Sérgio Guerreiro

João Bettencourt, Sérgio Guerreiro

Recent advances in Generative Artificial Intelligence, particularly Large Language Models (LLMs), have stimulated growing interest in automating or assisting Business Process Modeling tasks using natural language. Several approaches have been proposed to transform textual process descriptions into BPMN and related workflow models. However, the extent to which these approaches effectively support complex process modeling in organizational settings remains unclear. This article presents a literature review of AI-driven methods for transforming natural language into BPMN process models, with a particular focus on the role of LLMs. Following a structured review strategy, relevant studies were identified and analyzed to classify existing approaches, examine how LLMs are integrated into text-to-model pipelines, and investigate the evaluation practices used to assess generated models. The analysis reveals a clear shift from rule-based and traditional NLP pipelines toward LLM-based architectures that rely on prompt engineering, intermediate representations, and iterative refinement mechanisms. While these approaches significantly expand the capabilities of automated process model generation, the literature also exposes persistent challenges related to semantic correctness, evaluation fragmentation, reproducibility, and limited validation in real-world organizational contexts. Based on these findings, this review identifies key research gaps and discusses promising directions for future research, including the integration of contextual knowledge through Retrieval-Augmented Generation (RAG), its integration with LLMs, the development of interactive modeling architectures, and the need for more comprehensive and standardized evaluation frameworks.

Sérgio Guerreiro, Pedro Sousa

BPMN is a specification language widely used by industry and researchers for business process modeling and execution. It defines clearly how to articulate its concepts, but do not provide mechanism to represent the semantics of the produced models. This paper addresses the problem of how to improve the expressiveness of BPMN models, proposing a definition for the semantics of a business process within a BPMN model, and improving the completeness of the models in a systematic manner, so that models can describe far more situations with few extra managed complexity. We conceive a framework based on the business transaction patterns available in the enterprise ontology body of knowledge to prescribe the foundations of semantic BPMN models. A tool has been developed to automate the framework. Then, two industrial proof-of-concepts are used to measure its coverage, both positive and negative, and to argue about our proposal's usefulness. After that, the proposal is compared with others using a systematic literature review. A full BPMN pattern is proposed encompassing the happy flow, the declinations, the rejections and the revocations, without adding any new element to the BPMN specification. A software tool has been developed, and made publicly available, to support the automatic generation of the BPMN models from the proposed patterns. Our semantified BPMN pattern allowed the identification of a large amount of implicit, and other not implemented, situations in both proof-of-concepts. It is concluded that the usage of a semantic solution, grounded on a sound pattern, allows the systematic enrichment of the BPMN models with a bounded effort. Moreover, to simplify the BPMN executable models' implementation, its elements could be classified as implicit, explicit, or not implemented yet. Finally, related work indicates that this work is demanded, but no full solutions are available.

Rafael Belchior, Sérgio Guerreiro, André Vasconcelos et al.

The complexity of a business environment often causes organizations to produce several inconsistent views on the same business process, leading to fragmentation and inefficiencies. Business process view integration attempts to produce an integrated view from different views of the same model, facilitating the management of models. To study trends around business process view integration, we conduct a systematic literature review to summarize findings since the 1970s, up to its potential novel applications. With a starting corpus of 798 documents, this survey draws up a systematic inventory of solutions used in academia and in the industry. By narrowing it down to 51 articles, we discuss in-depth 15 business process integration techniques papers. After that, we classify existing solutions according to their practicality. Our study shows that most integrated views are constructed by annotation, using formal merging rules. Finally, we explore possible future research directions. We highlight the application of view integration to the blockchain research area, where stakeholders can have different views on the same blockchain. We expect that this study contributes to interdisciplinary research across view integration.

Rafael Belchior, André Vasconcelos, Sérgio Guerreiro et al.

Blockchain interoperability is emerging as one of the crucial features of blockchain technology, but the knowledge necessary for achieving it is fragmented. This fact makes it challenging for academics and the industry to seamlessly achieve interoperability among blockchains. Given the novelty and potential of this new domain, we conduct a literature review on blockchain interoperability, by collecting 262 papers, and 70 grey literature documents, constituting a corpus of 332 documents. From those 332 documents, we systematically analyzed and discussed 80 documents, including both peer-reviewed papers and grey literature. Our review classifies studies in three categories: Cryptocurrency-directed interoperability approaches, Blockchain Engines, and Blockchain Connectors. Each category is further divided into sub-categories based on defined criteria. We discuss not only studies within each category and subcategory but also across categories, providing a holistic overview of blockchain interoperability, paving the way for systematic research in this domain. Our findings show that blockchain interoperability has a much broader spectrum than cryptocurrencies. The present survey leverages an interesting approach: we systematically contacted the authors of grey literature papers and industry solutions to obtain an updated view of their work. Finally, this paper discusses supporting technologies, standards, use cases, open challenges, and provides several future research directions.