BiLSTM-CRF-KG: A Construction Method of Software Requirements Specification Graph

A requirement analysis is the basis and source of software system development, its accuracy, consistency completeness are keys to determining quality. However, at present, most requirements specifications prepared manually, which has some problems, such as inconsistency with business description, low preparation efficiency, being error prone difficulty communicating effectively personnel. Aiming above this paper realizes a construction model specification graph BiSLTM-CRF-KG by using natural language processing knowledge technology. Simulation experiments on 150 real description corpora show that can obtain 96.31% functional entity recognition accuracy directly from original corpus, better than classical BiSLTM-CRF, IDCNN-CRF CRF++ models, good performance different kinds data sets.