关键词: 软件复用, 软件构件, 卷积神经网络, 构件分类, 构件检索

Abstract: To improve the efficiency of component retrieval in software reuse process, advantages and disadvantages of software component classification technology and component features are analyzed. From the aspect of component faceting information, convolution neural network technology is used to propose a component based on convolution neural network. The convolutional neural network is used to extract the facet features, reduce the human factors, improve the accuracy of faceted information extraction, and train the component classification model based on convolution neural network. Through the specific experiments, the model is demonstrated to improve the efficiency of component retrieval.

Key words: software reuse, software component, convolution neural network, component classification, component retrieval