Abstract: Network properties are studied in the perspective of member correlation.Firstly，a correlation computing algorithm called Ad-Ch algorithm is introduced.The advantages and disadvantages of Ad-Ch algorithm are analyzed through experiments.Subsequently，a new correlation computing algorithm called disjoint paths weight accumulating algorithm is proposed.Finally，experiments are conducted to verify the performances of disjoint paths weight accumulating algorithm.Disjoint paths weight accumulating algorithm is proved to be effective in correlation computing by analyzing the results of the experiments.

摘要： 从成员相互关系角度研究网络。首先介绍一种现有的网络成员关联度计算方法——Ad-Ch算法，结合实例分析了Ad-Ch算法并指出其不足之处，然后提出一种新的网络成员关联度计算方法——不相交路径权值累积算法，最后通过实验对不相交路径权值累积算法的性能进行了验证。分析实验结果发现，不相交路径权值累积算法能有效计算网络成员关联度。