In recent years, the safety of traditional Chinese medicine has gradually attracted consumers’ attention. Therefore, the qualitative and quantitative detection of traditional Chinese medicine has become a hot research topic in recent years. In this paper, we chose prepared Rehmannia root as the research object. By using the fluorescence polarization spectrum and the least-square method, a method for predicting the concentration of traditional Chinese medicine solutions was established. First, we scanned the fluorescence polarization spectra of the prepared Rehmannia root solution to obtain the inner anisotropy and anisotropy of each sample. Then, the least-square method was used to obtain the functional relationship between concentration and anisotropy. Finally, the functional relation was applied to predict the concentration of the prepared Rehmannia root solution. The correlation coefficients of the predicted concentration were 0.9944 and 0.9928, with an average recovery rate of 100.94% and 99.58%, respectively. The results show that fluorescence polarization spectroscopy combined with the least-squares method can quickly and accurately detect the concentration of Rehmannia glutinosa root solution. This provides a new method for the content detection of traditional Chinese medicine components.