Collaborative Decision Support with Ontology-Based Neuro-Symbolic Artificial Intelligence: Challenges and Conceptual Model

Abstract

The development of artificial intelligence technologies and the growing complexity of decision-making in the management of modern production systems necessitate the collaboration of humans and AI, including teams of heterogeneous participants (for example, experts and agents operating on the basis of artificial intelligence). The paper discusses the tasks that have to be resolved to enable collaborative human-machine decision support systems and the main problems that arise during the creation of such systems. The analysis of modern results in the field of ontology-oriented neuro-symbolic artificial intelligence is carried out, primarily aimed at explaining neural network models using ontologies and at using symbolic knowledge to improve the efficiency of neural network models. A conceptual model of a collaborative human-machine decision support based on ontology-oriented neuro-symbolic artificial intelligence is proposed.