Fitness scheme recommendation method based on AKC model

The invention discloses a fitness scheme recommendation method based on an AKC (automatic encoder and K-means algorithm) model, and the method comprises the steps: obtaining the near-infrared spectrumdata of a to-be-detected part of a human body, and importing the near-infrared spectrum data into a body fat detection model based on a plurality of types of inputted data: age, gender, weight, threecircumferences, arm circumferences and leg circumferences; and inputting the data into an automatic encoder based on a full-connection neural network to obtain a low-dimensional feature vector matrixof the user, and inputting the low-dimensional feature vector matrix of the user into a classification model based on a K-Means algorithm to obtain the body type of the user. A fitness scheme is setinto a scheme module according to the body type and various exercise expectations of the user; and finally, according to the body type and the exercise expectation of the user and based on scheme modules, the fitness scheme is o