Abstract: To establish a fast and non-destructive analysis method for identifying paper express document bags.50 samples of paper delivery document bags were inspected by handheld X-ray fluorescence,and the samples were classified by analyzing the element types and contents of the X-ray spectrum data of the samples.Establish Bayesian discriminant analysis,RBF neural network,and K-nearest neighbor classification models for normalized spectral data,and analyze and verify the classification results.The 50 samples can be divided into four categories.The classification accuracy of Bayesian Discriminative model,RBF neural network and K-nearest neighbor classification model is 96%,98%and 100%respectively.By comparing the classification accuracy,the K-nearest neighbor classification model is more suitable for XRF spectral data of such samples.The combination of XRF and Chemometrics can effectively identify paper express document bags.The combination of XRF and Chemometrics can effectively identify paper express document bags.This method is simple,fast,and non-destructive for samples.It can provide scientific basis for the identification of physical evidence in express delivery document bags.