Main Component and Architecture of the Semantic-Based Process Mining and Analysis Framework (SPMaAF)

Semantic-Based Process Mining And Analysis Framework (Spmaaf)

The design structure of the SPMaAF is primarily constructed on the following building blocks (or phases) as shown in Figure 1.

Figure 1.

The Semantic-based Process Mining and Analysis Framework (SPMaAF)

In Figure 1 the work describes the proposed framework for the semantic-based process mining and analysis method of this book (SPMaAF). Typically, the method consists of the following phases or individual components:

• •

  Extraction of Process Models from Event Data Logs: Whereby the derived models are represented as a set of annotated terms that links or connects (relates) to defined terms in an ontology, and in so doing, encodes the process logs and deployed models in the formal structure of ontology (semantic modelling) for further analysis.

• •

  The Inferred Ontology Classifications: Helps in association of meaning to the labels in the event logs and models by pointing to concepts (references) defined within the ontologies.

• •

  The Reasoner (inference engine): Designed to perform automatic classification of the various elements or tasks, and carries out consistency checking to validate the resulting model as well as clean out inconsistent results. In turn, it presents the inferred (underlying) associations.

• •

  The Conceptual Referencing: Which supports semantic reasoning over the ontologies in order to derive new information (or knowledge) about the process elements and the relationships they share amongst themselves within the knowledge base.

In short definition, the main mechanism (components) applied towards achieving an effective application of the aforementioned process was focused on connecting the mining algorithms with two key core elements:

• 1.

  Event logs or process models where the labels have references to concepts in an ontology, and

• 2.

  Reasoners which are invoked to reason over the resulting ontologies or semantic models.

To summarize the SPMaAF design framework - the work notes in Okoye et al (2019) that the development and application of such semantically-based framework has gained significant interest within the field of process mining.

On the one hand, the proposed framework (SPMaAF) focuses on making use of the semantics captured in the event logs or models (i.e. metadata) to create new techniques for process mining, or better still, support the enhancement (or in some cases, re-modification) of existing approaches to provide a more improved real-time process analysis that is closer to human understanding (e.g, a machine-understandable system). For example, methods that can be applied to assist humans in gaining a novel and more accurate results for process mining tasks. Perhaps, by being able to analyse the datasets or models at a higher level of conceptualization as opposed to the traditional process mining techniques that tend to analyse the data at the syntactic level.

On the other hand, owing to the semantic (conceptual) level of analysis, the outcome of the method (SPMaAF) can be easily understood by the process owners, process analysts, or IT experts. Besides, event logs from the different process domains usually carry domain-specific information (semantics), but quite often, the classical process mining techniques/algorithms lack the ability to interpret or make use of the underlying semantics across the different domains.