In order to solve the problems of the current non-intrusive load identification, such as too long model training time and low identification accuracy of electrical appliances with similar load characteristics, a non-intrusive load identification method based on CF-MF-SE joint feature was proposed. Based on the steady-state current signal, the method extracted the peak factor to represent the distortion degree of the waveform, the margin factor to represent the stability degree of the signal, the spectral entropy to represent the complexity degree of the spectrum structure, and combined with PSO-SVM to realize load identification. Experimental results show that this method can reduce the training time, improve the recognition accuracy and efficiency, which solve the problem that the electrical current waveform is too similar to identify successfully. This method introduces vibration signal characteristics as load characteristics into the field of load identification, which provides a new idea for feature selection of non-invasive load identification technology. As a key feature sensitive to load, spectral entropy can significantly improve the identification rate when combined with other features, which provides guidance for the flexible selection of load characteristics in practical application.