Method and device for constructing health prediction model based on dressing meteorological index

Abstract

The invention relates to a method and a device for constructing a health prediction model of a dressing meteorological index. The method comprises the following steps: acquiring clothes matching information of people of different ages in different seasons and different climate conditions; determining a dressing weather index according to the clothes matching information and the climate information; acquiring corresponding health risk information according to different people under different human body comfort index conditions; matching the human body comfort index and the dressing weather index with health risk information, and constructing a sample data set; training a multi-task convolutional neural network by using the sample data set; and inputting age information, climate information and dressing information of a to-be-predicted person into the trained multi-task convolutional neural network to obtain health risk and dressing recommendation information of the to-be-predicted person. The age information, the climate information, the dressing information and the health risk information are matched, the data set is established, the prediction model is established in combination with deep learning, the prediction speed is high, and the accuracy is high.

Description

technical field [0001] The invention belongs to the field of medical information, and in particular relates to a method and device for constructing a health prediction model based on a weather index for clothing. Background technique [0002] The saying that "babies under three months have one more layer than adults, and those over three months can wear the same layer as their parents" has been circulating for a long time, but the actual operation is slightly difficult. Even for adults, everyone's physique is different. Dressing is also different. Otherwise, it is not only bad for your health, but you may also get sick. [0003] With the improvement of people's living standards, the problem of dressing children, especially children under 3 years old, has been paid more and more attention by parents. However, each child has different feelings about weather changes and dressing, and parents need long-term company and cooperation. Only by observing can we make accurate judgme...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the existing health prediction technology does not comprehensively consider the physical fitness of the crowd, clothing matching and climatic conditions, the first aspect of the present invention provides a method for constructing a health prediction model based on the weather index of clothing, including the following steps: Obtain the clothing matching information of different age groups in different seasons and different climate conditions; determine the clothing meteorological index according to the clothing matching information and climate information; calculate the human comfort index, and obtain it according to different groups of people under different human comfort index conditions Corresponding health risk information; match the human comfort index, clothing meteorological index and health risk information to construct a sample data set; use the sample data set to train a multi-task convolutional neural network until its error is lower than the threshold And it tends to be stable, and the trained multi-task convolutional neural network is obtained; the age information, climate information, and clothing information of the person to be predicted are input into the trained multi-task convolutional neural network, and the health of the person to be predicted is obtained. Risks and clothing recommendations

Images