Proceedings of the International scientific and practical conference ―Science, Technology and Culture: Interaction, Evolution and Progress‖ (December 21-23, 2025) / Publisher website: www.naukainfo.com. – Copenhagen, Denmark, 2026. – 161 p.

38 highlights the importance of unified frameworks that combine hierarchical information models with machine learning. The proposed research niche develops an adaptive model to address these gaps, with hypotheses predicting reduced variability, SMART objectives for analysis and validation, and methods involving UML and ML algorithms. Keywords: Quality assurance; Comprehensive quality indicator; Manufacturing processes; Industry 4.0; AI integration; Predictive analytics; Process optimization; Technological operations; Defect detection; Scalability in manufacturing. Quality assurance plays a vital role in modern manufacturing, ensuring that products meet customer expectations while optimizing costs and efficiency. In the last few decades, there has been a growing interest in integrating advanced technologies and metrics to maintain high standards in technological processes. Manufacturing processes have become increasingly complex, involving multiple stages from design to execution, where deviations can lead to significant defects and waste. Quite recently, considerable attention has been paid to the development of comprehensive quality indicators that aggregate various parameters such as cost, time, defect rates, and process variability to provide a holistic view of operational performance. Previous studies indicate that traditional quality control methods, often reactive and focused on inspection, are insufficient for dynamic environments like Industry 4.0, where real-time monitoring and predictive analytics are essential. The literature on quality assurance shows a variety of approaches, from statistical process control to AI-driven models, but many fail to fully integrate these into a unified framework for technological process operations. Much research on comprehensive indicators has been done, yet gaps remain in addressing uncertainty, interoperability, and scalability across distributed manufacturing sites. This highlights the need for a model that ensures technological process operations based on a comprehensive quality indicator, bridging design, planning,