Aiming to upgrade air transport communications and information technology, the client, a global leader in the field, embarked on an ambitious project aimed at simplifying the airport experience for passengers.
With a focus on leveraging Generative AI to boost customer service, the company partnered with Addepto, drawing on their successful collaboration in a prior Digital Twin project. This partnership aimed to bring the innovative concept of assistance bot to life, enhancing the efficiency and satisfaction of both passengers and airport personnel.
Goal
The envisioned LLM-powered airport bot would not only provide information but also guide passengers through the airport with the help of an integrated map, recognizing individuals and tailoring responses based on their boarding pass details. This seamless interaction was expected to make the bot an information point within the airport.
- Enhance Passenger Experience with Seamless, Real-Time Assistance
- Reduce Manual Workload for Airport Staff
- Integrate AI Tools into a Unified, Scalable System
Outcome
Before
- Passengers often experienced confusion and delays when seeking information like gate changes, terminal directions, or flight updates.
- Staff were burdened with manual tasks such as answering routine questions and performing basic identity checks.
- Navigation and communication within the airport lacked personalization and real-time interactivity.
After
- A GPT-4-powered AI assistant now provides real-time, conversational support to passengers via a virtual face and voice interface.
- Facial recognition enables the bot to tailor responses based on individual boarding pass data, enhancing personalization and speeding up identity verification.
- Staff workload is reduced through automated support and alerts, leading to greater operational efficiency.
- Overall, the AI assistant transforms the airport into a more predictable, safer, and less stressful environment, setting a new standard for digital service in aviation
Integrate those solutions in your company
Case Study Details
Approach
Supporting Both Passengers and Staff
- The solution was designed to simultaneously enhance the passenger journey and streamline staff operations, ensuring balanced benefits for all airport stakeholders.
LLM-Powered Conversational Bot with RAG
- Built an airport assistant using GPT-4 and LlamaIndex to enable retrieval-augmented generation (RAG), allowing the bot to provide precise, real-time answers sourced from a custom airport knowledge base.
Facial Recognition for Personalization and Security
- Integrated face recognition algorithms to match passengers with boarding pass data, enabling identity checks and personalized interactions, while enhancing security protocols.
Cloud-Based Architecture with Scalable Infrastructure
- Deployed the solution in the cloud, ensuring high availability and scalability across multiple airport terminals. This also simplified future integration with existing systems.
User-Friendly Interface with Virtual Face and Voice Interaction
- Due to budget constraints, the robot concept was simplified into a virtual assistant with a digital face, microphone, and camera, providing a friendly, intuitive, and accessible interaction point for travelers.
Our Team Expert Opinion
By leveraging cutting-edge AI, including Generative AI for customer service enhancement and facial recognition for security, we aimed to create a seamless, stress-free airport journey. We focused on connecting all the elements into one solution designed to effectively solve a very specific business problem.
Volodymyr Kepsha Senior Data Scientist at Addepto
