Procedure Model for Building Knowledge Graphs for Industry Applications

TL;DR

This paper introduces a practical, step-by-step procedure model for constructing industry-specific knowledge graphs that integrate heterogeneous data and expert knowledge, facilitating intelligent applications.

Contribution

It presents a comprehensive, adaptable process model based on the CRISP-DM methodology for building RDF knowledge graphs in industry contexts.

Findings

Provides a detailed procedure for knowledge graph construction

Uses competency questions to guide development and evaluation

Supports integration of diverse data sources and domain knowledge

Abstract

Enterprise knowledge graphs combine business data and organizational knowledge by means of a semantic network of concepts, properties, individuals and relationships. The graph-based integration of previously unconnected information with domain knowledge provides new insights and enables intelligent business applications. However, knowledge graph construction is a large investment which requires a joint effort of domain and technical experts. This paper presents a practical step-by-step procedure model for building an RDF knowledge graph that interconnects heterogeneous data and expert knowledge for an industry use case. The self-contained process adapts the "Cross Industry Standard Process for Data Mining" and uses competency questions throughout the entire development cycle. The procedure model starts with business and data understanding, describes tasks for ontology modeling and the graph setup, and ends with process steps for evaluation and deployment.