The evolution of software quality models (SQMs) reflects the dynamic of the development of information technologies and systems. For new specialised information technologies, it is necessary to develop appropriate software quality models. If there are no standardised models for these technologies then IT companies or individual researchers develop corporate SQMs. Standardised and corporate quality models for the same information technologies often have significant differences that are associated with discrepancies in the number of characteristics and their semantic content. The objective of the paper is to develop a unified approach to the formation of technology-based software quality models (TBSQMs). The research method is based on the principle of evolutionary analysis of SQMs. This principle consists of identifying and comparing key models that record the stages and determine the content of the evolution process, as well as a unified approach to the development of SQMs and metric assessment of their complexity. The paper presents the results of a comparison of corporate and standardised quality models for artificial intelligence and identifies the differences between them. The obtained results have allowed us to establish certain regularities for the current stage of the evolution of software quality models and to develop a classification of such models. A unified approach to developing TBSQMs was developed and an example of its application for blockchain technology-based software quality model was presented. In the future, it is planned to analyse TBSQMs for other information technologies and develop a tool to support the process of forming such models.

This paper addresses the growing need for reliable methods to evaluate the quality of artificial intelligence (AI) systems as they become widely used in both critical domains and everyday applications. The study aims to develop a metric-based approach to assessing AI system quality by harmonising product quality and quality in use models in line with updated international standards. To achieve this, the authors analyse existing ISO/IEC 25000 series standards, identifying inconsistencies between older and newer versions, and propose an updated quality model that incorporates both perspectives. Building on guidance documents, international standards, and contemporary research, the study introduces a set of metrics designed to measure new subcharacteristics of AI system quality, particularly where standardised metrics have not yet been developed. The proposed approach bridges the gap between established quality models (ISO/IEC 25010:2023, ISO/IEC 25019:2023, ISO/IEC 25059:2023) and standardised measurement practices (ISO/IEC 25023:2016, ISO/IEC 25022:2016), enabling more consistent and practical evaluation of AI systems. These metrics can be applied by researchers and practitioners to improve the quality of AI systems, enhance their reliability, and reduce risks associated with insufficient quality. Future work will focus on empirical validation of the proposed approach to confirm its applicability and usefulness across diverse AI applications.

Non-functional requirements to software quality (SWQ) is described in general by SWQ models characteristics. Last the most famous software quality model ISO/IEC 25010 includes eight characteristics: functional suitability, performance efficiency, compatibility, usability, reliability, security, maintainability and portability. Usability as a SWQ characteristic must include subcharacteristics, inherent to software user interface quality as static object and also as subcharacteristics of process user interaction, i.e. is user-computer interaction in real time. In existing models of quality and quality assessment of usability the peculiarities of human- computer interaction (HCI) in real time are not taken into account in real time. Software interface usability model (SIUM) for HCI and models for its assessment are suggested. Such models are interconnected through a single nomenclature of subcharacteristics. HCI SIUM consists of two parts and includes a set of metrics, which correspond to the defined under subcharacteristics. Particularity of model is that all primitives for calculation software interface usability metrics for HCI obtained only with use of software and hardware complex of the eye-tracker.