Control-flow Perspective Research Articles

Analysis the patients' careflows using process mining.

Recently, The Egyptian health sector whether it is public or private; utilizes emerging technologies such as data mining, business intelligence, Internet of Things (IoT), among many others to enhance the service and to deal with increasing costs and growing pressures. However, process mining has not yet been used in the Egyptian organizations, whereas the process mining can enable the domain experts in many fields to achieve a realistic view of the problems that are currently happening in the undertaken field, and thus solve it. This paper presents application of the process mining techniques in the healthcare field to obtain meaningful insights about its careflows, e.g., to discover typical paths followed by certain patient groups. Also, to analyze careflows that have a high degree of dynamic and complexity. The proposed methodology starts by the preprocess step on the event logs to eliminate outliers and clean the event log. And then apply a set of the popular discovery miner algorithms to discover the process model. Then careflows processes are analyzed from three main perspectives: the control-flow perspective, the performance perspective and, the organizational perspective. That contributes with many insights for the domain experts to improve the existing careflows. Through evaluating the simplicity metric of extracted models; the paper suggested a method to quantify the simplicity metric. The paper used a dataset from a cardiac surgery unit in an Egyptian hospital. The results of the applied process mining techniques provide the hospital managers a real analysis and insights to make the patient journey easier.

Using Unified Modeling Language to Analyze Business Processes in the Delivery of Child Health Services.

Business Process Management (BPM) has been increasingly used in recent years in the healthcare domain to analyze, optimize, harmonize and compare clinical and healthcare processes. The main aim of this methodology is to model the interactions between medical and organizational activities needed to deliver health services, measure their complexity, variability and deviations to improve the quality of care and its efficiency. Among the different tools, languages and notations developed in the decades, UML (Unified Modeling Language) represents a widely adopted technique to model, analyze and compare business processes in healthcare. We adopted its diagrams in the MOCHA project to compare the different ways of organizing, coordinating and delivering child care across 30 EU/EEA countries both from an organization and control-flow perspectives. This paper provides an overview of the main components used to represent the business process using UML diagrams, also highlighting how we customized them to capture the specificity of the healthcare domain taking into account that processes are reconstructed on the basis of country experts’ responses to questionnaires. The benefits of the application of this methodology are demonstrated by providing examples of comparing different aspects of child care.

Data attribute oriented business process effective infrequency behavior mining method

SummaryThe current process mining method takes high‐frequency behavior as the mainstream behavior, and directly filters out the infrequent logs as noise to obtain a concise business process model. However, effective infrequency behaviors that are important to business processes are often data constrained. From a control flow perspective, it is difficult to accurately capture the effective infrequency behavior. A method for mining effective infrequent behaviors based on data attributes is proposed to solve the above problems. First, the important data attributes of target business processes are obtained by feature combination. Then, attribute assignment rules are set according to the needs of the business process to determine whether it has a beneficial impact on the business process. Lastly, it is suggested that a confidence interval be used instead of the traditional threshold to evaluate and mine effective low‐frequency behavior. The experiment results show that compared with other methods, it can significantly improve the fitness of the business process model and can more accurately mine effective infrequency behavior to optimize the business process model.

Conformance-oriented Predictive Process Monitoring in BPaaS Based on Combination of Neural Networks

As a new cloud service for delivering complex business applications, Business Process as a Service (BPaaS) is another challenge faced by cloud service platforms recently. To effectively reduce the security risk caused by business process execution load in BPaaS, it is necessary to detect the non-compliant process executions (instances) from tenants in advance by checking and monitoring the conformance of the executing process instances in real-time. However, the vast majority of existing conformance checking techniques can only be applied to the process instances that have been executed completely offline and only focus on the conformance from the single control-flow perspective. We develop an extensible multi-perspective conformance measurement method to address these issues first and then investigate the predictive conformance monitoring approach by automatically constructing an online multi-perspective conformance prediction model based on deep learning techniques. In addition, to capture more decisive features in the model from both local information and long-distance dependency within an executed process instance, we propose an approach, called CNN-BiGRU, by combining Convolutional Neural Network (CNN) with a variant and enhancement of Recurrent Neural Network (RNN). Extensive experiments on two data sets demonstrate the effectiveness and efficiency of the proposed CNN-BiGRU.

Online incremental updating for model enhancement based on multi-perspective trusted intervals

Model incremental updating enhances the initial model by analysing discrepancy parts of the system to improve the model's adaptability for new scenarios. These discrepancy components originate from the deviation between the increasing business process operational state and the outdated original planning model. Considerable domain-specific knowledge is required to determine the threshold points for selecting appropriate activities, but process analysts rarely know each scenario's domain knowledge. Moreover, most analytical processes only focussed on the control flow level. Aiming at these issues, this paper proposes a Hybrid Behavioural and Resource Trusted intervals Updating algorithm (BI&RI Updating) for model enhancement based on control level and resource level of online event streams. First, analyse the reference model to construct multi-perspective trusted interval constraints in the offline stage. From a control-flow perspective, the behavioural relationships between activities are researched using a deep clustering approach. Moreover, from a data-flow standpoint, resource co-occurrence relationships are analysed based on association rules. Next, the incremental update algorithm in online scenarios is proposed to update the model by filtering the event streams and iteratively optimising the trusted intervals. Finally, the proposed algorithm is implemented based on the PM4PY framework and evaluated using real logs with both outcome model quality and execution efficiency. The results show that the algorithm can execute quickly and improve the quality of the model even in a non-ideal state where the logs contain noise.

Business Process Outcome Prediction Based on Deep Latent Factor Model

Business process outcome prediction plays an essential role in business process monitoring. It continuously analyzes completed process events to predict the executing cases’ outcome. Most of the current outcome prediction focuses only on the activity information in historical logs and less on the embedded and implicit knowledge that has not been explicitly represented. To address these issues, this paper proposes a Deep Latent Factor Model Predictor (DLFM Predictor) for uncovering the implicit factors affecting system operation and predicting the final results of continuous operation cases based on log behavior characteristics and resource information. First, the event logs are analyzed from the control flow and resource perspectives to construct composite data. Then, the stack autoencoder model is trained to extract the data’s main feature components for improving the training data’s reliability. Next, we capture the implicit factors at the control and data flow levels among events and construct a deep implicit factor model to optimize the parameter settings. After that, an expansive prefix sequence construction method is proposed to realize the outcome prediction of online event streams. Finally, the proposed algorithm is implemented based on the mainstream framework of neural networks and evaluated by real logs. The results show that the algorithm performs well under several evaluation metrics.

Process Aware Host-based Intrusion Detection Model

Nowadays, many organizations use Process Aware Information Systems (PAISs) to automate their business process. As any other information systems, security plays a major role in PAIS to provide a secure state and maintain the system in it. In order to provide security in a PAIS, a Process Aware Host-based Intrusion Detection (PAHID) model is proposed in this paper. The model detects host-based intrusions in a PAIS using process mining techniques.The proposed model uses both anomaly detection and misuse detection techniques for more efficiency, and organizational perspective of process mining is considered (rather than control-flow perspective) to detect more attack types. The model is automated and can deal with large logs and is suitable for flexible application domains. The PAHID model is implemented by the use of ProM framework and Java programming. It is evaluated by using a simulated log based on a real-world organization information system. Results demonstrate that the model provides high accuracy and low false positive rate.

Solving reachability problems on data-aware workflows

Recent advances in the field of Business Process Management (BPM) have brought about several suites able to model data objects along with the traditional control flow perspective. Nonetheless, when it comes to formal verification there is still a lack of effective verification tools on imperative data-aware process models and executions: the data perspective is often abstracted away and verification tools are often missing.Automated Planning is one of the core areas of Artificial Intelligence where theoretical investigations and concrete and robust tools have made possible the reasoning about dynamic systems and domains. Moreover planning techniques are gaining popularity in the context of BPM. Starting from these observations, we provide here a concrete framework for formal verification of reachability properties on an expressive, yet empirically tractable class of data-aware process models, an extension of Workflow Nets. Then we provide a rigorous mapping between the semantics of such models and that of three important Automated Planning paradigms: Action Languages, Classical Planning, and Model-Checking. Finally, we perform a comprehensive assessment of the performance of three popular tools supporting the above paradigms in solving reachability problems for imperative data-aware business processes, which paves the way for a theoretically well founded and practically viable exploitation of planning-based techniques on data-aware business processes.

Soundness Verification of Data-Aware Process Models with Variable-to-Variable Conditions

Traditionally Business Process Modeling has only focused on the control-flow perspective, thus allowing process designers to specify the constraints on the activities of the process: the order and potential concurrency of their execution, their mutual exclusivity, the possibility of being repeated, etc. However, activities are executed by different resources, manipulate data objects and are constrained by the state of such objects. This requires that the traditional notion of soundness, typically introduced for control-flow-only models, is extended so as to consider data. Intuitively, a (data-aware) process model is sound if (1) it does not contain deadlocks, (2) no more activities are enabled when the process instance is marked as completed and finally (3) there are no parts of the model that cannot be executed. Although several data-aware notations have been introduced in the literature, not all of these are given a formal semantics. In this paper, we propose a technique for checking the data-aware soundness for a specific class of such integrated models, with a simple syntax and semantics, building on Data Petri Nets (DPNs). These are Petri nets enriched with case variables, where transitions are guarded by formulas that inspect and update such variables, and are of the form variable-operator-variable or variable-operator-constant. Even though DPNs are less expressive than Petri nets where data are carried by tokens, they elegantly capture business processes operating over simple case data, allowing to model complex data-aware decisions. We show that, if a DPN is data-aware sound, the Constraint Graph is a finite-state automaton; however, a finite-state Constraint Graph does not guarantee data-aware soundness, but provides a finite structure through which this property can be checked. Finally, we investigate further properties beyond data-aware soundness, such as the problem of verifying that an actor participating in the business process can unilaterally enforce data-aware soundness by restricting the possible executions of a bounded DPN, assuming this actor to be able to control the firing of some transitions and decide the value of some of the case variables whenever these are updated.

Text-Aware Predictive Monitoring of Business Processes

The real-time prediction of business processes using historical event data is an important capability of modern business process monitoring systems. Existing process prediction methods are able to also exploit the data perspective of recorded events, in addition to the control-flow perspective. However, while well-structured numerical or categorical attributes are considered in many prediction techniques, almost no technique is able to utilize text documents written in natural language, which can hold information critical to the prediction task. In this paper, we illustrate the design, implementation, and evaluation of a novel text-aware process prediction model based on Long Short-Term Memory (LSTM) neural networks and natural language models. The proposed model can take categorical, numerical and textual attributes in event data into account to predict the activity and timestamp of the next event, the outcome, and the cycle time of a running process instance. Experiments show that the text-aware model is able to outperform state-of-the-art process prediction methods on simulated and real-world event logs containing textual data.

A multi-perspective approach for the analysis of complex business processes behavior

Business processes are often monitored by transactional information systems that produce massive dataset called event logs. Such logs contain the process execution traces, typically characterized by heterogeneous and high-dimensional data. Process mining techniques offer a great opportunity to gain valuable knowledge hidden in the data to be used for analysing the multiple characteristics of processes (i.e. perspectives in process mining, like structural aspects, activities, resources, data and time). Therefore, raw data must be encoded into a suitable format that can be more conveniently provided to the mining algorithms. However, most of the existing process encoding techniques focus on the control-flow perspective, i.e. only encode the sequence of activities that characterize a trace, leaving out other process perspectives that are fundamental for describing the process behavior in all its aspects. In this paper we address the problem of computing a concise and informative representation of execution traces that considers the multiple perspectives of the process behavior. We propose a holistic approach that computes trace embedding able to capture patterns of dependencies between the perspectives that are lost in a one-dimensional analysis and, at the same time, it is unsupervised, meaning that no a priori knowledge is needed. The experiments conducted on two real life logs demonstrate that our proposed embedding is appropriate to concisely describe the multiple and various characteristics of the processes, and that the proposed method outperforms existing trace encoding techniques. Furthermore, the embedding includes the elapsed time between events as an additional feature to make us capable to use it as a further dimension of analysis.

Process discovery with context-aware process trees

Discovery plays a key role in data-driven analysis of business processes. The vast majority of contemporary discovery algorithms aims at the identification of control-flow constructs. The increase in data richness, however, enables discovery that incorporates the context of process execution beyond the control-flow perspective. A “control-flow first” approach, where context data serves for refinement and annotation, is limited and fails to detect fundamental changes in the control-flow that depend on context data. In this work, we thus propose a novel approach for combining the control-flow and data perspectives under a single roof by extending inductive process discovery. Our approach provides criteria under which context data, handled through unsupervised learning, take priority over control-flow in guiding process discovery. The resulting model is a process tree, in which some operators carry data semantics instead of control-flow semantics. We show that the proposed approach produces trees that are context consistent, deterministic, complete, and can be explainable without a major quality reduction. We evaluate the approach using synthetic and real-world datasets, showing that the resulting models are superior to state-of-the-art discovery methods in terms of measures based on multi-perspective alignments.

OrgMiner: A Framework for Discovering User-Related Process Intelligence from Event Logs

Process Intelligence refers to the extraction and analysis of valuable knowledge nuggets embedded in business process instances/event logs or enterprise applications, for the purpose of supporting various decision-making processes. Researchers and practitioners mine such event logs using Process Mining and Analytics (PMA) techniques that help analyze business processes across three perspectives: control flow, organization, and data. While previous PMA studies have made advances toward the control flow and data flow perspectives, there is limited research toward the organizational perspective of process intelligence. In this study, we propose an organizational mining framework, OrgMiner, that supports constructing organizational models from event logs. The framework utilizes the notion of behavioral patterns, which rely on the weak order relations appearing in event logs. The various modules and knowledge elements in the framework are described in detail. The components of the framework support identifying, selecting, and applying behavioral patterns using different metrics for organizational mining purposes. The derived organizational models can be used to support decision making in scenarios such as task assignment, resource allocation, as well as role-based access control. Compared to extant studies, the proposed approach does not assume prior availability of explicit process models. Additionally, the process patterns presented in this study can be used as building blocks, so that researchers and practitioners can use them directly or extend them further to identify complex organizational processes. A case study is presented to evaluate the feasibility and effectiveness of the OrgMiner framework.

Supporting Governance in Healthcare Through Process Mining: A Case Study

Healthcare organizations are under increasing pressure to improve productivity, gain competitive advantage and reduce costs. In many cases, despite management already gained some kind of qualitative intuition about inefficiencies and possible bottlenecks related to the enactment of patients' careflows, it does not have the right tools to extract knowledge from available data and make decisions based on a quantitative analysis. To tackle this issue, starting from a real case study conducted in San Carlo di Nancy hospital in Rome (Italy), this article presents the results of a process mining project in the healthcare domain. Process mining techniques are here used to infer meaningful knowledge about the patient careflows from raw event logs consisting of clinical data stored by the hospital information systems. These event logs are analyzed using the ProM framework from three different perspectives: the control flow perspective, the organizational perspective and the performance perspective. The results on the proposed case study show that process mining provided useful insights for the governance of the hospital. In particular, we were able to provide answers to the management of the hospital concerning the value of last investments, and the temporal distribution of abandonments from emergency room and exams without reservation.

Automated discovery of declarative process models with correlated data conditions

Automated process discovery techniques enable users to generate business process models from event logs extracted from enterprise information systems. Traditional techniques in this field generate procedural process models (e.g., in the BPMN notation). When dealing with highly variable processes, the resulting procedural models are often too complex to be practically usable. An alternative approach is to discover declarative process models, which represent the behavior of the process as a set of constraints. Declarative process discovery techniques have been shown to produce simpler models than procedural ones, particularly for processes with high variability. However, the bulk of approaches for automated discovery of declarative process models focus on the control-flow perspective, ignoring the data perspective. This paper addresses the problem of discovering declarative process models with data conditions. Specifically, the paper tackles the problem of discovering constraints that involve two activities of the process such that each of these two activities is associated with a condition that must hold when the activity occurs. The paper presents and compares two approaches to the problem of discovering such conditions. The first approach uses clustering techniques in conjunction with a rule mining technique, while the second approach relies on redescription mining techniques. The two approaches (and their variants) are empirically compared using a combination of synthetic and real-life event logs. The experimental results show that the former approach outperforms the latter when it comes to re-discovering constraints artificially injected in a log. Also, the former approach is in most of the cases more computationally efficient. On the other hand, redescription mining discovers rules with higher confidence (and lower support) suggesting that it may be used to discover constraints that hold for smaller subsets of cases of a process.

Collection and Elicitation of Business Process Compliance Patterns with Focus on Data Aspects

Business process compliance is one of the prevalent challenges for companies. Despite an abundance of research proposals, companies still struggle with manual compliance checks and the understanding of compliance violations in the light of missing root-cause explanations. Moreover, approaches have merely focused on the control flow perspective in compliance checking, neglecting other aspects such as the data perspective. This paper aims at analyzing the gap between existing academic work and compliance demands from practice with a focus on the data aspects. The latter emerges from a small set of regulatory documents from different domains. Patterns are assumed as the right level of abstraction for compliance specification due to their independence of (technical) implementation in (process-aware) information systems, potential for reuse, and understandability. A systematic literature review collects and assesses existing compliance patterns. A first analysis of ten regulatory documents from different domains specifically reveals data-oriented compliance constraints that are not yet reflected by existing compliance patterns. Accordingly, data-related compliance patterns are specified.

Measuring Business Process Consistency Across Different Abstraction Levels

Business process modeling can take place at three abstraction levels, namely the conceptual level for system requirements, the logical level for system specification, and the physical level for software development. The consistency between these process models is crucial in process mapping, process integration, and difference detection. Existing work either only provides a simple “yes” or “no” answer as the consistency result, or simply checks the consistency from the control flow perspective. This paper presents a systematic approach to the quantitative measurement of the consistency between business processes across different abstraction levels. We use the essential event constraints to quantify the consistency from the perspectives of control flow and data flow, where the importance of different essential event constraints can also be distinguished. Our approach is implemented in a prototype tool. We evaluate our approach using synthetic datasets, the results of which demonstrate the effectiveness and efficiency of our approach.

A process mining approach to improve emergency rescue processes of fatal gas explosion accidents in Chinese coal mines

Gas explosion has always been one of the major accident types in the coal mines of China, and reliable emergency rescue process is one of the key guarantees to minimize accident losses. As an emerging discipline to discover bottlenecks and position deviations of processes, process mining is widely used to improve various business processes in recent years. Nevertheless, scarcely does any research apply it to the field of coal mine emergency rescue to our knowledge. In this study, we apply the technique of process mining to domain of gas explosion accident emergency rescue in coal mines. 50 considerable and major gas explosion accidents, which occurred from the second half of 2006–2014 in Chinese coal mines, are selected as log data. The aspects of control-flow perspective, case perspective, helicopter view, organizational dimension and performance perspective are analyzed by process mining. In terms of control-flow perspective, the emergency rescue model is extracted by the inductive miner in ProM, correspondingly, conformance checking and comparison with real-life model have shown the validity of our work. Research also shows that the average length of cases is 23.72 events, and 60% of the cases are under the average length; 56% of the gas explosion accident emergency rescue processes last less than two days; emergency rescue headquarters, barmaster and medical staff share the highest centrality in social network of rescue; the rescue performance is more affected by accident grade, compared with the factors of accident site, region of coal mine and coal mine ownership.

Time prediction on multi-perspective declarative business processes

Process-aware information systems (PAISs) are increasingly used to provide flexible support for business processes. The support given through a PAIS is greatly enhanced when it is able to provide accurate time predictions which is typically a very challenging task. Predictions should be (1) multi-dimensional and (2) not based on a single process instance. Furthermore, the prediction system should be able to (3) adapt to changing circumstances and (4) deal with multi-perspective declarative languages (e.g., models which consider time, resource, data and control flow perspectives). In this work, a novel approach for generating time predictions considering the aforementioned characteristics is proposed. For this, first, a multi-perspective constraint-based language is used to model the scenario. Thereafter, an optimized enactment plan (representing a potential execution alternative) is generated from such a model considering the current execution state of the process instances. Finally, predictions are performed by evaluating a desired function over this enactment plan. To evaluate the applicability of our approach in practical settings we apply it to a real process scenario. Despite the high complexity of the considered problems, results indicate that our approach produces a satisfactory number of good predictions in a reasonable time.

Measuring Data-Aware Process Consistency Based on Activity Constraint Graphs

Data-aware processes play a crucial role in various IT systems, including requirement elicitation, domain analysis, software design, and system execution. Due to frequent changes in business environments and continual internal adjustments of enterprises, data-aware processes are increasingly evolved into multiple process variants. The detection of differences between variants can be related to process mapping, process integration, or process substitution. A critical step of the procedure is to investigate the data-aware process consistency. Unfortunately, existing studies only provide a simple “yes” or “no” answer or look for an answer purely from the control flow perspective. The objective of this paper is to propose a systematic solution for effective measurement of consistency between data-aware processes. First, we identify essential activity constraints which reside in data-aware processes. Then, we introduce a novel concept of activity constraint graph (ACG) and propose an algorithm for constructing ACGs. Finally, we use ACGs to measure the data-aware process consistency on a scale from 0 to 1. Our technique has been implemented in a prototype tool, and extensive experiments using both real and synthetic datasets are conducted to evaluate the accuracy, distribution of consistency degrees, and capacity of difference detection of our approach. Results show that our approach is more accurate, generates a finer distribution of consistency degrees, and detects differences more effectively than other state-of-the-art approaches.