Towards Ontology Reshaping for KG Generation with User-in-the-Loop: Applied to Bosch Welding

Abstract

Knowledge graphs (KG) are used in a wide range of applications. The automation of KG generation is very desired due to the data volume and variety in industries. One important approach of KG generation is to map the raw data to a given KG schema, namely a domain ontology, and construct the entities and properties according to the ontology. However, the automatic generation of such ontology is demanding and existing solutions are often not satisfactory. An important challenge is a trade-off between two principles of ontology engineering: knowledge-orientation and data-orientation. The former one prescribes that an ontology should model the general knowledge of a domain, while the latter one emphasises on reflecting the data specificities to ensure good usability. We address this challenge by our method of ontology reshaping, which automates the process of converting a given domain ontology to a smaller ontology that serves as the KG schema. The domain ontology can be designed to be knowledge-oriented and the KG schema covers the data specificities. In addition, our approach allows the option of including user preferences in the loop. We demonstrate our on-going research on ontology reshaping and present an evaluation using real industrial data, with promising results. CCS CONCEPTS• Mathematics of computing → Graph algorithms; • Computing methodologies → Knowledge representation and reasoning; Ontology engineering.

Data Science Methods and Tools for Industry 4.0: A Systematic Literature Review and Taxonomy

“…The SPARQL is the language used to retrieve information and Hermit, Pallet, and RDFox are examples of reasoners found in the review. An important aspect of ontologies is that they are extendable and reusable [26,49,59].…”

Query-Based Industrial Analytics over Knowledge Graphs with Ontology Reshaping

“…The resulting ontology is a (compact) version of the original one and essentially consists of (1) all corresponding information (table names and attributes) from the raw data and (2) other essential connecting elements, which are partially from the original ontology and partially from users, to attain some optimality defined by user heuristics, efficiency, simplicity, etc. We adopt our OR algorithm [11]. In the nutshell OR firstly selects a subset of nodes and edges in the domain ontology [12], creating its sub-graph, which is a sparse sub-graph that consists of many disconnected small graph fragments; secondly, it extends the sub-graph to a KG schema with the help of two sources of information: (a) retaining other nodes and edges of the domain ontology to preserve part of its knowledge, (b) some optional information given by users (welding experts) that help to connect the fragments in the sub-graph.…”

ExeKG: Executable Knowledge Graph System for User-friendly Data Analytics

“…The executable KGs construction follows the task ontologies 𝑂 𝑣𝑖𝑠𝑢 , 𝑂 𝑠𝑡𝑎𝑡𝑠 , and 𝑂 𝑚𝑙 as schemata [15,16,18], and rely on KG templates [27,28], which are parameterised ontologies with pre-defined structures and a set of variables of entities and properties. We adopt a solution similar to Reasonable Ontology Templates framework [10].…”