The selected decision support systems or DSSs are data-driven DSS and knowledge-driven DSS because they facilitate data analysis enhancement, enables large database manipulation, boost analytical processing, and increase specialized problem-solving expertise. These categories of DSS are especially useful for AI implementation in future e-commerce services in the practice of cyber-physical system applications for smart buildings and cities. CCT principles and techniques improve the use of the selected DSSs due to the structured procedural elements of decision support, human computer integrated tools, and communication protocols.
Firstly, since the context involves an AI integration into highly complex systems, such as cities and smart buildings, the key problematic areas will most likely involve an analysis of extensive amounts of data with a subsequent need for a detailed analysis. Data-driven decision support systems have critical subcategories, such as data-driven spatial decision support systems or SDSS, and executive information systems or EIS, both of which can significantly boost cyber-physical system application (Nof et al., 2015). In accordance with the collaborative control theory or CCT, the key steps include decision support system, communication protocols, software agents and active middleware, and human computer integrated tools (Nof et al., 2015). These steps of CCT can easily integrate the underlying processes in order to improve data analysis enhancement, enables large database manipulation, and boost analytical processing.
Emphasis on data analysis is an essence of data-driven DSS, and the database of city or building systems can be extensive and massive, which is why one needs to be able to manipulate such a large amount of information with an effective method of communicating the plausible course of action. AI should be able to enhance its capability through the format of data-driven DSS, which opens a gateway to proceed with subsequent steps of CCT to deliver a high level of functionality and decision support.
Secondly, knowledge-driven DSS is action-focused and puts a great deal of emphasis on recommending a specific action. Since AI integration into e-commerce in a cyber-physical system application revolves around problem-solving expertise within domain knowledge, knowledge-driven DSS is of paramount importance (Nof et al., 2015). Therefore, unlike data-driven DSS, knowledge-driven DSS increases specialized problem-solving expertise. It can boost the CCT steps, such as active middleware and software agent, which manifests in conflict and error reduction to a high degree of specialization and problem-solving focus. The given DSS can be further enhanced by improving its communication protocols since the decision support recommendation needs to be direct with no ambivalent outcomes. AI integration in a complex system of smart buildings and cities makes it critical to ensure precision when supporting a decision, and thus, CCT’s communication protocols, agents, and middleware can facilitate the functional application in the desired path. Cyber-physical system application is further complicated by the fact that it relies on both internal data as well as external data, which favor database component more than model one, but these two elements need to undergo communication component in accordance with CCT.
In conclusion, both knowledge-driven and data-driven DSSs can be critically important for AI implementation in future e-commerce services in the practice of cyber-physical system applications for smart buildings and cities. However, proper CCT techniques and measures need to be set in place in order to facilitate data analysis enhancement, enable large database manipulation, boost analytical processing, and increase specialized problem-solving expertise.
Reference
Nof, S. Y., Ceroni, J., Jeong, W., & Moghaddam, M. (2015). Revolutionizing collaboration through e-work, e-business, and e-service. Springer.