The invention discloses a non-invasive load identification method, terminal equipment and a storage medium. The method comprises the following steps: acquiring power signal information; calculating adifference value between the active power signal Pi and the active power signal Pi-1 to generate a power variable; if the power variable is greater than a first preset threshold, associating the active power signal Pi with a high-threshold mutation identifier, and cleaning the active power signal Pi according to a first preset rule to generate high-threshold detection information; if the power variable is greater than a second preset threshold, associating the active power signal Pi with a low-threshold mutation identifier, and preprocessing the active power signal Pi according to a second preset rule to generate an input vector; inputting the input vector into a preset neural network model to generate low-threshold detection information; and generating a detection result according to thehigh threshold detection information and the low threshold detection information. According to the invention, the load switching event can be automatically identified, and the identification accuracyis high.