Resumo

TORRES SAKIPOVA, Dina Yaksilik. Algorithms and discovering techniques for unstructured processes: state of art. Rev cuba cienc informat [online]. 2014, vol.8, n.3, pp.121-148. ISSN 2227-1899.

The execution of the business processes generates a great volume of data, from where information can be extracted helping to understand phenomena or to make decisions applying techniques and tools. The process mining is in charge of discovering, monitoring and improving the real processes carried out in a company, extracting knowledge from the logs managed by the current computer systems and generating models that describe the processes. When the processes are unstructured, not very comprehensible models that hinder the analysis of the process, are generated. The goal of this research is to perform a study of some of the more relevant algorithms and techniques during the last 10 years, focused in the discovery stage of process mining to identify the main existing difficulties in this area. The research showed that many aspects related to the interaction of the users with the models during its generation and analysis, and the way they are exposed, disturb their understanding. Identifying these difficulties addresses the investigation toward the increase of user interaction during the models generation, and emphasize the importance of studying the graphic visualizations area as a variant to improve their understanding. These models provide a great help for the analysis and process management, decision-making and even audits.

Palavras-chave : discovering techniques; graphic visualizations; process mining; unstructured processes.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )