Intelligent depression recognition method and device

The invention relates to the technical field of depression level measurement and recognition, and discloses an intelligent depression recognition method and device, and the method comprises the steps: collecting depression measurement data of a patient; carrying out interpretable feature extraction on the acquired depression measurement data; constructing a multi-dimensional feature dynamic depression measurement model, and optimizing and solving the multi-dimensional feature dynamic depression measurement model to obtain an optimal model; and inputting the depression measurement characteristics into the optimal multi-dimensional characteristic dynamic depression measurement model, outputting depression measurement probability by the model, comparing a probability result with a preset depression grade evaluation table, and judging the depression grade of the patient. According to the method, irrelevant items in the depression measurement process are removed by using the BORUTA method, the reserved items have