Keywords: Enterprise Architecture, Architectural Coordination, Digital Twins
Astract: Digital Twins (DTs) carry the promise of supporting better decision-making, monitoring, and learning in relation to the twinned entity, by integrating novel technologies, including digital models, symbolic and sub-symbolic artificial intelligence, as well as advanced optimisation, simulation, and visualisation techniques. However, delivering such a promise requires considerable investments, which can only valorise in the long run, as DTs tend to be ‘data hungry’, in need of ample sensors, actuators and serious computing power. Yet, most current approaches to DT development focus on isolated scenarios, which not only limits the understanding of the value of DTs, but also their broader implications. The introduction of DTs, generally, also entails a wider digital transformation in an (inter-)organisational context, while such transformations need to be properly managed. We also observe that, since DTs are fundamentally a class of (highly advanced) information systems, this inevitably makes them an integral part of an enterprise’s broader (inter-organisational) portfolio of information systems. In line with this, we argue that, in order to (also) improve the socio-economical sustainability of DT solutions, their development, deployment and evolution need to be subject to architectural coordination within the broader frame of enterprise architecture management (EAM). From this perspective, we discuss some potential directions of research in (enterprise) architectural coordination of DT development, in order to help address some crucial challenges of socio-economically sustainable development and evolution of DTs as part of a broader portfolio of information systems.

Keywords: Process Patterns, Teaching Modelling

Keywords: Conceptual Modeling, Multimodal data, Model Enrichment

Keywords: Multimodal data analysis, Mixed Reality, Process Mining
Astract: This paper discusses an end-to-end methodology for real-time surgical conformance checking that uses multimodal process mining, mixed reality (MR), and large language model (LLM) prompting. Our approach aims to support surgeons and medical teams by comparing as-is operational data—captured through a variety of sensors including MR-based gaze tracking—with a reference surgical process model encoded in Business Process Modeling Notation (BPMN). We illustrate how shallow and deep human-in-the-loop feedback mechanisms can be integrated with chain-of-thought prompting to provide relevant, context-aware, and iterative feedback during surgery. We further indicate which aspects of the surgery can be monitored (and hence queried) by our multimodal process mining engine. By enabling precise, actionable feedback during critical surgical procedures, our approach enhances the ability to identify deviations, ensure adherence to best practices, and reduce human error. Ultimately, this methodology empowers surgical teams to make data-driven adjustments, promotes better patient outcomes, and allows hospitals to monitor surgical conformance effectively, setting a new standard for process-driven healthcare assistance.

Keywords: Artificial Intelligence, Event Log Completion, Event Log Creation, Event Log Quality Improvement, Multimodal data
Astract: Process mining uses data from event logs to understand which activities were undertaken, their timing, and the involved entities, providing a data trail for process analysis and improvement. However, a significant challenge involves ensuring that these logs accurately reflect the actual processes. Some processes leave few digital traces, and their event logs often lack details about manual and physical work that does not involve computers or simple sensors. We introduce the Business-knowledge Integration Cycles (BICycle) method and mm_proc_miner tool to convert raw and unstructured data from various modalities, such as video, audio, and sensor data, into a structured and unified event log, while keeping human-in-the-loop. Our method analyzes the semantic distance between visible, audible, and textual evidence within a self-hosted joint embedding space. Our approach is designed to consider (1) preserving the privacy of evidence data, (2) achieving real-time performance and scalability, and (3) preventing AI hallucinations. We also publish a dataset consisting of over 2K processes with 16K steps to facilitate domain inference-related tasks. For the evaluation, we created a novel test dataset in the domain of DNA home kit testing, for which we can guarantee that it was not encountered during the training of the employed AI foundational models. We show positive insights in both event log enrichment with multimodal evidence and human-in-the-loop contribution.