In support vector machine,for the phenomenon of local risk in the application of singlescale Gaussian kernel algorithm,a multiscale Gaussian kernel algorithm based on kernel arrangement was proposed.The kernel target alignment was used to select the scale of Gaussian kernel function,and multi weak classifiers were integrated into a strong classifiers to get the multiscale Gaussian kernel,thereby the support vector machine was constructed.The experimental results of UCI dataset Iris Plants,Wine Recognition etc.show that the proposed multiscale Gaussian kernel algorithm based on kernel target alignment has higher classification accuracy than the traditional singlescale Gaussian kernel function.