论文部分内容阅读
本文首先提出了以前文献对DCM(1,1)与GM(1,1)模型关系的证明错误,否定了以前文献的一些观点.第二,证明了DGOM(1,1)模型的MAPE值与边值x~((1))(m)(1≤m≤n)无关.第三,发现DGOM(1,1)模型的MAPE值变劣现象并分析其原因.第四,用最小一乘法,构建了边值优化的DGOMII(1,1)模型,其效果优于DGOM(1,1)模型.最后,将DGM(1,1)及DGOMII(1,1)模型应用于技术创新领域中.
In the first place, the paper proves that the previous literature has wrongly proved the relationship between DCM (1,1) and the GM (1,1) model and negates some of the previous literatures.Secondly, we prove that the MAPE value of DGOM (1,1) (M) (1≤m≤n) .Finally, we find out the phenomenon of deterioration of MAPE value in DGOM (1,1) model and analyze its cause.Fourthly, we use the least-squares method , The DGOMII (1,1) model with boundary value optimization is constructed, which is superior to the DGOM (1,1) model.Finally, the DGM (1,1) and DGOMII (1,1) models are applied to the field of technological innovation .