Method and system for predicting age of human body

• Main Authors: WEN MING, DANG CHENYANG, CHEN QI, LIU TIANGE
• Format: Patent
• Language: Chinese; English
• Published: 08.03.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention relates to a method and system for predicting the age of a human body. The method comprises the following steps: screening a target type of skin surface microorganisms based on screening data to obtain target skin surface microorganisms; extracting feature representation of abundance data of the target skin surface microorganisms based on at least three pairs of convolutional layers and pooling layers of a pre-trained convolutional neural network, and classifying the feature representation based on a full connection layer and a softmax layer of the convolutional neural network to obtain an age prediction result of the human body. According to the invention, the problem of human body age prediction is solved, and the beneficial effect of accurately predicting the human body age based on the microorganisms on the human skin surface is realized. 本申请涉及一种用于预测人体年龄的方法及其系统。其中，该方法基于筛选数据筛选皮肤表面微生物的目标种类，得到目标皮肤表面微生物；基于预先训练的卷积神经网络的至少三对卷积层和池化层提取目标皮肤表面微生物的丰度数据的特征表示，以及基于卷积神经网络的全连接层和softmax层对特征表示进行分类，得到人体的年龄预测结果。