A Semantic Question Answering through Heterogeneous Data Source in the Domain of Smart Factory

Abstract

Manufacturing technologies have evolved with advancements of Industry 4.0 about big data systems, generation system for linked data from unstructured data sources, and streaming data pools. A heterogeneous data source is still problematic for restricted domain question answering due to the nature of unstructured data in manufacturing companies and data-intensive applications in smart factories. Smart factories have emerged with data-intensive operations that are occurring from manufacturing monitoring systems, hand terminals, mobile tablets, and assembly line controllers. Today, human operators experience an increased complexity of the data-intensive applications in the smart factory. Fetching data from various data sources brings a necessity of decreasing data size and derive an idea regarding what is happening by inductive reasoning at the smart factory. Heterogeneous data source occurs adversity in converting linked data to get answers asked questions by human operators, experts, workers through question answering systems. When dealing with a large amount of linked data, we need to design and implement a software solution that should enhance human operators’ and experts’ capabilities. In this study, we propose a semantic question answering that connects with heterogeneous data sources from different areas and devices of a smart factory. In the end, we will perform qualitative and quantitative evaluation regarding the semantic question answering that exploits heterogeneous data sources, as well as findings and conclude the main points concerning our research questions.