Slow obstructive pulmonary motion rehabilitation system and method based on data processing

Abstract

The invention discloses a chronic obstructive pulmonary motion rehabilitation system and method based on data processing, and relates to the technical field of medical treatment. The system comprises a user data acquisition unit which is used for acquiring physiological data of a chronic obstructive pulmonary disease patient through wearable equipment and uploading the physiological data of the chronic obstructive pulmonary disease patient to a data processing unit; the deterioration degree analysis module is used for classifying the disease deterioration degree of the chronic obstructive pulmonary disease patient through a support vector machine based on the corrected physiological data to obtain the deterioration degree grade of the chronic obstructive pulmonary disease patient; the data processing unit also comprises a medication supervision module, and the medication supervision module is used for monitoring the deterioration degree of the chronic obstructive pulmonary disease patient based on the deterioration degree of the chronic obstructive pulmonary disease patient and the specific quantized value of the deterioration degree of the chronic obstructive pulmonary disease patient. And monitoring and recording the conditions of using the pressurized metering inhaler and the dry powder inhaler by the chronic obstructive pulmonary disease patient by using the trained medication process specification model. The management efficiency of the exercise rehabilitation process of the chronic obstructive pulmonary disease patient is improved.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a system and method for exercise rehabilitation of chronic obstructive pulmonary disease based on data processing. Background Art

[0002] The course of COPD can be divided into a stable phase and an acute exacerbation phase. Its treatment strategies mainly focus on smoking cessation, lung rehabilitation and symptom relief. Studies have shown that digital management of COPD can improve treatment outcomes.

[0003] Therefore, there is an urgent need for a COPD exercise rehabilitation system and method based on data processing. Summary of the invention

[0004] The embodiments of the present application provide a COPD exercise rehabilitation system and method based on data processing to solve the above-mentioned technical problems.

[0005] The present application provides a COPD exercise rehabilitation system based on data processing, comprising: a user data acquisition unit, for acquiring physiological data of COPD patients through wearable devices, and uploading the physiological data of the COPD patients to a data processing unit; wherein the physiological data include blood oxygen data, heart rate data, body temperature data, step data and respiratory rate data of the COPD patients during exercise; the data processing unit comprises a deterioration degree analysis module, wherein the deterioration degree analysis module is used to correct the physiological data of the COPD patients; based on the corrected physiological data, the deterioration degree of the COPD patients is classified by means of a support vector machine to obtain the deterioration degree grade of the COPD patients; and the deterioration degree of the COPD patients is quantitatively calculated by means of a Bayesian linear regression to obtain the chronic obstructive pulmonary disease (COPD) patient's deterioration degree. The data processing unit also includes a medication supervision module, which is used to monitor and record the use of pressurized metered-dose inhalers and dry powder inhalers by COPD patients based on the deterioration level of the COPD patients and the specific quantitative value of the deterioration level of the COPD patients, using the medication process specification model obtained through training; wherein the pressurized metered-dose inhaler and the dry powder inhaler are both delivery devices for COPD drugs; the data processing unit also includes a rehabilitation training supervision module, which is used to obtain and record the exercise data of the COPD patients during rehabilitation training through a sports bracelet device; wherein the rehabilitation training includes aerobic training, resistance training and respiratory training; the exercise data includes training type, training intensity and number of training sessions.

[0006] Furthermore, the medication process standard model obtained by training is used to supervise and record the use of pressurized metered dose inhaler and dry powder inhaler by the COPD patients, including: dividing the process of using the pressurized metered dose inhaler and the dry powder inhaler into three key step segments; wherein the three key step segments are recorded as the pre-inhalation step segment, the inhalation step segment and the post-inhalation step segment; collecting the first point cloud data of the pre-inhalation step segment; collecting the second point cloud data of the inhalation step segment; collecting the third point cloud data of the post-inhalation step segment; obtaining the first standard point cloud data of the pre-inhalation step segment; obtaining the second standard point cloud data of the inhalation step segment; obtaining the third standard point cloud data of the post-inhalation step segment; and according to the first registration information between the first point cloud data and the first standard point cloud data, the second registration information between the second point cloud data and the second standard point cloud data, and the third point cloud data According to the third registration information between the third standard point cloud data, the standard level of the COPD patient using the pressurized metered dose inhaler and the dry powder inhaler is analyzed; when the standard level is less than the preset standard level, the first image data of the pre-inhalation step segment is collected; the second image data of the inhalation step segment is collected; the third image data of the post-inhalation step segment is collected; the grayscale matrix of the color channel of the first image data, the second image data and the third image data is extracted, the edge information of the grayscale matrix is ​​extracted to obtain the feature matrix of the color channel, and the feature matrix is ​​vertically spliced ​​to obtain the first image feature vector, the second image feature vector and the third image feature vector; the number of elements of the first image feature vector, the second image feature vector and the third image feature vector is used as the number of training samples, and the medication process standard model is initialized based on the following expression;

[0007] p(vec i )=f(s1,s2,s3,vec1,vec2,…,vec i ) where vec1, vec2, …, vec i is the i-th weight vector of the multilayer perceptron neuron; s1 is the first image feature vector; s2 is the second image feature vector; s3 is the third image feature vector; p() is a behavior classification model; a loss function is constructed for the initialized medication process specification model based on the first image feature vector, the second image feature vector and the third image feature vector; the medication process specification model is trained based on the loss function; the trained medication process specification model is used to supervise and record the use of the pressurized metered dose inhaler and the dry powder inhaler by the COPD patients.

[0008] Furthermore, before analyzing the standard levels of the pressurized metered dose inhaler and the dry powder inhaler used by the COPD patients, the method also includes: performing data cleaning on the first point cloud data, the second point cloud data and the third point cloud data to obtain first cleaned point cloud data, second cleaned point cloud data and third cleaned point cloud data; using a registration algorithm model to register the first cleaned point cloud data with the first standard point cloud data to obtain the first registration information; using the registration algorithm model to register the second cleaned point cloud data with the second standard point cloud data to obtain the second registration information; using the registration algorithm model to register the third cleaned point cloud data with the third standard point cloud data to obtain the third registration information.

[0009] Furthermore, the user data acquisition unit includes a blood oxygen acquisition module, wherein the blood oxygen acquisition module is used to continuously measure the blood oxygen fluctuation changes of the COPD patient through a wearable finger pulse oximeter.

[0010] Furthermore, the user data collection unit further includes a non-sensing collection module, wherein the non-sensing collection module is used to analyze the light intensity change in the optical fiber caused by body vibration through a non-sensing device based on optical fiber to obtain the heart rate data and respiratory rate data of the COPD patient;

[0011] Furthermore, the rehabilitation training supervision module is also used to feed back the recorded movement data of the COPD patient during rehabilitation training to the deterioration degree analysis module.

[0012] The present application provides a COPD exercise rehabilitation method based on data processing, comprising: obtaining physiological data of COPD patients through wearable devices, and uploading the physiological data of the COPD patients to a data processing unit; wherein the physiological data include blood oxygen data, heart rate data, body temperature data, step data and respiratory rate data of the COPD patients during exercise; correcting the physiological data of the COPD patients; classifying the degree of deterioration of the COPD patients' condition by means of a support vector machine based on the corrected physiological data to obtain the degree of deterioration of the COPD patients; and quantifying the degree of deterioration of the COPD patients' condition by means of a Bayesian linear regression method. Calculate and obtain the specific quantitative value of the degree of deterioration of the COPD patient's condition; based on the COPD patient's deterioration level and the specific quantitative value of the COPD patient's condition deterioration, use the trained medication process standard model to monitor and record the use of pressurized metered-dose inhalers and dry powder inhalers by the COPD patients; wherein the pressurized metered-dose inhalers and the dry powder inhalers are both COPD drug delivery devices; obtain and record the exercise data of the COPD patient during rehabilitation training through a sports bracelet device; wherein the rehabilitation training includes aerobic training, resistance training and breathing training; the exercise data includes training type, training intensity and number of training sessions.

[0013] Furthermore, the blood oxygen fluctuation changes of the COPD patient are continuously measured by a wearable finger pulse oximeter.

[0014] Furthermore, after acquiring and recording the motion data of the COPD patient during rehabilitation training through the sports bracelet device, the method also includes: feeding back the recorded motion data of the COPD patient during rehabilitation training to the deterioration degree analysis module.

[0015] Based on the embodiments provided in the present application, in combination with the user data acquisition unit, the deterioration degree analysis module, the medication supervision module and the rehabilitation training supervision module included in the data processing unit, the physiological data of the COPD patient is obtained through a wearable device, and the physiological data of the COPD patient is uploaded to the data processing unit; the degree of deterioration of the COPD patient's condition is classified by a support vector machine to obtain the deterioration degree level of the COPD patient; and the degree of deterioration of the COPD patient's condition is quantitatively calculated by a Bayesian linear regression method to obtain a specific quantitative value of the deterioration degree of the COPD patient's condition; based on the deterioration degree level of the COPD patient and the specific quantitative value of the deterioration degree of the COPD patient's condition, the medication process specification model obtained by training is used to supervise and record the use of pressurized metered dose inhalers and dry powder inhalers by the COPD patients; the data processing unit also includes a rehabilitation training supervision module, which is used to obtain and record the exercise data of the COPD patient during rehabilitation training through a sports bracelet device. In other words, the present application realizes the automated recording of the entire exercise rehabilitation process of COPD patients and can monitor the medication and rehabilitation training of COPD patients in real time, thereby improving the management efficiency of the exercise rehabilitation process of COPD patients and enabling the personalized digital therapy of COPD to achieve more accurate results. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the embodiments of the present invention and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 is a structural diagram of an optional COPD exercise rehabilitation system based on data processing according to an embodiment of the present application;

[0018] Figure 2 The present invention is a flowchart of an optional method for COPD exercise rehabilitation based on data processing according to an embodiment of the present application.

[0019] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0021] Alternatively, if Figure 1 As shown, the present application provides a COPD exercise rehabilitation system based on data processing, comprising:

[0022] The user data acquisition unit 101 is used to obtain the physiological data of the COPD patient through the wearable device, and upload the physiological data of the COPD patient to the data processing unit 102; wherein the physiological data includes the blood oxygen data, heart rate data, body temperature data, step data and respiratory rate data of the COPD patient during exercise;

[0023] The data processing unit 102 includes a deterioration degree analysis module 103, wherein the deterioration degree analysis module 103 is used to correct the physiological data of the COPD patient; classify the deterioration degree of the COPD patient by a support vector machine based on the corrected physiological data to obtain the deterioration degree grade of the COPD patient; and quantitatively calculate the deterioration degree of the COPD patient by a Bayesian linear regression method to obtain a specific quantitative value of the deterioration degree of the COPD patient;

[0024] The data processing unit further includes a medication monitoring module 104, which is used to monitor and record the use of pressurized metered-dose inhalers and dry powder inhalers by COPD patients based on the deterioration level of COPD patients and the specific quantitative value of the deterioration level of COPD patients, using the trained medication process specification model; wherein the pressurized metered-dose inhaler and the dry powder inhaler are both delivery devices for COPD drugs;

[0025] The data processing unit also includes a rehabilitation training supervision module 105, which is used to obtain and record the exercise data of COPD patients during rehabilitation training through a sports bracelet device; wherein, rehabilitation training includes aerobic training, resistance training and breathing training; exercise data includes training type, training intensity and number of training times.

[0026] Based on the embodiments provided in the present application, in combination with the user data acquisition unit, the deterioration degree analysis module, the medication supervision module and the rehabilitation training supervision module included in the data processing unit, the physiological data of the COPD patient is obtained through a wearable device, and the physiological data of the COPD patient is uploaded to the data processing unit; the degree of deterioration of the COPD patient's condition is classified by means of a support vector machine to obtain the deterioration degree level of the COPD patient; and the degree of deterioration of the COPD patient's condition is quantitatively calculated by means of a Bayesian linear regression to obtain a specific quantitative value of the deterioration degree of the COPD patient's condition; based on the deterioration degree level of the COPD patient and the specific quantitative value of the deterioration degree of the COPD patient's condition, the medication process specification model obtained by training is used to supervise and record the use of pressurized metered dose inhalers and dry powder inhalers by COPD patients; the data processing unit also includes a rehabilitation training supervision module, which is used to obtain and record the exercise data of COPD patients during rehabilitation training through a sports bracelet device. In other words, the present application realizes the automated recording of the entire exercise rehabilitation process of COPD patients and can monitor the medication and rehabilitation training of COPD patients in real time, thereby improving the management efficiency of the exercise rehabilitation process of COPD patients and enabling the personalized digital therapy of COPD to achieve more accurate results.

[0027] Furthermore, the trained medication process standard model is used to monitor and record the use of pressurized metered dose inhalers and dry powder inhalers by COPD patients, including:

[0028] The process of using a pressurized metered dose inhaler and a dry powder inhaler is divided into three key steps; wherein the three key steps are recorded as a pre-inhalation step, an inhalation step, and a post-inhalation step;

[0029] Collecting the first point cloud data of the step segment before inhalation; collecting the second point cloud data of the step segment after inhalation; collecting the third point cloud data of the step segment after inhalation;

[0030] Acquire the first standard point cloud data of the step segment before inhalation; acquire the second standard point cloud data of the step segment after inhalation; acquire the third standard point cloud data of the step segment after inhalation;

[0031] Analyzing the standard levels of COPD patients using pressurized metered dose inhalers and dry powder inhalers according to first registration information between the first point cloud data and the first standard point cloud data, second registration information between the second point cloud data and the second standard point cloud data, and third registration information between the third point cloud data and the third standard point cloud data;

[0032] When the standard level is less than the preset standard level, the first image data of the step segment before inhalation is collected; the second image data of the step segment after inhalation is collected; and the third image data of the step segment after inhalation is collected;

[0033] Extracting grayscale matrices of the color channels of the first image data, the second image data, and the third image data, extracting edge information from the grayscale matrices to obtain feature matrices of the color channels, and vertically splicing the feature matrices to obtain a first image feature vector, a second image feature vector, and a third image feature vector;

[0034] The number of elements of the first image feature vector, the second image feature vector, and the third image feature vector is used as the number of training samples, and the medication process specification model is initialized based on the following expression;

[0035] p(vec i )=f(s1,s2,s3,vec1,vec2,…,vec i )

[0036] Among them, vec1, vec2, …, vec i is the i-th weight vector of the multilayer perceptron neuron; s1 is the first image feature vector; s2 is the second image feature vector; s3 is the third image feature vector; p() is the behavior classification model;

[0037] constructing a loss function for the initialized medication process specification model based on the first image feature vector, the second image feature vector, and the third image feature vector;

[0038] A medication process specification model is obtained based on loss function training;

[0039] The trained medication process standard model is used to monitor and record the use of pressurized metered dose inhalers and dry powder inhalers by patients with COPD.

[0040] Further, a loss function is constructed for the initialized medication process specification model based on the first image feature vector, the second image feature vector, and the third image feature vector, including:

[0041]

[0042] Where s1 is the first image feature vector; s2 is the second image feature vector; s3 is the third image feature vector; Loss(s1,s2,s3) is a loss function based on the first image feature vector s1, the second image feature vector s2 and the third image feature vector s3; log(u j ) is the logarithmic value of the expected output, v j is the output value after training; w j Represents the weight matrix of the convolutional neural network; l is the number of parameters contained in the sample format of the training sample; n is the number of training samples.

[0043] Further, before analyzing the compliance levels of PMDI and DPI in COPD patients, the method also includes:

[0044] Performing data cleaning on the first point cloud data, the second point cloud data, and the third point cloud data to obtain first cleaned point cloud data, second cleaned point cloud data, and third cleaned point cloud data;

[0045] Using a registration algorithm model to register the first cleaned point cloud data with the first standard point cloud data to obtain first registration information;

[0046] Using a registration algorithm model to register the second cleaned point cloud data with the second standard point cloud data to obtain second registration information;

[0047] The third cleaned point cloud data and the third standard point cloud data are registered using a registration algorithm model to obtain third registration information.

[0048] Furthermore, the user data collection unit includes a blood oxygen collection module, wherein:

[0049] The blood oxygen collection module is used to continuously measure the blood oxygen fluctuations of COPD patients through a wearable finger pulse oximeter.

[0050] Furthermore, the user data collection unit also includes a non-sensing collection module, wherein:

[0051] The sensorless data collection module is used to analyze the changes in light intensity in the optical fiber caused by body vibrations through a sensorless device based on optical fiber to obtain the heart rate and respiratory rate data of COPD patients;

[0052] Furthermore, the rehabilitation training supervision module is also used to feed back the recorded movement data of COPD patients during rehabilitation training to the deterioration degree analysis module.

[0053] like Figure 2 As shown, the present application provides a COPD exercise rehabilitation method based on data processing, comprising:

[0054] S201, obtaining physiological data of a COPD patient through a wearable device, and uploading the physiological data of the COPD patient to a data processing unit; wherein the physiological data includes blood oxygen data, heart rate data, body temperature data, step count data, and respiratory rate data of the COPD patient during exercise;

[0055] S202, correcting the physiological data of the COPD patient; classifying the degree of deterioration of the COPD patient's condition by means of a support vector machine based on the corrected physiological data to obtain the degree of deterioration of the COPD patient; and quantitatively calculating the degree of deterioration of the COPD patient's condition by means of a Bayesian linear regression to obtain a specific quantitative value of the degree of deterioration of the COPD patient's condition;

[0056] S203, based on the deterioration degree of COPD patients and the specific quantitative value of the deterioration degree of COPD patients, the trained medication process specification model is used to monitor and record the use of pressurized metered dose inhalers and dry powder inhalers by COPD patients; wherein the pressurized metered dose inhaler and dry powder inhaler are both delivery devices for COPD drugs;

[0057] S204, obtaining and recording the exercise data of COPD patients during rehabilitation training through a sports bracelet device; wherein the rehabilitation training includes aerobic training, resistance training and breathing training; the exercise data includes training type, training intensity and number of training times.

[0058] Furthermore, the blood oxygen fluctuations of COPD patients are continuously measured through a wearable finger pulse oximeter.

[0059] Furthermore, after obtaining and recording the exercise data of the COPD patient during rehabilitation training through the sports bracelet device, the method further includes:

[0060] The recorded movement data of COPD patients during rehabilitation training is fed back to the deterioration degree analysis module.

[0061] It should be noted that the embodiments of the COPD exercise rehabilitation method based on data processing provided in the present application can refer to the embodiments of the COPD exercise rehabilitation system based on data processing, and the present application will not repeat them.

[0062] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A COPD exercise rehabilitation system based on data processing, characterized in that: include: A user data acquisition unit, used to obtain the physiological data of the COPD patient through a wearable device, and upload the physiological data of the COPD patient to a data processing unit; wherein the physiological data includes blood oxygen data, heart rate data, body temperature data, step data and respiratory rate data of the COPD patient during exercise; The data processing unit includes a deterioration degree analysis module, wherein the deterioration degree analysis module is used to correct the physiological data of the COPD patient; classify the deterioration degree of the COPD patient by a support vector machine based on the corrected physiological data to obtain the deterioration degree grade of the COPD patient; and quantitatively calculate the deterioration degree of the COPD patient by a Bayesian linear regression to obtain a specific quantitative value of the deterioration degree of the COPD patient; The data processing unit further includes a medication supervision module, which is used to supervise and record the use of a pressurized metered-dose inhaler and a dry powder inhaler by the COPD patient based on the deterioration level of the COPD patient and the specific quantitative value of the deterioration level of the COPD patient's condition, using a trained medication process specification model; wherein the pressurized metered-dose inhaler and the dry powder inhaler are both delivery devices for COPD drugs; The data processing unit also includes a rehabilitation training supervision module, which is used to obtain and record the motion data of the COPD patient during rehabilitation training through a sports bracelet device; wherein the rehabilitation training includes aerobic training, resistance training and breathing training; the motion data includes training type, training intensity and number of training times.

2. The COPD exercise rehabilitation system based on data processing according to claim 1, characterized in that: The medication process standard model obtained by training is used to supervise and record the use of pressurized metered dose inhalers and dry powder inhalers by the COPD patients, including: The process of using the pressurized metered dose inhaler and the dry powder inhaler is divided into three key step sections; wherein the three key step sections are recorded as a pre-inhalation step section, an inhalation step section, and a post-inhalation step section; Collecting the first point cloud data of the pre-inhalation step segment; collecting the second point cloud data of the inhalation step segment; collecting the third point cloud data of the post-inhalation step segment; Acquire the first standard point cloud data of the pre-inhalation step segment; acquire the second standard point cloud data of the inhalation step segment; acquire the third standard point cloud data of the post-inhalation step segment; Analyze the standard level of the COPD patient using the pressurized metered dose inhaler and the dry powder inhaler according to the first registration information between the first point cloud data and the first standard point cloud data, the second registration information between the second point cloud data and the second standard point cloud data, and the third registration information between the third point cloud data and the third standard point cloud data; In the case where the standard level is less than the preset standard level, the first image data of the pre-inhalation step segment is collected; the second image data of the inhalation step segment is collected; and the third image data of the post-inhalation step segment is collected; Extracting grayscale matrices of the color channels of the first image data, the second image data, and the third image data, extracting edge information from the grayscale matrices to obtain feature matrices of the color channels, and vertically splicing the feature matrices to obtain a first image feature vector, a second image feature vector, and a third image feature vector; Taking the number of elements of the first image feature vector, the second image feature vector and the third image feature vector as the number of training samples, the medication process specification model is initialized based on the following expression; p(thing i )=f(s1,s2,s3,vec1,vec2,…,vec i ) Among them, vec1, vec2, …, vec i is the i-th weight vector of the multilayer perceptron neuron; s1 is the first image feature vector; s2 is the second image feature vector; s3 is the third image feature vector; p() is the behavior classification model; constructing a loss function for the initialized medication process specification model based on the first image feature vector, the second image feature vector, and the third image feature vector; The medication process specification model is obtained based on the loss function training; The trained medication process standard model is used to monitor and record the use of the pressurized metered dose inhaler and the dry powder inhaler by the COPD patient.

3. The COPD exercise rehabilitation system based on data processing according to claim 2 is characterized in that: Prior to analyzing the regulatory levels of the COPD patient using the pressurized metered dose inhaler and the dry powder inhaler, the method further comprises: Performing data cleaning on the first point cloud data, the second point cloud data, and the third point cloud data to obtain first cleaned point cloud data, second cleaned point cloud data, and third cleaned point cloud data; Using a registration algorithm model to register the first cleaned point cloud data with the first standard point cloud data to obtain the first registration information; Using the registration algorithm model to register the second cleaned point cloud data with the second standard point cloud data to obtain the second registration information; The third cleaned point cloud data and the third standard point cloud data are registered using the registration algorithm model to obtain the third registration information.

4. The COPD exercise rehabilitation system based on data processing according to claim 1, characterized in that: The user data collection unit includes a blood oxygen collection module, wherein: The blood oxygen collection module is used to continuously measure the blood oxygen fluctuation changes of the COPD patient through a wearable finger pulse oximeter.

5. The COPD exercise rehabilitation system based on data processing according to claim 1, characterized in that: The user data collection unit also includes a non-sensing collection module, wherein: The non-sensing acquisition module is used to obtain the heart rate data and respiratory rate data of the COPD patient by analyzing the changes in light intensity in the optical fiber caused by body vibration through a non-sensing device based on optical fiber.

6. The COPD exercise rehabilitation system based on data processing according to claim 1, characterized in that: The rehabilitation training supervision module is also used to feed back the recorded movement data of the COPD patient during rehabilitation training to the deterioration degree analysis module.

7. A COPD exercise rehabilitation method based on data processing, based on the COPD exercise rehabilitation system based on data processing as claimed in any one of claims 1 to 7, characterized in that: include: Acquire the physiological data of the COPD patient through a wearable device, and upload the physiological data of the COPD patient to a data processing unit; wherein the physiological data includes blood oxygen data, heart rate data, body temperature data, step count data, and respiratory rate data of the COPD patient during exercise; Correcting the physiological data of the COPD patient; classifying the degree of deterioration of the COPD patient's condition by means of a support vector machine based on the corrected physiological data to obtain the deterioration level of the COPD patient; and quantitatively calculating the degree of deterioration of the COPD patient's condition by means of a Bayesian linear regression to obtain a specific quantitative value of the degree of deterioration of the COPD patient's condition; Based on the deterioration degree of the COPD patient and the specific quantitative value of the deterioration degree of the COPD patient, the trained medication process specification model is used to monitor and record the use of a pressurized metered dose inhaler and a dry powder inhaler by the COPD patient; wherein the pressurized metered dose inhaler and the dry powder inhaler are both delivery devices for COPD drugs; The exercise data of the COPD patient during rehabilitation training is obtained and recorded through a sports bracelet device; wherein the rehabilitation training includes aerobic training, resistance training and breathing training; the exercise data includes training type, training intensity and number of training times.

8. The COPD exercise rehabilitation method based on data processing according to claim 7, characterized in that: The blood oxygen fluctuation changes of the COPD patient are continuously measured by a wearable finger pulse oximeter.

9. The COPD exercise rehabilitation method based on data processing according to claim 8, characterized in that: After acquiring and recording the exercise data of the COPD patient during rehabilitation training through the sports bracelet device, the method further includes: The recorded movement data of the COPD patient during rehabilitation training is fed back to the deterioration degree analysis module.

Images