根据军队知识管理的特点,构建了军队知识管理水平评价指标体系.指标体系从组织结构、人力、技术及知识系统4个一级指标和12个二级指标体系.运用四层模糊神经网络确定模糊综合评价中的权重值,同时采用改进的反向传播算法,用样本对网络进行训练,逐步修正网络的连接权值,使权重值更符合实际情况,最后用训练好的样本对六个单位的知识管理进行评估,结果表明,训练好的模糊神经网络可以对军队的知识管理进行评估,并得到很好的结果.
According to the characteristics of armed forces knowledge management, construct the armed forces knowledge management performance evaluation system. The index system includes four first level indexes (organizational structure, human, technology, and knowledge systems) and 12 secondary level indexes. Ascertain the weight of fuzzy compre- hensive evaluation by using the neural network. At the same time, the network is trained by using the improved back propagation algorithm and revise the neural network weight step by step , it make the weight in fuzzy evaluation accord with the fact well. which can get better effect.