The invention discloses a non-invasive household electrical appliance load identification method. The method comprises the steps of calculating a second target parameter according to an acquired firsttarget parameter; performing normalization processing on the second target parameter; carrying out FFT on the normalized second target data to obtain a harmonic spectrum and an amplitude, and takingthe harmonic spectrum and the amplitude as sample data; constructing a neural network model according to the sample data, and training the neural network model; and identifying the load of the household electrical appliance according to the trained neural network model. According to the method, after the second target data is calculated, normalization processing is carried out on the second targetdata, FFT conversion is carried out on the processed second target data, the accuracy of the sample data can be ensured, a neural network model with high accuracy can be obtained, and then the load identification accuracy of the household appliance can be improved. In addition, the invention also provides a non-invasive household electrical appliance load identification device and a storage medium, and the effects are as mentioned above.