A Web service composition system based on semantic parsing

Web service plays an important role in implementing Service Oriented Architecture (SOA) for achieving dynamic business process. With the increased number of Web services advertised in public repository, it is becoming vital to provide an efficient Web service discovery and selection mechanism with respect to a user´s requirement In addition, a single Web service has been unable to satisfy the needs of users. Through a combination of multiple Web services to meet the needs of users is an effective method. How to find a suitable set of services and select the fit services to compose them as a workflow which can satisfy the user´s functional attributes and nonfunctional properties is a thorny issue. To solve this problem, we propose an automatic generation workflow system. This system can generate workflow automatically according to the request provided by the Web service requester. First, construct the field repository, the workflow repository and the Web service repository. Then use automatic generation workflow algorithm to generate the workflow automatically which can satisfy the user´s functional attributes and non-functional properties. Classifying the Web service and the workflow according to the field can reduce the semantic ambiguity during the search. Thus, it can improve the precision of the service composition by improving the accuracy of the service discovery.