Intelligent regulation and control method and device for rehabilitation training of patient

Abstract

The invention discloses an intelligent regulation and control method and device for rehabilitation training of a patient, and relates to the technical field of data analysis. According to the consumable inventory management system based on the image-text order platform, rehabilitation training data of a patient is converted into images for display through the arrangement of the data conversion module, so that the problem of large data volume during data detection is reduced; meanwhile, a problem point can be accurately searched by comparing the converted image with a standard rehabilitation training plan image, and meanwhile, whether the rehabilitation training plan of a patient is qualified or not can be judged through the arrangement of a quality evaluation module; meanwhile, through the arrangement of the key frame extraction module, the patient training plan image data and the patient disease image data are extracted under the condition that the image continuity is guaranteed, the patient training plan change and the patient disease change can be found in time, and therefore intelligent regulation and control of patient rehabilitation training are achieved.

Description

Technical Field

[0001] The present invention relates to the field of monitoring and analysis technology, and in particular to an intelligent control method and device for patient rehabilitation training. Background Art

[0002] Chronic kidney disease is a serious and often debilitating medical condition that millions of individuals around the world experience each year. People with chronic kidney disease have damaged kidneys that are unable to filter the blood at all, or at least unable to filter toxins from the blood. Individuals experiencing chronic kidney disease or renal failure can no longer balance water and minerals or excrete daily metabolic loads. Toxic end products of nitrogen metabolism (urea, creatinine, uric acid, calcium, phosphorus, sodium, potassium, etc.) accumulate in the individual's blood and tissues. Some patients with chronic kidney disease or renal failure may also experience high / low blood pressure and a decrease in red blood cell counts. Typically, chronic kidney disease is a chronic condition that deteriorates over time to the point of complete renal failure or death.

[0003] Currently, after recovery, patients with chronic kidney disease need to undergo rehabilitation training based on their physical and recovery conditions, but the existing rehabilitation training plans cannot accurately realize intelligent regulation of patients' rehabilitation training based on the symptom data sets of patients with chronic kidney disease. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent control method and device for patient rehabilitation training to solve the above-mentioned deficiencies in the prior art.

[0005] In order to achieve the above object, the present invention provides the following technical solution: an intelligent control method for patient rehabilitation training, comprising the following working steps: S1, collecting a symptom data set of patients with chronic kidney disease and a rehabilitation training plan data set of patients with chronic kidney disease, and performing data processing on the collected symptom data set of patients with chronic kidney disease and the rehabilitation training plan data set of patients with chronic kidney disease; S2, receiving the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed in step S1, and performing data conversion, converting the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed into an image data set; S3, extracting key frames from the image dataset in step S2 using a key frame extraction model; S4, by comparing the key image frames, determining whether the rehabilitation training plan of the chronic kidney disease patient is qualified, and discarding the rehabilitation training plan of the chronic kidney disease patient that is determined to be unqualified.

[0006] Furthermore, the step S1 specifically includes the following working steps: A11. Collect the disease data set of patients with chronic kidney disease online through the data collection module and generate the disease feature data set of patients with chronic kidney disease ; A12. Input the rehabilitation training plan data set of patients with chronic kidney disease online through the data acquisition module and generate the rehabilitation training plan feature data set of patients with chronic kidney disease ; A13, using adaptive filtering method to analyze the disease feature data set and the rehabilitation training program feature dataset Perform data denoising preprocessing and generate standard disease feature dataset and standard rehabilitation training program feature dataset ; A14. The standard disease characteristic data set and standard rehabilitation training program feature dataset Output data.

[0007] Furthermore, the step S2 specifically includes the following working steps: B1, first divide the standard disease feature data set of length n into Q elements according to the value range, each data point i belongs to a unique qi and qi∈{1, 2, .., Q}, where qi represents the element where the data point i is located; B2, construct the Markov transfer matrix W, and set the matrix size to [Q, Q], where W[i, j] is determined by the frequency of the data in qi being adjacent to the data in qj, where qj represents the element where the data point j is located. The calculation formula is as follows:

[0008] B3, construct the Markov transform field M, assuming the matrix size is [n, n], the value of M[i, j] is W[qi, qj], the specific expression is: ; B4, for the Markov transfer matrix W with stable accuracy degradation, collect the performance label Q of the Markov transfer matrix W; B5, collect the performance change trajectory P of the current Markov transfer matrix W, divide the performance change trajectory P into performance improvement movement P1 and performance degradation movement P2, where the performance improvement movement P1 and the performance degradation movement P2 have the same sampling interval, and calculate the performance change trajectory of the current Markov transfer matrix W at the next moment:

[0009] Among them, Z1 indicates that the next moment of the Markov transfer matrix W is performance improvement, and Z1 indicates that the next moment of the previous Markov transfer matrix W is performance degradation; B6, calculate the current possible performance change trajectory:

[0010] Where Z T represents the possible performance change trajectory of the Markov transfer matrix W in the current time period T, represents the possible performance change trajectory of the Markov transfer matrix W at time t, and Any item in it is not 0; B7, since the performance change of the Markov transfer matrix W occurs at any time, the specific formula for calculating the possible performance change trajectory is:

[0011] Where P t represents the performance change probability density function of the Markov transfer matrix W at time t, and integrates the possible performance change trajectory of the Markov transfer matrix W with the Markov transfer matrix W to obtain a new Markov transfer matrix W'; B8, according to the Markov transition field transfer matrix W whose parameters are optimized in step B2, a blank image with n*n pixels is selected; B9, using the values ​​in the Markov transition field M' matrix after data optimization in step B7 as pixels to fill the blank image, and sending the newly generated image to the key frame extraction module.

[0012] Furthermore, the step S3 specifically includes the following steps: E1, set the sampling interval; E2, acquiring an image within a sampling interval, and performing screen segmentation on the image within the sampling interval and the standard image based on screen segmentation, and dividing the image within the sampling interval and the standard image into variable data and fixed data; E3, judging whether the variable data of the image in the sampling interval has changed relative to the variable data of the standard image based on the image comparison model, marking the changed image in the sampling interval as a changed image and marking the changed position in the image in the sampling interval based on the image annotation model, and marking the unchanged image in the sampling interval as an unchanged image; E4, judging the reason why the variable data in the changed image in step E3 changes based on the judgment model; E5, calculate the importance of the current change based on the importance calculation model, sort according to the importance, preset a detection threshold, retain the annotation for the change image whose importance of the current change is higher than the preset detection threshold, and delete the annotation for the change image whose importance of the current change is lower than the preset detection threshold; E6, determining whether the change of the change image with the mark retained in step E5 is a continuous change; E7, for the changing image judged as continuously changing in step E6, according to the change of the corresponding annotation in step S4, intercept the image frame with complete annotation change, and for the changing image with multiple annotation changes, intercept and classify and store according to different annotations, wherein the specific standard for video interception is a complete change process of the annotation of the changing image; E8, performing interception authentication on each image frame intercepted in step E7 based on the image comparison authentication model.

[0013] Furthermore, the step E6 of determining whether the important change is a continuous change specifically includes the following steps: C1, first, detect each sub-annotation data spectrum in the image annotation result based on the local model; C2, if the posterior score of a sub-annotated spectrogram exceeds the threshold, it is considered a local change; C3, the system records the start time and end time of continuous local changes. The start time is the left edge of the window corresponding to the first local change, and the end time is the right edge of the window corresponding to the last local change. C4, when continuous local changes occur, it indicates that there are continuous changes in the image annotations within the time period from the start time to the end time, that is, the important changes currently detected are continuous changes; C5, if no continuous local changes occur, the currently detected important changes are considered as discontinuous changes; C6, re-inputting the non-continuous change image annotations in step C5 into step C1 for subsequent operations until there is no continuous change in the important change annotations.

[0014] Furthermore, the video capture authentication in step E8 specifically includes the following steps: D1, in response to each video segment captured in step E8, extracting image data that meets the specified image condition from each video segment; any image data that meets the specified image condition carries at least identification information and timestamp information of the beacon device that sent the image data; D2, if extracted, obtaining the specified data in the extracted image data; wherein the specified data at least includes the identification information and timestamp information of the beacon device that sent the extracted image data; D3, obtaining target identification information of each video segment captured in step E8, and target timestamp information of the video; D4, performing a matching analysis on the target timestamp information and the timestamp information in the specified data to obtain a first analysis result, and performing a matching analysis on the target identification information and the identification information in the specified data to obtain a second analysis result; D5, based on the first analysis result and the second analysis result, determining the authentication result of the video; wherein the authentication result is used to indicate whether each video segment captured in the step E8 is fake.

[0015] An intelligent control device for patient rehabilitation training includes a data acquisition module, a data conversion module, a key frame extraction module and a quality assessment module: The data acquisition module is used to collect the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient, and perform data processing on the collected symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient; The data conversion module is used to receive the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed in the data acquisition module for data conversion, and convert the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed into an image data set; The key frame extraction module is used to extract the key frames of the image after the data conversion module completes the conversion; The quality assessment module is used to determine whether the rehabilitation training program for patients with chronic kidney disease is qualified by comparing key image frames, and to discard the rehabilitation training program for patients with chronic kidney disease that is judged to be unqualified.

[0016] Compared with the prior art, the intelligent control method and device for patient rehabilitation training provided by the present invention, which converts patient rehabilitation training data into images for display through the setting of a data conversion module, not only reduces the problem of large data volume during data detection, but also accurately finds problem points by comparing the converted images with standard rehabilitation training plan images. At the same time, through the setting of a quality assessment module, it can not only determine whether the patient's rehabilitation training plan is qualified, but also through the setting of a key frame extraction module, the patient training plan image data and the patient's symptom image data are extracted under the condition of ensuring image continuity, which can timely discover changes in the patient's training plan and changes in the patient's condition, thereby realizing intelligent control of the patient's rehabilitation training. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 A system structure block diagram provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0020] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0021] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] Example embodiments will be described more fully below with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. On the contrary, the purpose of providing these embodiments is to make the present disclosure thorough and complete and to enable those skilled in the art to fully understand the scope of the present disclosure.

[0023] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0024] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0025] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded.

[0026] The embodiments described herein may be described with reference to plan views and / or cross-sectional views by means of idealized schematic diagrams of the present disclosure. Therefore, the example illustrations may be modified according to manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings have schematic properties, and the shapes of the regions shown in the figures illustrate the specific shapes of the regions of the elements, but are not intended to be limiting.

[0027] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined as such herein.

[0028] See also Figure 1 , an intelligent control method for patient rehabilitation training, including the following working steps: S1, collecting a symptom data set of patients with chronic kidney disease and a rehabilitation training plan data set of patients with chronic kidney disease, and performing data processing on the collected symptom data set of patients with chronic kidney disease and the rehabilitation training plan data set of patients with chronic kidney disease; S2, receiving the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed in step S1, and performing data conversion, converting the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed into an image data set; S3, extracting key frames from the image dataset in step S2 using a key frame extraction model; S4, by comparing the key image frames, determining whether the rehabilitation training plan of the chronic kidney disease patient is qualified, and discarding the rehabilitation training plan of the chronic kidney disease patient that is determined to be unqualified.

[0029] Step S1 specifically includes the following working steps: A11. Collect the disease data set of patients with chronic kidney disease online through the data collection module and generate the disease feature data set of patients with chronic kidney disease ; A12. Input the rehabilitation training plan data set of patients with chronic kidney disease online through the data acquisition module and generate the rehabilitation training plan feature data set of patients with chronic kidney disease ; A13, using adaptive filtering method to analyze the disease feature data set and the rehabilitation training program feature dataset Perform data denoising preprocessing and generate standard disease feature dataset and standard rehabilitation training program feature dataset ; A14. The standard disease characteristic data set and standard rehabilitation training program feature dataset Output data.

[0030] Step S2 specifically includes the following working steps: B1, first divide the standard disease feature data set of length n into Q elements according to the value range, each data point i belongs to a unique qi and qi∈{1, 2, .., Q}, where qi represents the element where the data point i is located; B2, construct the Markov transfer matrix W, and set the matrix size to [Q, Q], where W[i, j] is determined by the frequency of the data in qi being adjacent to the data in qj, where qj represents the element where the data point j is located. The calculation formula is as follows:

[0031] B3, construct the Markov transform field M, assuming the matrix size is [n, n], the value of M[i, j] is W[qi, qj], the specific expression is: ; B4, for the Markov transfer matrix W with stable accuracy degradation, collect the performance label Q of the Markov transfer matrix W; B5, collect the performance change trajectory P of the current Markov transfer matrix W, divide the performance change trajectory P into performance improvement movement P1 and performance degradation movement P2, where the performance improvement movement P1 and the performance degradation movement P2 have the same sampling interval, and calculate the performance change trajectory of the current Markov transfer matrix W at the next moment:

[0032] Among them, Z1 indicates that the next moment of the Markov transfer matrix W is performance improvement, and Z1 indicates that the next moment of the previous Markov transfer matrix W is performance degradation; B6, calculate the current possible performance change trajectory:

[0033] Where Z T represents the possible performance change trajectory of the Markov transfer matrix W in the current time period T, represents the possible performance change trajectory of the Markov transfer matrix W at time t, and Any item in it is not 0; B7, since the performance change of the Markov transfer matrix W occurs at any time, the specific formula for calculating the possible performance change trajectory is:

[0034] Where P t represents the performance change probability density function of the Markov transfer matrix W at time t, and integrates the possible performance change trajectory of the Markov transfer matrix W with the Markov transfer matrix W to obtain a new Markov transfer matrix W'; B8, according to the Markov transition field transfer matrix W whose parameters are optimized in step B2, a blank image with n*n pixels is selected; B9, using the values ​​in the Markov transition field M' matrix after data optimization in step B7 as pixels to fill the blank image, and sending the newly generated image to the key frame extraction module.

[0035] The data conversion module is also used to convert the data of the standard rehabilitation training plan input by the medical staff, so as to obtain a standard rehabilitation training plan diagram. By comparing the difference between the generated rehabilitation training plan diagram and the standard rehabilitation training plan diagram, the problem points of the rehabilitation training plan can be accurately found. At the same time, by comparing the pixel difference between the generated rehabilitation training plan diagram and the standard rehabilitation training plan diagram, it is possible to find out where the rehabilitation training plan error of the fully automated production line is. At the same time, by comparing the composite vector of each adjacent pixel of the rehabilitation training plan diagram with the composite vector of each adjacent pixel of the standard rehabilitation training plan diagram, the quality of the training plan can be quickly detected. When the composite vector of each adjacent pixel of the rehabilitation training plan diagram is equal to the composite vector of each adjacent pixel of the standard rehabilitation training plan diagram, the quality of the training plan can be quickly detected. If the composite vectors are the same, it means that there is no problem with the quality of the training plan. If the composite vectors of each adjacent pixel of the rehabilitation training plan diagram are different from the composite vectors of each adjacent pixel of the standard rehabilitation training plan diagram, it means that there is a problem with the quality of the training plan. The severity of the training plan problem can be determined by comparing the angular difference between the composite vectors of each adjacent pixel of the rehabilitation training plan diagram and the composite vectors of each adjacent pixel of the standard rehabilitation training plan diagram. The more serious the training plan problem is, the greater the angular difference between the composite vectors of each adjacent pixel of the rehabilitation training plan diagram and the composite vectors of each adjacent pixel of the standard rehabilitation training plan diagram. The less serious the training plan problem is, the smaller the angular difference between the composite vectors of each adjacent pixel of the rehabilitation training plan diagram and the composite vectors of each adjacent pixel of the standard rehabilitation training plan diagram.

[0036] The data conversion module is also used to generate a demand map based on the demand data. By comparing the angle difference between the composite vector of each adjacent pixel of the rehabilitation training plan map and the composite vector of each adjacent pixel of the demand map, it can be determined whether the training plan meets the demand. The less close the training plan is to the demand, the greater the angle difference between the composite vector of each adjacent pixel of the rehabilitation training plan map and the composite vector of each adjacent pixel of the demand map. The closer the training plan is to the demand, the smaller the angle difference between the composite vector of each adjacent pixel of the rehabilitation training plan map and the composite vector of each adjacent pixel of the demand map.

[0037] Step S3 specifically includes the following steps: E1, set the sampling interval; E2, acquiring an image within a sampling interval, and performing screen segmentation on the image within the sampling interval and the standard image based on screen segmentation, and dividing the image within the sampling interval and the standard image into variable data and fixed data; E3, judging whether the variable data of the image in the sampling interval has changed relative to the variable data of the standard image based on the image comparison model, marking the changed image in the sampling interval as a changed image and marking the changed position in the image in the sampling interval based on the image annotation model, and marking the unchanged image in the sampling interval as an unchanged image; E4, judging the reason why the variable data in the changed image in step E3 changes based on the judgment model; E5, calculate the importance of the current change based on the importance calculation model, sort according to the importance, preset a detection threshold, retain the annotation for the change image whose importance of the current change is higher than the preset detection threshold, and delete the annotation for the change image whose importance of the current change is lower than the preset detection threshold; E6, determining whether the change of the change image with the mark retained in step E5 is a continuous change; E7, for the changing image judged as continuously changing in step E6, according to the change of the corresponding annotation in step S4, intercept the image frame with complete annotation change, and for the changing image with multiple annotation changes, intercept and classify and store according to different annotations, wherein the specific standard for video interception is a complete change process of the annotation of the changing image; E8, performing interception authentication on each image frame intercepted in step E7 based on the image comparison authentication model.

[0038] In step E6, determining whether the important change is a continuous change specifically includes the following steps: C1, first, detect each sub-annotation data spectrum in the image annotation result based on the local model; C2, if the posterior score of a sub-annotated spectrogram exceeds the threshold, it is considered a local change; C3, the system records the start time and end time of continuous local changes. The start time is the left edge of the window corresponding to the first local change, and the end time is the right edge of the window corresponding to the last local change. C4, when continuous local changes occur, it indicates that there are continuous changes in the image annotations within the time period from the start time to the end time, that is, the important changes currently detected are continuous changes; C5, if no continuous local changes occur, the currently detected important changes are considered as discontinuous changes; C6, re-inputting the non-continuous change image annotations in step C5 into step C1 for subsequent operations until there is no continuous change in the important change annotations.

[0039] The video capture authentication in step E8 specifically includes the following steps: D1, in response to each video segment captured in step E8, extracting image data that meets the specified image condition from each video segment; any image data that meets the specified image condition carries at least identification information and timestamp information of the beacon device that sent the image data; D2, if extracted, obtaining the specified data in the extracted image data; wherein the specified data at least includes the identification information and timestamp information of the beacon device that sent the extracted image data; D3, obtaining target identification information of each video segment captured in step E8, and target timestamp information of the video; D4, performing matching analysis on the target timestamp information and the timestamp information in the specified data to obtain a first analysis result, and performing matching analysis on the target identification information and the identification information in the specified data to obtain a second analysis result; D5, based on the first analysis result and the second analysis result, determine the authentication result of the video; wherein the authentication result is used to indicate whether each video segment captured in step E8 is fake.

[0040] An intelligent control device for patient rehabilitation training includes a data acquisition module, a data conversion module, a key frame extraction module and a quality assessment module: The data acquisition module is used to collect the symptom data set of the chronic kidney disease patients and the rehabilitation training plan data set of the chronic kidney disease patients, and perform data processing on the collected symptom data set of the chronic kidney disease patients and the rehabilitation training plan data set of the chronic kidney disease patients; The data conversion module is used to receive the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed in the data acquisition module for data conversion, and convert the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed into an image data set; The key frame extraction module is used to complete the key frame extraction of the image after the data conversion module converts it; The quality assessment module is used to determine whether the rehabilitation training program for patients with chronic kidney disease is qualified by comparing key image frames, and to discard the rehabilitation training program for patients with chronic kidney disease that is judged unqualified.

[0041] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An intelligent control method for patient rehabilitation training, characterized in that: The following steps are included: S1, collecting a symptom data set of patients with chronic kidney disease and a rehabilitation training plan data set of patients with chronic kidney disease, and performing data processing on the collected symptom data set of patients with chronic kidney disease and the rehabilitation training plan data set of patients with chronic kidney disease; S2, receiving the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed in step S1, and performing data conversion, converting the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed into an image data set; S3, extracting key frames from the image dataset in step S2 using a key frame extraction model; S4, by comparing the key image frames, determining whether the rehabilitation training plan of the chronic kidney disease patient is qualified, and discarding the rehabilitation training plan of the chronic kidney disease patient that is determined to be unqualified.

2. The intelligent control method for patient rehabilitation training according to claim 1, characterized in that: The step S1 specifically includes the following working steps: A11. Collect the disease data set of patients with chronic kidney disease online through the data collection module and generate the disease feature data set of patients with chronic kidney disease ; A12. Input the rehabilitation training plan data set of patients with chronic kidney disease online through the data acquisition module and generate the rehabilitation training plan feature data set of patients with chronic kidney disease ; A13, using adaptive filtering method to analyze the disease feature data set and the rehabilitation training program feature dataset Perform data denoising preprocessing and generate standard disease feature dataset and standard rehabilitation training program feature dataset ; A14. The standard disease characteristic data set and standard rehabilitation training program feature dataset Output data.

3. The intelligent control method for patient rehabilitation training according to claim 1, characterized in that: The step S2 specifically includes the following working steps: B1, first divide the standard disease feature data set of length n into Q elements according to the value range, each data point i belongs to a unique qi and qi∈{1, 2, .., Q}, where qi represents the element where the data point i is located; B2, construct the Markov transfer matrix W, and set the matrix size to [Q, Q], where W[i, j] is determined by the frequency of the data in qi being adjacent to the data in qj, where qj represents the element where the data point j is located. The calculation formula is as follows: ； B3, construct the Markov transform field M, assuming the matrix size is [n, n], the value of M[i, j] is W[qi, qj], the specific expression is: ； B4, for the Markov transfer matrix W with stable accuracy degradation, collect the performance label Q of the Markov transfer matrix W; B5, collect the performance change trajectory P of the current Markov transfer matrix W, divide the performance change trajectory P into performance improvement movement P1 and performance degradation movement P2, where the performance improvement movement P1 and the performance degradation movement P2 have the same sampling interval, and calculate the performance change trajectory of the current Markov transfer matrix W at the next moment: ； Among them, Z1 indicates that the next moment of the Markov transfer matrix W is performance improvement, and Z1 indicates that the next moment of the previous Markov transfer matrix W is performance degradation; B6, calculate the current possible performance change trajectory: ； Where Z T represents the possible performance change trajectory of the Markov transfer matrix W in the current time period T, represents the possible performance change trajectory of the Markov transfer matrix W at time t, and Any item in it is not 0; B7, since the performance change of the Markov transfer matrix W occurs at any time, the specific formula for calculating the possible performance change trajectory is: ； Where P t represents the performance change probability density function of the Markov transfer matrix W at time t, and integrates the possible performance change trajectory of the Markov transfer matrix W with the Markov transfer matrix W to obtain a new Markov transfer matrix W'; B8, according to the Markov transition field transfer matrix W whose parameters are optimized in step B2, a blank image with n*n pixels is selected; B9, using the values ​​in the Markov transition field M' matrix after data optimization in step B7 as pixels to fill the blank image, and sending the newly generated image to the key frame extraction module.

4. The intelligent control method for patient rehabilitation training according to claim 1, characterized in that: The step S3 specifically comprises the following steps: E1, set the sampling interval; E2, acquiring an image within a sampling interval, and performing screen segmentation on the image within the sampling interval and the standard image based on screen segmentation, and dividing the image within the sampling interval and the standard image into variable data and fixed data; E3, judging whether the variable data of the image in the sampling interval has changed relative to the variable data of the standard image based on the image comparison model, marking the changed image in the sampling interval as a changed image and marking the changed position in the image in the sampling interval based on the image annotation model, and marking the unchanged image in the sampling interval as an unchanged image; E4, judging the reason why the variable data in the changed image in step E3 changes based on the judgment model; E5, calculate the importance of the current change based on the importance calculation model, sort according to the importance, preset a detection threshold, retain the annotation for the change image whose importance of the current change is higher than the preset detection threshold, and delete the annotation for the change image whose importance of the current change is lower than the preset detection threshold; E6, determining whether the change of the marked change image retained in step E5 is a continuous change; E7, for the changing image judged as continuously changing in step E6, according to the change of the corresponding annotation in step S4, intercept the image frame with complete annotation change, and for the changing image with multiple annotation changes, intercept and classify and store according to different annotations, wherein the specific standard for video interception is a complete change process of the annotation of the changing image; E8, performing interception authentication on each image frame intercepted in step E7 based on the image comparison authentication model.

5. The intelligent control method for patient rehabilitation training according to claim 4, characterized in that: The step E6 of determining whether the important change is a continuous change specifically includes the following steps: C1, first, detect each sub-annotation data spectrum in the image annotation result based on the local model; C2, if the posterior score of a sub-annotated spectrogram exceeds the threshold, it is considered a local change; C3, the system records the start time and end time of continuous local changes. The start time is the left edge of the window corresponding to the first local change, and the end time is the right edge of the window corresponding to the last local change. C4, when continuous local changes occur, it indicates that there are continuous changes in the image annotations within the time period from the start time to the end time, that is, the important changes currently detected are continuous changes; C5, if no continuous local changes occur, the currently detected important changes are considered as discontinuous changes; C6, re-inputting the non-continuous change image annotations in step C5 into step C1 for subsequent operations until there is no continuous change in the important change annotations.

6. The intelligent control method for patient rehabilitation training according to claim 5, characterized in that: The video capture authentication in step E8 specifically includes the following steps: D1, in response to each video segment captured in step E8, extracting image data that meets the specified image condition from each video segment; any image data that meets the specified image condition carries at least identification information and timestamp information of the beacon device that sent the image data; D2, if extracted, obtaining the specified data in the extracted image data; wherein the specified data at least includes the identification information and timestamp information of the beacon device that sent the extracted image data; D3, obtaining target identification information of each video segment captured in step E8, and target timestamp information of the video; D4, performing a matching analysis on the target timestamp information and the timestamp information in the specified data to obtain a first analysis result, and performing a matching analysis on the target identification information and the identification information in the specified data to obtain a second analysis result; D5, based on the first analysis result and the second analysis result, determining the authentication result of the video; wherein the authentication result is used to indicate whether each video segment captured in the step E8 is fake.

7. An intelligent control device for patient rehabilitation training, which is applicable to the intelligent control method for patient rehabilitation training according to any one of claims 1 to 6, characterized in that: Including data acquisition module, data conversion module, key frame extraction module and quality assessment module: The data acquisition module is used to collect the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient, and perform data processing on the collected symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient; The data conversion module is used to receive the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed in the data acquisition module for data conversion, and convert the symptom data set of the chronic kidney disease patient and the rehabilitation training plan data set of the chronic kidney disease patient processed into an image data set; The key frame extraction module is used to extract the key frames of the image after the data conversion module completes the conversion; The quality assessment module is used to determine whether the rehabilitation training program for patients with chronic kidney disease is qualified by comparing key image frames, and to discard the rehabilitation training program for patients with chronic kidney disease that is judged to be unqualified.

Images