论文部分内容阅读
当前,随着我国科技水平的不断提高,软件系统越加复杂,相应的功能也趋于完善、强大,如何确保软件质量符合要求成为一大焦点问题。在对软件质量进行评价时,软件质量预测建模是一大重要技术,其主要目的在于能够在软件开发的早期及时明确软件质量等级,从而为后期的软件质量控制、维护奠定良好的基础。但是,当前我国大部分的软件质量预测模型较为粗糙,必须进一步选择合适的方法构建更为科学的模型。本文基于人工神经网络技术展开软件质量预测模型的分析,并以学习向量量化(LVQ)神经网络为具体研究对象,构建相应模型。
At present, with the continuous improvement of science and technology in our country, the software system becomes more complicated and the corresponding functions tend to be perfect and powerful. How to ensure the software quality meets the requirements becomes a major issue. When evaluating software quality, software quality prediction modeling is an important technology. The main purpose of software quality prediction modeling is to clearly define the software quality level in the early stage of software development so as to lay a good foundation for software quality control and maintenance in the later period. However, at present, most of our country’s software quality prediction model is rough, we must further select the appropriate method to build a more scientific model. In this paper, the software quality prediction model is developed based on artificial neural network technology, and the corresponding model is constructed with the learning vector quantization (LVQ) neural network as the specific research object.