The invention discloses an acute ischemic thalamic stroke early diagnosis method based on electroencephalogram nonlinear dynamic characteristics. The method comprises the following steps: first acquiring an EEG signal, then preprocessing the acquired data, extracting nonlinear dynamic characteristics of the electroencephalogram signal, processing and analyzing the data by using MATLAB, and finally classifying and identifying an obtained result. The nonlinear dynamic characteristics (complexity and sample entropy) of the EEG signal are used as classification and identification parameters of the thalamic stroke, so that not only can the deficiency of the clinical diagnosis on the electroencephalogram aspect in the thalamic stroke be compensated, but also the accuracy and the sensitivity are high; and compared with the prior art such as CT, MRI and the like, the method has the advantages of real-time performance, and continuity in detection and is simpler and more convenient in operation. Experiments show that the identification accuracy of the method for the thalamic stroke is high, and the identification accuracy of different thalamic strokes at different parts is improved. Therefore, the thalamic stroke can be clinically diagnosed in an assisting manner, and a later rehabilitation plan can be made.