In healthcare, documenting patient care activities through medical notes, such as those written by doctors and nurses, is a mandatory practice. These records contain valuable information that, when analyzed using data mining and process mining techniques, can improve the understanding of care processes, identify areas for improvement, address errors, and predict health-related care for the coming period. However, the textual nature of these documents poses a significant challenge, as it prevents the direct application of data and process mining techniques. To overcome this, the extraction of events—and subsequently, event logs—from medical notes is needed. We evaluate and compare two zero-shot approaches to event extraction: a sentence transformer–based approach and a large language model–based approach. The evaluation is carried out on a human-annotated dataset derived from an annotated subset of nurse notes in the MIMICS-III dataset. We highlight the strengths and weaknesses of each approach and discuss further steps necessary to effectively obtain event logs from medical notes.

The assessment of process mining techniques using real-life data is often compromised by the lack of ground truth knowledge, the presence of non-essential outliers in system behavior and recording errors in event logs. Using synthetically generated data could leverage ground truth for better evaluation. Existing log generation tools inject noise directly into the logs, which does not capture many typical behavioral deviations. Furthermore, the link between the model and the log, which is needed for later assessment, becomes lost. We propose a ground-truth approach for generating process data from existing or synthetic initial process models, whether automatically generated or hand-made. This approach incorporates patterns of behavioral deviations and recording errors to produce a synthetic yet realistic deviating model and imperfect event log. These, together with the initial model, are required to assess process mining techniques based on ground truth knowledge. We demonstrate this approach to create datasets of synthetic process data for three processes, one of which we used in a conformance checking use case, focusing on the assessment of (relaxed) systemic alignments to expose and explain deviations in modeled and recorded behavior. Our results show that this approach, unlike traditional methods, provides detailed insights into the strengths and weaknesses of process mining techniques, both quantitatively and qualitatively.

Alignments are a well-established conformance checking technique that serve to reconcile system logs with normative process models. For processes involving multiple entities, such as objects and resources performing different tasks, the interaction of these entities must be taken into account in the alignments. In traditional approaches, it is achieved by considering a log event as matching a model event when all the entities registered in the logged event fully match the ones required by the model, thus considering events as unbreakable process atoms. We relax this requirement to deal with partial agreements between logged and modeled events and define relaxed alignments, aiming at maximizing the synchronized interactions between entities. Our approach is based on the use of projections of the log and model on individual objects, to deal with partial agreements. The optimality criterion is based on the cost function taking into account the deviating moves (events with non-matching event labels), the degree of (partial) event matches, and the correlations between non-matching parts of events involved in the process execution. Illustrating with a running example, we demonstrate that our approach yields alignments that better capture deviations in the context of complex, multi-object processes.

Alignments are a well-established conformance checking technique that serve to reconcile system logs with normative process models. For processes involving multiple entities, such as objects and resources performing different tasks, the interaction of these entities must be taken into account in the alignments. In traditional approaches, it is achieved by considering a log event as matching a model event when all the entities registered in the logged event fully match the ones required by the model, thus considering events as unbreakable process atoms. We relax this requirement to deal with partial agreements between logged and modeled events and define relaxed alignments , aiming at maximizing the synchronized interactions between entities. Our approach is based on the use of projections of the log and model on individual objects, to deal with partial agreements. The optimality criterion is based on the cost function taking into account the deviating moves (events with non-matching event labels), the degree of (partial) event matches, and the correlations between non-matching parts of events involved in the process execution. Illustrating with a running example, we demonstrate that our approach yields alignments that better capture deviations in the context of complex, multi-object processes.

Artifact-centric process models aim to describe complex processes as a collection of interacting artifacts. Recent development in process mining allow for the discovery of such models. However, the focus is often on the representation of the individual artifacts rather than their interactions. Based on event data we can automatically discover composite state machines representing artifact-centric processes. Moreover, we provide ways of visualizing and quantifying interactions among different artifacts. For example, we are able to highlight strongly correlated behaviours in different artifacts. The approach has been fully implemented as a ProM plug-in; the CSM Miner provides an interactive artifact-centric process discovery tool focussing on interactions. The approach has been evaluated using real life data sets, including the personal loan and overdraft process of a Dutch financial institution.

In this paper, we present a data-driven approach to enable the creation of evidence-based usability test scenarios. By utilising product usage data to create usability test scenarios, we aim to improve the reliability of the test results and to provide better insights into product usability. The approach consists of four elements: the collection of product usage data, the transformation of these data into logs of user activities, the creation of models of user behaviour, and the guided creation of usability test scenarios based on the models. We discuss the challenges that can be encountered when applying this approach based on our experiences with two case studies in product development. We have created a prototype scenario planning tool and performed a preliminary evaluation of the tool with usability engineers working at Philips Healthcare. The evaluation shows that tool-supported evidence-based usability test creation would be valuable in their daily work.

This paper introduces the tool LocalProcessModelDiscovery, which is available as a package in the process mining toolkit ProM. LocalProcessModelDiscovery aims to discover local process models, i.e., frequent patterns extracted from event logs, where each frequent pattern is expressed in the form of a Petri net. Local process models can be positioned in-between process discovery and Petri net synthesis on the one hand, and sequential pattern mining on the other hand. Like pattern mining techniques, the LocalProcessModelDiscovery tool focuses on the extraction of a set of frequent patterns, in contrast to Petri net synthesis and process discovery techniques that aim to describe all behavior seen in an event log in the form of a single model. Like Petri net synthesis and process discovery techniques, the models discovered with LocalProcessModelDiscovery can express a diverse set of behavioral constructs. This contrasts sequential pattern mining techniques, which are limited to patterns that describe sequential orderings in the data and are unable to express loops, choices, and concurrency.

Local Process Models (LPM) describe structured fragments of process behavior occurring in the context of less structured business processes. Traditional LPM discovery aims to generate a collection of process models that describe highly frequent behavior, but these models do not always provide useful answers for questions posed by process analysts aiming at business process improvement. We propose a framework for goal-driven LPM discovery, based on utility functions and constraints. We describe four scopes on which these utility functions and constrains can be defined, and show that utility functions and constraints on different scopes can be combined to form composite utility functions/constraints. Finally, we demonstrate the applicability of our approach by presenting several actionable business insights discovered with LPM discovery on two real life data sets.

In complex systems one can often identify various entities or artifacts. The lifecycles of these artifacts and the loosely coupled interactions between them define the system behavior. The analysis of such artifact system behavior with traditional process discovery techniques is often problematic due to the existence of many-to-many relationships between artifacts, resulting in models that are difficult to understand and statistics that are inaccurate. The aim of this work is to address these issues and enable the calculation of statistics regarding the synchronisation of behaviour between artifact instances. By using a Petri net formalisation with step sequence execution semantics to support true concurrency, we create state-based artifact lifecycle models that support many-to-many relations between artifacts. The approach has been implemented as an interactive visualisation in ProM and evaluated using real-life public data.

In process mining, precision measures are used to quantify how much a process model overapproximates the behavior seen in an event log. Although several measures have been proposed throughout the years, no research has been done to validate whether these measures achieve the intended aim of quantifying over-approximation in a consistent way for all models and logs. This paper fills this gap by postulating a number of axioms for quantifying precision consistently for any log and any model. Further, we show through counter-examples that none of the existing measures consistently quantifies precision.

Sequential pattern mining and temporal association rule mining techniques are established techniques to mine insights into the data collected by smart home environments and ambient living systems. Local process models are a recent technique that uses constructs from the field of business process modeling to represent frequent patterns that go beyond sequential patterns and can additionally express rich ordering relations that include concurrent execution, choices, and repetition. To gain insight into the behavior within smart home environments using local process models, it is vital to focus on patterns where the activities that are described by the pattern are truly related. We show on real-life smart home data that existing techniques for mining local process models fail to do so, and address this problem by proposing novel techniques for constraint-based local process model mining, focusing on event gap constraints and time gap constraints. We observe that in order to get an accurate support count of a local process model, it is sufficient to only consider specific parts of the datasets instead of the full dataset, which allows to speed up the counting of the support of a pattern. We provide a novel algorithm to extract those relevant parts of the data for support counting. We evaluate our approach on a collection of real-life smart home data sets. We show that more insightful local process models can be mined when applying such constraints, and show the novel algorithm allows to mine them efficiently.

Planning human activities within business processes often happens based on the same methods and algorithms as are used in the area of manufacturing systems. However, human behaviour is quite different from machine behaviour. Their performance depends on a number of factors, including workload, stress, personal preferences, etc. In this article we describe an approach for scheduling activities of people that takes into account business rules and dynamic human performance in order to optimise the schedule. We formally describe the scheduling problem we address and discuss how it can be constructed from inputs in the form of business process models and performance measurements. Finally, we discuss and evaluate an implementation for our planning approach to show the impact of considering dynamic human performance in scheduling.

Process mining techniques focus on extracting insight in processes from event logs. In many cases, events recorded in the event log are too fine-grained, causing process discovery algorithms to discover incomprehensible process models or process models that are not representative of the event log. We show that when process discovery algorithms are only able to discover an unrepresentative process model from a low-level event log, structure in the process can in some cases still be discovered by first abstracting the event log to a higher level of granularity. This gives rise to the challenge to bridge the gap between an original low-level event log and a desired high-level perspective on this log, such that a more structured or more comprehensible process model can be discovered. We show that supervised learning can be leveraged for the event abstraction task when annotations with high-level interpretations of the low-level events are available for a subset of the sequences (i.e., traces). We present a method to generate feature vector representations of events based on XES extensions, and describe an approach to abstract events in an event log with Condition Random Fields using these event features. Furthermore, we propose a sequence-focused metric to evaluate supervised event abstraction results that fits closely to the tasks of process discovery and conformance checking. We conclude this paper by demonstrating the usefulness of supervised event abstraction for obtaining more structured and/or more comprehensible process models using both real life event data and synthetic event data.

Process mining provides fact-based insights into processes based on behaviour captured in event data. An important aspect of this is the discovery of process models from such data. Traditionally, the focus of process discovery is on learning the ordering of activities. We deviate from this dominating activity view on processes to focus on states and state changes. Specifically, we aim to discover state-based models for processes where different facets, or perspectives, of the process can be identified. In this paper we describe an interactive process discovery tool that can be used to discover and explore state-based models for such multi-perspective processes: the Composite State Machine Miner. It quantifies and visualises the interactions between perspectives to provide additional process insights. This tool has been used to analyse the BPI Challenge 2012 data of a loan application process and product user behaviour data gathered by Philips during the development of a smart baby bottle equipped with various sensors.

Process mining techniques aim to extract insights in processes from event logs. One of the challenges in process mining is identifying interesting and meaningful event labels that contribute to a better understanding of the process. Our application area is mining data from smart homes for elderly, where the ultimate goal is to signal deviations from usual behavior and provide timely recommendations in order to extend the period of independent living. Extracting individual process models showing user behavior is an important instrument in achieving this goal. However, the interpretation of sensor data at an appropriate abstraction level is not straightforward. For example, a motion sensor in a bedroom can be triggered by tossing and turning in bed or by getting up. We try to derive the actual activity depending on the context (time, previous events, etc.). In this paper we introduce the notion of label refinements, which links more abstract event descriptions with their more refined counterparts. We present a statistical evaluation method to determine the usefulness of a label refinement for a given event log from a process perspective. Based on data from smart homes, we show how our statistical evaluation method for label refinements can be used in practice. Our method was able to select two label refinements out of a set of candidate label refinements that both had a positive effect on model precision.

In this paper we describe a method to discover frequent behavioral patterns in event logs. We express these patterns as local process models. Local process model mining can be positioned in-between process discovery and episode / sequential pattern mining. The technique presented in this paper is able to learn behavioral patterns involving sequential composition, concurrency, choice and loop, like in process mining. However, we do not look at start-to-end models, which distinguishes our approach from process discovery and creates a link to episode / sequential pattern mining. We propose an incremental procedure for building local process models capturing frequent patterns based on so-called process trees. We propose five quality dimensions and corresponding metrics for local process models, given an event log. We show monotonicity properties for some quality dimensions, enabling a speedup of local process model discovery through pruning. We demonstrate through a real life case study that mining local patterns allows us to get insights in processes where regular start-to-end process discovery techniques are only able to learn unstructured, flower-like, models.

Process mining provides fact-based insights into process behaviour captured in event data. In this work we aim to discover models for processes where different facets, or perspectives, of the process can be identified. Instead of focussing on the events or activities that are executed in the context of a particular process, we concentrate on the states of the different perspectives and discover how they are related. We present a formalisation of these relations and an approach to discover state-based models highlighting them. The approach has been implemented using the process mining framework ProM and provides a highly interactive visualisation of the multi-perspective state-based models. This tool has been evaluated on the BPI Challenge 2012 data of a loan application process and on product user behaviour data gathered by Philips during the development of a smart baby bottle equipped with various sensors.

Planning human activities within business processes often happens based on the same methods and algorithms as are used in the area of manufacturing systems. However, human resources are more complex than machines. Their performance depends on a number of factors, including stress, personal preferences, etc. In this paper we describe an approach for planning activities of people that takes into account business rules and optimises the schedule with respect to one or more KPIs. Taking a task list, a set of rules or constraints and a KPI calculation model as input, we automatically create an executable model that captures all the possible scheduling scenarios. The state space of this executable model is explored to find an optimal schedule.