The accuracy of existing hierarchical clustering algorithms in distance measurement is not high, in order to improve it, this paper proposes a condensing hierarchical clustering algorithm based on global distance measurement. This method puts forward the concept of global distance and local distance for the distance measurement, effectively depicting the distance between the data objects, in the merger of the clusters, it also proposes two new concepts: the cohesion within the class and the separability between classes, at the same time, on the basis of these two concepts, it constructs an objective function and maximizes the objective function to reach the purpose that the cohesion within the class be as large as possible, the separability between classes be as small as possible, in order to obtain the optimal clustering results. The experimental accuracy of this algorithm is higher than traditional hierarchical clustering algorithms both on the artificial data and real data sets, which shows that the algorithm has higher clustering validity.