Identifying the Components of AI Algorithm-Based Interactive Industrial Design

Abstract

This study aimed to identify and explain the components of AI algorithm-based interactive industrial design and to develop a conceptual framework for organizing its contextual conditions, inputs, processes, and outputs. This applied qualitative study was conducted using a meta-synthesis approach. The research corpus included national and international studies related to interactive industrial design, artificial intelligence, generative design, human–machine interaction, human–robot interaction, industrial knowledge management, and intelligent technologies published between 2020 and 2026. Data were collected through a systematic search of reputable scientific databases. After removing duplicate, irrelevant, and methodologically weak sources, 55 studies were selected for final analysis. The seven-step model proposed by Sandelowski and Barroso was used to conduct the meta-synthesis. The quality of the selected studies was assessed using the Critical Appraisal Skills Programme checklist, and coding reliability was examined through inter-coder agreement. The meta-synthesis findings indicated that the components of AI algorithm-based interactive industrial design can be classified into 4 main categories, 19 concepts, and 96 codes. The main categories were context, inputs, process, and outputs. At the contextual level, digital transformation, technological and data-driven infrastructure, human–machine interaction, ethical requirements, trust, and knowledge management were identified. The input category included user data, interactive needs, design and environmental data, AI algorithms and technologies, and human expertise. The process category comprised design problem identification, data collection and preparation, intelligent analysis, generation of design alternatives, human–AI interaction in the design loop, simulation, evaluation, optimization, and continuous learning. The output category included improved design quality and accuracy, innovation and creativity, enhanced user experience, increased productivity, strengthened design decision-making, knowledge management, and ethical, organizational, and social implications. AI-based interactive industrial design is a multidimensional, data-driven, human-centered, and learning-oriented approach that integrates algorithmic analytical capabilities with human creativity and expertise to enhance the quality, innovation, interactivity, and effectiveness of industrial design processes.