Discovery with Split Miner

Dependency

To use these algorithms in your Java Maven project it is necessary to include, in the pom.xml file, the dependency:

<dependency>
    <groupId>com.github.beamline</groupId>
    <artifactId>discovery-splitminer</artifactId>
    <version>master-SNAPSHOT</version>
</dependency>

See the introduction page for further instructions.

Usage

This miner can be used to extract a BPMN process model in a similar way as performed by the Split Miner.

Once a XesSource is available, the miner can be configured and used as follows:

LossyCountingBudgetSplitMiner miner = new LossyCountingBudgetSplitMiner(
    10, // the budget for cases
    10, // the budget for relations
    0.01, // concurrency threshold
    0.01, // the frequency threshold
    5); // the sliding window size

StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env
    .addSource(new StringTestSource("ABCDF", "ABCEF"))
    .keyBy(BEvent::getProcessName)
    .flatMap(miner)
    .addSink(new SinkFunction<BPMNTemplateResponse>() {
        public void invoke(BPMNTemplateResponse value, Context context) throws Exception {
            PaliaLikeBPMNDiagramGenerator.fromBPMNTemplate(
                "process",
                value.getBpmnTemplate(),
                "output.svg");
        }
    });
env.execute();

This code will produce the following model:

Scientific literature

The techniques implemented in this package are described in:

Split Miner process discovery technique in streaming process mining environments
A. Jarmolkowicz
Master Thesis, DTU, Jun. 2023.

The Split Miner algorithm is presented in:

Split miner: automated discovery of accurate and simple business process models from event logs
Augusto, A., Conforti, R., Dumas, M. et al.
In Knowledge and Information Systems 59, 251-284 (2019)