Resultados de búsqueda para Process Mining
Recommending Interesting Results in Process Mining Analysis
Autores: Carlos Capitán-Agudo / María Salas-Urbano / Cristina Cabanillas / Manuel Resinas /
Palabras Clave: BPI challenge - interestingness - Process Mining - recommendation
A Query Language for Exploring Directly-Follows Graph Collections
Autores: María Salas-Urbano / Carlos Capitán-Agudo / Cristina Cabanillas / Manuel Resinas /
Palabras Clave: Data Exploration - directly-follows graphs - Process Mining - Queries - visualizations
Deep Learning for Predictive Business Process Monitoring: Review and Benchmark (Summary)
Autores: Efrén Rama Maneiro / Juan C. Vidal / Manuel Lama Penin /
Palabras Clave: Business Process Monitoring - Deep Learning - Neural Networks - Process Mining - Systematic literature review
Discovering Configuration Workflows From Existing Logs Using Process Mining (Summary)
Autores: Belén Ramos / Ángel Jesús Varela Vaca / José A. Galindo / María Teresa Gómez López / David Benavides /
Palabras Clave: Clustering - configuration workflow - process discovery - Process Mining - Variability
Hybridizing humans and robots: An RPA horizon envisaged from the trenches
Autores: Rafael Cabello Ruiz / Andrés Jiménez Ramírez / María José Escalona Cuaresma / José González Enríquez /
Palabras Clave: Computer-human interaction - Process Mining - Robotic Process Automation
A Conformance Checking-based Approach for Sudden Drift Detection in Business Processes (Summary)
Autores: Víctor Gallego-Fontenla / Juan C. Vidal / Manuel Lama /
Palabras Clave: business processes - Concept drift - Conformance checking-based detection - Process Mining
SOWCompact: A federated process mining method for social workflows (Summary)
Autores: Javier Rojo / Jose García-Alonso / Javier Berrocal / Juan Hernandez / Juan Manuel Murillo Rodríguez / Carlos Canal /
Palabras Clave: Federated Process Mining - Pattern discovery - Process Mining - Social Workflows
Social Events Analyzer (SEA): Un toolkit para minar Social Workflows mediante Federated Process Mining
La ingente cantidad de información recogida por los dispositivos móviles proporciona una visión de los distintos procesos que un usuario sigue en su día a a día. Estos procesos pueden ser analizados, con el fin de saber más acerca del usuario como individuo y como parte de distintos grupos sociales. Sin embargo, analizar eventos que están sujetos al comportamiento humano, donde el indeterminismo y la variabilidad prevalecen, no es sencillo. No existen, por lo tanto, técnicas sencillas que permitan discernir que usuarios pertenecen a un determinado grupo y cuales no, impidiendo crear Social Workflows solo con la información de aquellos usuarios que tienen algo en común. En esta demo presentamos Social Events Analyzer (SEA), un toolkit que permite analizar Social Workflows mediante Federated Process Mining. SEA proporciona modelos más fieles al comportamiento de los usuarios que conforman un Social Workflow y abre la puerta al uso de la minería de procesos como base para la creación de nuevos procedimientos automáticos adaptados al comportamiento de los usuarios.
Autores: Javier Rojo / Jose García-Alonso / Javier Berrocal / Juan Hernandez / Juan Manuel Murillo Rodríguez / Carlos Canal /
Palabras Clave: Federated Process Mining - Pattern discovery - Process Mining - Social Workflows
Automated Testing in Robotic Process Automation Projects
Robotic Process Automation (RPA) has received increasingattention in recent years. It enables task automation by software componentswhich interact with user interfaces in a similar way to that ofhumans. An RPA project lifecycle is closely resembling a software projectone. However, in certain contexts (e.g., business process outsourcing), atesting environment is not always available. Thus, deploying the robotsin the production environment entails high risk. To mitigate it, an innovativeapproach to automatically generate a testing environment anda test suite for an RPA project is presented. The activities of the humanswhose processes are to be robotized are monitored and a UI logis confirmed. On one side, the test environment is generated as a fakeapplication, which mimics the real environment by leveraging the UI loginformation. The control flow of the application is governed by an invisiblecontrol layer which decides which image to show depending on theinterface actions that it receives. On the other side, the test case checkswhether the robot can reproduce the behaviour of the UI log. Promisingresults were obtained and a number of limitations were identified suchthat it may be applied in more realistic domains.
Autores: Andrés Jiménez Ramírez / Chacon Montero Jesus / Tomasz Wojdynsky / José González Enríquez /
Palabras Clave: Automated Testing - Process Mining - Robotic Process Automation
Context-Aware Process Performance Indicator Prediction
It is well-known that context impacts running instances of a process. Thus, defining and using contextual information may help to improve the predictive monitoring of business processes, which is one of the main challenges in process mining. However, identifying this contextual information is not an easy task because it might change depending on the target of the prediction. In this paper, we propose a novel methodology named CAP3 (Context-aware Process Performance indicator Prediction) which involves two phases. The first phaseguides process analysts on identifying the context for the predictive monitoring of process performance indicators (PPIs), which are quantifiable metrics focused on measuring the progress of strategic objectives aimed to improve the process. The second phase involves a context-aware predictive monitoring technique that incorporates the relevant context information as input for the prediction. Our methodology leverages context-oriented domain knowledge and experts’ feedback to discover the contextual information useful to improve the quality of PPI prediction with a decrease of error rates in most cases, by adding this information as features to the datasets used as input of the predictive monitoring process. We experimentally evaluated our approach using two-real-life organizations. Process experts from both organizations applied CAP3 methodology and identified the contextual information to be used for prediction. The model learned using this information achieved lower error rates in most cases than the model learned without contextual information confirming the benefits of CAP3.This paper was published in IEEE Access, 2020, Vol. 8, pp. 222050 – 222063, doi: 10.1109/ACCESS.2020.3044670
Autores: Alfonso E. Márquez-Chamorro / Kate Revoredo / Manuel Resinas / Adela Del-Río-Ortega / Flavia Santoro / Antonio Ruiz-Cortés /
Palabras Clave: Business Process Management - context-awareness - predictive monitoring - process indicator prediction - Process Mining
No encuentra los resultados que busca? Prueba nuestra Búsqueda avanzada