Abstract: This study aims to develop a quick and accurate discrimination method to realize the identification of Chinese Huzhu Qingke Liquor (CHQL), and to provide reliable technical support for the quality control and authenticity identification of Qingke liquor. First, ultraviolet spectrum (UV) and near-infrared spectroscopy (NIR) were used to examine the spectral properties of CHQL, Other Brand Qingke Liquor (OBQL), and Non-Qingke Based Liquor (NQBL). Then, partial least square-discriminant analysis (PLS-DA), support vector machine (SVM), and random forest (RF) were established using UV, NIR single spectrum and UV-NIR fusion spectrum. Additionally, interval partial least squares (iPLS), variable importance of projection (VIP), and competitive adaptive reweighted sampling (CARS) were used respectively for extracting feature variables from spectra. The results showed that the fusion spectra could complement each other and improve the performance of the classification model. The feature variable screening method further improved the model performance and reduced the model complexity. The RF model constructed using the 78 optimal wavelengths filtered by the VIP technique had the best classification and prediction results, with 100% accuracy on both the training and test sets. In summary, the combination of data fusion strategy and chemometrics method can effectively enhance the model performance and realize the rapid discriminant analysis of Huzhu Qingke liquor.