A Low-Code Methodology for Developing AI Kiosks: a Case Study with the DIZEST Platform

TL;DR

This paper introduces a low-code methodology using the DIZEST platform to improve AI kiosk development, demonstrating enhanced performance, interoperability, and user experience through a case study.

Contribution

It presents a novel low-code platform, DIZEST, specifically designed for AI kiosk development, addressing integration and flexibility challenges of existing systems.

Findings

DIZEST outperforms Jupyter, ComfyUI, and Orange3 in key metrics.

The case study shows improved interoperability and user experience.

Deployment flexibility is significantly increased with DIZEST.

Abstract

This paper presents a comprehensive study on enhancing kiosk systems through a low-code architecture, with a focus on AI-based implementations. Modern kiosk systems are confronted with significant challenges, including a lack of integration, structural rigidity, performance bottlenecks, and the absence of collaborative frameworks. To overcome these limitations, we propose a DIZEST-based approach methodology, a specialized low-code platform that enables intuitive workflow design and seamless AI integration. Through a comparative analysis with existing platforms, including Jupyter Notebook, ComfyUI, and Orange3, we demonstrate that DIZEST delivers superior performance across key evaluation criteria. Our photo kiosk case study further validates the effectiveness of this approach in improving interoperability, enhancing user experience, and increasing deployment flexibility.