Trace retrieval for business process operational support

Abstract

Operational support assists users while process instances are being executed, by making predictions about the instance completion, or recommending suitable actions, resources or routing decisions, on the basis of the already completed instances, stored as execution traces in the event log.In this paper, we propose a case-based retrieval approach to business process management operational support, where log traces are exploited as cases. Once past traces have been retrieved, classical statistical techniques can be applied to them, to support prediction and recommendation. The framework enables the user to submit queries able to express complex patterns exhibited by the current process instance. Such queries can be composed by several simple patterns (i.e., single actions, or direct sequences of actions), separated by delays (i.e., actions we do not care about). Delays can also be imprecise (i.e., the number of actions can be given as a range). The tool also relies on a tree structure, adopted as an index for a quick retrieval from the available event log.Our approach is highly innovative with respect to the existing literature panorama, since it is the first work that exploits case-based retrieval techniques in the operational support context; moreover, the possibility of * Corresponding author. Tel. +39 0131 360340Email addresses: alessio.bottrighi@uniupo.it (Alessio Bottrighi), canensi@di.unito.it (Luca Canensi), giorgio.leonardi@mfn.unipmn.it (Giorgio Leonardi), stefania.montani@uniupo.it (Stefania Montani), terenz@di.unito.it (Paolo Terenziani) Preprint submitted to Expert Systems with ApplicationsOctober 1, 2015 retrieving traces by querying complex patterns and the indexing strategy are major departures also with respect to other existing trace retrieval tools proposed in the Case Based Reasoning area. Thanks to its characteristics and methodological solutions, the tool implements operational support tasks in a flexible and efficient way, as demonstrated by our experimental results.

Multi-Dimensional Event Data in Graph Databases

“…Of the 95 works surveyed [24, pp.133], several approaches exist to retrieve cases from event logs for temporal properties [5,7], for most frequent behavior [4], for sequences of activities [3] or algebraic expressions of sequence, choice, and parallelism over activities [8], or to check whether a temporal-logic property holds [6]. Several techniques support graph-based queries [5,44,45].…”

“…It can be stored in an event log as one sequence of events per case according to the data model of the XES-Standard [2]. Such sequences can be easily queried for behavioral properties such as event (sub-)sequences or temporal relations such as "directly/eventually-follows" in combination with other data attributes [3][4][5][6][7][8]. Aggregating directly/eventuallyfollows relations between events is fundamental for discovering process models from event logs [1,9,10].…”

Trilhas de solução: otimização do processo de atendimento e controle em pedidos complexos

“…Ao mesmo tempo Bergmann e Gil (2014) chamaram a atenção para os entraves na escolha de trilhas de decisão, tendo em vista as dificuldades de comparação entre trilhas semelhantes, propondo então o uso de algoritmos para a escolha da trilha a ser seguida na solução do problema. Dentro desse escopo, Bottrighi et al (2016) apresentam framework desenvolvido com foco em ATRP, que tem por base o processo de aprendizagem constante, que ocorre via realimentação das estruturas de árvores e registros de novas soluções adotadas, o que é corroborado por Peng et al (2016) quando citam, que a eficácia dos serviços desempenhados nas instituições possui relação direta com a boa utilização da TI, no sentido de viabilizar a utilização de base de conhecimento das instituições.…”

Storing and Querying Multi-dimensional Process Event Logs Using Graph Databases

“…If all events use the same, single case identifier attribute, the event data is single-dimensional and can be stored in an event log as a sequence of events. Such sequences can be easily queried for behavioral properties such as event (sub-)sequences or temporal relations such as "directly/eventually-follows" in combination with other data attributes [13,19,6,4,20,17].…”

“…Of the 95 works surveyed [10, pp.133], several approaches exist to retrieve cases from event logs (R7) for temporal properties (R8) [13,19], for most frequent behavior [6], for sequences of activities [4] or algebraic expressions of sequence, choice, and parallelism over activities [20], or to check whether a temporal-logic property holds [17]. Several techniques support graph-based queries [5,11,13].…”