An Integrated Product Service System Framework for On-Site Digital Human Guide Systems

On-site digital human guide systems, which integrate intelligent interactive technologies with guidance, interpretation, and information services, are emerging as an important form of intelligent on-site service. However, existing knowledge remains largely fragmented across technological configurations, interaction modalities, application contexts, and user experience objectives, lacking an integrated cross-dimensional analytical perspective that explains how these systems create and deliver value. To address this gap, this paper aims to adopt a Product–Service Systems (PSS) perspective to systematically examine the development of on-site digital human guide systems. Specifically, it explores their product–service configurations, service delivery modes and user participation, and artificial intelligence (AI) capability integration pathways, while identifying the value creation opportunities and challenges associated with system development and continuous optimization. The PSS paradigm offers such an integrative lens, which has gained renewed relevance as the Fourth Industrial Revolution (Industry 4.0) accelerates the servitization and digital transformation of traditional services. This paper conducts a scoping review employing content analysis based on a structured cross-database search across Google Scholar, Scopus, and Web of Science, supplemented by snowball sampling, covering 40 studies, including 34 deployed projects. The findings reveal that: (1) on-site digital human guide systems can be categorized into four product–service configurations: fixed terminal (stationary dialogue); mobile terminal (location-aware guidance); Head-Mounted Display/Mixed Reality (immersive experience); and robot (full-process mobile service). The selection of these configurations is shaped by spatial characteristics, target user group, and institutional operational conditions; (2) a user behavior taxonomy of nine active and five passive types was developed, demonstrating that user participation patterns are jointly shaped by control allocation in service delivery and the social behavior design of digital humans, with users showing a preference for controllable and interruptible engagement; (3) AI integration has evolved from rule-and-script-driven approaches to modular AI integration, and subsequently to large language model (LLM)/Retrieval-Augmented Generation (RAG)-driven architectures, with corresponding design implications proposed; and (4) challenges were classified into four major categories and 26 subcategories across three digital transformation stages. The contribution of this paper lies in the development of an integrated PSS analytical framework for on-site digital human guide systems, spanning product, service, and AI integration layers. The framework provides a multi-layer analytical lens for understanding system configurations, user participation, technological evolution, and implementation challenges, while offering structured guidance for configuration and service selection, system design, and continuous optimization across diverse deployment contexts. These findings provide practical implications for researchers and practitioners seeking to design, deploy, and optimize on-site digital human guide systems across diverse service environments.