Discovery and Evaluation of Cross-organization Business Process Models

In a cross-organization business process, organizations need to collaborate with each other to complete missions that cannot be handled by a single organization. Due to the complexity and geographical dispersion of cross-organization business processes, the construction is a time-consuming and error-prone task that requires practitioners to have extensive experience and business background. Process mining provides an automated method for model construction by analyzing event logs collected from the execution of business information systems. However, traditional process mining technologies only support model discovery of a single organization, and cannot effectively deal with the problem of cross-organization business process mining. To solve this problem, a cross-organization business process model discovery method is proposed. More specifically, it first extends existing process mining methods to discover business process model of a single organizations. Then, three typical collaboration patterns among organization and their corresponding discovery algorithms are introduced. Next, process models and collaboration patterns are integrated to obtain a global cross-organization business process model. Finally, the traditional quality evaluation metrics and the fitness of collaboration pattern are invented to quantify the quality of discovered cross-organizational business process models. By comparing with the state-of-the-art process discovery techniques using four public cross-organization business process cases, the effectiveness and applicability of the proposed approach is illustrated. © 2023 Science Press. All rights reserved.