A pelvic floor rehabilitation system and method based on Internet edge computing

Abstract

The present invention discloses a pelvic floor rehabilitation system and method based on Internet edge computing, which belongs to the field of health management technology. The system of the present invention includes a user electromyography acquisition module, a sampling data processing module, a doctor program library formulation module, a user information acquisition module, a doctor diagnosis and program matching module, a treatment instrument allocation module and a data sharing module; the user electromyography acquisition module is used to store the electromyography amplitudes of the pelvic floor muscles of the four feature groups obtained by the user according to the template training in a local database; the sampling data processing module is used to process the electromyography values ​​of the pelvic floor muscles stored in the local database to obtain the detection results; the present invention is based on the Internet edge computing method, a large amount of collected data is first calculated by the local machine settings, the obtained results are provided for professional doctors to give a diagnosis, and the diagnosis results are matched with the training program and uploaded to the server end for sharing by devices in the local area network, thereby reducing the load of the server and improving the response speed.

Description

Technical Field

[0001] The present invention relates to the field of health management technology, and specifically to a pelvic floor rehabilitation system and method based on Internet edge computing. Background Art

[0002] Edge computing refers to the use of an open platform that integrates network, computing, storage, and application core capabilities to provide the nearest service on the side close to the source of objects or data. Edge computing is closer to users and can provide users with faster responses.

[0003] After collecting information, the existing pelvic floor rehabilitation system uploads all the information to the server, and then the server completes the algorithm, resulting in excessive cloud load, thereby reducing the user's response speed. The existing pelvic floor rehabilitation system uses electric current to stimulate the user's pelvic floor muscles, and plans the user's pelvic floor rehabilitation based on the images of the user's pelvic floor muscles before and after the electric current stimulation. Electric current stimulation is prone to accidents, which reduces the safety of the rehabilitation system. The system server is unable to judge data updates, or when judging data updates, it compares all data received by the server with the data already existing in the server, and processes the server data based on the comparison results. The large amount of data operated in this process will reduce the processing speed of the main application, thereby reducing the use effect of the system. Summary of the invention

[0004] The purpose of the present invention is to provide a pelvic floor rehabilitation system and method based on Internet edge computing to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a pelvic floor rehabilitation system based on Internet edge computing, the system comprising a user electromyography acquisition module, a sampling data processing module, a doctor plan library formulation module, a user information acquisition module, a doctor diagnosis and plan matching module, a treatment instrument allocation module and a data sharing module;

[0006] The user electromyography acquisition module is used to store the electromyography amplitudes of the pelvic floor muscles of the four feature groups obtained by the user according to the template training in a local database;

[0007] The sampling data processing module is used to process the pelvic floor muscle electromyography values ​​stored in the local database to obtain the detection results;

[0008] The doctor program library formulation module is used to formulate a program library according to the test results obtained by the sampling data processing module and the program template, and store the formulated program content in the encrypted database through MD5 encryption. The formulated program is stored in the encrypted database through MD5 encryption because MD5 has compressibility, which allows data of any length to be stored in a database field of a fixed size. At the same time, its strong anti-modification and irreversibility make it have good security. The program template content includes the treatment disease, the treatment instrument used, the treatment type, the treatment time, the stimulation frequency, the pulse width and the number of treatment courses. The treatment instruments used include biostimulation feedback instruments, magnetic stimulation instruments and electro-ultrasonic instruments;

[0009] The user information acquisition module is used to obtain the patient's basic information and medical history information from the questionnaire information given by the application when creating a doctor's file, formulate matching rules using regular expressions, convert the patient's questionnaire information content into multiple strings that meet the matching rules, and store the strings in an encrypted database;

[0010] The doctor diagnosis and plan matching module is used to query the basic information, medical history information and test results corresponding to the patient in the application through the patient's UUID. The doctor gives the patient's symptom results based on the query information. The application searches the database for the corresponding development plan based on the patient's symptom result keywords, generates a plan belonging to the patient, and stores the generated patient plan in the database. UUID represents a universal unique identification code;

[0011] The therapeutic instrument allocation module is used to match the corresponding therapeutic instrument according to the patient's condition;

[0012] The data sharing module is used to share the program library and patient information with all instruments in the local area network. The module is independent of the main application and resides in the memory in the form of a sub-application.

[0013] Furthermore, the four feature groups trained in the user electromyography acquisition module are the front resting group, the fast muscle group, the slow muscle group and the rear resting group. Users in the front resting group only need to relax their pelvic floor muscles, users in the fast muscle group need to quickly contract and release their pelvic floor muscles according to the template prompts, users in the slow muscle group need to contract and maintain their pelvic floor muscles according to the template until the template prompts them to release and relax, and the rear resting group is used to obtain the relaxation of the user's pelvic floor muscles after the training is completed.

[0014] Further, the sampling data processing module includes a fast muscle group processing unit, a slow muscle group processing unit, and a front rest group and a rear rest group processing unit;

[0015] Extract the pelvic floor muscle electromyography amplitude collected by the user from the local database, and draw a waveform graph with the X-axis as the sampling point N and the Y-axis as the electromyography amplitude A;

[0016] The fast muscle group processing unit reads the fast muscle group value through the drawn waveform graph, processes the read value to obtain the fast muscle group test result, and transmits the test result to the doctor plan library formulation module;

[0017] The slow muscle group processing unit reads the slow muscle group value through the drawn waveform graph, processes the read value to obtain the slow muscle group detection result, and transmits the detection result to the doctor plan library formulation module;

[0018] The front resting group and the rear resting group processing unit reads the front resting group and the rear resting group values ​​through the drawn waveform diagram, processes the read values ​​to obtain the front resting group and the rear resting group detection results, and transmits the detection results to the doctor plan library formulation module.

[0019] A pelvic floor rehabilitation method based on Internet edge computing, using a fast muscle group processing unit to process the read fast muscle group values ​​to obtain the specific method of the test result is:

[0020] 1) intercept all the EMG amplitudes of the fast muscle group in the time period T1, and find the point Pmax=(Nmax,Amax) corresponding to the maximum EMG amplitude in the time period, where T1 represents the sampling time of the fast muscle group, Nmax represents the number of sampling points corresponding to the maximum EMG amplitude in the time period T1, and Amax represents the maximum EMG amplitude in the time period T1;

[0021] 2) Select the first sampling point of the fast muscle group template as the center, obtain the point N corresponding to the first sampling point ±3s, and at the same time, the value of Nmax-N needs to be greater than the number of rising points of the template. Use the points that meet the above conditions within ±3s of the first sampling point to calculate the linear fit with the maximum amplitude point (Nmax, Amax) every other point, and obtain the linear fitting equation ystart=a1x+b1. The linear fitting equation is obtained by the least squares method;

[0022] 3) Compare the coefficients of determination R-square of the linear fitting equations that meet the above conditions, select the fitting equation ystart with the R-square closest to 1, and obtain the first sampling point of the equation as the first point Pstart=(Nstart,A1) where the user's fast muscle group actually starts to contract;

[0023] 4) Using formula T 上 = (Nmax-Nstart) / sampling rate to calculate the rising time of the user's pelvic floor muscles, and use the formula V1 = slope a1*sampling rate to calculate the rising speed of the user's pelvic floor muscles, the rising speed unit is uv / s;

[0024] 5) Select the last sampling point of the fast muscle group template as the center, obtain the points corresponding to ±3s of the sampling point, calculate the linear fitting between every 5 points and the maximum amplitude point (Nmax, Amax), and obtain the linear fitting equation yend = a2x + b2. Similarly, calculate the determination coefficient of each linear fitting equation, obtain the fitting equation yend with the determination coefficient closest to 1, and obtain the last sampling point of the equation as the last point of the user's real fast muscle group Pend = (Nend, A2);

[0025] 6) Using formula T 下 =(Nend-Nmax) / sampling rate to calculate the descent time of the user's pelvic floor muscles, and use the formula V2=slope a2*sampling rate to calculate the descent speed of the user's pelvic floor muscles, and the unit of descent speed is uv / s.

[0026] Furthermore, the specific method of using the slow muscle group processing unit to process the read slow muscle group value to obtain the test result is:

[0027] (a) Intercept all the EMG amplitudes of the slow muscle group in time period T2 and find the point corresponding to the maximum EMG amplitude in this time period Among them, T2 represents the sampling time of the slow muscle group, Indicates the number of sampling points corresponding to the maximum value of the electromyographic amplitude in time period T2. represents the maximum EMG amplitude in time period T2;

[0028] (b) Using the formula ΔT = T 2 -T 模板 Calculate the user's muscle contraction time, where T 模板 Indicates the sampling time corresponding to the maximum amplitude point of the template in time period T2, T 2 =n2 / sampling rate, indicating the sampling point The corresponding sampling time, n2 represents the number of sampling points corresponding to the maximum amplitude of the slow muscle group in time period T2;

[0029] (c) Select the first contraction sampling point of the slow muscle group template as the center and obtain the points corresponding to ±3s of the sampling point. At the same time, The value needs to be greater than the number of rising points of the template. For the points that meet the above conditions within ±3s of the sampling point, every other point is equal to the maximum amplitude point. Calculate the linear fitting respectively and get the linear fitting equation The linear fitting equation was obtained using the least squares method;

[0030] (d) Compare the coefficients of determination of the linear fitting equations that meet the above conditions Select The fitting equation closest to 1 And obtain the first sampling point of the equation as the first point where the user's slow muscle group actually starts to contract

[0031] (e) using the last sampling point of the fast muscle group and the first contraction point of the slow muscle group to calculate a linear regression equation, and obtaining the amplitude change trend of the user in the relaxation state after contraction through the slope corresponding to the linear regression equation;

[0032] (f) The last sampling point of the slow muscle group template is shifted to the right by ΔT, and the sampling point obtained after the shift is used as the central sampling point. The maximum value of the points corresponding to the central sampling point within ±3s is obtained as the last point of the user's real slow muscle group.

[0033] (g) The first sampling point and the last sampling point of the slow muscle group are used to calculate the linear fit, and the slope corresponding to the linear regression equation is used to describe the user's muscle maintenance ability. The smaller the slope, the stronger the user's muscle maintenance ability.

[0034] Furthermore, the specific method of using the pre-rest group and post-rest group processing units to process the read pre-rest group and post-rest group values ​​to obtain the detection results is:

[0035] (1) Obtain all points between the first sampling point of the previous resting group and the first point Pstart of the fast muscle group, obtain the average value, and calculate the linear fit to obtain the slope of the previous resting group equation, and use the slope to describe the relaxation of the user's pelvic floor muscles before training;

[0036] (2) Obtain all points between the last sampling point Pend of the slow muscle group and the last sampling point of the post-resting group, obtain the average value, and calculate the linear fit to obtain the slope of the post-resting group equation. The slope is used to describe the relaxation of the user's pelvic floor muscles after training.

[0037] Furthermore, the specific method of using the treatment equipment allocation module to allocate treatment equipment according to the disease requirements is:

[0038] (I) Determine whether the current treatment device can meet the treatment needs and whether the treatment device is in an idle state. If it can meet the needs and is in an idle state, use the current treatment device; otherwise, execute (II);

[0039] (II) Connect to other devices in the same LAN segment through IP, and obtain the encrypted file in the shared folder of other devices. If the encrypted file exists, execute (III), otherwise execute (V);

[0040] (III) Obtain the device information in the encrypted file. If it matches the required device, execute (IV); otherwise, execute (V);

[0041] (IV) Obtain the use status of the device. If it is in use, record the waiting time and execute (V). If it is idle, the local application will prompt the device information and room number to facilitate the patient to find it accurately;

[0042] (V) Connecting to the next device. If the device is in working condition, the waiting time is compared, and the device information and device room number corresponding to the shortest waiting time are provided to the patient. The patient then searches for a matching treatment device based on the provided information;

[0043] Every treatment device in the local area network can find the required device in this way, avoiding crowding of patients and idle devices.

[0044] Furthermore, the specific method of processing the shared data using the data sharing module is as follows:

[0045] ①. Determine whether there is any data update in the main application database obtained by the data sharing module. If there is any update, upload the updated data to the hospital server;

[0046] ②. Starting from the first data, the hospital server compares the received updated data A with the existing data B in the server. If the generation time T corresponding to the updated data is a Greater than the generation time T corresponding to the existing data b , then update the server data. If the generation time corresponding to the updated data is T a Less than the generation time T corresponding to the existing data b , then the local device updates the server data. If the generation time corresponding to the updated data is T a Equal to the generation time T corresponding to the existing data b , then compare the next piece of data;

[0047] ③. If the machine has no data update, it will s Capture the server data once to achieve consistency of data for all instruments in the local area network, where t is the user-set value.

[0048] Furthermore, the regular expression used in the user information acquisition module formulates the matching rule as follows:

[0049] Set the template string, pass the string to be matched and the template string into regex_match, and return a bool value to indicate whether the string to be matched meets the rules of the template string. If not, match the next template and repeat the above operations. regex_match represents the regular matching formula and bool represents a Boolean type variable.

[0050] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0051] 1. The present invention is based on the Internet edge computing method. A large amount of collected data is first calculated by the local setting, and the obtained results are provided to professional doctors for diagnosis. The diagnosis results are matched with the training plan and then uploaded to the server for sharing by devices in the local area network, thereby reducing the load on the server and improving the response speed.

[0052] 2. The present invention divides the user's electromyographic training into four feature groups, uses the fast muscle group data to obtain the rise time, fall time, rise speed and fall speed of the user's pelvic floor muscles, uses the slow muscle group data to obtain the user's muscle maintenance ability, and uses the values ​​of the front resting group and the post resting group to obtain the pelvic floor muscle conditions of the user when relaxing before training and when relaxing after training, respectively, to ensure that the user's pelvic floor muscle conditions are effectively understood, so as to improve the probability of recovery of the user's pelvic floor muscles.

[0053] 3. The present invention compares the data received by the server with the existing data on the server to determine whether the server data is updated, and performs relevant operations on the server according to the judgment result, thereby achieving consistency of data of all instruments in the local area network. By comparing the data received by the server one by one, it can avoid the impact of simultaneous operations on a large amount of data on the processing speed of the main application, and further improve the stability of the program. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0055] Figure 1 It is a schematic diagram of the working principle structure of a pelvic floor rehabilitation system and method based on Internet edge computing of the present invention;

[0056] Figure 2 It is a schematic diagram of the workflow of a therapeutic instrument allocation module of a pelvic floor rehabilitation system and method based on Internet edge computing of the present invention;

[0057] Figure 3 This is a pelvic floor muscle electromyography waveform of a pelvic floor rehabilitation system and method based on Internet edge computing of the present invention Figure 1 ;

[0058] Figure 4 This is a pelvic floor muscle electromyography waveform of a pelvic floor rehabilitation system and method based on Internet edge computing of the present invention Figure 2 . DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] See also Figure 1 , Figure 2 , Figure 3 and Figure 4 , the present invention provides a technical solution: a pelvic floor rehabilitation system based on Internet edge computing, the system includes a user electromyography acquisition module, a sampling data processing module, a doctor plan library formulation module, a user information acquisition module, a doctor diagnosis and plan matching module, a treatment instrument allocation module and a data sharing module;

[0061] The user electromyography acquisition module is used to store the electromyography amplitudes of the pelvic floor muscles of the four feature groups obtained by the user according to the template training in a local database;

[0062] The four feature groups trained in the user electromyography acquisition module are the front resting group, the fast muscle group, the slow muscle group and the rear resting group. The front resting group users only need to relax the pelvic floor muscles, the fast muscle group users need to quickly contract and release the pelvic floor muscles according to the template prompts, the slow muscle group users need to contract and maintain the pelvic floor muscles according to the template until the template prompts to release and relax, and the rear resting group is used to obtain the relaxation of the user's pelvic floor muscles after the training is completed;

[0063] The sampling data processing module is used to process the pelvic floor muscle electromyography values ​​stored in the local database to obtain the detection results;

[0064] The sampling data processing module includes a fast muscle group processing unit, a slow muscle group processing unit, and a front rest group and a rear rest group processing unit;

[0065] Extract the pelvic floor muscle electromyography amplitude collected by the user from the local database, and draw a waveform graph with the X-axis as the sampling point N and the Y-axis as the electromyography amplitude A;

[0066] The fast muscle group processing unit reads the fast muscle group value through the drawn waveform graph, processes the read value to obtain the fast muscle group test result, and transmits the test result to the doctor plan library formulation module;

[0067] The specific method of using the fast muscle group processing unit to process the read fast muscle group value to obtain the test result is:

[0068] 1) intercept all the EMG amplitudes of the fast muscle group in the time period T1, and find the point Pmax=(Nmax,Amax) corresponding to the maximum EMG amplitude in the time period, where T1 represents the sampling time of the fast muscle group, Nmax represents the number of sampling points corresponding to the maximum EMG amplitude in the time period T1, and Amax represents the maximum EMG amplitude in the time period T1;

[0069] 2) Select the first sampling point of the fast muscle group template as the center, obtain the point N corresponding to the first sampling point ±3s, read the maximum amplitude point (Nmax, Amax), and at the same time, the value of N-Nmax needs to be greater than the number of rising points of the template. Therefore, adjust the sequence range of the first sampling point N, assuming that the number of rising points of the template is E, that is, N = [Nmax-E, Nmax+E], use N sequence points, calculate the linear fit for every other point and the maximum amplitude point (Nmax, Amax), and obtain the linear fitting equation ystart = a1x + b1. The linear fitting equation is obtained by the least squares method, where E is an arbitrary positive number;

[0070] 3) Compare the coefficients of determination R-square of the linear fitting equations that meet the above conditions, select the fitting equation ystart with the R-square closest to 1, and obtain the first sampling point of the equation as the first point Pstart=(Nstart,A1) where the user's fast muscle group actually starts to contract;

[0071] 4) Using formula T 上 = (Nmax-Nstart) / sampling rate to calculate the rising time of the user's pelvic floor muscles, and use the formula V1 = slope a1*sampling rate to calculate the rising speed of the user's pelvic floor muscles, the rising speed unit is uv / s;

[0072] 5) Select the last sampling point of the fast muscle group template as the center, obtain the points corresponding to ±3s of the sampling point, calculate the linear fitting between every 5 points and the maximum amplitude point (Nmax, Amax), and obtain the linear fitting equation yend = a2x + b2. Similarly, calculate the determination coefficient of each linear fitting equation, obtain the fitting equation yend with the determination coefficient closest to 1, and obtain the last sampling point of the equation as the last point of the user's real fast muscle group Pend = (Nend, A2);

[0073] 6) Using formula T 下 = (Nend-Nmax) / sampling rate to calculate the descent time of the user's pelvic floor muscles, and use the formula V2 = slope a2*sampling rate to calculate the descent speed of the user's pelvic floor muscles, the descent speed unit is uv / s;

[0074] The slow muscle group processing unit reads the slow muscle group value through the drawn waveform graph, processes the read value to obtain the slow muscle group detection result, and transmits the detection result to the doctor plan library formulation module;

[0075] The specific method of using the slow muscle group processing unit to process the read slow muscle group value to obtain the test result is:

[0076] (a) Intercept all the EMG amplitudes of the slow muscle group in time period T2 and find the point corresponding to the maximum EMG amplitude in this time period Among them, T2 represents the sampling time of the slow muscle group, Indicates the number of sampling points corresponding to the maximum value of the electromyographic amplitude in time period T2. represents the maximum EMG amplitude in time period T2;

[0077] (b) Using the formula ΔT = T 2 -T 模板 Calculate the user's muscle contraction time, where T 模板 Indicates the sampling time corresponding to the maximum amplitude point of the template in time period T2, T 2 =n2 / sampling rate, indicating the sampling point The corresponding sampling time, n2 represents the number of sampling points corresponding to the maximum amplitude of the slow muscle group in time period T2;

[0078] (c) Select the first contraction sampling point of the slow muscle group template as the center and obtain the points corresponding to ±3s of the sampling point. At the same time, The value of needs to be greater than the number of rising points of the template, that is, For points that meet the above conditions within ±3s of the sampling point, every other point is compared with the maximum amplitude point. Calculate the linear fitting respectively and get the linear fitting equation The linear fitting equation was obtained using the least squares method;

[0079] (d) Compare the coefficients of determination of the linear fitting equations that meet the above conditions Select The fitting equation closest to 1 And obtain the first sampling point of the equation as the first point where the user's slow muscle group actually starts to contract

[0080] (e) using the last sampling point of the fast muscle group and the first contraction point of the slow muscle group to calculate a linear regression equation, and obtaining the amplitude change trend of the user in the relaxation state after contraction through the slope corresponding to the linear regression equation;

[0081] (f) The last sampling point of the slow muscle group template is shifted to the right by ΔT, and the sampling point obtained after the shift is used as the central sampling point. The maximum value of the points corresponding to the central sampling point within ±3s is obtained as the last point of the user's real slow muscle group.

[0082] (g) The first sampling point and the last sampling point of the slow muscle group are used to calculate the linear fit, and the slope corresponding to the linear regression equation is used to describe the strength of the user's muscle maintenance ability. The smaller the slope, the stronger the user's muscle maintenance ability;

[0083] The pre-resting group and post-resting group processing unit reads the pre-resting group and post-resting group values ​​through the drawn waveform graph, processes the read values ​​to obtain the pre-resting group and post-resting group test results, and transmits the test results to the doctor plan library formulation module;

[0084] The specific method of using the pre-rest group and post-rest group processing units to process the read pre-rest group and post-rest group values ​​to obtain the test results is:

[0085] (1) Obtain all points between the first sampling point of the previous resting group and the first point Pstart of the fast muscle group, obtain the average value, and calculate the linear fit to obtain the slope of the previous resting group equation, and use the slope to describe the relaxation of the user's pelvic floor muscles before training;

[0086] (2) Obtain all points between the last sampling point Pend of the slow muscle group and the last sampling point of the post-resting group, obtain the average value, and calculate the linear fit to obtain the slope of the post-resting group equation. The slope is used to describe the relaxation of the user's pelvic floor muscles after training;

[0087] The doctor program library formulation module is used to formulate a program library according to the test results obtained by the sampling data processing module and the program template, and store the formulated program content in the encrypted database through MD5 encryption. The formulated program is stored in the encrypted database through MD5 encryption because MD5 has compressibility, which allows data of any length to be stored in a database field of a fixed size. At the same time, its strong anti-modification and irreversibility make it have good security. The program template content includes the treatment disease, the treatment instrument used, the treatment type, the treatment time, the stimulation frequency, the pulse width and the number of treatment courses. The treatment instruments used include biostimulation feedback instruments, magnetic stimulation instruments and electro-ultrasonic instruments;

[0088] The user information acquisition module is used to obtain the patient's basic information and medical history information from the questionnaire information given by the application when creating a doctor's file, formulate matching rules using regular expressions, convert the patient's questionnaire information content into multiple strings that meet the matching rules, and store the strings in an encrypted database;

[0089] The regular expression used in the user information acquisition module to formulate the matching rule is:

[0090] Set the template string, pass the string to be matched and the template string into regex_match, and return a bool value to indicate whether the string to be matched meets the rules of the template string. If not, match the next template and repeat the above operation;

[0091] The doctor diagnosis and plan matching module is used to query the basic information, medical history information and test results corresponding to the patient in the application through the patient's UUID. The doctor gives the patient's symptom results based on the query information. The application searches the database for the corresponding development plan based on the patient's symptom result keywords, generates a plan belonging to the patient, and stores the generated patient plan in the database. UUID represents a universal unique identification code;

[0092] The therapeutic instrument allocation module is used to match the corresponding therapeutic instrument according to the patient's condition;

[0093] The specific method of using the treatment equipment allocation module to allocate treatment equipment according to the needs of the disease is as follows:

[0094] (I) Determine whether the current treatment device can meet the treatment needs and whether the treatment device is in an idle state. If it can meet the needs and is in an idle state, use the current treatment device; otherwise, execute (II);

[0095] (II) Connect to other devices in the same LAN segment through IP, and obtain the encrypted file in the shared folder of other devices. If the encrypted file exists, execute (III), otherwise execute (V);

[0096] (III) Obtain the device information in the encrypted file. If it matches the required device, execute (IV); otherwise, execute (V);

[0097] (IV) Obtain the use status of the device. If it is in use, record the waiting time and execute (V). If it is idle, the local application will prompt the device information and room number to facilitate the patient to find it accurately;

[0098] (V) Connecting to the next device. If the device is in working condition, the waiting time is compared, and the device information and device room number corresponding to the shortest waiting time are provided to the patient. The patient then searches for a matching treatment device based on the provided information;

[0099] Each treatment device in the local area network can find the required device in this way, avoiding the crowding of patients and the idleness of devices;

[0100] The data sharing module is used to share the protocol library and patient information with all instruments in the local area network. The module is independent of the main application and resides in the memory in the form of a sub-application;

[0101] The specific method of using the data sharing module to process shared data is:

[0102] ①. Determine whether there is any data update in the main application database obtained by the data sharing module. If there is any update, upload the updated data to the hospital server;

[0103] ②. Starting from the first data, the hospital server compares the received updated data A with the existing data B in the server. If the generation time T corresponding to the updated data is a Greater than the generation time T corresponding to the existing data b , then update the server data. If the generation time corresponding to the updated data is T a Less than the generation time T corresponding to the existing data b , then the local device updates the server data. If the generation time corresponding to the updated data is T a Equal to the generation time T corresponding to the existing data b , then compare the next piece of data;

[0104] ③. If the machine has no data update, it will fetch the server data every ts, so as to achieve the consistency of data of all instruments in the LAN, where t is the user-set value;

[0105] Coefficient of determination R-square is also called goodness of fit, which is used to describe the degree of fit of the regression line to the observed value. The range of R-squared is [0,1]. The closer the value is to 1, the better the model fit is.

[0106] Implementation column: Set Figure 3 and Figure 4 The collected pelvic floor muscle electromyography waveform, where the curve is the pelvic floor electromyography real-time value sequence, the thick straight line is the template sequence, the thin straight line is the linear fitting line, T1 = [1600, 2400], T2 = [1100, 1400], and the sampling rate is 128;

[0107] Implementation 1:

[0108] 1) Based on Figure 3 Find the point with the largest amplitude in the T1 time period as Pmax=(1725,42);

[0109] 2) Select the X value of the abscissa of the first sampling point of the fast muscle group template, that is, X = 1600 as the center, and obtain the sequence N of ±3s of the sampling point, that is, ±384 points. Then the X-axis range of the point is [1216, 1984]. The maximum value of the real-time electromyography in the range of [1216, 1984] is Nmax = 1725. Figure 3 In the figure, the difference in the number of horizontal coordinate points when the amplitude of the template rises from 0 to 50 microvolts in the rapid contraction stage is 45, that is, N = [1725-45, 1725 + 45]. Therefore, the X-axis range of the adjustment point is [1680, 1770]. The data is read to obtain the amplitude within this range, and the sequence of points is obtained. The linear fit is calculated for every other point and the point with the maximum amplitude (1725, 42), and the linear fit equation ystart = a1x + b1 is obtained.

[0110] 3) Compare the coefficients of determination R-square of the linear fitting equations that meet the above conditions, select the fitting equation ystart=1.2343x-2084.88 with the R-square closest to 1, and obtain the first sampling point of the equation as the first point Pstart=(1699,12.298) where the user's fast muscle group actually starts to contract;

[0111] 4) Using formula T 上 = (Nmax-Nstart) / sampling rate to calculate the rising time of the user's pelvic floor muscles, and use the formula V1 = slope a1*sampling rate to calculate the rising speed of the user's pelvic floor muscles, then:

[0112] T 上 =(Nmax-Nstart) / sampling rate=(1725-1699) / 128=0.203125s;

[0113] V1 = slope a1 * sampling rate = 1.23436 * 128 = 157.99808uv / s;

[0114] 5) Select the abscissa X=1800 of the last sampling point of the fast muscle group template as the center, obtain the abscissa ±3s in the real value, that is, a sequence N of ±384 points, calculate the linear fitting of every 5 points and the amplitude maximum point (1725,42), and obtain the linear fitting equation yend=a2x+b2. Similarly, calculate the determination coefficient of each linear fitting equation, obtain the fitting equation yend=-0.614893x+1102.27 closest to 1, and obtain the last sampling point of the equation as the last point of the user's real fast muscle group Pend=(1780,7.7);

[0115] 6) Using formula T 下= (Nend-Nmax) / sampling rate to calculate the descent time of the user's pelvic floor muscles, and use the formula V2 = slope a2*sampling rate to calculate the descent speed of the user's pelvic floor muscles, then:

[0116] T 下 =(Nend-Nmax) / sampling rate=(1780-1725) / 128=0.4296875s;

[0117] V2 = slope a2 * sampling rate = 0.614893 * 128 = 78.706304uv / s.

[0118] Implementation 2:

[0119] (a) Based on Figure 4 Find the first point with the largest amplitude in the T2 time period T 2 = n2 / sampling rate = 1320 / 128 = 10.3125s;

[0120] (b) Using the formula ΔT = T 2 -T 模板 Calculate the user's muscle contraction time, then:

[0121] ΔT=T 2 -T 模板 =10.3125-9.53125=0.78125s;

[0122] (c) Select the sampling point of the first contraction of the slow muscle group template with the horizontal coordinate X=1220 as the center, and obtain the sampling point ±3s in the true value, that is, ±384 points. At the same time, Calculate the linear fit between every other point and the maximum amplitude point (1320,42) to obtain the linear fit equation;

[0123] (d) Compare the coefficients of determination of the linear fitting equations that meet the above conditions Select The fitting equation closest to 1 And obtain the first sampling point of the equation as the first point where the user actually starts to shrink

[0124] (e) using the last sampling point of the fast muscle group and the first contraction point of the slow muscle group to calculate a linear regression equation, and obtaining the amplitude change trend of the user in the relaxation state after contraction through the slope corresponding to the linear regression equation;

[0125] (f) Select the horizontal coordinate X of the last sampling point of the slow muscle group template, take the point obtained after shifting to the right by ΔT = 0.78125s as the center, and obtain the maximum value of the points within ±3s of the sampling point as the last point of the user's real slow muscle group

[0126] (g) The first sampling point and the last sampling point of the slow muscle group are used to calculate the linear fit, and the slope corresponding to the linear regression equation is used to describe the user's muscle maintenance ability. The smaller the slope, the stronger the user's muscle maintenance ability.

[0127] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0128] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A pelvic floor rehabilitation system based on Internet edge computing, characterized by: The system includes a user electromyography acquisition module, a sampling data processing module, a doctor's plan library formulation module, a user information acquisition module, a doctor's diagnosis and plan matching module, a treatment instrument allocation module and a data sharing module; The user electromyography acquisition module is used to store the electromyography amplitudes of the pelvic floor muscles of the four feature groups obtained by the user according to the template training in a local database; The four feature groups trained in the user electromyography acquisition module are the front resting group, the fast muscle group, the slow muscle group and the rear resting group. The front resting group users only need to relax the pelvic floor muscles, the fast muscle group users need to quickly contract and release the pelvic floor muscles according to the template prompts, the slow muscle group users need to contract and maintain the pelvic floor muscles according to the template until the template prompts to release and relax, and the rear resting group is used to obtain the relaxation of the user's pelvic floor muscles after the training is completed; The sampling data processing module is used to process the pelvic floor muscle electromyography values ​​stored in the local database to obtain the detection results; The sampling data processing module includes a fast muscle group processing unit, a slow muscle group processing unit, and a front rest group and a rear rest group processing unit; Extract the pelvic floor muscle electromyography amplitude collected by the user from the local database, and draw a waveform graph with the X-axis as the sampling point N and the Y-axis as the electromyography amplitude A; The fast muscle group processing unit reads the fast muscle group value through the drawn waveform graph, processes the read value to obtain the fast muscle group test result, and transmits the test result to the doctor plan library formulation module; The slow muscle group processing unit reads the slow muscle group value through the drawn waveform graph, processes the read value to obtain the slow muscle group detection result, and transmits the detection result to the doctor plan library formulation module; The pre-resting group and post-resting group processing unit reads the pre-resting group and post-resting group values ​​through the drawn waveform graph, processes the read values ​​to obtain the pre-resting group and post-resting group test results, and transmits the test results to the doctor plan library formulation module; The doctor plan library formulation module is used to formulate a plan library according to the test results obtained by the sampling data processing module according to the plan template, and store the formulated plan content in the encrypted database through MD5 encryption; The user information acquisition module is used to obtain the patient's basic information and medical history information from the questionnaire information given by the application when creating a doctor's file, use regular expressions to formulate matching rules, convert the patient's questionnaire information content into multiple strings that meet the matching rules, and store the strings in an encrypted database; The doctor diagnosis and plan matching module is used to query the basic information, medical history information and test results of the patient in the application through the patient's UUID. The doctor gives the patient's symptom results according to the query information. The application searches the database for the corresponding development plan according to the patient's symptom result keywords, generates a plan belonging to the patient, and stores the generated patient plan in the database; The therapeutic instrument allocation module is used to match the corresponding therapeutic instrument according to the patient's condition; The data sharing module is used to share the program library and patient information with all instruments in the local area network. The module is independent of the main application and resides in the memory in the form of a sub-application.

2. A pelvic floor rehabilitation method applied to the system of claim 1, characterized in that: The specific method of using the fast muscle group processing unit to process the read fast muscle group value to obtain the test result is: 1) intercept all the EMG amplitudes of the fast muscle group in the time period T1, and find the point Pmax=(Nmax,Amax) corresponding to the maximum EMG amplitude in the time period, where T1 represents the sampling time of the fast muscle group, Nmax represents the number of sampling points corresponding to the maximum EMG amplitude in the time period T1, and Amax represents the maximum EMG amplitude in the time period T1; 2) Select the first sampling point of the fast muscle group template as the center, obtain the point N corresponding to the first sampling point ±3s, and at the same time, the value of Nmax-N needs to be greater than the number of rising points of the template. Use the points that meet the above conditions within ±3s of the first sampling point to calculate the linear fit with the maximum amplitude point (Nmax, Amax) every other point, and obtain the linear fitting equation ystart=a1x+b1. The linear fitting equation is obtained by the least squares method; 3) Compare the coefficients of determination R-square of the linear fitting equations that meet the above conditions, select the fitting equation ystart with the R-square closest to 1, and obtain the first sampling point of the equation as the first point Pstart=(Nstart,A1) where the user's fast muscle group actually starts to contract; 4) Using formula T 上 = (Nmax-Nstart) / sampling rate to calculate the rising time of the user's pelvic floor muscles, and use the formula V1 = slope a1*sampling rate to calculate the rising speed of the user's pelvic floor muscles, the rising speed unit is uv / s; 5) Select the last sampling point of the fast muscle group template as the center, obtain the points corresponding to ±3s of the sampling point, calculate the linear fitting between every 5 points and the maximum amplitude point (Nmax, Amax), and obtain the linear fitting equation yend = a2x + b2. Similarly, calculate the determination coefficient of each linear fitting equation, obtain the fitting equation yend with the determination coefficient closest to 1, and obtain the last sampling point of the equation as the last point of the user's real fast muscle group Pend = (Nend, A2); 6) Using formula T 下 =(Nend-Nmax) / sampling rate to calculate the descent time of the user's pelvic floor muscles, and use the formula V2=slope a2*sampling rate to calculate the descent speed of the user's pelvic floor muscles, and the unit of descent speed is uv / s.

3. The pelvic floor rehabilitation method according to claim 2, characterized in that: The specific method of using the slow muscle group processing unit to process the read slow muscle group value to obtain the test result is: (a) Intercept all the EMG amplitudes of the slow muscle group in time period T2 and find the point corresponding to the maximum EMG amplitude in this time period Among them, T2 represents the sampling time of the slow muscle group, Indicates the number of sampling points corresponding to the maximum value of the electromyographic amplitude in time period T2. represents the maximum EMG amplitude in time period T2; (b) Using the formula ΔT = T 2 -T 模扳 Calculate the user's muscle contraction time, where T 模扳 Indicates the sampling time corresponding to the maximum amplitude point of the template in time period T2, T 2 =n2 / sampling rate, indicating the sampling point The corresponding sampling time, n2 represents the number of sampling points corresponding to the maximum amplitude of the slow muscle group in time period T2; (c) Select the first contraction sampling point of the slow muscle group template as the center and obtain the points corresponding to ±3s of the sampling point. At the same time, The value needs to be greater than the number of rising points of the template. For the points that meet the above conditions within ±3s of the sampling point, every other point is equal to the maximum amplitude point. Calculate the linear fitting respectively and get the linear fitting equation The linear fitting equation was obtained using the least squares method; (d) Compare the coefficients of determination of the linear fitting equations that meet the above conditions Select The fitting equation closest to 1 And obtain the first sampling point of the equation as the first point where the user's slow muscle group actually starts to contract (e) using the last sampling point of the fast muscle group and the first contraction point of the slow muscle group to calculate a linear regression equation, and obtaining the amplitude change trend of the user in the relaxation state after contraction through the slope corresponding to the linear regression equation; (f) The last sampling point of the slow muscle group template is shifted to the right by ΔT, and the sampling point obtained after the shift is used as the central sampling point. The maximum value of the points corresponding to the central sampling point within ±3s is obtained as the last point of the user's real slow muscle group. (g) The first sampling point and the last sampling point of the slow muscle group are used to calculate the linear fit, and the slope corresponding to the linear regression equation is used to describe the strength of the user's muscle maintenance ability.

4. The pelvic floor rehabilitation method according to claim 3, characterized in that: The specific method of using the pre-rest group and post-rest group processing units to process the read pre-rest group and post-rest group values ​​to obtain the test results is: (1) Obtain all points between the first sampling point of the previous resting group and the first point Pstart of the fast muscle group, obtain the average value, and calculate the linear fit to obtain the slope of the previous resting group equation, and use the slope to describe the relaxation of the user's pelvic floor muscles before training; (2) Obtain all points between the last sampling point Pend of the slow muscle group and the last sampling point of the post-resting group, obtain the average value, and calculate the linear fit to obtain the slope of the post-resting group equation. The slope is used to describe the relaxation of the user's pelvic floor muscles after training.

5. The pelvic floor rehabilitation method according to claim 4, characterized in that: The specific method of using the treatment equipment allocation module to allocate treatment equipment according to the needs of the disease is as follows: (I) determining whether the current treatment device can meet the treatment needs and whether the treatment device is in an idle state; if the treatment device can meet the needs and is in an idle state, using the current treatment device; otherwise, executing (II); (II) Connect to other devices in the same LAN segment through IP, and obtain the encrypted file in the shared folder on other devices. If the encrypted file exists, execute (III), otherwise execute (V); (III) Obtain the device information in the encrypted file. If it matches the required device, execute (IV); otherwise, execute (V); (IV) obtaining the use status of the device. If the device is in use, recording the waiting time, and executing (V). If the device is idle, the local application will prompt the device information and room number to facilitate the patient to find the device accurately. (V) Connect the next device. If the device is in working condition, compare the waiting time and provide the patient with the device information and device room number corresponding to the shortest waiting time. The patient then searches for matching treatment equipment based on the provided information.

6. The pelvic floor rehabilitation method according to claim 5, characterized in that: The specific method of using the data sharing module to process shared data is: ①. Determine whether there is any data update in the main application database obtained by the data sharing module. If there is any update, upload the updated data to the hospital server; ②. Starting from the first data, the hospital server compares the received updated data A with the existing data B in the server. If the generation time T corresponding to the updated data is a Greater than the generation time T corresponding to the existing data b , then update the server data. If the generation time corresponding to the updated data is T a Less than the generation time T corresponding to the existing data b , then the local device updates the server data. If the generation time corresponding to the updated data is T a Equal to the generation time T corresponding to the existing data b , then compare the next piece of data; ③. If the local machine has no data update, it will fetch the server data every ts to make all the instrument data in the local area network consistent, where t is the user-set value.

7. The pelvic floor rehabilitation method according to claim 6, characterized in that: The regular expression used in the user information acquisition module to formulate the matching rule is: Set the template string, pass the string to be matched and the template string into regex_match, and return a bool value to indicate whether the string to be matched meets the rules of the template string. If not, match the next template and repeat the above operation.

Images