This paper introduces the MIP Platform architecture model, a novel AI-based cognitive computing platform architecture. The goal of the proposed application of MIP is to reduce the implementation burden for the usage of AI algorithms applied to cognitive computing and fluent HMI interactions within the manufacturing process in a cyber-physical production system. The cognitive inferencing engine of MIP is a deterministic cognitive module that processes declarative goals, identifies Intents and Entities, selects suitable actions and associated algorithms, and invokes for the execution a processing logic (Function) configured in the internal Function-as-aService or Connectivity Engine. Constant observation and evaluation against performance criteria assess the performance of Lambda(s) for many and varying scenarios. The modular design with well-defined interfaces enables the reusability and extensibility of FaaS components. An integrated BigData platform implements this modular design supported by technologies such as Docker, Kubernetes for virtualization and orchestration of the individual components and their communication. The implementation of the architecture is evaluated using a real-world use case later discussed in this paper.
تحميل البحث