Edible oil safety early warning method based on analytic hierarchy process-neural network

The invention discloses an edible oil safety early warning method based on an analytic hierarchy process-neural network. The method comprises the steps: firstly carrying out preprocessing of an edible oil detection result, selecting evaluation factors, and obtaining an evaluation factor data set; then evaluating each evaluation index of edible oil by using an analytic hierarchy process, evaluating each evaluation index of the edible oil by using an entropy weight method, then integrating results of the two methods to obtain comprehensive evaluation of each index, and further calculating a risk level of each sample; and further learning the edible oil detection data set with the existing risk level by using a long-short-term memory neural network to generate a safety early warning model, and directly applying the model later, taking the detection data of the future edible oil sample as the model input, and taking the model output as a prediction result of the risk level of the samples. The method disclosed by