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.

41 Together these studies provide important insights into the evolution of quality assurance from traditional inspection to AI-integrated predictive models. All of the studies reviewed here support the hypothesis that comprehensive indicators enhance process efficiency, yet contradictions in previous research include the reactive nature of many methods and challenges in data integration. Overall, there seems to be some evidence to indicate that Industry 4.0 technologies offer ways of solving the problem through real-time monitoring and optimization. What are the contradictions in previous research Traditional models [1,2] excel in planning but lack predictive capabilities, while AI approaches [3,4] predict defects but struggle with interoperability. Point out the ways of solving the problem: Developing unified frameworks that combine hierarchical information models with ML for dynamic quality assessment. Identify your research niche: This study fills the gap by proposing a comprehensive quality indicator that ensures technological process operations across all stages, addressing scalability and uncertainty in manufacturing. This research aims to develop a model for ensuring technological process operations based on a comprehensive quality indicator, integrating metrics like cost, time, defect rates, and variability to optimize manufacturing efficiency. The specific objective of this study is to investigate the factors that determine quality in dynamic processes and propose an adaptive framework. The research hypothesis contributes to the solution of the research problem by positing that a comprehensive quality indicator, derived from real-time data analytics, will significantly reduce defects and improve operational reliability compared to traditional methods. This includes directional hypotheses: Implementing the indicator will decrease process variability by at least 20%. Rejecting the null hypothesis (no improvement) and accepting the alternative forms the basis for building a good research study. The research question formulates a research problem: How can a comprehensive quality indicator be designed and applied to ensure optimal operations