of the Google Maps API provides distances and travel times between destinations, while the Ant Colony Optimization (ACO) algorithm optimizes routes by minimizing travel time and cost.
2. Targeted Location Promoting Based on Seasonal Preferences and Personal Calendars
This part focuses on promoting destinations that match users’ seasonal preferences and personal schedules. It involves collecting calendar data, analyzing patterns of free and busy periods, and utilizing a regression model to predict availability. The system integrates seasonal data like peak travel seasons and weather to send personalized promotional notifications using Natural Language Processing (NLP). A custom Large Language Model (LLM) also allows users to inquire about hotels and receive immediate responses.
3. Knowledge Base Development and AR Tour Guide
To enhance users’ understanding of destinations, an Augmented Reality (AR) experience is developed using Unity and Vuforia. This AR component recognizes image targets and overlays multimedia such as text and videos, providing immersive, informative experiences about tourist sites. The system includes a chatbot that acts as a tour guide, answering users’ queries, and an Optical Character Recognition (OCR) feature to translate ancient inscriptions at historical sites.
4. Aspect-Based Comment Personalization
This final component analyzes user-generated hotel reviews to extract insights through sentiment analysis and topic categorization. The data is collected from platforms like TripAdvisor and Kaggle, processed to remove noise, and tokenized for analysis. This process helps align promotional strategies with users’ preferences, offering businesses a deeper understanding of customer feedback.
Python
React
Tensorflow
Firebase
Google Cloud
Google Colab
Google map API
Hugging Face
Unity
Vuforia
February 2024
A Project Proposal is presented to potential sponsors or clients to receive funding or get your project approved.
Marks Allocated : 6
May 2024
Progress Presentation I reviews the 50% completetion status of the project. This reveals any gaps or inconsistencies in the design/requirements.
Marks Allocated : 6
June 2024
Describes what you contribute to existing knowledge, giving due recognition to all work that you referred in making new knowledge
Marks Allocated : 10
September 2024
Progress Presentation II reviews the 90% completetion status demonstration of the project. Along with a Poster presesntation which describes the project as a whole.
Marks Allocated : 18
October 2024
The Website helps to promote our research project and reveals all details related to the project.
Marks Allocated : 2
October 2024
Status of the project is validated through the Logbook. This also includes, Status documents 1 & 2.
Marks Allocated : 3
October 2024
Final Report evalutes the completed project done throughout the year. Marks mentioned below includes marks for Individual & group reports and also Final report.
Marks Allocated : 19
October 2024
Viva is held individually to assess each members contribution to the project.
Marks Allocated : 20
Please find all documents related to this project below.
Contact Details
For further queries please reach us at tharushaperera6199@gmail.com
Hope this project helped you in some manner. Thank you!
-Team LinkQuest
