With the rapid development of electric vehicles (EV), electric vehicle wireless power transmission (WPT) technology has also received widespread attention. In this paper, we propose to use fuzzy wavelet neural network (FWNN) to realize the uncertainty quantification for the safety assessment of human electromagnetic exposure of EV-WPT system. By establishing a three-dimensional electromagnetic simulation model of EV-WPT system and human body, and reasonably setting the distribution type of each uncertainty factor, the induced electric field strength and its probability density curve, expectation and overrun probability in human body characterizing the human body located in the vicinity of the EV-WPT system are obtained by using the FWNN method, and by comparing it with the Monte Carlo (MC) method and the back propagation neural network (BPNN) method, the accuracy of the proposed method is verified. Verify the accuracy and efficiency of the proposed method in this paper. The proposed method is verified to be accurate and efficient, which provides a theoretical basis for the safety assessment of human electromagnetic exposure in EV-WPT system.