KRAFT -- A Knowledge-Graph-Based Resource Allocation Framework
Leon Bein, Niels Martin, Luise Pufahl
TL;DR
Resource allocation in business processes is complex due to diverse resources, case characteristics, and regulatory constraints, and existing systems struggle with rigidity and lack of explainability. The authors propose KRAFT, a Knowledge-Graph-Based Resource Allocation Framework that combines a resource allocation knowledge graph, knowledge extraction, and knowledge graph reasoning to support adaptable, explainable run-time decisions. The paper details a classification of allocation knowledge, methods for populating and reasoning over the graph, and a prototypical implementation demonstrated on a loan-application process using RDF/OWL/SHACL and process-mining inputs. The work advances practical explainable resource allocation by enabling dynamic knowledge integration, run-time reasoning, and human-in-the-loop decision support.
Abstract
Resource allocation in business process management involves assigning resources to open tasks while considering factors such as individual roles, aptitudes, case-specific characteristics, and regulatory constraints. Current information systems for resource allocation often require extensive manual effort to specify and maintain allocation rules, making them rigid and challenging to adapt. In contrast, fully automated approaches provide limited explainability, making it difficult to understand and justify allocation decisions. Knowledge graphs, which represent real-world entities and their relationships, offer a promising solution by capturing complex dependencies and enabling dynamic, context-aware resource allocation. This paper introduces KRAFT, a novel approach that leverages knowledge graphs and reasoning techniques to support resource allocation decisions. We demonstrate that integrating knowledge graphs into resource allocation software allows for adaptable and transparent decision-making based on an evolving knowledge base.