The Behavior Trustworthiness Analysis Methods of Composite Web Services Based on Process Mining

At present, the behavior trustworthiness of the composite Web service was very important. The soundness of the composite Web service model was the core of the behavior trustworthiness of the service composition, which includes two steps, one was to determine whether or not the composite model satisfied the behavior relativity, in order to analyze the function predictability; the other was to compare the behavior conformance for analyzing the influence of external factors . But the proposed judging algorithm of behavior relativity was feasible only in the case that T-invariant of Petri net model exists, and the behavior conformance was also difficult to handle. In the paper, firstly, in order to analyze the behavior relativity between theWeb services, an algorithm for determining the behavior weak soundness of the composite service was presented based on the theory of the service tree. Then, we present an effective analysis method of behavior conformance based on process mining. Finally, we develop plug-ins and test our methods in large benchmarks, and compare our methods with genetic process mining methods. The theoretical analysis and experimental results indicate that this method can realize the predictable behavior of software well, and satisfy the behavior trustworthiness requirements of software