A method and system for detecting and evaluating electroshock simulation training

Abstract

The present invention discloses a method and system for detecting and evaluating electroshock simulation training, relating to the technical field of electroshock simulation training, and comprising the following steps: selecting an electrostimulation instrument, applying a preset controllable electrostimulation signal to a specified muscle area, and simulating the electrical signal of a real external environment under precise control conditions; directly monitoring the electric field change of muscle tissue within a demarcated area through a micro field effect sensor to reflect the diffusion trend of charges in real time; applying signal processing technology to preprocess the electric field change data obtained in real time, then extracting key features reflecting charge accumulation, and deeply analyzing the extracted key features. By monitoring the electric field change in muscle tissue in real time, the present invention uses a deep learning model to identify the risk of charge accumulation in advance, and automatically adjusts the pulse duty ratio when the risk appears, effectively preventing abnormal polarization and electrolytic reactions, and reducing the risks of tissue damage, cell necrosis and nerve damage.

Description

Technical Field

[0001] The present invention relates to the technical field of electroshock simulation training, and particularly to a method and system for electroshock simulation training detection and evaluation. Background Art

[0002] Electroshock simulation training detection is an experimental method based on electrical stimulation, which is commonly used in fields such as neuroscience, psychology, and biomedical engineering to study the response of the nervous system to electrical stimulation or for neurorehabilitation training. In this method, researchers use controllable electrical stimulation to simulate electrical signals in the external environment, stimulate specific regions of the nerves, muscles, or brain of the test subject to induce specific physiological or behavioral responses, and record relevant data through biosensors or other detection devices. This technology can be used to evaluate nerve function, detect nerve damage, train nerve adaptive recovery, or study an individual's sensitivity to electrical stimulation and stress response.

[0003] The existing technology has the following deficiencies:

[0004] When using controllable electrical stimulation to simulate external electrical signals and applying them to the muscles of the test subject, if the charge cannot diffuse normally and causes charge accumulation, resulting in too high a local potential difference, it may trigger abnormal polarization effects or electrolytic reactions, causing a series of physiological abnormalities such as cell membrane ion channel disorders and metabolic imbalances. Since the existing technology is still difficult to monitor charge accumulation in real time and perform effective adaptive regulation, once the above situation occurs, it often leads to tissue damage, electric burns, cell necrosis, and even further evolves into long-term damage to the nervous system or chronic pain syndrome, thus bringing serious risks to the patient's rehabilitation training and daily function recovery.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The object of the present invention is to provide a method and system for electroshock simulation training detection and evaluation. By real-time monitoring of the electric field changes in muscle tissue, using a deep learning model to identify the risk of charge accumulation in advance, and automatically adjusting the pulse duty cycle when the risk appears, it effectively prevents abnormal polarization and electrolytic reactions, and reduces the risks of tissue damage, cell necrosis, and nerve damage. This system based on multi-level data processing and adaptive regulation can not only ensure the uniform diffusion of charges in the muscle, but also dynamically optimize the electrical stimulation parameters during the treatment process, so that the rehabilitation training and other electrical stimulation treatments are more accurate and safe, which helps to improve the long-term rehabilitation effect of patients, in order to solve the problems in the above background art.

[0007] To achieve the above object, the present invention provides the following technical solution: An electroshock simulation training detection and evaluation method, comprising the following steps:

[0008] Select an electrostimulation instrument, apply a pre-set controllable electrostimulation signal to a specified muscle area, and simulate the electrical signal of the real external environment under precise control conditions;

[0009] Directly monitor the electric field change of the muscle tissue within the defined area through a micro field effect sensor to reflect the diffusion trend of charges in real time;

[0010] Apply signal processing technology to preprocess the real-time obtained electric field change data, then extract the key features reflecting charge accumulation, deeply analyze the extracted key features, characterize the charge accumulation risk, and construct a standardized feature vector input into the deep learning model;

[0011] Input the constructed feature vector into a pre-trained and fully verified deep learning model, analyze the current input real-time feature vector, and output the prediction result of the potential charge accumulation risk in the charge diffusion trend, so as to realize the early identification and warning of the charge accumulation risk;

[0012] Once the deep learning model issues a warning of accumulation risk, it automatically enters the real-time risk assessment mode, and immediately accurately calculates the real-time change value of the potential difference between different positions within the defined area through the data provided by the micro field effect sensor to quantify the current severity of charge accumulation;

[0013] After quantitatively calculating the potential difference, automatically execute the pulse duty cycle adjustment action according to the intelligent regulation strategy. When the potential difference exceeds the preset potential difference threshold, extend the "low" state time of the pulse signal, that is, increase the pulse interval, reduce the total charge injection per unit time, and relieve the local accumulation degree.

[0014] Preferably, the defined area refers to the tissue range that is pre-determined and directly affected by the electrode or affected by charge accumulation during the muscle electrostimulation experiment or treatment, and is accurately selected according to the anatomical structure, electrostimulation target, clinical treatment requirements or experimental design.

[0015] Preferably, extract the features reflecting the charge accumulation situation. Among them, the extracted features include the time required for the potential to return to the baseline level and the cumulative value of the potential change rate. Deeply analyze the time required for the potential to return to the baseline level and the cumulative value of the potential change rate, and respectively generate the potential regression delay reference value and the charge accumulation rate reference value. Characterize the charge accumulation risk through the potential regression delay reference value and the charge accumulation rate reference value, and construct a standardized feature vector input into the deep learning model.

[0016] Preferably, the constructed potential regression delay reference value and charge accumulation rate reference value are input into a pre-trained and well-verified deep learning model to analyze the currently input real-time feature vector. An accumulation evaluation coefficient is output through the deep learning model, and based on the accumulation evaluation coefficient, early identification and warning of potential charge accumulation risks in the charge diffusion trend are carried out.

[0017] Preferably, the accumulation evaluation coefficient generated when predicting potential charge accumulation risks in the charge diffusion trend through the deep learning model is compared and analyzed with a preset accumulation evaluation coefficient reference threshold to conduct early identification and warning of charge accumulation risks. The specific steps are as follows:

[0018] If the accumulation evaluation coefficient is greater than the accumulation evaluation coefficient reference threshold, a risk signal is generated, indicating that there is a risk of charge accumulation in the electric field change of the muscle tissue within the designated area. At this time, an accumulation risk warning is issued; if the accumulation evaluation coefficient is less than or equal to the accumulation evaluation coefficient reference threshold, a normal change signal is generated, indicating that the electric field of the muscle tissue within the designated area is changing normally. At this time, no risk warning is issued.

[0019] Preferably, the real-time change value of the potential difference between different positions inside the designated area is accurately calculated through the data provided by the micro field effect sensor to quantify the current severity of charge accumulation. The specific steps are as follows:

[0020] When the deep learning model issues an accumulation risk warning, it automatically enters the real-time risk assessment mode, measures the potential data of different positions within the designated area using the micro field effect sensor, calculates the potential difference within the designated area through the instantaneous electric field change value collected by the micro field effect sensor, and conducts quantitative analysis in combination with the accumulation evaluation coefficient to generate a charge accumulation severity index to judge the severity of charge accumulation. The calculation formula of the charge accumulation severity index is as follows:

[0021] ,

[0022] Where: is the charge accumulation severity index, is the accumulation evaluation coefficient output by the deep learning model, which is used to measure the risk degree of charge accumulation, is the accumulation evaluation coefficient reference threshold, is the maximum potential difference between different positions inside the designated area, indicating the degree of local polarization caused by charge accumulation in the designated area. The calculation expression is:

[0023] ,

[0024] Where: and are the maximum and minimum electric field intensities within the designated area respectively.

[0025] Preferably, the pulse duty ratio adjustment action is automatically executed according to the intelligent control strategy, and the specific steps are as follows:

[0026] According to the calculated charge accumulation severity index , an adaptive pulse duty ratio control strategy is adopted to ensure uniform charge diffusion, and the control expression is as follows:

[0027] ,

[0028] Where: is the adjusted pulse duty ratio, which is used to reduce the influence of charge accumulation, is the reference pulse duty ratio, that is, the default pulse duty ratio under normal conditions, is the adjustment coefficient, which controls the sensitivity of the duty ratio adjustment.

[0029] The electric shock simulation training detection and evaluation system includes an electric stimulation signal application module, an electric field monitoring module, a signal processing and feature extraction module, a deep learning risk prediction module, a real-time risk assessment module, and an adaptive pulse regulation module;

[0030] The electric stimulation signal application module applies a pre-set controllable electric stimulation signal to a specified muscle area to simulate the electric signal in a real external environment under precise control conditions;

[0031] The electric field monitoring module directly monitors the electric field change of the muscle tissue in the delimited area through a micro field effect sensor, and reflects the charge diffusion trend in real time;

[0032] The signal processing and feature extraction module applies signal processing technology to preprocess the real-time acquired electric field change data, then extracts the key features reflecting charge accumulation, deeply analyzes the extracted key features, characterizes the charge accumulation risk, and constructs a standardized feature vector for input into the deep learning model at the same time;

[0033] The deep learning risk prediction module inputs the constructed feature vector into a pre-trained and well-verified deep learning model, analyzes the current input real-time feature vector, and outputs the potential charge accumulation risk prediction result in the charge diffusion trend, realizing the early identification and warning of the charge accumulation risk;

[0034] The real-time risk assessment module, once the deep learning model issues an accumulation risk warning, automatically enters the real-time risk assessment mode, and immediately accurately calculates the real-time change value of the potential difference between different positions inside the delimited area through the data provided by the micro field effect sensor to quantify the current charge accumulation severity;

[0035] The adaptive pulse regulation module automatically performs the pulse duty cycle adjustment action according to the intelligent regulation strategy after quantitatively calculating the potential difference. When the potential difference exceeds the preset potential difference threshold, it extends the "low" state time of the pulse signal, that is, increases the pulse gap, reduces the total amount of charge injection per unit time, and alleviates the degree of local accumulation.

[0036] In the above technical solution, the technical effects and advantages provided by the present invention are as follows:

[0037] By real-time monitoring of the electric field changes in muscle tissue, using a deep learning model to identify the risk of charge accumulation in advance, and automatically adjusting the pulse duty cycle when the risk appears, it effectively prevents abnormal polarization and electrolysis reactions, and reduces the risks of tissue damage, cell necrosis and nerve damage. This system based on multi-level data processing and adaptive regulation can not only ensure the uniform diffusion of charges in the muscle, but also dynamically optimize the electrical stimulation parameters during the treatment process, making the rehabilitation training and other electrical stimulation treatments more accurate and safe, and contributing to improving the long-term rehabilitation effect of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0039] Figure 1 It is a method flow chart of a method for detecting and evaluating an electric shock simulation training of the present invention.

[0040] Figure 2 It is a module schematic diagram of a system for detecting and evaluating an electric shock simulation training of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] Now, the exemplary embodiments will be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these exemplary embodiments are provided so that the present disclosure will be more thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art.

[0042] The present invention provides a method for detecting and evaluating an electric shock simulation training as Figure 1 shown, including the following steps:

[0043] Select an electrical stimulation instrument, and apply a preset controllable electrical stimulation signal to the specified muscle area through externally attached or implanted electrodes to simulate the electrical signal in a real external environment under precise control conditions;

[0044] Stimulation parameters include stimulation voltage, current, pulse frequency, pulse waveform, and initial duty cycle. The initial parameter settings are optimized based on the physiological characteristics of the subject, treatment objectives, and safety requirements. Under precise control conditions, electrical signals simulating the real external environment are generated, laying the foundation for subsequent charge monitoring, feature extraction, and dynamic regulation.

[0045] The electric field changes in the muscle tissue within the defined area are directly monitored through a micro field-effect sensor, which can reflect the diffusion trend of charges in real time;

[0046] The defined area refers to a specific tissue range that is pre-determined during muscle electrical stimulation experiments or treatments and is directly affected by the electrodes or may be influenced by charge accumulation. This area is usually precisely selected based on anatomical structures, the objectives of electrical stimulation, clinical treatment requirements, or experimental designs.

[0047] Based on anatomical structures means that it is necessary to refer to the distribution of muscles, nerves, blood vessel directions, and surrounding tissues to select the most suitable electrode placement positions to ensure that the stimulation signals can effectively act on the target tissues while avoiding unnecessary side effects or interference. Based on the objectives of electrical stimulation, it means selecting the best stimulation area according to specific electrical stimulation application scenarios (such as muscle rehabilitation, nerve regulation, sports enhancement, etc.). For example, for the motor rehabilitation of hemiplegic patients, the quadriceps femoris or the flexor muscles of the upper limb may be selected as the defined area to enhance their contraction ability. Based on clinical treatment requirements, it means that in medical applications, according to the disease characteristics of patients, such as muscle atrophy, nerve injury, or pain management, the most suitable area to improve symptoms is selected. For example, electrical stimulation for treating chronic pain may select specific nerve nodes, while stimulation for motor recovery may target specific muscle groups. Based on experimental designs means that in the process of scientific research or technical optimization, in order to study the charge diffusion law, electric field distribution characteristics, or optimize stimulation parameters, researchers may select specific muscle or nerve areas as research objects and set reasonable control groups and variable controls to ensure the comparability and scientific nature of experimental data. Considering these factors comprehensively can accurately define the stimulation area, optimize the electrical stimulation effect, and minimize adverse reactions to the greatest extent.

[0048] Signal processing techniques are applied to preprocess the real-time acquired electric field change data, and then key features reflecting charge accumulation are extracted. The extracted key features are deeply analyzed to characterize the charge accumulation risk, and at the same time, a standardized feature vector for input into the deep learning model is constructed;

[0049] When preprocessing the real-time acquired electric field change data using signal processing techniques, various methods are usually adopted to ensure data quality and accuracy. These include filtering (such as low-pass filtering, high-pass filtering, and band-pass filtering) to remove high-frequency noise and interference signals, smooth the data curve, and enhance the main features of the signal; in addition, denoising techniques (such as wavelet denoising, Kalman filtering) can further reduce the impact of random noise on the data; at the same time, normalization and standardization processing may also be carried out to make the data collected at different time periods or by different sensors have a unified scale, facilitating subsequent feature extraction and model training; in addition, time-frequency analysis methods such as Fourier transform and wavelet transform can convert the signal from the time domain to the frequency domain, revealing the periodic and transient features in the data, which helps to accurately capture the dynamic changes of charge accumulation. Through these comprehensive signal processing techniques, the stability and reliability of real-time data can be ensured, providing a solid foundation for subsequent extraction of key features and prediction by deep learning models.

[0050] Extract features reflecting charge accumulation. Among them, the extracted features include the time required for the electric potential to return to the baseline level and the cumulative value of the rate of change of the electric potential. Conduct in-depth analysis on the time required for the electric potential to return to the baseline level and the cumulative value of the rate of change of the electric potential, and generate a reference value for electric potential regression delay and a reference value for charge accumulation rate respectively. Characterize the charge accumulation risk through the reference value for electric potential regression delay and the reference value for charge accumulation rate, and at the same time construct a standardized feature vector for input into the deep learning model.

[0051] When the time required for the electric potential to return to the baseline level is longer than the normal recovery time, it usually means that there is a potential risk of charge accumulation in the muscle tissue within the demarcated area. Under normal circumstances, after the electrical stimulation ends, the electric potential in the tissue should return to the steady state within a short time, which mainly depends on tissue conductivity, ion diffusion ability, membrane potential recovery mechanism, and the charge redistribution ability of the surrounding environment. However, if this recovery time is significantly prolonged, it may indicate that the charge diffusion in the local area is restricted, resulting in the retention of residual electric potential. This phenomenon may be due to charge shielding effect, abnormal cell membrane polarization, ion channel disorder, or tissue impedance change, thus affecting the normal physiological function of the muscle tissue. Long-term charge accumulation may also cause cell membrane potential imbalance, abnormal tissue metabolism, and even lead to chronic inflammation or decreased stimulus tolerance.

[0052] The specific steps for generating the reference value for electric potential regression delay through in-depth analysis of the time required for the electric potential to return to the baseline level are as follows:

[0053] First, establish an electric potential regression time curve to describe the dynamic change of the electric field returning to the baseline. The construction expression of the electric potential regression time curve is as follows:

[0054] ,

[0055] Wherein: is the potential regression time curve, characterizing the non-linear change in the potential recovery process, represents the potential value measured at time t, is the potential change rate, reflecting the speed of potential recovery, and respectively represent the moment when the electrical stimulation terminates and the moment when the potential recovers to the set threshold, which are used to define the calculation interval, is the non-linear adjustment parameter. If , the influence of the drastic change in the potential recovery rate is enhanced. If , the minor changes in the potential recovery rate are smoothed, is the time decay factor, which is used to reduce the influence far from the end point of the electrical stimulation, making the weight of the early recovery stage larger;

[0056] This step calculates the weighted cumulative value of the potential recovery rate in an integral form, combined with the exponential decay factor , ensuring that the influence of the early potential change is more significant, while avoiding the interference of minor fluctuations at the distal end on the calculation result. This process can accurately capture the abnormal recovery characteristics caused by charge shielding, polarization lag, etc. during the potential regression process, providing a basis for the construction of the subsequent reference value of potential regression delay.

[0057] After obtaining the potential regression time curve, a reference value of potential regression delay characterizing the charge accumulation risk is generated through the potential regression time curve, and the generated expression is:

[0058] ,

[0059] Wherein: is the reference value of potential regression delay, is the scale constant of the potential recovery time, which normalizes the recovery time ranges of different individuals, is the exponential scaling parameter, which is used to adjust the influence degree of the recovery time on the reference value of potential regression delay, is the baseline potential of the muscle tissue within the defined area in the resting state.

[0060] A logarithmic normalization term is added, that is , and this term is used to avoid the over-amplification of extreme situations on the reference value of potential regression delay, while emphasizing the influence of abnormal potential retention. Combining the time integral to calculate the cumulative situation of the potential deviation, ensuring that the reference value of potential regression delay not only depends on the recovery time, but also can consider the abnormal potential accumulation effect during the entire recovery process.

[0061] From the reference value of potential regression delay, it can be seen that the larger the performance value of the potential regression delay reference value generated by in-depth analysis of the time required for the potential to return to the baseline level, the greater the risk of charge accumulation in the electric field change of the muscle tissue within the defined area. Conversely, it indicates that the risk of charge accumulation in the electric field change of the muscle tissue within the defined area is smaller. The potential regression delay reference value analyzes in depth the time required for the potential to return to the baseline level and the cumulative effect of abnormal offsets during the potential recovery process. The larger its performance value, the slower the local potential recovery and the more obvious the abnormal phenomenon, thus indicating a greater risk of charge accumulation in the muscle tissue in this area; conversely, a lower potential regression delay reference value means that the potential recovers faster and there are fewer abnormal offsets, indicating a lower risk of charge accumulation.

[0062] By monitoring the electric field change of the muscle tissue within the defined area through a micro field effect sensor, if the cumulative value of the potential change rate continues to rise, it indicates that the charge in this area fails to diffuse effectively and there is a risk of potential charge accumulation. This phenomenon usually means that the local potential continuously increases or maintains a high value within a short period of time, rather than returning to the baseline level according to the normal charge diffusion pattern. Under normal circumstances, after electrical stimulation, the charge should quickly diffuse in the tissue and tend to be stable. If the potential change rate continues to accumulate and rise, it may be due to the continuous accumulation of charge in the local area, rather than being effectively dissipated through natural diffusion or neutralization mechanisms. This may lead to abnormal polarization effects, affecting the normal functions of muscle and nerve cells, and may cause tissue damage, electrolysis reactions, or chronic stimulation adaptation problems.

[0063] The specific steps for generating the charge accumulation rate reference value by in-depth analysis of the cumulative value of the potential change rate are as follows:

[0064] In the muscle tissue within the defined area, the charge accumulation is characterized by the cumulative trend of the electric field change rate. Let be the spatial position and the electric field strength at this position. In order to quantify the charge accumulation rate, first calculate the instantaneous cumulative value of the potential change rate. The calculation expression is:

[0065] ,

[0066] where: is the instantaneous cumulative value of the potential change rate, characterizing the intensity of the electric field change and its distribution trend in space, is the defined area (three-dimensional monitoring area), that is, the electric field monitoring range within the muscle tissue, is the potential gradient change rate along the local potential direction characterizing how the local electric field changes with the stimulation conditions, is the spatial attenuation factor, where represents the distance from this point to the stimulation electrode, is the adjustment coefficient of the spatial weight to ensure that regions far from the stimulation source do not contribute too much to the overall potential change. denotes a tiny volume element integrated within ;

[0067] This step calculates the rate of change of the electric potential within the monitoring region through integration, combines the exponential decay weight, making regions closer to the stimulation source contribute more to the overall charge accumulation rate, and takes into account the differences in the electric field changes at different positions, thereby providing a spatially weighted characterization of the instantaneous charge change rate for subsequent calculations.

[0068] To more accurately evaluate the charge accumulation risk, a non - linear growth factor is introduced based on the instantaneous cumulative value of the rate of change of the electric potential to construct a reference value for the charge accumulation rate. The constructed expression is:

[0069] ,

[0070] where: is the reference value of the charge accumulation rate, used to characterize the charge accumulation risk in the local region. The larger the value, the more blocked the charge diffusion and the higher the accumulation degree. is the balance parameter to avoid the denominator approaching zero and ensure the stability of the exponential calculation. is the divergence of the current density, characterizing the flow of charge within the tissue. If its value is large, it indicates that there is a strong inflow or outflow of charge in this region. Integrating the square of the divergence of the current density over the entire monitoring region measures the non - uniformity of local charge movement; if this value is small, it indicates that the charge diffusion is relatively uniform and the accumulation risk is low. The hyperbolic sine function is used to enhance the non - linear response, where controls the influence of the rate of change of the electric potential on the final reference value of the charge accumulation rate, ensuring that the response can be amplified when the charge accumulation rapidly intensifies.

[0071] It should be noted that , where , , respectively represent the components of the current density in x , y , and the z - direction, , , respectively represent the rates of change of the current density in x , y , and the z - direction. The current density refers to the amount of electric current flowing through a unit area and is used to describe the distribution of electric current in space.

[0072] From the reference value of the charge accumulation rate, it can be seen that the larger the performance value of the charge accumulation rate reference value generated by in-depth analysis of the cumulative value of the potential change rate, the greater the risk of charge accumulation in the electric field change of the muscle tissue within the defined area. On the contrary, it indicates that the risk of charge accumulation in the electric field change of the muscle tissue within the defined area is smaller. The charge accumulation rate reference value directly reflects the cumulative situation of the potential change rate and is used to measure the charge accumulation risk of local muscle tissue. The larger its performance value, the higher the change rate of the local electric field, and the charge diffusion may be blocked, resulting in continuous charge accumulation without timely diffusion or dissipation, which may trigger abnormal polarization effects, electrolytic reactions, or local tissue damage. On the contrary, if the charge accumulation rate reference value is small, it indicates that the potential change rate is low, the charge can be evenly diffused and reach a steady state, which means that the risk of charge accumulation is low and the electrical stimulation environment of the muscle tissue is relatively safe.

[0073] Input the constructed feature vector into a pre-trained and well-verified deep learning model (such as LSTM recurrent neural network, Transformer model, CNN, or hybrid model) to analyze the real-time feature vector of the current input, and output the prediction result of the potential charge accumulation risk in the charge diffusion trend, so as to achieve early identification and warning of the charge accumulation risk;

[0074] Input the constructed potential regression delay reference value and charge accumulation rate reference value into a pre-trained and well-verified deep learning model (such as LSTM recurrent neural network, Transformer model, CNN, or hybrid model) to analyze the real-time feature vector of the current input, and output the accumulation evaluation coefficient through the deep learning model, and early identify and warn the potential charge accumulation risk in the charge diffusion trend based on the accumulation evaluation coefficient.

[0075] The pre-trained and well-verified deep learning model refers to a neural network model that has been fully trained and optimized on a large number of high-quality data sets. This model has stable generalization ability, can accurately identify the charge accumulation risk, and predict the potential change rate of the potential and the charge diffusion trend. Since charge diffusion involves complex time series dynamics, spatial distribution characteristics, and non-linear signal patterns, using deep learning (DeepLearning) to automatically extract features and make predictions is one of the best choices. Deep learning models, such as LSTM (Long Short-Term Memory network), Transformer, CNN (Convolutional Neural Network), or their hybrid architectures, can learn different charge diffusion patterns from a large amount of electric field change data and predict the potential charge accumulation trend based on historical data.

[0076] To make the model reliable and accurate, sufficient pre-training and validation must be carried out. Pre-training refers to the initial training of a neural network using a large amount of labeled data so that it can learn basic patterns, such as early signals of charge accumulation, normal diffusion characteristics, and abnormal electric field behaviors. Rigorous Validation is to ensure the generalization ability of the model through various evaluation methods (such as cross-validation, independent test set evaluation, real experiment comparison), that is, the model can not only perform well on the training data, but also maintain stable prediction ability on new data. In this process, various optimization techniques may be adopted, such as Hyperparameter Tuning, Regularization, Data Augmentation, and Adaptive Learning Rate Optimization to improve the robustness and adaptability of the model. Ensure that the model can not only accurately identify known charge accumulation patterns, but also effectively detect new and unseen abnormal situations, so as to have the ability to be applied in real scenarios.

[0077] LSTM (Long Short-Term Memory Network) is suitable for processing time series data, capable of memorizing long-term charge diffusion patterns, and capturing the accumulation trend caused by the delay of potential change. For example, during muscle electrical stimulation, charge accumulation may not be immediately apparent, but gradually accumulates over time, which requires a recurrent neural network (RNN) structure like LSTM to identify long-term accumulation trends. Through the Gating Mechanism, LSTM can filter out irrelevant information when analyzing the potential regression delay reference value and the charge accumulation rate reference value, and only retain the important features related to charge diffusion, thus providing more accurate risk prediction.

[0078] Transformer models (such as the Time-Series Transformer for time series prediction) provide an architecture based on the Self-Attention Mechanism, which can establish long-range dependencies between different time steps. In charge diffusion modeling, Transformer can effectively process the spatial potential change data collected by multiple sensors, identify the charge exchange patterns between different muscle regions, and provide a more comprehensive risk assessment by integrating multi-dimensional data. In addition, Transformer can also combine the potential regression delay reference value and the charge accumulation rate reference value to identify charge anomalies with rapid changes in a short time and predict whether accumulation will occur in the future.

[0079] The CNN (Convolutional Neural Network) is mainly used to extract the spatial features of charge diffusion. During the monitoring of muscle electric fields, the CNN can be used to analyze the charge distribution in different regions and detect abnormal charge accumulation points. Especially when the charge accumulation is manifested as a local high-potential region, the CNN can identify the spatial patterns of these regions through convolutional layers and combine with other deep learning networks for trend prediction. In addition, the CNN can also be combined with LSTM or Transformer to achieve spatio-temporal joint modeling, synchronously analyzing the charge accumulation risk in the time and space dimensions.

[0080] To ensure the stability and efficiency of the deep learning model, a hybrid model is usually adopted, combining CNN+LSTM or Transformer+LSTM, respectively using the CNN to extract spatial features, the LSTM to process time series information, and the Transformer to establish long-range dependencies, in order to obtain the most comprehensive charge diffusion prediction ability. For example, an efficient hybrid model architecture may be as follows:

[0081] Input layer: Input the potential regression delay reference value and the charge accumulation rate reference value;

[0082] CNN extracts spatial features: Analyze the potential distribution at different positions of muscle tissue through convolutional layers;

[0083] LSTM identifies time dynamic features: Analyze the charge diffusion pattern in the past period of time and predict future trends;

[0084] Transformer conducts global pattern learning: Integrate the results of CNN and LSTM, establish long-term dependencies, and optimize the risk assessment of charge accumulation;

[0085] Output layer: Generate an accumulation assessment coefficient and provide the prediction result of the charge diffusion trend.

[0086] Through this deep learning architecture, the system can give a real-time warning when detecting potential charge accumulation risks.

[0087] The deep learning model is not specifically limited here, as long as it can realize the comprehensive analysis of the potential regression delay reference value and the charge accumulation rate reference value to generate an accumulation assessment coefficient is acceptable. To implement the technical solution of the present invention, the present invention provides a specific implementation method; the calculation formula for generating the accumulation assessment coefficient is: , where, , The potential regression delay reference value and the charge accumulation rate reference value of the preset proportionality coefficient, and , are both greater than 0. The preset proportionality coefficient here refers to the weight parameter preset in order to reasonably balance the influence of the potential regression delay reference value and the charge accumulation rate reference value on the final evaluation result when calculating the accumulation evaluation coefficient. Their role is to adjust the contribution of different features to the final accumulation evaluation coefficient during the calculation process to reflect the relative importance of each index to the charge accumulation risk.

[0088] Specifically:

[0089] If , it means that the weight of the potential regression delay reference value in the accumulation risk assessment is greater, that is, it is more inclined to consider that the delay of potential regression is the main factor of the accumulation risk.

[0090] If , it means that the influence of the charge accumulation rate reference value on the accumulation risk is stronger, that is, the system pays more attention to the rate change of charge accumulation.

[0091] The preset proportionality coefficient and satisfy , are both greater than 0 to ensure that both the potential regression delay reference value and the charge accumulation rate reference value contribute to the result in the calculation and will not be completely ignored.

[0092] These coefficients can usually be set through experimental data statistics, machine learning optimization or empirical adjustment to ensure that the accumulation evaluation coefficient can accurately and reasonably reflect the charge accumulation risk and is applicable to different individuals and application scenarios.

[0093] It can be seen from the accumulation evaluation coefficient that the larger the value of the potential regression delay reference value generated by in-depth analysis of the time required for the potential to return to the baseline level, and the larger the value of the charge accumulation rate reference value generated by in-depth analysis of the cumulative value of the potential change rate, that is, the larger the value of the accumulation evaluation coefficient generated when predicting the potential charge accumulation risk in the charge diffusion trend through the deep learning model, the greater the risk of charge accumulation in the electric field change of the muscle tissue in the designated area, and vice versa, it indicates that the risk of charge accumulation in the electric field change of the muscle tissue in the designated area is smaller.

[0094] Compare and analyze the accumulation evaluation coefficient generated when predicting the potential charge accumulation risk in the charge diffusion trend through the deep learning model with the preset accumulation evaluation coefficient reference threshold to conduct early identification and warning of the charge accumulation risk. The specific steps are as follows:

[0095] If the accumulation evaluation coefficient is greater than the accumulation evaluation coefficient reference threshold, a risk signal is generated, indicating that there is a risk of charge accumulation in the electric field change of the muscle tissue within the defined area. At this time, an accumulation risk warning is issued. If the accumulation evaluation coefficient is less than or equal to the accumulation evaluation coefficient reference threshold, a normal change signal is generated, indicating that the electric field of the muscle tissue within the defined area is changing normally. At this time, no risk warning is issued.

[0096] Once the deep learning model issues an accumulation risk warning, it automatically enters the real-time risk assessment mode and immediately calculates the real-time change value of the potential difference between different positions within the defined area accurately through the data provided by the micro field effect sensor to quantify the current severity of charge accumulation.

[0097] Accurately calculate the real-time change value of the potential difference between different positions within the defined area through the data provided by the micro field effect sensor to quantify the current severity of charge accumulation. The specific steps are as follows:

[0098] When the deep learning model issues an accumulation risk warning, it automatically enters the real-time risk assessment mode, measures the potential data of different positions within the defined area using the micro field effect sensor, calculates the potential difference within the defined area through the instantaneous electric field change value collected by the micro field effect sensor, and conducts a quantitative analysis in combination with the accumulation evaluation coefficient to generate a charge accumulation severity index to judge the severity of charge accumulation. The calculation formula of the charge accumulation severity index is as follows:

[0099] ,

[0100] Where: is the charge accumulation severity index, is the accumulation evaluation coefficient output by the deep learning model, which is used to measure the risk degree of charge accumulation, is the accumulation evaluation coefficient reference threshold, which is used to judge the warning critical point of charge accumulation, is the maximum potential difference between different positions within the defined area, indicating the degree of local polarization that may be caused by charge accumulation in the defined area. The calculation expression is:

[0101] ,

[0102] Where: and are the maximum electric field strength and the minimum electric field strength within the defined area respectively.

[0103] This step calculates the real-time potential difference and conducts comprehensive processing in combination with the accumulation evaluation coefficient, and finally generates a charge accumulation severity index. If the charge accumulation severity index is too high, it indicates that the charge accumulation is serious and the electric stimulation parameters need to be adjusted immediately.

[0104] After quantitatively calculating the potential difference, the pulse duty cycle adjustment action is automatically executed according to the intelligent regulation strategy. When the potential difference exceeds the preset potential difference threshold, the "low" state time of the pulse signal is extended, that is, the pulse interval is increased, the total amount of charge injection per unit time is reduced, and the degree of local accumulation is alleviated;

[0105] The pulse duty cycle adjustment action is automatically executed according to the intelligent regulation strategy. The specific steps are as follows:

[0106] According to the calculated charge accumulation severity index , an adaptive pulse duty cycle regulation strategy is adopted to ensure uniform charge diffusion, avoid abnormal accumulation, and the regulation expression is as follows:

[0107] ,

[0108] where: is the adjusted pulse duty cycle, which is used to reduce the impact of charge accumulation, is the reference pulse duty cycle, that is, the default pulse duty cycle under normal conditions, is the adjustment coefficient, which controls the sensitivity of the duty cycle adjustment. A larger value represents more sensitivity to charge accumulation and a larger adjustment amplitude;

[0109] When > , the adjusted pulse duty cycle gradually decreases (that is, the pulse interval is extended and the charge injection amount per unit time is reduced) to promote the natural diffusion of charges and prevent biological tissue damage caused by polarization effects or electrolytic reactions; when the charge accumulation severity index decreases to near the accumulation assessment coefficient reference threshold, the pulse duty cycle gradually returns to the reference pulse duty cycle to ensure the normal function of muscle electrical stimulation.

[0110] Through the application of the above solution, a significant beneficial effect is the realization of intelligent and real-time closed-loop regulation of the electrical stimulation process, thereby significantly improving the treatment safety and effect. This solution monitors the electric field changes in muscle tissue in real time, uses a deep learning model to identify the charge accumulation risk in advance, and automatically adjusts the pulse duty cycle when the risk appears, effectively preventing abnormal polarization and electrolytic reactions, and reducing the risks of tissue damage, cell necrosis, and nerve damage. This system based on multi-level data processing and adaptive regulation can not only ensure uniform charge diffusion in the muscle, but also dynamically optimize the electrical stimulation parameters during the treatment process, making the rehabilitation training and other electrical stimulation treatments more accurate and safe, and contributing to the improvement of the long-term rehabilitation effect of patients.

[0111] The present invention provides as Figure 2The shown electric shock simulation training detection and evaluation system includes an electric stimulation signal application module, an electric field monitoring module, a signal processing and feature extraction module, a deep learning risk prediction module, a real-time risk assessment module, and an adaptive pulse regulation module;

[0112] The electric stimulation signal application module applies a preset controllable electric stimulation signal to a specified muscle area to simulate the electric signal of the real external environment under precise control conditions;

[0113] The electric field monitoring module directly monitors the electric field change of the muscle tissue within the delimited area through a micro field effect sensor to reflect the diffusion trend of charges in real time;

[0114] The signal processing and feature extraction module applies signal processing technology to preprocess the real-time acquired electric field change data, then extracts the key features reflecting charge accumulation, deeply analyzes the extracted key features to characterize the charge accumulation risk, and constructs a standardized feature vector input into the deep learning model at the same time;

[0115] The deep learning risk prediction module inputs the constructed feature vector into a pre-trained and well-verified deep learning model, analyzes the current input real-time feature vector, and outputs the prediction result of the potential charge accumulation risk in the charge diffusion trend to realize the early identification and warning of the charge accumulation risk;

[0116] The real-time risk assessment module, once the deep learning model issues an accumulation risk warning, automatically enters the real-time risk assessment mode, and immediately calculates the real-time change value of the potential difference between different positions within the delimited area accurately through the data provided by the micro field effect sensor to quantify the current severity of charge accumulation;

[0117] The adaptive pulse regulation module, after quantitatively calculating the potential difference, automatically executes the pulse duty cycle adjustment action according to the intelligent regulation strategy. When the potential difference exceeds the preset potential difference threshold, it extends the "low" state time of the pulse signal, that is, increases the pulse gap, reduces the total charge injection amount per unit time, and alleviates the local accumulation degree.

[0118] The electric shock simulation training detection and evaluation method provided by the embodiment of the present invention is implemented through the above-mentioned electric shock simulation training detection and evaluation system. For the specific methods and processes of the electric shock simulation training detection and evaluation system, refer to the embodiments of the above-mentioned electric shock simulation training detection and evaluation method, which will not be elaborated here.

[0119] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0120] Only some exemplary embodiments of the present invention have been described by way of illustration. Without doubt, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0121] As described above, the foregoing is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily conceive of changes or substitutions, which should all be covered within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the scope of protection of the claims.

Claims

1. An electric shock simulation training detection and evaluation system, characterized in that: It includes an electrical stimulation signal application module, an electric field monitoring module, a signal processing and feature extraction module, a deep learning risk prediction module, a real-time risk assessment module, and an adaptive pulse control module; The electrical stimulation signal application module applies a pre-set controllable electrical stimulation signal to the designated muscle area, simulating the electrical signal of the real external environment under precise control conditions; The electric field monitoring module directly monitors the electric field changes of muscle tissue in the defined area through micro field effect sensors, reflecting the diffusion trend of charge in real time; The signal processing and feature extraction module uses signal processing technology to pre-process the electric field change data acquired in real time, then extracts the key features reflecting charge accumulation, conducts in-depth analysis on the extracted key features, characterizes the risk of charge accumulation, and constructs a standardized feature vector for input into the deep learning model; The deep learning risk prediction module inputs the constructed feature vector into a pre-trained and fully verified deep learning model, analyzes the current real-time feature vector input, and outputs the potential charge accumulation risk prediction results in the charge diffusion trend, thus realizing early identification and early warning of charge accumulation risks; The real-time risk assessment module automatically enters the real-time risk assessment mode once the deep learning model issues an accumulation risk warning. It immediately uses the data provided by the micro field effect sensor to accurately calculate the real-time change value of the potential difference between different locations within the defined area and quantify the current severity of charge accumulation. After quantitatively calculating the potential difference, the adaptive pulse control module automatically performs pulse duty cycle adjustment according to the intelligent control strategy. When the potential difference exceeds the preset potential difference threshold, the "low" state time of the pulse signal is extended, that is, the pulse interval is increased, the total amount of charge injection per unit time is reduced, and the degree of local accumulation is alleviated.

2. The electric shock simulation training detection and evaluation system according to claim 1, characterized in that: The demarcated area refers to the predetermined range of tissue that is directly acted upon by electrodes or affected by charge accumulation during muscle electrical stimulation experiments or treatments. It is precisely selected based on the anatomical structure, electrical stimulation target, clinical treatment needs or experimental design.

3. The electric shock simulation training detection and evaluation system according to claim 1, characterized in that: Features reflecting the charge accumulation situation are extracted, wherein the extracted features include the cumulative value of the time required for the potential to return to the baseline level and the cumulative value of the potential change rate. The time required for the potential to return to the baseline level and the cumulative value of the potential change rate are deeply analyzed to generate a potential regression delay reference value and a charge accumulation rate reference value, respectively. The charge accumulation risk is characterized by the potential regression delay reference value and the charge accumulation rate reference value, and a standardized feature vector is constructed for input into the deep learning model.

4. The electric shock simulation training detection and evaluation system according to claim 3, characterized in that: The constructed potential regression delay reference value and charge accumulation rate reference value are input into a pre-trained and fully verified deep learning model, the real-time feature vector of the current input is analyzed, and the accumulation assessment coefficient is output through the deep learning model. Based on the accumulation assessment coefficient, early identification and warning of potential charge accumulation risks in the charge diffusion trend are carried out.

5. The electric shock simulation training detection and evaluation system according to claim 4, characterized in that: The accumulation assessment coefficient generated when predicting the potential charge accumulation risk in the charge diffusion trend through the deep learning model is compared and analyzed with the preset accumulation assessment coefficient reference threshold to perform early identification and early warning of the charge accumulation risk. The specific steps are as follows: If the accumulation assessment coefficient is greater than the accumulation assessment coefficient reference threshold, a risk signal is generated, indicating that there is a risk of charge accumulation in the electric field change of the muscle tissue in the demarcated area, and an accumulation risk warning is issued; If the accumulation assessment coefficient is less than or equal to the accumulation assessment coefficient reference threshold, a normal change signal is generated, indicating that the electric field of the muscle tissue in the defined area is changing normally, and no risk warning is issued at this time.

6. The electric shock simulation training detection and evaluation system according to claim 5, characterized in that: The data provided by the micro field effect sensor is used to accurately calculate the real-time change value of the potential difference between different positions within the defined area and quantify the severity of the current charge accumulation. The specific steps are as follows: When the deep learning model issues an accumulation risk warning, it automatically enters the real-time risk assessment mode and uses the micro field effect sensor to measure the potential data at different locations in the designated area. The potential difference in the designated area is calculated by the instantaneous electric field change value collected by the micro field effect sensor, and the accumulation assessment coefficient is combined for quantitative analysis to generate a charge accumulation severity index to determine the severity of the charge accumulation. The calculation formula of the charge accumulation severity index is as follows: ， in: is an indicator of the severity of charge accumulation, It is the accumulation assessment coefficient output by the deep learning model, which is used to measure the risk level of charge accumulation. is the reference threshold of the accumulation evaluation coefficient, is the maximum potential difference at different positions within the demarcated area, indicating the degree of local polarization caused by charge accumulation in the demarcated area. The calculation expression is: ， in: and are the maximum and minimum electric field strengths in the demarcated area, respectively.

7. The electric shock simulation training detection and evaluation system according to claim 6, characterized in that: The pulse duty cycle adjustment action is automatically performed according to the intelligent control strategy. The specific steps are as follows: Based on the calculated charge accumulation severity index , an adaptive pulse duty cycle control strategy is adopted to ensure uniform charge diffusion. The control expression is as follows: ， in: is the adjusted pulse duty cycle used to reduce the effect of charge accumulation, is the reference pulse duty cycle, i.e. the default pulse duty cycle under normal circumstances. It is the adjustment coefficient that controls the sensitivity of duty cycle adjustment.

Images