A graph-based context-aware requirement elicitation approach in smart product-service systems

Abstract

The paradigm of Smart product-service systems (Smart PSS) has emerged recently owing to the edge-cutting Information and Communication Technology (ICT) and artificial intelligence (AI) techniques. The unique features of Smart PSS including smartness and connectedness, value co-creation and data-driven design manner, enable the collection and analysis of large volume and heterogeneous contextual data to extract useful knowledge. Therefore, requirement elicitation, as a critical process for new solution (i.e. product-service) design, can be conducted in a rather context-aware manner, assured by those massive user-generated data and product-sensed data during the usage stage. Nevertheless, despite a few works on semantic modelling, scarcely any reports on such mechanism in today's smart, connected environment. Aiming to fill this gap, for the first time, a graph-based context-aware requirement elicitation approach considering contextual information within the Smart PSS is proposed. It leverages the pre-defined product, service, and condition ontologies together with Deepwalk technique, to formulate those concepts as nodes and their relationships as the edge of the proposed requirement graph. Implicit stakeholder requirements within a specific context can be further derived based on such interrelationships in a data-driven manner. To demonstrate its feasibility and effectiveness, an example of smart bike share system is addressed to illustrate the requirement elicitation process. It is hoped that this explorative study can offer valuable insights for the service providers who would like to extract requirements not only from the voice of customers but also from the user-generated data and product-sensed data.

Keywords:

• product-service systems
• requirement elicitation
• information modelling
• graph embedding
• context-awareness
• ontology

Disclosure statement

No potential conflict of interest was reported by the authors.

ORCID

Zuoxu Wang http://orcid.org/0000-0003-2524-1217

Chun-Hsien Chen http://orcid.org/0000-0003-2193-5270

Pai Zheng http://orcid.org/0000-0002-2329-8634

Xinyu Li http://orcid.org/0000-0002-4117-9698

Additional information

Funding

The authors wish to acknowledge the financial support from the National Research Foundation Singapore (NRF) Singapore and Delta Electronics International (Singapore) Pte Ltd., under the Corporate Laboratory@ University Scheme (Ref. SCO-RP1; RCA-16/434) at Nanyang Technological University, Singapore.