A method and system for performing dynamic pelvic floor functional assessment

Abstract

The embodiment of the present application relates to the technical field of detection and evaluation, and discloses a method for dynamic pelvic floor function detection and evaluation, comprising: filtering the surface electromyography signals of a first detection area according to a first area filter matrix, and extracting the filtered surface electromyography signals to obtain a first area feature group; filtering the surface electromyography signals of a second detection area according to a second area filter matrix, and extracting the filtered surface electromyography signals to obtain a second area feature group; determining a third area feature group according to fast muscle signals and slow muscle signals; and using a pelvic floor evaluation algorithm to evaluate and calculate the first area feature group, the second area feature group and the third area feature group. The method for dynamic pelvic floor function detection and evaluation in the embodiment of the present application realizes accurate detection of each part of the pelvic floor by using a surface electromyography detection component, and optimizes the electromyography signals detected by each part through a specific filter algorithm.

Description

Technical Field

[0001] This invention relates to the field of testing and evaluation technology, specifically to a method and system for dynamic pelvic floor function testing and evaluation. Background Technology

[0002] Currently, the incidence of pelvic floor dysfunction (such as vaginal wall prolapse, pelvic organ prolapse, and urinary incontinence) is high, seriously affecting patients' quality of life. Traditional methods for assessing pelvic floor function mainly rely on the doctor's subjective judgment, lacking quantitative and objective evaluation methods, and the diagnostic process is inherently subjective and uncertain. Therefore, designing a comprehensive and accurate pelvic floor function assessment scheme has become a pressing technical problem for those skilled in the art. Summary of the Invention

[0003] To address the aforementioned deficiencies, this invention discloses a method for dynamic pelvic floor function detection and evaluation, which enables accurate assessment of pelvic floor function.

[0004] The first aspect of this invention discloses a method for dynamic pelvic floor function testing and evaluation, comprising:

[0005] The surface electromyography (SEMG) detection component is used to acquire surface electromyography (SEMG) signals in corresponding detection areas during each detection stage. The SEMG detection component includes a first detection component, a second detection component, and a third detection component. The detection areas include a first detection area, a second detection area, and a third detection area.

[0006] The acquired surface electromyography signals are frequency domain converted to obtain corresponding frequency domain signals. The frequency bands of interest for each detection region are determined according to the attribute characteristics of each detection region. The frequency bands of interest include the first frequency band and the second frequency band corresponding to the first detection region and the second detection region, respectively.

[0007] Calculate the first covariance matrix of the first detection region, the second detection region, and the third detection region in the first frequency band of interest; construct a first region filtering matrix based on the first covariance matrix; filter the surface electromyography (EMG) signal of the first detection region based on the first region filtering matrix; and extract the filtered EMG signal to obtain the first region feature group.

[0008] Calculate the second covariance matrix between the second detection region and the first detection region in the second frequency band of interest. Determine and construct the second region filtering matrix based on the second covariance matrix. Filter the surface electromyography (EMG) signal of the second detection region based on the second region filtering matrix, and extract the filtered EMG signal to obtain the second region feature group.

[0009] An improved independent component analysis algorithm is used to analyze the surface electromyography signal in the third detection region to obtain the fast-twitch and slow-twitch signals in the third detection region, and the feature group of the third region is determined based on the fast-twitch and slow-twitch signals.

[0010] The pelvic floor assessment algorithm is used to evaluate and calculate the feature groups of the first, second, and third regions to determine the scores of each detection region and the overall score.

[0011] As an optional implementation, in the first aspect of the present invention, the step of using a pelvic floor assessment algorithm to evaluate and calculate the first region feature group, the second region feature group, and the third region feature group to determine the score results of each detection region and the comprehensive score result includes:

[0012] A first region feature group is determined in the first detection region of the corresponding detection stage. The first region feature group includes peak electromyographic amplitude, contraction rise time and high frequency signal ratio, so as to determine the region score result of the first detection region based on peak electromyographic amplitude, contraction rise time and high frequency signal ratio.

[0013] The second region feature group in the second detection area of ​​the corresponding detection stage is determined. The second region feature group includes the standard deviation of electromyography signal, the amplitude ratio at the end of endurance contraction to the initial stage, and the proportion of low-frequency signal. The region score result of the second detection area is determined based on the standard deviation of electromyography signal, the amplitude ratio at the end of endurance contraction to the initial stage, and the proportion of low-frequency signal.

[0014] The third region feature group of the third detection area in the corresponding detection stage is determined. The peak value of rapid contraction and the endurance parameter of sustained contraction of the third region feature group are used to determine the synergy result of fast and slow muscle groups in the third detection area based on the peak value of rapid contraction and the endurance parameter of sustained contraction. The region score result of the third detection area is determined based on the peak value of rapid contraction, the endurance parameter of sustained contraction and the synergy result.

[0015] The corresponding comprehensive score is determined based on the regional score results of the first detection area, the regional score results of the second detection area, and the regional score results of the third detection area.

[0016] As an optional implementation, in the first aspect of the present invention, the detection and evaluation method further includes:

[0017] The surface electromyography (EMG) signal of the first detection area after filtering is processed to determine the corresponding contraction rise rate and peak decay rate; wherein, the contraction rise rate is the slope of the rise from the baseline to the peak, and the peak decay rate is the ratio of the decrease in amplitude to the time between two adjacent peaks;

[0018] The surface electromyography (EMG) signals of the second detection area after filtering are processed to determine the corresponding contraction stabilization rate and fatigue decay rate. The contraction stabilization rate is the fluctuation rate of the low-frequency component amplitude. The fatigue decay rate includes the ratio of the amplitude difference between the end and beginning of the endurance contraction to the time.

[0019] Data processing is performed on the surface electromyography signal of the second detection area after filtering to determine the synergistic contraction synchronization rate, wherein the synergistic contraction synchronization rate is the rate of change of the activation time difference between the high-frequency component of fast muscle and the low-frequency component of slow muscle.

[0020] The corresponding rate parameters in the first, second, and third detection areas are matched with the rate detection model to determine the current warning level.

[0021] As an optional implementation, in a first aspect of the present invention, matching the corresponding rate parameters in the first detection region, the second detection region, and the third detection region with a rate detection model to determine the current warning level includes:

[0022] The corresponding rate parameters in the first, second, and third detection areas are matched with the individual and group baselines in the rate detection model to determine the current warning level and the corresponding functional defect results.

[0023] As an optional implementation, in the first aspect of the present invention, after determining the score results of each detection region and the overall score result, the method further includes:

[0024] Output the scores for each region, and match the scores of each region with a pre-set knowledge database to obtain dynamic evaluation results for each detection region;

[0025] Determine the dynamic assessment results of each testing area of ​​the person to be tested and the rehabilitation training model, wherein the rehabilitation training model includes: a variety of standard rehabilitation training movements obtained by training the rehabilitation training model with the historical rehabilitation training plan of the historical rehabilitation person, and the historical rehabilitation training plan includes multiple rehabilitation training movements.

[0026] The dynamic evaluation results of each detection area are input into the rehabilitation training model, so that the rehabilitation training model selects standard rehabilitation training actions that match the dynamic evaluation results from the multiple standard rehabilitation training actions, and generates and outputs the final rehabilitation training plan based on the information of the person to be tested and the selected standard rehabilitation training actions.

[0027] The final rehabilitation training plan is sent to the corresponding display terminal.

[0028] As an optional implementation, in the first aspect of the present invention, the rehabilitation training model is constructed through the following steps:

[0029] Obtain historical rehabilitation training plans and dynamic assessment results of various testing areas of historical rehabilitation personnel, wherein the historical rehabilitation training plans include multiple rehabilitation training actions;

[0030] Feature recognition is performed on the dynamic assessment results to obtain the rehabilitation needs information corresponding to the dynamic assessment results;

[0031] Based on the rehabilitation needs information and dynamic assessment results, generate rehabilitation training actions corresponding to each type of rehabilitation needs information;

[0032] Based on the dynamic evaluation results of each detection area and their corresponding rehabilitation training actions, as well as the historical rehabilitation personnel information, the initial rehabilitation training model is trained to obtain the final rehabilitation training model.

[0033] As an optional implementation, in the first aspect of the present invention, training the initial rehabilitation training model based on the dynamic evaluation results of each detection area and its corresponding rehabilitation training actions, as well as the historical rehabilitation personnel information, to obtain the final rehabilitation training model includes:

[0034] The dynamic evaluation results of each detection area and the historical rehabilitation personnel information are input into the initial rehabilitation training model to generate the initial rehabilitation action corresponding to each dynamic evaluation result.

[0035] Based on the dynamic evaluation results of each detection area, determine the differences in movement and intensity between the corresponding initial rehabilitation movement and the corresponding standard rehabilitation movement;

[0036] Based on the differences in movement and intensity between the corresponding standard rehabilitation movements, the initial rehabilitation training model is trained to obtain the final rehabilitation training model.

[0037] A second aspect of this invention discloses a system for dynamic pelvic floor function detection and evaluation, comprising:

[0038] Acquisition module: used to acquire surface electromyography (SEMG) signals of corresponding detection areas in each detection stage through surface electromyography (SEMG) detection components, the surface electromyography (SEMG) detection components including a first detection component, a second detection component, and a third detection component; the detection areas include a first detection area, a second detection area, and a third detection area;

[0039] The conversion module is used to perform frequency domain conversion on the acquired surface electromyography signals to obtain corresponding frequency domain signals. It determines the frequency band of interest for each detection region based on the attribute characteristics of each detection region. The frequency band of interest includes the first frequency band of interest and the second frequency band of interest corresponding to the first detection region and the second detection region, respectively.

[0040] The first calculation module is used to calculate the first covariance matrix of the first detection region, the second detection region, and the third detection region in the first frequency band of interest; construct a first region filtering matrix based on the first covariance matrix; filter the surface electromyography (EMG) signal of the first detection region based on the first region filtering matrix; and extract the filtered EMG signal to obtain the first region feature group.

[0041] The second calculation module is used to calculate the second covariance matrix between the second detection region and the first detection region in the second frequency band of interest, determine the construction of the second region filtering matrix based on the second covariance matrix, filter the surface electromyography (EMG) signal of the second detection region based on the second region filtering matrix, and extract the filtered EMG signal to obtain the second region feature group.

[0042] The third calculation module is used to analyze the surface electromyography signal of the third detection area using an improved independent component analysis algorithm to obtain the fast muscle signal and slow muscle signal in the third detection area, and to determine the feature group of the third area based on the fast muscle signal and slow muscle signal.

[0043] Analysis module: Used to evaluate and calculate the first region feature group, the second region feature group, and the third region feature group using the pelvic floor assessment algorithm to determine the score results of each detection region and the comprehensive score result.

[0044] A third aspect of the present invention discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the method for dynamic pelvic floor function detection and evaluation disclosed in the first aspect of the present invention.

[0045] A fourth aspect of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the method for dynamic pelvic floor function detection and evaluation disclosed in the first aspect of the present invention.

[0046] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0047] The method for dynamic pelvic floor function detection and evaluation in this embodiment of the invention uses a surface electromyography (EMG) detection component to achieve accurate detection of various parts of the pelvic floor, and optimizes the EMG signals detected in each part through a specific filtering algorithm to improve the accuracy of the final identification results and provide a targeted basis for the formulation of subsequent rehabilitation plans. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating the method for dynamic pelvic floor function detection and evaluation disclosed in an embodiment of the present invention.

[0050] Figure 2 This is a schematic diagram of the regional score calculation process disclosed in an embodiment of the present invention;

[0051] Figure 3 This is a schematic diagram of the process for determining the warning level disclosed in an embodiment of the present invention;

[0052] Figure 4 This is a schematic diagram illustrating the rehabilitation training process disclosed in an embodiment of the present invention;

[0053] Figure 5 This is a schematic diagram of the structure of a system for dynamic pelvic floor function detection and evaluation provided in an embodiment of the present invention;

[0054] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] It should be noted that the terms "first," "second," "third," "fourth," etc., in the specification and claims of this invention are used to distinguish different objects, not to describe a specific order. The terms "comprising" and "having," and any variations thereof, in the embodiments of this invention are intended to cover non-exclusive inclusion. Exemplarily, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices.

[0057] Example 1

[0058] Please see Figure 1 , Figure 1 This is a flowchart illustrating the method for dynamic pelvic floor function detection and evaluation disclosed in an embodiment of the present invention. The execution entity of the method described in this embodiment is an execution entity composed of software and / or hardware. This execution entity can receive relevant information via wired or / or wireless means and can send certain instructions. It may also have certain processing and storage functions. This execution entity can control multiple devices, such as remote physical servers or cloud servers and related software, or local hosts or servers and related software that perform related operations on devices located in a certain location. In some scenarios, multiple storage devices can also be controlled; these storage devices may be placed in the same location as the devices or in different locations. Figure 1 As shown, the method for dynamic pelvic floor function testing and evaluation includes the following steps:

[0059] S101: Surface electromyography (SEMG) signals of corresponding detection areas in each detection stage are acquired using a surface electromyography (SEMG) detection component, which includes a first detection component, a second detection component, and a third detection component; the detection area includes a first detection area, a second detection area, and a third detection area.

[0060] S102: The acquired surface electromyography signal is converted into a frequency domain to obtain a corresponding frequency domain signal. The frequency band of interest of the frequency domain signal of each detection area is determined according to the attribute characteristics of each detection area. The frequency band of interest includes a first frequency band of interest and a second frequency band of interest corresponding to the first detection area and the second detection area, respectively.

[0061] S103: Calculate the first covariance matrix of the first detection region, the second detection region, and the third detection region in the first frequency band of interest; construct a first region filtering matrix based on the first covariance matrix; filter the surface electromyography signal of the first detection region based on the first region filtering matrix; and extract the filtered surface electromyography signal to obtain the first region feature group.

[0062] S104: Calculate the second covariance matrix between the second detection region and the first detection region in the second frequency band of interest; determine the second region filtering matrix based on the second covariance matrix; filter the surface electromyography (EMG) signal of the second detection region based on the second region filtering matrix; and extract the filtered EMG signal to obtain the second region feature group.

[0063] S105: An improved independent component analysis algorithm is used to analyze the surface electromyography signal in the third detection area to obtain the fast muscle signal and slow muscle signal in the third detection area, and the feature group of the third area is determined based on the fast muscle signal and slow muscle signal.

[0064] S106: The pelvic floor evaluation algorithm is used to evaluate and calculate the first region feature group, the second region feature group, and the third region feature group to determine the score results of each detection region and the comprehensive score results.

[0065] In this embodiment of the invention, the pelvic floor muscles can be divided into multiple regions when making specific regional divisions. Specifically, the pelvic floor muscles are usually divided into three main regions, with the urogenital hiatus and anal hiatus as the boundaries, corresponding to different functional areas of the pelvic cavity:

[0066] The anterior region (urogenital region) is located between the pubic symphysis and the ischial tuberosity. It includes the urethral sphincter, bulbospongiosus muscle, and superficial transverse perineal muscle, and mainly surrounds the urethra and vagina. It is responsible for controlling urination and supporting the anterior vaginal wall.

[0067] The central area, with the levator ani muscle at its core, is the main area of ​​the pelvic floor muscles. It supports the uterus, bladder, rectum and other core organs, and is a key structure to prevent pelvic organ prolapse.

[0068] The posterior region (anal region), surrounding the anus, includes the external anal sphincter and coccygeal muscle, and is mainly responsible for controlling defecation and maintaining the anus's closing and opening functions.

[0069] The various stages in this invention embodiment include a resting stage, a rapid contraction stage, a sustained contraction stage, and a durable contraction stage; their main purpose is to conduct a comprehensive assessment of the pelvic floor muscles. By acquiring surface electromyography (SEMG) signals from different detection areas through a surface electromyography (SEMG) detection component, it can accurately capture the electrophysiological activity of the pelvic floor muscles at each detection stage, diagnose pelvic floor muscle dysfunction such as muscle weakness and poor muscle coordination, and provide basic data for subsequent analysis.

[0070] This invention performs frequency domain conversion on surface electromyography signals and determines the frequency band of interest. This decomposes the electrophysiological signals of muscles into components of different frequencies, thereby assessing the activity patterns and frequency characteristics of muscles and helping to identify abnormal muscle activity patterns. Setting different frequency bands of interest for different detection areas allows for more targeted analysis of the characteristics of muscles in each area, improving the accuracy of the analysis.

[0071] By constructing a filtering matrix through covariance matrix calculation, the surface electromyography (EMG) signals of each detection area are filtered to remove noise and interference, improving signal clarity and stability. The filtered signal more accurately reflects the true state of the pelvic floor muscles, aiding in subsequent feature extraction and analysis, thereby enhancing the reliability of the detection and assessment. An improved independent component analysis (ICA) algorithm is used to analyze the EMG signals of the third detection area, separating fast-twitch and slow-twitch muscle signals. Fast-twitch and slow-twitch muscle signals play different roles in pelvic floor muscle function; clearly identifying their signals helps understand the contraction characteristics and endurance of the pelvic floor muscles, providing more detailed information for assessing pelvic floor muscle function, facilitating the determination of normal muscle function, and enabling the development of more precise rehabilitation training programs.

[0072] The pelvic floor assessment algorithm is used to evaluate and calculate the feature groups of each region, and the scores of each detection region and the comprehensive score are obtained, which can quantify the pelvic floor function.

[0073] Specifically, the filter matrix is ​​constructed as follows:

[0074] Preprocessing involves applying a 50Hz notch filter to the raw multi-channel signals to remove power frequency interference, followed by bandpass filtering to retain the effective frequency band for electromyography (EMG). This preliminary processing of the acquired raw signals removes interference signals, making subsequent analysis more accurate.

[0075] Covariance Matrix Construction: The covariance matrix of the multi-channel signals is calculated to reflect the signal correlation between channels. Three principal components (cumulative variance contribution rate > 90%) are extracted through eigenvalue decomposition to construct a spatial filtering matrix. Constructing the covariance matrix and spatial filtering matrix prepares for subsequent regional signal separation, using signal correlation analysis to separate signals from different regions.

[0076] Regional signal separation: For the anterior channel, the weight of high-frequency signals (>100Hz) is increased to suppress low-frequency crosstalk in the middle / posterior channels; for the middle channel, the gain of low-frequency signals (<50Hz) is increased to weaken high-frequency interference from fast-twitch muscle contractions in the anterior channel. This step achieves preliminary separation of signals from different regions, reducing signal interference between regions.

[0077] Independent Component Analysis Optimization: For the mixed muscle region (posterior region), an improved ICA algorithm is used to separate fast and slow muscle signals. The number of iterations is set to 150, and a tanh nonlinear function is selected. The separation effect is verified by muscle recruitment timing; fast muscle signals should be activated during the rapid contraction phase, while slow muscle signals should dominate during the sustained contraction phase, resulting in high separation accuracy. This step further refines the separation of fast and slow muscle signals in the mixed muscle region, addressing the problem of difficult-to-distinguish mixed signals in this area.

[0078] Implementation of differential measurement parameters for fast-twitch / slow-twitch muscle fibers:

[0079] Preamplitude zone (fast-twitch dominant zone) parameter design: During the rapid contraction phase, the peak electromyographic amplitude (the maximum amplitude value of each contraction), the rise time (the time interval from 10% to 90% of the peak amplitude), and the proportion of high-frequency components (the energy proportion in the 100-200Hz frequency band calculated by short-time Fourier transform) are measured. These parameters are used to evaluate the explosive power, activation speed, and functional status of fast-twitch muscles.

[0080] Mid-zone (slow-twitch muscle dominant zone) parameter design: During sustained contraction, contraction stability is measured (calculating the ratio of the standard deviation to the mean of the electromyographic signal during each contraction); during endurance contraction, fatigue index (the ratio of amplitude at the end of contraction to that at the beginning) and the proportion of low-frequency components (calculating the energy proportion in the 20-50Hz frequency band) are measured. These parameters are used to assess the sustained contraction stability, endurance, and recruitment of slow-twitch muscle fibers.

[0081] Posterior zone (mixed muscle zone) synergy analysis: The peak time difference of rapid contractions (the contraction initiation interval between the anterior and posterior zones) and the amplitude correlation of sustained contractions (signal correlation coefficient between the middle and posterior zones) are recorded simultaneously to assess the synergistic function of fast and slow muscle groups. This step comprehensively analyzes the synergistic effect of fast and slow muscle groups in the mixed muscle zone, providing a basis for a comprehensive assessment of pelvic floor muscle function.

[0082] An improved ICA algorithm was selected, with 150 iterations and a tanh nonlinear function. This improved ICA algorithm likely optimizes upon traditional algorithms like FastICA for the characteristics of electromyographic signals, such as adjusting the objective function and optimizing the iteration steps, to improve the accuracy and stability of signal separation.

[0083] Algorithm initialization: Set the initial parameters of the algorithm, such as the initial estimate of the mixing matrix and the learning rate. The choice of initial parameters will affect the convergence speed and separation effect of the algorithm, and can be reasonably set through multiple trials or based on experience.

[0084] Iterative calculation: The calculation is performed according to the iterative formula of the improved ICA algorithm. In each iteration, the input signal is transformed based on the currently estimated mixing matrix and separation matrix, and the transformed signal is processed using a nonlinear function (such as the tanh function) to update the separation matrix, gradually approximating the true unmixed matrix. After 150 iterations, the final separation matrix is ​​obtained.

[0085] Signal separation: The preprocessed mixed electromyographic signals are separated using the obtained separation matrix to obtain independent component signals. These independent component signals correspond to the fast and slow muscle activity signals in the posterior muscle zone.

[0086] Subsequent separation validation can be performed based on the separation effect measured by muscle recruitment timing.

[0087] Determine the contraction phase: Based on the experimental design and muscle physiology, identify the rapid contraction phase and the sustained contraction phase. During the experiment, these phases can be determined by recording the onset and end times of muscle contraction, or by using specific stimulus signals.

[0088] Feature extraction: For the separated independent component signals, features of the rapid contraction phase and the sustained contraction phase are extracted respectively. Time-domain features (such as root mean square value, zero-crossing rate, etc.) and frequency-domain features (such as power spectral density, intermediate frequency, etc.) can be used to describe the characteristics of the signal at different stages.

[0089] Temporal characteristics: The root mean square (RMS) value of the signal at each stage is calculated, reflecting the energy level of the signal. Fast-twitch muscles generate more energy during the rapid contraction phase, so the corresponding signal's RMS value at this stage should be relatively large; slow-twitch muscles dominate muscle activity during the sustained contraction phase, so their signal's RMS value at this stage should be relatively large.

[0090] Frequency domain characteristics: The time-domain signal is converted into a frequency-domain signal using Fourier transform, and the power spectral density is calculated. The frequency components of electromyographic signals differ between fast-twitch and slow-twitch muscle fibers; fast-twitch signals have relatively more high-frequency components, while slow-twitch signals have relatively more low-frequency components. The frequency characteristics of the signal at different stages can be analyzed based on the distribution of the power spectral density.

[0091] Temporal matching analysis: The extracted features are matched with the muscle recruitment time sequence. It is determined whether the separated signals conform to the pattern that fast-twitch muscle signals are activated during the rapid contraction phase (0-0.5 seconds) and slow-twitch muscle signals dominate during the sustained contraction phase (1-5 seconds). If a certain independent component signal has significant characteristics during the rapid contraction phase but weak characteristics during the sustained contraction phase, and matches known fast-twitch muscle activity characteristics, then the signal can be considered a fast-twitch muscle signal; conversely, if the signal has prominent characteristics during the sustained contraction phase and matches slow-twitch muscle activity characteristics, then it can be identified as a slow-twitch muscle signal.

[0092] More preferably, such as Figure 2 As shown, the pelvic floor assessment algorithm is used to evaluate and calculate the first region feature group, the second region feature group, and the third region feature group to determine the score results of each detection region and the comprehensive score result, including:

[0093] S1061: Determine the first region feature group in the first detection region in the corresponding detection stage. The first region feature group includes peak electromyographic amplitude, contraction rise time and high frequency signal ratio, so as to determine the region score result of the first detection region based on the peak electromyographic amplitude, contraction rise time and high frequency signal ratio.

[0094] S1062: Determine the second region feature group in the second detection region in the corresponding detection stage. The second region feature group includes the standard deviation of electromyography signal, the amplitude ratio at the end of endurance contraction to the initial stage, and the proportion of low-frequency signal, so as to determine the region score result of the second detection region based on the standard deviation of electromyography signal, the amplitude ratio at the end of endurance contraction to the initial stage, and the proportion of low-frequency signal.

[0095] S1063: Determine the third region feature group of the third detection area in the corresponding detection stage, the peak value of rapid contraction and the endurance parameter of sustained contraction of the third region feature group, determine the synergy result of fast and slow muscle in the third detection area based on the peak value of rapid contraction and the endurance parameter of sustained contraction, and determine the region score result of the third detection area based on the peak value of rapid contraction, the endurance parameter of sustained contraction and the synergy result.

[0096] S1064: Determine the corresponding comprehensive score based on the regional score results of the first detection area, the regional score results of the second detection area, and the regional score results of the third detection area.

[0097] In this embodiment of the invention, the first detection area focuses on features such as peak electromyographic amplitude, contraction rise time, and the proportion of high-frequency signals. Peak electromyographic amplitude directly reflects muscle contraction force, contraction rise time reflects muscle initiation speed, and the proportion of high-frequency signals is related to the muscle's rapid contraction ability (such as fast-twitch muscle fiber activity). Through quantitative analysis of these three dimensions, the explosive power, reaction speed, and fast-twitch dominant functional state of the muscles in this area can be accurately assessed, and problems such as insufficient muscle strength and slow contraction can be identified in a targeted manner.

[0098] The second detection area focuses on the standard deviation of electromyographic (EMG) signals, the amplitude ratio at the end of endurance contraction to that at the beginning, and the proportion of low-frequency signals. The standard deviation of EMG signals reflects the stability and coordination of muscle contraction; the amplitude ratio at the endurance contraction assesses muscle endurance (the ability to avoid fatigue); and the proportion of low-frequency signals is related to the sustained activity of slow-twitch muscle fibers. These characteristics can accurately capture the endurance level, contraction stability, and slow-twitch muscle-dominated functional state of the muscles in this area, effectively identifying abnormalities such as muscle fatigue and contraction incoordination.

[0099] The third testing area combines rapid contraction peak value, sustained contraction endurance parameters, and fast-twitch and slow-twitch muscle synergy. Rapid contraction peak value reflects the explosive power of fast-twitch muscles, sustained contraction endurance parameters reflect the endurance of slow-twitch muscles, and synergy results assess the efficiency of their coordination (e.g., the synergistic working ability of pelvic floor muscles in complex movements). By combining these three factors, the fast-twitch and slow-twitch muscle functions and synergy of the muscles in this area are comprehensively covered, avoiding the limitations of a single indicator and more accurately reflecting the overall functional state of the muscles.

[0100] The solutions of this invention comprehensively reflect pelvic floor function from the local to the overall (e.g., the first area focuses on fast-twitch muscle power, the second area focuses on slow-twitch muscle endurance, and the third area focuses on synergy, which together constitute the core dimensions of pelvic floor function); identify overall coordination problems that are difficult to detect due to abnormalities in a single area (e.g., pelvic floor disorders caused by poor overall synergy despite normal function in a certain area); and provide a more comprehensive basis for clinical diagnosis and treatment planning (e.g., when the overall score is low, the specific weak links can be located by combining the scores of each area).

[0101] The multi-region parameter fusion and comprehensive scoring method of this invention constructs a three-dimensional scoring system of region-muscle fiber-function:

[0102] Anterior zone: Fast-twitch muscle function score (weight 30%) = Peak contraction time × 0.6 + Rise time × 0.4; Middle zone: Slow-twitch muscle function score (weight 40%) = Sustained contraction stability × 0.5 + Endurance contraction fatigue index × 0.5; The overall score is improved by adjusting the proportion of high-frequency and low-frequency signals; Posterior zone: Mixed function score (weight 30%) = Peak fast-twitch time × 0.3 + Slow-twitch endurance × 0.3 + Synergistic contraction synchronicity × 0.4

[0103] The final comprehensive score directly reflects the functional status of each area (such as the specific ability deficiencies of the anterior zone fast muscle weakness, the middle zone slow muscle endurance insufficient, and the posterior zone external anal sphincter fast muscle response delay).

[0104] In addition to the parameters mentioned above, high-frequency power spectral density peaks can be used for the anterior region, which are more resistant to high-frequency noise; the coefficient of variation of contraction rise time can be used to assess the stability of fast-twitch muscle activation and reduce false positives caused by artifacts. For the mid-region, low-frequency power spectral density integrals are used instead of the original amplitude; slow-twitch muscle fatigue is assessed by the entropy value of endurance contraction (the lower the entropy value, the more stable the signal), and a sudden increase in entropy value indicates true fatigue (rather than noise interference).

[0105] More preferably, such as Figure 3 As shown, the detection and evaluation method further includes:

[0106] S1051: Perform data processing on the surface electromyography signal of the first detection area after filtering to determine the corresponding contraction rise rate and peak decay rate; wherein, the contraction rise rate is the slope of the rise from the baseline to the peak, and the peak decay rate is the ratio of the decrease amplitude to the time of two adjacent peaks;

[0107] S1052: Perform data processing on the surface electromyography signal of the second detection area after filtering to determine the corresponding contraction stability rate and fatigue decay rate, wherein the contraction stability rate is the fluctuation rate of the low-frequency component amplitude; the fatigue decay rate includes the amplitude difference between the end and the beginning of the endurance contraction and the time ratio.

[0108] S1053: Perform data processing on the surface electromyography signal of the second detection area after filtering to determine the synergistic contraction synchronization rate, wherein the synergistic contraction synchronization rate is the rate of change of the activation time difference between the high-frequency component of fast muscle and the low-frequency component of slow muscle.

[0109] S1054: Match the corresponding rate parameters in the first, second, and third detection areas with the rate detection model to determine the current warning level.

[0110] The solution proposed in this invention refines the analysis of pelvic floor muscle function from a dynamic perspective by extracting rate parameters, thus overcoming the limitations of static features (such as peak value and amplitude ratio).

[0111] The rate of contraction rise and peak decay rate in the first detection region:

[0112] The rate of contraction rise (the slope from baseline to peak) directly reflects the muscle's initiation efficiency from rest to exertion and can identify muscle contraction sluggishness; the rate of peak decay (the ratio of the decrease in adjacent peak values ​​to time) reflects the muscle's ability to maintain strength during continuous contraction and is used to determine whether the muscle is experiencing rapid fatigue or abnormal contraction continuity.

[0113] The second detection area includes the contraction stability rate and fatigue decay rate: the contraction stability rate (low-frequency component amplitude fluctuation rate) focuses on the stability of muscles during sustained contraction. Excessive fluctuation indicates poor contraction coordination (such as antagonistic imbalance between the pelvic floor muscles and surrounding muscle groups); the fatigue decay rate (difference between the amplitude at the end and the beginning of endurance contraction / time) quantifies the rate at which muscle endurance declines, and more accurately reflects the degree of fatigue of slow muscle fibers (such as the rate of progression of postpartum pelvic floor muscle insufficiency).

[0114] The third detection area measures the rate of change in the activation time difference between the high-frequency components of fast-twitch muscle fibers and the low-frequency components of slow-twitch muscle fibers. This directly assesses the synergistic efficiency of fast and slow muscle fibers in complex movements (such as coughing or lifting heavy objects). Abnormal synchronization rates indicate muscle coordination dysco-coordination (such as the asynchronous activation of fast and slow muscle fibers commonly seen in stress urinary incontinence). These parameters reveal the progression trend of muscle dysfunction from the perspective of dynamic change rate, rather than being limited to assessments of the static state.

[0115] The solution in this invention is based on a preset model (such as a normal range threshold or an abnormal progression rate threshold) and converts the rate parameter into a warning level (such as low, medium, or high risk). This allows users to quickly identify the urgency of the functional abnormality. For example, a high warning level indicates that muscle function is deteriorating rapidly and requires immediate intervention.

[0116] Targeted intervention timing indicators: Different warning levels correspond to different intervention strategies. For example, low-risk cases can be improved through home training, while high-risk cases require clinical treatment. This avoids a one-size-fits-all approach to all abnormalities and improves the timeliness and precision of intervention. Changes in rate parameters can be used to track treatment or training effects. For example, an increase in the rate of contraction rise and a decrease in the rate of fatigue decay after intervention indicate functional improvement, making the warning level a dynamic indicator for evaluating efficacy.

[0117] Specifically, the model can also automatically recommend and adjust training strategies based on the warning level:

[0118] Level 1 warning: Maintain basic training and increase the frequency of rate monitoring, such as assessment twice a week;

[0119] Level 2 warning: Strengthen training for abnormal rate parameters, such as low fast muscle rise rate, then add 0.5-second fast contraction training, 3 sets × 20 repetitions per day;

[0120] Level 3 warning: Initiate a personalized rehabilitation plan. If slow muscle fatigue declines rapidly, use interval training with 20 seconds of contraction and 10 seconds of rest to slow down the rate of fatigue progression. Quantify the rehabilitation effect through the above methods: compare the rate parameters before and after training to intuitively reflect the degree of improvement in fast muscle explosive power.

[0121] The solution in this embodiment of the invention can also perform regional comparison monitoring: synchronously compare the rate parameters of the anterior, middle and posterior regions to identify regional rate abnormalities: if only the rate of ascent of fast muscle in the anterior region is abnormal, while the rate of ascent of the middle and posterior regions is normal, it suggests that the problem is limited to the fast muscle in the anterior region; if the rate of fatigue decay of slow muscle in the middle region and the rate of synergistic synchronization in the posterior region are both abnormal, it suggests multi-regional linkage dysfunction.

[0122] More preferably, the step of matching the corresponding rate parameters in the first detection region, the second detection region, and the third detection region with the rate detection model to determine the current warning level includes:

[0123] The corresponding rate parameters in the first, second, and third detection areas are matched with the individual and group baselines in the rate detection model to determine the current warning level and the corresponding functional defect results.

[0124] The individual baseline in this invention is a benchmark established based on the historical test data of the same subject (such as rate parameters in a healthy state). By comparing the current rate parameters with the individual baseline, the dynamic trend of one's own function can be accurately captured. This approach avoids the problem of individual differences being masked by relying solely on group standards, and is particularly suitable for monitoring changes in pelvic floor function over time (such as postpartum rehabilitation tracking and early warning of functional decline in middle-aged and elderly people).

[0125] The population baseline is a normal range derived from statistics of a large number of people of the same type (same age, same sex, and without pelvic floor disorders). By comparing it with the population baseline, the degree of deviation of the examinee's current rate parameter from the overall population can be quickly determined. This cross-reference can clarify the general degree of abnormality of functional deficits and provide a basis for distinguishing between individual-specific fluctuations and pathological abnormalities.

[0126] By combining individual baselines with population baselines, a dual standard of longitudinal tracking and lateral reference was constructed, making the matching of rate parameters and the determination of early warning levels more scientific and operable. This system preserves individual differences while ensuring the reference value of the assessment results.

[0127] More preferably, such as Figure 4 As shown, after determining the scores for each detection area and the overall score, the process also includes:

[0128] S107: Output the scores for each region and match them with a pre-set knowledge database to obtain dynamic evaluation results for each detection region.

[0129] S108: Determine the dynamic evaluation results of each detection area of ​​the person to be tested and the rehabilitation training model, wherein the rehabilitation training model includes: a variety of standard rehabilitation training movements obtained by training the rehabilitation training model with the historical rehabilitation training plan of the historical rehabilitation person, and the historical rehabilitation training plan includes multiple rehabilitation training movements.

[0130] S109: Input the dynamic evaluation results of each detection area into the rehabilitation training model, so that the rehabilitation training model selects standard rehabilitation training actions that match the dynamic evaluation results from the multiple standard rehabilitation training actions, and generates and outputs the final rehabilitation training plan based on the information of the person to be tested and the selected standard rehabilitation training actions.

[0131] S1010: Send the final rehabilitation training plan to the corresponding display terminal.

[0132] The solution of this invention matches the scores of each region with a preset knowledge database, and the generated dynamic evaluation results are no longer limited to static score values, but combine information such as clinical cases, pathological features, and functional correspondences stored in the database to transform them into functional descriptions that can be directly understood.

[0133] The model is developed based on training plans from historical rehabilitation participants and covers a variety of standard rehabilitation training movements. Essentially, it utilizes machine learning to refine the correspondence between functional deficits and effective training programs. This model, based on real rehabilitation data, avoids the subjectivity of traditional training programs (such as reliance on experience) and ensures the effectiveness and safety of recommended movements.

[0134] By inputting dynamic assessment results into the model, the model selects training movements from standard movements that closely match the current functional deficit (e.g., when there is insufficient fast-twitch muscle function in the first region, rapid contraction training to improve explosive power is prioritized; when there is insufficient endurance in the second region, sustained contraction training is recommended). Simultaneously, by incorporating the individual's information (such as age, physical condition, and medical history), the intensity, frequency, and other parameters of the training movements are further optimized, ultimately generating a plan that truly achieves personalized rehabilitation training.

[0135] The final rehabilitation training plan output includes specific and standardized movements, avoiding the ambiguity of traditional verbal instructions or written descriptions. Patients can directly follow the plan, reducing the risk of ineffective training or injury due to incorrect movements. By receiving the plan through a display terminal (such as a mobile phone or tablet), patients can view and track their training progress at any time. Simultaneously, the terminal push notifications facilitate real-time adjustments to the plan based on monitoring data (such as electromyographic feedback during home training).

[0136] The method described in this invention directly links pelvic floor function testing with rehabilitation intervention through a process of evaluating results, generating training plans, and pushing them to the terminal. This avoids the disconnect that requires separate training plans to be developed after testing. As the dynamic evaluation results are updated in subsequent tests, the rehabilitation training model can be re-matched with training movements, allowing the plan to be adjusted in real time as function improves (e.g., gradually transitioning from basic endurance training to high-intensity coordination training). This ensures the continuity and relevance of the rehabilitation process and improves rehabilitation outcomes.

[0137] More preferably, the rehabilitation training model is constructed through the following steps:

[0138] Obtain historical rehabilitation training plans and dynamic assessment results of various testing areas of historical rehabilitation personnel, wherein the historical rehabilitation training plans include multiple rehabilitation training actions;

[0139] Feature recognition is performed on the dynamic assessment results to obtain the rehabilitation needs information corresponding to the dynamic assessment results;

[0140] Based on the rehabilitation needs information and dynamic assessment results, generate rehabilitation training actions corresponding to each type of rehabilitation needs information;

[0141] Based on the dynamic evaluation results of each detection area and its corresponding rehabilitation training actions, as well as the historical rehabilitation personnel information, the initial rehabilitation training model is trained to obtain the final rehabilitation training model. This rehabilitation training model can be a neural network model or a gradient boosting model.

[0142] The solution in this invention generates rehabilitation training movements corresponding to each rehabilitation need based on rehabilitation needs information. Essentially, it constructs a training movement library covering various pelvic floor dysfunctions. For example, for the need for insufficient endurance, the library includes movements such as sustained contraction and stepped endurance training; for the need for poor coordination, it includes movements such as alternating fast and slow muscle contractions and synchronized activation training. This structured correspondence enables the model to address diverse functional deficiencies in different individuals (such as pelvic floor muscle relaxation in postpartum women and urinary incontinence-related functional disorders in middle-aged and elderly men).

[0143] When training the model, historical rehabilitation patient information (such as age, physical condition, medical history, rehabilitation period, etc.) is incorporated. This allows the model to not only learn the correlation between functional deficits and movements, but also the impact of individual differences on training effectiveness. For example, the model may identify patterns such as younger patients having better tolerance for high-intensity training and patients with a history of lumbar spine disease needing to avoid certain movements that increase abdominal pressure. This allows the model to take individual characteristics into account in subsequent recommendations, further improving the safety and suitability of training plans.

[0144] The model's training process is based on a clear link between dynamic assessment results, rehabilitation needs, training movements, and individual information. Each recommended movement can be traced back to its corresponding rehabilitation needs and historical case studies. This interpretability facilitates user understanding and verification of the model's recommendations, and also helps patients trust and cooperate with the training plan. Specific training movements include: rehabilitation movements, movement time sets, number of movement sets, movement intensity, presence of resistance, and resistance force, etc.

[0145] As new historical rehabilitation data is continuously added, the model can be retrained to update the demand-action correspondence database and continuously optimize its recommendation logic. For example, when a new collaborative training action is proven to be more effective for a specific coordination deficiency, the model can quickly learn it and incorporate it into its recommendations, ensuring that the model remains adaptable to the latest rehabilitation techniques. This enables precise action recommendations.

[0146] More preferably, the step of training the initial rehabilitation training model based on the dynamic evaluation results of each detection area and its corresponding rehabilitation training actions, as well as the historical rehabilitation personnel information, to obtain the final rehabilitation training model includes:

[0147] The dynamic evaluation results of each detection area and the historical rehabilitation personnel information are input into the initial rehabilitation training model to generate the initial rehabilitation action corresponding to each dynamic evaluation result.

[0148] Based on the dynamic evaluation results of each detection area, determine the differences in movement and intensity between the corresponding initial rehabilitation movement and the corresponding standard rehabilitation movement;

[0149] Based on the differences in movement and intensity between the corresponding standard rehabilitation movements, the initial rehabilitation training model is trained to obtain the final rehabilitation training model.

[0150] This invention compares the initial rehabilitation movements generated by the initial rehabilitation training model with standard rehabilitation movements (effective movements validated by historical data) to accurately identify differences in movement details (such as contraction angle and force application points) and intensity parameters (such as contraction duration, interval time, and number of repetitions). This quantification of differences provides a clear correction target for model optimization, avoiding the blindness of model training.

[0151] The training model uses standard rehabilitation movements as a benchmark to ensure that the final model outputs movements that consistently align with clinically validated standard paradigms. For example, for rehabilitation needs related to insufficient fast-twitch muscle power, the standard movement might be a rapid contraction for 3 seconds followed by a 2-second relaxation, repeated 10 times. If the initial model generates a movement of a contraction for 5 seconds followed by a 1-second relaxation, parameters can be adjusted through comparison to ensure that the recommended movements strictly match the standard, thereby guaranteeing the stability of training effects.

[0152] The essence of differential training is to enable the model to continuously learn how to generate recommendations that are closer to the standard movements from dynamic assessment results. For example, when the model repeatedly deviates significantly from the standard movements due to biases in recognizing the need for insufficient slow-twitch muscle endurance, the training process will focus on optimizing the feature recognition weights for such needs. This will gradually improve the model's sensitivity to specific rehabilitation needs, ultimately achieving a precise mapping from assessment results to movement recommendations.

[0153] When training with historical rehabilitation data, comparative analysis can further refine the adaptation and adjustment patterns of different individuals to the same standard movement. For example, in slow muscle endurance training for elderly patients, the intensity of the standard movement needs to be reduced. By learning the differences between the initial movement and the standard movement adapted to this type of individual, the model will gradually master the correction coefficient of the intensity parameter due to age, so that the recommended movement takes into account individual specificities while maintaining standardization.

[0154] By comparing the differences between the initial action and the standard action, the deviation points (such as incorrect action type or unreasonable intensity parameters) can be located. This allows the model training to focus on key dimensions with significant differences instead of adjusting all parameters indiscriminately, thus greatly improving training efficiency.

[0155] Each model optimization can be mapped to a specific point of difference. For example, the time parameter is corrected for differences in contraction duration, and the motion description features are adjusted for deviations in the force application location, making the model's decision-making logic interpretable and traceable. This transparent training process facilitates clinicians' verification of the model's reliability and provides a clear direction for further model improvement. For instance, for recurring differences, the problem can be traced back to the feature recognition stage.

[0156] In the electrode circuit of this invention, a weak 500Hz test current (<10μA) is integrated. The signal quality is judged by measuring the electrode-skin contact impedance: when the impedance is <5kΩ, the indicator light is green (signal qualified); when the impedance is 5-10kΩ, a slight vibration is emitted as a prompt (electrode position needs to be adjusted); when the impedance is >10kΩ, an alarm is triggered (skin needs to be cleaned again or electrode pads need to be replaced), ensuring that the signal path is stable before acquisition.

[0157] The method for dynamic pelvic floor function detection and evaluation in this embodiment of the invention uses a surface electromyography (EMG) detection component to achieve accurate detection of various parts of the pelvic floor, and optimizes the EMG signals detected in each part through a specific filtering algorithm to improve the accuracy of the final identification results and provide a targeted basis for the formulation of subsequent rehabilitation plans.

[0158] Example 2

[0159] Please see Figure 5 , Figure 5This is a schematic diagram of the system for dynamic pelvic floor function detection and evaluation disclosed in an embodiment of the present invention. Figure 5 As shown, the system for dynamic pelvic floor function testing and evaluation may include:

[0160] Acquisition module 21: used to acquire surface electromyography (SEMG) signals of corresponding detection areas in each detection stage through surface electromyography (SEMG) detection components, wherein the surface electromyography (SEMG) detection components include a first detection component, a second detection component, and a third detection component; the detection areas include a first detection area, a second detection area, and a third detection area;

[0161] Conversion module 22: used to perform frequency domain conversion on the acquired surface electromyography signal to obtain the corresponding frequency domain signal, and to determine the frequency band of interest of the frequency domain signal of each detection area according to the attribute characteristics of each detection area. The frequency band of interest includes the first frequency band of interest and the second frequency band of interest corresponding to the first detection area and the second detection area, respectively.

[0162] First calculation module 23: used to calculate the first covariance matrix of the first detection region, the second detection region, and the third detection region in the first frequency band of interest; construct a first region filtering matrix based on the first covariance matrix; filter the surface electromyography signal of the first detection region based on the first region filtering matrix; and extract the filtered surface electromyography signal to obtain the first region feature group.

[0163] The second calculation module 24 is used to calculate the second covariance matrix between the second detection region and the first detection region in the second frequency band of interest, determine the construction of the second region filtering matrix based on the second covariance matrix, filter the surface electromyography signal of the second detection region based on the second region filtering matrix, and extract the filtered surface electromyography signal to obtain the second region feature group.

[0164] The third calculation module 25 is used to analyze the surface electromyography signal of the third detection area using an improved independent component analysis algorithm to obtain the fast muscle signal and slow muscle signal in the third detection area, and to determine the feature group of the third area based on the fast muscle signal and slow muscle signal.

[0165] Analysis module 26: Used to evaluate and calculate the first region feature group, the second region feature group and the third region feature group using the pelvic floor assessment algorithm to determine the score results of each detection region and the comprehensive score results.

[0166] The method for dynamic pelvic floor function detection and evaluation in this embodiment of the invention uses a surface electromyography (EMG) detection component to achieve accurate detection of various parts of the pelvic floor, and optimizes the EMG signals detected in each part through a specific filtering algorithm to improve the accuracy of the final identification results and provide a targeted basis for the formulation of subsequent rehabilitation plans.

[0167] Example 3

[0168] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. The electronic device can be a computer, a server, etc. Of course, in certain cases, it can also be a mobile phone, tablet computer, monitoring terminal, or other smart device, as well as an image acquisition device with processing capabilities. Figure 6 As shown, the electronic device may include:

[0169] Memory 510 storing executable program code;

[0170] Processor 520 coupled to memory 510;

[0171] The processor 520 calls the executable program code stored in the memory 510 to execute some or all of the steps in the method for dynamic pelvic floor function detection and evaluation in Embodiment 1.

[0172] This invention discloses a computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps in the method for dynamic pelvic floor function detection and evaluation in Embodiment 1.

[0173] This invention also discloses a computer program product, wherein when the computer program product is run on a computer, the computer performs some or all of the steps in the method for dynamic pelvic floor function detection and evaluation in Embodiment 1.

[0174] This invention also discloses an application publishing platform, which is used to publish computer program products. When the computer program products are run on a computer, the computer performs some or all of the steps in the method for dynamic pelvic floor function detection and evaluation in Embodiment 1.

[0175] In various embodiments of the present invention, it should be understood that the sequence number of each process does not necessarily imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0176] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they can be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0177] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0178] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several requests to cause a computer device (which can be a personal computer, server, or network device, specifically a processor in the computer device) to execute some or all of the steps of the methods described in the various embodiments of the present invention.

[0179] In the embodiments provided by this invention, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information.

[0180] Those skilled in the art will understand that some or all of the steps in the various methods of the embodiments described can be implemented by a program instructing related hardware. This program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0181] The above provides a detailed description of the method, system, electronic device, and storage medium for dynamic pelvic floor function detection and evaluation disclosed in the embodiments of the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for dynamic pelvic floor function testing and evaluation, characterized in that, include: The acquired surface electromyography (SEMG) signals are frequency-domain converted to obtain corresponding frequency domain signals. The frequency bands of interest for each detection region are determined based on the attribute characteristics of each region. These frequency bands of interest include a first frequency band of interest and a second frequency band of interest corresponding to the first and second detection regions, respectively. The SEMG signals are detected by a SEMG detection component in corresponding detection regions during each detection stage. The SEMG detection component includes a first detection component, a second detection component, and a third detection component. The detection regions include a first detection region, a second detection region, and a third detection region. The detection stages include a resting stage, a rapid contraction stage, a sustained contraction stage, and a durable contraction stage. The first detection region is located between the pubic symphysis and the ischial tuberosity, and includes the urethral sphincter, bulbospongiosus muscle, and superficial transverse perineal muscle. The second detection region includes the levator ani muscle. The third detection region surrounds the anus and includes the external anal sphincter and the coccygeal muscle. The detection parameters for the rapid shrinkage phase are detected in the first detection area, the corresponding detection parameters for the continuous shrinkage phase and the durable shrinkage phase are detected in the second detection area, and the corresponding detection parameters for the rapid shrinkage phase, the continuous shrinkage phase and the durable shrinkage phase are detected in the third detection area. Calculate the first covariance matrix of the first detection region, the second detection region, and the third detection region in the first frequency band of interest; construct a first region filtering matrix based on the first covariance matrix; filter the surface electromyography (EMG) signal of the first detection region based on the first region filtering matrix; and extract the filtered EMG signal to obtain the first region feature group. Calculate the second covariance matrix between the second detection region and the first detection region in the second frequency band of interest, and determine the second region filtering matrix based on the second covariance matrix; The surface electromyography (EMG) signal of the second detection region is filtered according to the second region filtering matrix, and the filtered EMG signal is extracted to obtain the second region feature group. An improved independent component analysis algorithm is used to analyze the surface electromyography signal in the third detection region to obtain the fast-twitch and slow-twitch signals in the third detection region, and the feature group of the third region is determined based on the fast-twitch and slow-twitch signals. The pelvic floor assessment algorithm is used to evaluate and calculate the feature groups of the first, second, and third regions to determine the scores of each detection region and the overall score.

2. The method for dynamic pelvic floor function testing and evaluation as described in claim 1, characterized in that, The pelvic floor assessment algorithm is used to evaluate and calculate the feature groups of the first, second, and third regions to determine the score results for each detection region and the overall score result, including: A first region feature group is determined in the first detection region of the corresponding detection stage. The first region feature group includes peak electromyographic amplitude, contraction rise time and high frequency signal ratio, so as to determine the region score result of the first detection region based on peak electromyographic amplitude, contraction rise time and high frequency signal ratio. The second region feature group in the second detection area of ​​the corresponding detection stage is determined. The second region feature group includes the standard deviation of electromyography signal, the amplitude ratio at the end of endurance contraction to the initial stage, and the proportion of low-frequency signal. The region score result of the second detection area is determined based on the standard deviation of electromyography signal, the amplitude ratio at the end of endurance contraction to the initial stage, and the proportion of low-frequency signal. The third region feature group of the third detection area in the corresponding detection stage is determined. The peak value of rapid contraction and the endurance parameter of sustained contraction of the third region feature group are used to determine the synergy result of fast and slow muscle groups in the third detection area based on the peak value of rapid contraction and the endurance parameter of sustained contraction. The region score result of the third detection area is determined based on the peak value of rapid contraction, the endurance parameter of sustained contraction and the synergy result. The corresponding comprehensive score is determined based on the regional score results of the first detection area, the regional score results of the second detection area, and the regional score results of the third detection area.

3. The method for dynamic pelvic floor function testing and evaluation as described in claim 1, characterized in that, The detection and evaluation method further includes: The surface electromyography (EMG) signal of the first detection area after filtering is processed to determine the corresponding contraction rise rate and peak decay rate; wherein, the contraction rise rate is the slope of the rise from the baseline to the peak, and the peak decay rate is the ratio of the decrease in amplitude to the time between two adjacent peaks; The surface electromyography (EMG) signals of the second detection area after filtering are processed to determine the corresponding contraction stabilization rate and fatigue decay rate. The contraction stabilization rate is the fluctuation rate of the low-frequency component amplitude. The fatigue decay rate includes the ratio of the amplitude difference between the end and beginning of the endurance contraction to the time. Data processing is performed on the surface electromyography signal of the second detection area after filtering to determine the synergistic contraction synchronization rate, wherein the synergistic contraction synchronization rate is the rate of change of the activation time difference between the high-frequency component of fast muscle and the low-frequency component of slow muscle. The corresponding rate parameters in the first, second, and third detection areas are matched with the rate detection model to determine the current warning level.

4. The method for dynamic pelvic floor function testing and evaluation as described in claim 3, characterized in that, The step of matching the corresponding rate parameters in the first, second, and third detection regions with the rate detection model to determine the current warning level includes: The corresponding rate parameters in the first, second, and third detection areas are matched with the individual and group baselines in the rate detection model to determine the current warning level and the corresponding functional defect results.

5. The method for dynamic pelvic floor function testing and evaluation as described in claim 3, characterized in that, After determining the scores for each detection area and the overall score, the following steps are also included: Output the scores for each region, and match the scores of each region with a pre-set knowledge database to obtain dynamic evaluation results for each detection region; Determine the dynamic assessment results of each testing area of ​​the person to be tested and the rehabilitation training model, wherein the rehabilitation training model includes: a variety of standard rehabilitation training movements obtained by training the rehabilitation training model with the historical rehabilitation training plan of the historical rehabilitation person, and the historical rehabilitation training plan includes multiple rehabilitation training movements. The dynamic evaluation results of each detection area are input into the rehabilitation training model, so that the rehabilitation training model selects standard rehabilitation training actions that match the dynamic evaluation results from the multiple standard rehabilitation training actions, and generates and outputs the final rehabilitation training plan based on the information of the person to be tested and the selected standard rehabilitation training actions. The final rehabilitation training plan is sent to the corresponding display terminal.

6. The method for dynamic pelvic floor function testing and evaluation as described in claim 5, characterized in that, The rehabilitation training model is constructed through the following steps: Obtain historical rehabilitation training plans and dynamic assessment results of various testing areas of historical rehabilitation personnel, wherein the historical rehabilitation training plans include multiple rehabilitation training actions; Feature recognition is performed on the dynamic assessment results to obtain the rehabilitation needs information corresponding to the dynamic assessment results; Based on the rehabilitation needs information and dynamic assessment results, generate rehabilitation training actions corresponding to each type of rehabilitation needs information; Based on the dynamic evaluation results of each detection area and their corresponding rehabilitation training actions, as well as the historical rehabilitation personnel information, an initial rehabilitation training model is trained to obtain the final rehabilitation training model.

7. The method for dynamic pelvic floor function testing and evaluation as described in claim 6, characterized in that, The process of training the initial rehabilitation training model based on the dynamic evaluation results of each detection area and its corresponding rehabilitation training actions, as well as the historical rehabilitation personnel information, to obtain the final rehabilitation training model includes: The dynamic evaluation results of each detection area and the historical rehabilitation personnel information are input into the initial rehabilitation training model to generate the initial rehabilitation action corresponding to each dynamic evaluation result. Based on the dynamic evaluation results of each detection area, determine the differences in movement and intensity between the corresponding initial rehabilitation movement and the corresponding standard rehabilitation movement; Based on the differences in movement and intensity between the corresponding standard rehabilitation movements, the initial rehabilitation training model is trained to obtain the final rehabilitation training model.

8. A system for dynamic pelvic floor function testing and evaluation, characterized in that, include: The conversion module is used to perform frequency domain conversion on the acquired surface electromyography (SEMG) signals to obtain corresponding frequency domain signals. It determines the frequency band of interest (MOI) for each detection region based on the attribute characteristics of each region. The MOI includes a first MOI and a second MOI corresponding to the first and second detection regions, respectively. The SEMG signals are detected by the SEMG detection components in corresponding detection regions during each detection stage. The SEMG detection components include a first detection component, a second detection component, and a third detection component. The detection regions include a first detection region, a second detection region, and a third detection region. The detection stages include a resting stage, a rapid contraction stage, a sustained contraction stage, and a durable contraction stage. The first detection region is located between the pubic symphysis and the ischial tuberosity, including the urethral sphincter, bulbospongiosus muscle, and superficial transverse perineal muscle. The second detection region includes the levator ani muscle. The third detection region surrounds the anus, including the external anal sphincter and the coccygeal muscle. The detection parameters for the rapid shrinkage phase are detected in the first detection area, the corresponding detection parameters for the continuous shrinkage phase and the durable shrinkage phase are detected in the second detection area, and the corresponding detection parameters for the rapid shrinkage phase, the continuous shrinkage phase and the durable shrinkage phase are detected in the third detection area. The first calculation module is used to calculate the first covariance matrix of the first detection region, the second detection region, and the third detection region in the first frequency band of interest; construct a first region filtering matrix based on the first covariance matrix; filter the surface electromyography (EMG) signal of the first detection region based on the first region filtering matrix; and extract the filtered EMG signal to obtain the first region feature group. The second calculation module is used to calculate the second covariance matrix between the second detection region and the first detection region in the second frequency band of interest, and to determine the second region filtering matrix based on the second covariance matrix. The surface electromyography (EMG) signal of the second detection region is filtered according to the second region filtering matrix, and the filtered EMG signal is extracted to obtain the second region feature group. The third calculation module is used to analyze the surface electromyography signal of the third detection area using an improved independent component analysis algorithm to obtain the fast muscle signal and slow muscle signal in the third detection area, and to determine the feature group of the third area based on the fast muscle signal and slow muscle signal. Analysis module: Used to evaluate and calculate the first region feature group, the second region feature group, and the third region feature group using the pelvic floor assessment algorithm to determine the score results of each detection region and the comprehensive score result.

9. An electronic device, characterized in that, include: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for dynamic pelvic floor function detection and evaluation as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program causes a computer to perform the method for dynamic pelvic floor function detection and evaluation as described in any one of claims 1 to 7.

Images