Thumbnail Image

SemDaServ: A Systematic Approach for Semantic Data Specification of AI-Based Smart Service Systems

Preidel, Maurice; Stark, Rainer

To develop smart services to successfully operate as a component of smart service systems (SSS), they need qualitatively and quantitatively sufficient data. This is especially true when using statistical methods from the field of artificial intelligence (AI): training data quality directly determines the quality of resulting AI models. However, AI model quality is only known when AI training can take place. Additionally, the creation of not yet available data sources (e.g., sensors) takes time. Therefore, systematic specification is needed alongside SSS development. Today, there is a lack of systematic support for specifying data relevant to smart services. This gap can be closed by realizing the systematic approach SemDaServ presented in this article. The research approach is based on Blessing’s Design Research Methodology (literature study, derivation of key factors, success criteria, solution functions, solution development, applicability evaluation). SemDaServ provides a three-step process and five accompanying artifacts. Using domain knowledge for data specification is critical and creates additional challenges. Therefore, the SemDaServ approach systematically captures and semantically formalizes domain knowledge in SysML-based models for information and data. The applicability evaluation in expert interviews and expert workshops has confirmed the suitability of SemDaServ for data specification in the context of SSS development. SemDaServ thus offers a systematic approach to specify the data requirements of smart services early on to aid development to continuous integration and continuous delivery scenarios.
Published in: Applied Sciences, 10.3390/app11115148, MDPI