Disclosed is a depression evaluating system based on physiological information, comprising: an information acquisition module, a signal processing module, a parameter calculation module, a characteristic selection module, a machine learning module, and a result output module. Also disclosed is a depression evaluating method based on a plurality of pieces of physiological information, comprising the following steps: 1, processing one or more of an electrocardiograph signal, a pulse wave signal, an electroencephalogram signal, a galvanic skin signal, an electrogastrogram signal, an electromyogram signal, an electrooculogram signal, a polysomnogram signal, and a temperature signal, and calculating signal parameters; 2, normalizing the obtained signal parameters, and performing characteristic selection on a parameter set formed by the normalized signal parameters, so as to obtain a characteristic parameter set; and 3, performing machine learning by means of the obtained characteristic parameter set, and establishing a mathematical depression evaluating model by means of a relation between the characteristic parameter set and a depression grade to evaluate the depression grade. The present invention has the advantages of capability of avoiding the subjectivity of scale evaluation, and the like.La présente invention concerne un système d'évaluation de la dépression sur la base d'informations physiologiques, comprenant : un module d'acquisition d'informations, un module de traitement de signal, un module de calcul de paramètre, un module de sélection de caractéristique, un module d'apprentissage de machine, et un module de sortie de résultat. L'invention concerne en outre un procédé d'évaluation de la dépression sur la base d'une pluralité d'éléments d'informations physiologiques, comprenant les étapes suivantes : 1, traitement d'un ou plusieurs parmi un signal d'électrocardiographe, un signal d'onde de pouls, un signal d'électroencéphalogramme, un signal galvanique cutané