基于证据体距离函数的选择和证据支持度的修正的一种改进的合成方法。首先引入明氏距离作为证据体距离函数，求出系统中证据的支持度，然后根据支持度标准差对支持度进行修正，最后利用归一化得到的证据可信度对系统的证据加权平均，再利用DS公式进行合成。实验结果表明，该方法提高了证据的有效性和可靠性。(A modified method is proposed based on the choice of distance function of evidences and correction of the support degree of each evidence. Firstly, it introduces the Ming's distance as distance function of evidences and finds the support degree of each evidence in system, then corrects the support degree on the basic of its standard deviation, finally, gets the weighted average of evidence by the normalized evidence credibility, and uses the DS combination rule to synthesis. The results demonstrate the effectiveness and reliability of evidences.)