Este estudo teve como objetivo verificar na literatura como a mineração de processos tem sido utilizada na área de saúde. Método: Trata-se de Scoping Review. A busca foi realizada nas bases de dados National Library of Medicine (PubMed), Cumulative Index to Nursing and Allied Health Literature (CINAHL), Search for anauthor profile (SCOPUS) e Scientific Electronic Library Online (Scielo), por meio da pergunta de pesquisa: \"Como tem sido aplicada a mineração de processos na área da saúde?\". Foram incluídas as pesquisas em inglês, espanhol e português, com abordagem quantitativa e qualitativa primárias, revisões sistemáticas, metanálises e/ou metasínteses, livros e guidelines, Resultado: As buscas foram executadas entre os meses de setembro à dezembro de 2017. Entre os 274 estudos, 15 foram incluídos na amostra. Os resultados demonstraram que o uso de mineração de processos na saúde têm sido utilizada com ênfase na área hospitalar, para distintas amostras de pacientes, analisando dados relacionados a protocolos, qualidade de atendimento, custos, performance dos serviços, mapeamento de processos e serviços epidemiológicos, temporalização de uso dos recursos, agendas de consultas, exames e procedimentos, diagnósticos, análise de complexidade do quadro clínico, além de possibilitarem a comparação entre dois serviços. Além disso, foram ainda identificados estudos de revisão de literatura que fomentam um processo de discussão sobre o tema em questão, com propósitos de descoberta, conformidade ou aprimoramento e desempenho. O processo de revisão demonstrou que esse é um tema promissor e de grande aplicabilidade na saúde / This study aimed to verify in the literature how process mining has been used in the health area. Method: This is Scoping Review. The search was conducted in the National Library of Medicine (PubMed), Cumulative Index to Nursing and Allied Health Literature (CINAHL), Search for anauthor profile (SCOPUS) and ScientificElectronic Library Online (Scielo), through How has mining been applied processes in the area of health?\". The researches were conducted in English, Spanish and Portuguese, with a quantitative and qualitative approach, primary, systematic reviews, meta-analyzes and / or meta-analyzes, books and guidelines, Result: Searches were performed between September and December 2017. 274 studies, 15 were included in the sample. The results demonstrated that the use of process mining in health has been used with emphasis in the hospital area for different patient samples, analyzing data related to protocols, quality of care, costs, performance of services, mapping of processes and epidemiological services, timing of resource use, consultation schedules, examinations and procedures, diagnoses, complexity analysis of the clinical picture, and allow the comparison between two services. In addition, literature review studies have been identified that foster a process of discussion about the topic in question. For discovery, compliance, or enhancement and performance purposes. Although this is a promising topic of great applicability in health identified in this review, this study presents limitations related to the number of databases consulted, which may have influenced the context and the number of studies analyzed

Made available in DSpace on 2018-08-01T23:38:03Z (GMT). No. of bitstreams: 1 tese_10969_Dissertação Luciana França_Versão Final.pdf: 2442120 bytes, checksum: c6bc5141d2f33e637a2a6eb80e448216 (MD5) Previous issue date: 2017-12-06 / A auditoria de processos de negócios é um tema de relevância crescente na literatura. No entanto, técnicas tradicionais e manuais demonstram-se insatisfatórias ou insuficientes, visto que as mesmas são custosas, podem ser tendenciosas e passíveis de erros, além de envolverem grande quantidade de recursos temporais, humanos e materiais. Nesse sentido, o presente estudo vem demonstrar como a técnica de process mining pode ser utilizada, de forma automática, na auditoria de processos governamentais, a partir de um sistema de informação e de uma ferramenta de mining denominada ProM. A partir de técnicas de verificação de conformidade, realizou-se a comparação entre os processos reais e seus respectivos modelos oficiais de uma organização governamental. Os resultados obtidos demonstram algumas divergências entre eles, e indicam que a técnica pode ser utilizada como um meio auxiliar na realização de auditoria de processos de negócios.

Até os dias de hoje, diversos algoritmos de mineração de modelos de processos já foram propostos para extrair conhecimento a partir de logs de eventos. O conhecimento que tais algoritmos são capazes de obter incluem modelos de processos de negócio, assim como aspectos da estrutura organizacional, como atores e papéis. A mineração de processos pode se beneficiar de uma estratégia incremental, especialmente quando as informações sobre um ou mais processos de negócio presentes no código fonte de um sistema de informação são logicamente complexas (diversas ramificações e atividades paralelas e/ou alternativas). Neste cenário, são necessárias muitas execuções da aplicação para a coleta de um grande conjunto de dados no arquivo de log, a fim de que o algoritmo de mineração possa descobrir e apresentar o processo de negócio completo. Outra situação que torna necessária a mineração incremental é a constante evolução dos processos de negócio, ocasionada geralmente por alterações nas regras de negócio de uma ou mais aplicações. Neste caso, o log pode apresentar novos fluxos de atividades, ou fluxos alterados ou simplesmente fluxos que não são mais executados. Estas mudanças devem ser refletidas no modelo do processo a fim de garantir a sincronização entre a aplicação (processo executado) e o modelo. A mineração incremental de processos pode ainda ser útil quando se faz necessária a extração gradual de um modelo de processo completo, extraindo modelos parciais (fragmentos de processo com início e fim) em um primeiro passo e integrando conhecimento adicional ao modelo em etapas até a obtenção do modelo completo. Contudo, os algoritmos atuais de mineração incremental de processos não apresentam total efetividade quanto aos aspectos acima citados, apresentando algumas limitações. Dentre elas podemos citar a não remoção de elementos obsoletos do modelo de processo descoberto, gerados após a atualização do processo executado, e também a descoberta de informações da estrutura organizacional associada ao processo como, por exemplo, os atores que executam as atividades. Este trabalho propõe um algoritmo incremental para a mineração de processos de negócio a partir de logs de execução. Ele permite a atualização completa de um modelo existente, bem como o incremento de um modelo de processo na medida em que novas instâncias são adicionadas ao log. Desta forma, podemos manter ambos, modelo de processo e o processo executado sincronizados, além de diminuirmos o tempo total de processamento uma vez que apenas novas instâncias de processo devem ser consideradas. Por fim, com este algoritmo é possível extrair modelos com acurácia igual ou superior aqueles que podem ser extraídos pelos algoritmos incrementais atuais. / Even today, several process mining algorithms have been proposed to extract knowledge from event logs of applications. The knowledge that such algorithms are able to discovery includes business process models, business rules, as well as aspects of organizational structure, such actors and roles of processes. These process mining algorithms can be divided into two: non-incremental and incremental. The mining process can benefit from an incremental strategy, especially when information about the process structure available in the system source code is logically complex (several branches and parallel activities). In this scenario, its necessary several executions of the application, to collect a large set of log data, so that the mining algorithm can discover and present the complete business process. Another use case where incremental mining is usefull is during the changing structure of the process, caused by the change in the business logic of an application. In this case, the log may provide new traces of activities, modified traces or simply traces that are no longer running. These changes must be reflected in the process model being generated to ensure synchronization between the application and model. The incremental process mining can also be useful when it is necessary to extract a complete process model in a gradual way, extracting partial models (process fragments with begin and end) in a first step and integrating additional knowledge to the model in stages to obtain the complete model. However, existing incremental process mining algorithms are not effective to all aspects mentioned above. All of them have limitations with respect to certain aspects of incremental mining, such as deletion of elements in the process model (process model update). Additionally, most of them do not extract all the information present in the structure of the process, such as the actors who perform the activities. This paper proposes an incremental process mining algorithm from execution logs of information systems. The new algorithm allows the full update (adding and removing elements) of an existing model, as well as the increment of a process model as new records are added to the log. Thus, we can keep process models and process execution syncronized, while reducting the total processing time, since only new process instances must be processed. Finally, are expected the extraction of process models with similar or higher accuracy compared to current incremental mining algorithms.

Até os dias de hoje, diversos algoritmos de mineração de modelos de processos já foram propostos para extrair conhecimento a partir de logs de eventos. O conhecimento que tais algoritmos são capazes de obter incluem modelos de processos de negócio, assim como aspectos da estrutura organizacional, como atores e papéis. A mineração de processos pode se beneficiar de uma estratégia incremental, especialmente quando as informações sobre um ou mais processos de negócio presentes no código fonte de um sistema de informação são logicamente complexas (diversas ramificações e atividades paralelas e/ou alternativas). Neste cenário, são necessárias muitas execuções da aplicação para a coleta de um grande conjunto de dados no arquivo de log, a fim de que o algoritmo de mineração possa descobrir e apresentar o processo de negócio completo. Outra situação que torna necessária a mineração incremental é a constante evolução dos processos de negócio, ocasionada geralmente por alterações nas regras de negócio de uma ou mais aplicações. Neste caso, o log pode apresentar novos fluxos de atividades, ou fluxos alterados ou simplesmente fluxos que não são mais executados. Estas mudanças devem ser refletidas no modelo do processo a fim de garantir a sincronização entre a aplicação (processo executado) e o modelo. A mineração incremental de processos pode ainda ser útil quando se faz necessária a extração gradual de um modelo de processo completo, extraindo modelos parciais (fragmentos de processo com início e fim) em um primeiro passo e integrando conhecimento adicional ao modelo em etapas até a obtenção do modelo completo. Contudo, os algoritmos atuais de mineração incremental de processos não apresentam total efetividade quanto aos aspectos acima citados, apresentando algumas limitações. Dentre elas podemos citar a não remoção de elementos obsoletos do modelo de processo descoberto, gerados após a atualização do processo executado, e também a descoberta de informações da estrutura organizacional associada ao processo como, por exemplo, os atores que executam as atividades. Este trabalho propõe um algoritmo incremental para a mineração de processos de negócio a partir de logs de execução. Ele permite a atualização completa de um modelo existente, bem como o incremento de um modelo de processo na medida em que novas instâncias são adicionadas ao log. Desta forma, podemos manter ambos, modelo de processo e o processo executado sincronizados, além de diminuirmos o tempo total de processamento uma vez que apenas novas instâncias de processo devem ser consideradas. Por fim, com este algoritmo é possível extrair modelos com acurácia igual ou superior aqueles que podem ser extraídos pelos algoritmos incrementais atuais. / Even today, several process mining algorithms have been proposed to extract knowledge from event logs of applications. The knowledge that such algorithms are able to discovery includes business process models, business rules, as well as aspects of organizational structure, such actors and roles of processes. These process mining algorithms can be divided into two: non-incremental and incremental. The mining process can benefit from an incremental strategy, especially when information about the process structure available in the system source code is logically complex (several branches and parallel activities). In this scenario, its necessary several executions of the application, to collect a large set of log data, so that the mining algorithm can discover and present the complete business process. Another use case where incremental mining is usefull is during the changing structure of the process, caused by the change in the business logic of an application. In this case, the log may provide new traces of activities, modified traces or simply traces that are no longer running. These changes must be reflected in the process model being generated to ensure synchronization between the application and model. The incremental process mining can also be useful when it is necessary to extract a complete process model in a gradual way, extracting partial models (process fragments with begin and end) in a first step and integrating additional knowledge to the model in stages to obtain the complete model. However, existing incremental process mining algorithms are not effective to all aspects mentioned above. All of them have limitations with respect to certain aspects of incremental mining, such as deletion of elements in the process model (process model update). Additionally, most of them do not extract all the information present in the structure of the process, such as the actors who perform the activities. This paper proposes an incremental process mining algorithm from execution logs of information systems. The new algorithm allows the full update (adding and removing elements) of an existing model, as well as the increment of a process model as new records are added to the log. Thus, we can keep process models and process execution syncronized, while reducting the total processing time, since only new process instances must be processed. Finally, are expected the extraction of process models with similar or higher accuracy compared to current incremental mining algorithms.

Até os dias de hoje, diversos algoritmos de mineração de modelos de processos já foram propostos para extrair conhecimento a partir de logs de eventos. O conhecimento que tais algoritmos são capazes de obter incluem modelos de processos de negócio, assim como aspectos da estrutura organizacional, como atores e papéis. A mineração de processos pode se beneficiar de uma estratégia incremental, especialmente quando as informações sobre um ou mais processos de negócio presentes no código fonte de um sistema de informação são logicamente complexas (diversas ramificações e atividades paralelas e/ou alternativas). Neste cenário, são necessárias muitas execuções da aplicação para a coleta de um grande conjunto de dados no arquivo de log, a fim de que o algoritmo de mineração possa descobrir e apresentar o processo de negócio completo. Outra situação que torna necessária a mineração incremental é a constante evolução dos processos de negócio, ocasionada geralmente por alterações nas regras de negócio de uma ou mais aplicações. Neste caso, o log pode apresentar novos fluxos de atividades, ou fluxos alterados ou simplesmente fluxos que não são mais executados. Estas mudanças devem ser refletidas no modelo do processo a fim de garantir a sincronização entre a aplicação (processo executado) e o modelo. A mineração incremental de processos pode ainda ser útil quando se faz necessária a extração gradual de um modelo de processo completo, extraindo modelos parciais (fragmentos de processo com início e fim) em um primeiro passo e integrando conhecimento adicional ao modelo em etapas até a obtenção do modelo completo. Contudo, os algoritmos atuais de mineração incremental de processos não apresentam total efetividade quanto aos aspectos acima citados, apresentando algumas limitações. Dentre elas podemos citar a não remoção de elementos obsoletos do modelo de processo descoberto, gerados após a atualização do processo executado, e também a descoberta de informações da estrutura organizacional associada ao processo como, por exemplo, os atores que executam as atividades. Este trabalho propõe um algoritmo incremental para a mineração de processos de negócio a partir de logs de execução. Ele permite a atualização completa de um modelo existente, bem como o incremento de um modelo de processo na medida em que novas instâncias são adicionadas ao log. Desta forma, podemos manter ambos, modelo de processo e o processo executado sincronizados, além de diminuirmos o tempo total de processamento uma vez que apenas novas instâncias de processo devem ser consideradas. Por fim, com este algoritmo é possível extrair modelos com acurácia igual ou superior aqueles que podem ser extraídos pelos algoritmos incrementais atuais. / Even today, several process mining algorithms have been proposed to extract knowledge from event logs of applications. The knowledge that such algorithms are able to discovery includes business process models, business rules, as well as aspects of organizational structure, such actors and roles of processes. These process mining algorithms can be divided into two: non-incremental and incremental. The mining process can benefit from an incremental strategy, especially when information about the process structure available in the system source code is logically complex (several branches and parallel activities). In this scenario, its necessary several executions of the application, to collect a large set of log data, so that the mining algorithm can discover and present the complete business process. Another use case where incremental mining is usefull is during the changing structure of the process, caused by the change in the business logic of an application. In this case, the log may provide new traces of activities, modified traces or simply traces that are no longer running. These changes must be reflected in the process model being generated to ensure synchronization between the application and model. The incremental process mining can also be useful when it is necessary to extract a complete process model in a gradual way, extracting partial models (process fragments with begin and end) in a first step and integrating additional knowledge to the model in stages to obtain the complete model. However, existing incremental process mining algorithms are not effective to all aspects mentioned above. All of them have limitations with respect to certain aspects of incremental mining, such as deletion of elements in the process model (process model update). Additionally, most of them do not extract all the information present in the structure of the process, such as the actors who perform the activities. This paper proposes an incremental process mining algorithm from execution logs of information systems. The new algorithm allows the full update (adding and removing elements) of an existing model, as well as the increment of a process model as new records are added to the log. Thus, we can keep process models and process execution syncronized, while reducting the total processing time, since only new process instances must be processed. Finally, are expected the extraction of process models with similar or higher accuracy compared to current incremental mining algorithms.

Process monitoring aims to provide transparency over operational aspects of a business process. In practice, it is a challenge that traces of business process executions span across a number of diverse systems. It is cumbersome manual engineering work to identify which attributes in unstructured event data can serve as case and activity identifiers for extracting and monitoring the business process. Approaches from literature assume that these identifiers are known a priori and data is readily available in formats like eXtensible Event Stream (XES). However, in practice this is hardly the case, specifically when event data from different sources are pooled together in event stores. In this paper, we address this research gap by inferring potential case and activity identifiers in a provenance agnostic way. More specifically, we propose a semi-automatic technique for discovering event relations that are semantically relevant for business process monitoring. The results are evaluated in an industry case study with an international telecommunication provider.

Companies working on safety-critical projects must adhere to strict rules imposed by the domain, especially when human safety is involved. These projects need to be compliant to standard norms and regulations. Thus, all the process steps must be clearly documented in order to be verifiable for compliance in a later stage by an auditor. Nevertheless, documentation often comes in the form of manually written textual documents in different formats. Moreover, the project members use diverse proprietary tools. This makes it difficult for auditors to understand how the actual project was conducted. My research addresses the project mining problem by exploiting logs from project-generated artifacts, which come from software repositories used by the project team.

Geschäftsprozesse stellen ein wichtiges Gut eines Unternehmens dar. Für den Unternehmenserfolg sind nicht einmalig optimal gestaltete Prozesse entscheidend, sondern die Fähigkeit, schnell auf neue Entwicklungen reagieren und die betroffenen Prozesse flexibel anpassen zu können. In vielen Unternehmen ist eine aktuelle Beschreibung ihrer Prozesse als wesentliche Voraussetzung für die Prozessverbesserung jedoch nicht oder nur unzureichend gegeben. Nicht selten wird ein erstelltes Prozessmodell nicht weiterverwendet, so dass es nach kurzer Zeit von der betrieblichen Realität abweicht. Diese fehlende Übereinstimmung kann durch die Nutzung von Prozess-Mining-Technologien verhindert werden, indem das in den Informationssystemen implizit vorhandene Prozesswissen automatisiert extrahiert und in Form von Prozessmodellen abgebildet wird. Ein weiteres wichtiges Element für die effiziente Gestaltung und Steuerung von Prozessen bilden Referenzmodelle, wie z. B. ITIL und CobiT. Die Prozessverbesserung durchläuft in der Regel mehrere Analyse-, Design-, Implementierungs- , Ausführungs-, Monitoring-, und Evaluierungsschritte. Die Arbeit stellt eine Methodik vor, die die Identifizierung und Lösung der auftretenden Aufgaben unterstützt und erleichtert. Eine empirische Untersuchung zeigt die Herausforderungen und die Potenziale für den erfolgreichen Einsatz von Process-Mining-Techniken. Auf der Basis der Resultate dieser Untersuchung wurden spezielle Aspekte der Datenaufbereitung für Process-Mining-Algorithmen detailliert betrachtet. Der Fokus liegt dabei auf der Bereitstellung von Enterprise- und RFID-Daten. Weiterhin beleuchtet die Arbeit die Wichtigkeit, die Referenzprozessausführung zu überprüfen, um deren Einhaltung in Bezug auf neue oder geänderte Prozesse zu sichern. Die Methodik wurde anhand einer Reihe von Praxisbeispielen erprobt. Die Ergebnisse unterstreichen ihre generelle unternehmensübergreifende Anwendbarkeit für die effiziente kontinuierliche Prozessverbesserung. / The dissertation at hand takes as its subject business processes. Naturally they are subject to continual improvement and are a major asset of any given organization. An optimally-designed process, having once proven itself, must be flexible, as new developments demand swift adaptations. However, many organizations do not adequately describe these processes, though doing so is a prerequisite for their improvement. Very often the process model created during an information system’s implementation either is not used in the first place or is not maintained, resulting in an obvious lack of correspondence between the model and operational reality. Process mining techniques prevent this. They extract the process knowledge inherent in an information system and visualize it in the form of process models. Indeed, continual process improvement depends greatly on this modeling approach, and reference models, such as ITIL and CobiT, are entirely suitable and powerful means for dealing with the efficient design and control of processes. Process improvement typically consists of a number of analysis, design, implementation, execution, monitoring, and evaluation activities. This dissertation proposes a methodology that supports and facilitates them. An empirical analysis both revealed the challenges and the potential benefits of these processes mining techniques’ successful. This in turn led to the detailed consideration of specific aspects of the data preparation for process mining algorithms. Here the focus is on the provision of enterprise data and RFID events. This dissertation as well examines the importance of analyzing the execution of reference processes to ensure compliance with modified or entirely new business processes. The methodology involved a number of cases’ practical trials; the results demonstrate its power and universality. This new approach ushers in an enhanced continual inter-departmental and inter-organizational improvement process.

ERP system has shaped the way modern organisations design, control, and execute business processes. It has not only paved the way for efficient use of organisational resources but also offered the opportunity to utilise data logged in the system for ensuring internal control. The key contribution of this research is that it has resulted in a method which can practically be employed by internal auditors for measuring internal fraud risk of business organisations with ERP systems, by utilising process mining technique and evidential reasoning in the form of Bayesian theorem, in a much more effective way compared to conventional frequentist method. The other significant contribution is that it has paved the way for combining process mining technique and evidential reasoning in addressing problems prevalent within organisational contexts. This research has contributed in developing IS theories for design and action especially in the area of soft systems methodology as it has relied on business process modelling in addressing the issue of internal fraud risk. The chosen method has contributed in facilitating incorporation of design science method in problem solving. Researchers have focused on applying data mining techniques within organisational contexts for extracting valuable information. Process mining is a comparatively new technique which allows business processes to be analysed based on event logs. Analysis of business processes can be useful for organisations not only for attaining greater efficiency but also for ensuring internal control inside the organisation. Large organisations have various measures in place for ensuring internal control. Measuring the risk of fraud within a business process is an important practice for preventing fraud as accurate measurement of fraud risk provides business experts with the opportunity to comprehend the extent of the problem. Business experts, such as internal auditors, still heavily rely upon conventional methods for measuring internal fraud risk way by of random check of process compliance. Organisations with ERP systems in place can avail themselves of the opportunity to use event logs for extending the scope of assessing process conformance. This has not been put into practice as there is a lack of well researched methods which can allow event logs to be utilised for enhancing internal control. This research can be proved to be useful for practitioners as it has developed a method for measuring internal fraud risk within organisations. This research aimed to utilise process mining technique that allows business experts to exert greater control over business process execution by allowing the internal fraud risk to be measured effectively. A method has been developed for measuring internal fraud risk of business originations with ERP systems by using process mining and Bayesian theorem. In this method, rate of process deviation is calculated by conducting process mining on relevant logs of events and then that process deviation rate is applied in Bayesian theorem along with historic internal fraud risk rate and process deviation rate calculated manually for arriving at a revised internal fraud risk rate. Bayesian theorem has been relied upon for the purpose of developing this new method as it allows evidential reasoning to be incorporated. The method has been developed as a Design Science Research Method (DSRM) artefact by conducting three case-studies. Data has been collected from three case companies, operating in readymade garments manufacturing industry, pharmaceuticals industry, and aviation industry, regarding their procurement process for conducting process mining. The revised internal fraud risk rates were then evaluated by considering the feedback received from respective business experts of each of the case company. The proposed method is beneficial as it has paved the way for practitioners to utilise process mining using a soft system methodology. The developed method is of immense significance as it has contributed in the field of business intelligence and analytics (BI&A) and the big data analytics which have become significantly important to both academics and practitioners over the past couple of decades.

[pt] Nesta tese propomos a aplicação de um paradigma de planejamento baseado em uma disciplina de modelagem conceitual para as tarefas de Mineração de Processos. Postulamos que a abordagem apresentada habilita as tarefas de descoberta de processos, checagem de conformidade e melhoria de modelos em domínios educacionais, que tem características de processos não-estruturados – dependências entre tarefas, múltiplas dependências, eventos concorrentes, atividades que falham, atividades repetidas, traços parciais e estruturas de nocaute. Relacionamos os conceitos em ambas as áreas de pesquisa e demonstramos a abordagem aplicada a um exemplo em um domínio acadêmico, implementando os algoritmos como parte de uma Biblioteca de Planos Típicos para Mineração de Processos que constrói sobre a extensa literatura prévia. / [en] In this thesis we propose the application of an automated planning paradigm based on a conceptual modeling discipline for the Process Mining tasks. We posit that the presented approach enables the process discovery, conformance checking and model enhancement tasks for educational domains, comprising characteristics of unstructured processes – with intertask dependencies, multiple dependencies, concurrent events, failing activities, repeated activities, partial traces and knock-out structures. We relate the concepts in both areas of research, and demonstrate the approach applied to an academic domain example, implementing the algorithms as part of a Library for Typical Plans for Process Mining that leverages the extensive prior art in the literature.