A kind of sports function data processing method and system

Abstract

The invention discloses a motor function data processing method and system, comprising: collecting initial evaluation results and final evaluation results of motor function and stroke hemiplegia in an electronic medical record system; The unified data preprocessing operation is performed to obtain a preprocessing result data set; the preprocessing result data set is sequentially spliced ​​to obtain a one-dimensional vector; the one-dimensional vector is input into the LSTM model to obtain the predicted final evaluation result, and the predicted The error generated between the last evaluation result and the collected last evaluation result is back-propagated to train the network parameters of the LSTM model to obtain a prediction model; the newly collected initial evaluation result is preprocessed through S1 and a one-dimensional vector is generated through S2 and then input Prediction model, get the last evaluation result of prediction. The improved long short-term memory network is used to effectively solve the shock that may occur only in the initial evaluation result data set.

Description

technical field [0001] The present invention relates to the field of sports function, in particular to a method and system for processing sports function data. Background technique [0002] Stroke is an acute cerebrovascular disease with a high fatality rate, and most of the stroke patients have physical dysfunction, which seriously affects daily life. The physical condition of stroke patients is related to various factors, such as the location of onset, the duration of the disease, the severity of the disease, and the degree of physical dysfunction. By predicting the motor function of the human body, the health status of the human body can be judged in time. If there is a stroke, treatment can be carried out in time and a prediction of the final health status of the current stroke patient can be made. The prediction of the physical health status of stroke patients mainly relies on the subjective experience of physicians. The patient's condition is predicted by evaluating t...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is that the prediction of the existing patient's health status requires a large number of medical images or various evaluation index information of the patient, the acquisition time of information is long, the calculation is complicated, and the time cost and economic cost are relatively large. The purpose is to provide A method and system for processing motor function data to solve the above problems

Images