Real-time intervention system for cervical and lumbar myalgia

Abstract

The invention discloses a real-time intervention system for cervical and lumbar myalgia, and the system comprises an acceleration sensor which is used for detecting the acceleration change of the body of a driver; the electrical stimulation unit is used for providing electrical stimulation according to the acceleration change; the intelligent control module is used for adjusting working parameters of the electrical stimulation unit according to data detected by the acceleration sensor; the intelligent control module comprises a microprocessor and a deep learning engine; the electrical stimulation parameters are dynamically adjusted through the intelligent control module according to the acceleration change; a deep learning engine is embedded in the intelligent control module, and self-learning and optimization can be carried out according to the physiological data of the user. The physical state of a driver is monitored in real time, preventive or remission electrical stimulation is provided in time, possible events in the future are predicted through a CNN model, and an electrical stimulation strategy is continuously optimized by using a DQN algorithm. Noise interference is removed, the accuracy and reliability of data analysis are improved, and the effectiveness of subsequent processing is ensured.

Description

Technical Field

[0001] The invention relates to the technical field of biomedical engineering, and in particular to a real-time intervention system for cervical and lumbar myalgia. Background Art

[0002] Cervical and lumbar myalgia is a common occupational disease, especially among people who drive for long periods of time or work in offices. Traditional treatments mainly include medication, physical therapy, and surgery, but these methods often have certain limitations. For example, medication may have side effects, physical therapy requires frequent visits to the doctor, and surgery has greater risks and a longer recovery period.

[0003] After searching, the invention patent with Chinese patent number CN118452825A discloses a post-stroke cognitive impairment assessment and intervention system, including a central processing unit, the output end of the central processing unit is electrically connected to a display module, a voice module, a light test module and an olfactory test module in a unidirectional manner, and the central processing unit is electrically connected to a pain detection module, a score assessment module, a timing module, a scoring module, a smart glove, a sound processing module, a storage module, a health measurement module, a head display module and an image processing module in a bidirectional manner. The present invention has the advantage of accurate measurement through the cooperation of the score assessment module, the timing module, the scoring module, the smart glove, the sound processing module, the storage module, the health measurement module, the head display module and the display module. Compared with the prior art, the invention patent with Chinese patent number CN118452825A can perform multi-faceted detection of the patient's cognitive state, and after the test is completed, it can also intervene and treat the cognitive impairment, thereby improving the patient's rehabilitation efficiency.

[0004] However, during actual use of the above invention, there is a lack of effective communication and coordination mechanism between devices, which makes the testing process cumbersome and error-prone, the data processing capability is limited, and it is difficult to perform complex data analysis, which affects the accuracy and reliability of the test results. The user interface is unfriendly, the operation is complicated, and there is a lack of convenient interaction methods, which causes inconvenience to users during use.

[0005] Therefore, a real-time intervention system for cervical and lumbar muscle pain is proposed. The intelligent control module coordinates the work of each device to ensure seamless collaboration between the modules. The data preprocessing module and the feature extraction module can convert the original signal into effective data that can be used for analysis. The deep learning engine can perform advanced data analysis, as well as touch screen operation, mobile application integration and voice control support, which greatly improves the user experience. Summary of the invention

[0006] The purpose of the present invention is to solve the shortcomings of the prior art, such as the lack of effective communication and coordination mechanism between devices, which leads to a cumbersome and error-prone testing process, limited data processing capabilities, difficulty in performing complex data analysis, affecting the accuracy and reliability of the test results, unfriendly user interface, complex operation, and lack of convenient interaction methods, which causes inconvenience to users during use, and propose a real-time intervention system for cervical and lumbar muscle pain.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] Real-time intervention system for cervical and lumbar myalgia, including:

[0009] An acceleration sensor for detecting acceleration changes of the driver's body;

[0010] an electrical stimulation unit for providing electrical stimulation according to the acceleration change;

[0011] An intelligent control module, used for adjusting the working parameters of the electrical stimulation unit according to the data detected by the acceleration sensor;

[0012] The intelligent control module includes a microprocessor and a deep learning engine;

[0013] The electrical stimulation unit includes multiple independently controlled electrodes and an adaptive intensity adjustment mechanism;

[0014] The acceleration sensor includes a multi-dimensional sensor fusion module and a bio-signal sensor;

[0015] The modules work in coordination through the intelligent control module.

[0016] The above technical solution further includes:

[0017] Preferably, the intelligent control module includes: a data preprocessing module, which is used to convert time domain signals into frequency domain signals and remove noise; a feature extraction module, which is used to extract key features from the processed data and simplify the model complexity; an event prediction module, which is used to predict possible future events through a trained CNN model; a strategy optimization module, which is used to continuously optimize the electrical stimulation strategy based on user feedback data; and a dynamic adjustment module, which is used to dynamically adjust the electrical stimulation parameters.

[0018] Preferably, it includes: a touch screen for displaying the current working status and allowing the user to adjust the settings through simple gestures; a mobile application that connects to a smartphone via Bluetooth or Wi-Fi, so that the user can view detailed historical data reports on the phone and customize a personalized electrical stimulation plan; a voice recognition module for supporting the user to control the device through voice commands; a natural language processing module for understanding the user's natural language expression and adjusting the electrical stimulation strategy according to the user's needs.

[0019] Preferably, it includes: an overheating protection mechanism, which automatically disconnects the electrical stimulation when local overheating is detected to prevent burns; an emergency stop button, which is used to quickly interrupt the electrical stimulation under any circumstances; a user adaptability test program, which is used to guide the user to complete the adaptability test before the first use to ensure that the electrical stimulation parameters are in line with the individual's physique.

[0020] Preferably, it includes: a user portrait building module, which is used to build a user portrait by collecting the user's behavior data and health data; a personalized recommendation system module, which is used to combine the user portrait and the deep learning model to provide the user with the electrical stimulation intensity and frequency recommendations that are most suitable for the current state.

[0021] Preferably, it includes: a user interface and interaction design module, which is used to provide touch screen operation, mobile application integration and voice control support; a graphical user interface (GUI), which is used to display various operation instructions and real-time status; and a voice assistant, which is used to provide voice prompts and receive user voice instructions.

[0022] Preferably, it includes: a safety consideration module for realizing overheat protection, emergency stop function and user adaptability test; a sensor fault detection mechanism for detecting whether the sensor is working properly; a hardware protection circuit for preventing short circuit and overload at the hardware level; a user safety training module for educating users to use the system correctly and avoid misoperation.

[0023] Preferably, the intelligent control module also includes: an FFT transformation module, which is used to convert time domain signals into frequency domain signals and remove noise; a PCA algorithm module, which is used to extract key features from processed data and simplify model complexity; a CNN model module, which is used to predict possible future events through a trained CNN model; a DQN algorithm module, which is used to continuously optimize the electrical stimulation strategy based on user feedback data; and a Ka lman filtering algorithm module, which is used to dynamically adjust electrical stimulation parameters to adapt to different environments and individual differences.

[0024] Preferably, it includes: a user behavior analysis module for analyzing user usage habits; a recommendation algorithm optimization module for improving the accuracy of the recommendation algorithm; and a user feedback collection module for collecting user usage feedback and adjusting the recommendation strategy.

[0025] Preferably, it includes: a user health monitoring module for monitoring the user's health status in real time and reminding the user to take measures when abnormalities occur; and a user personalization setting module for allowing the user to set electrical stimulation parameters according to his or her own preferences.

[0026] The present invention has the following beneficial effects:

[0027] 1. In the present invention, the system integrates an acceleration sensor and an electrical stimulation unit, and dynamically adjusts the electrical stimulation parameters according to the acceleration change through an intelligent control module; the intelligent control module has an embedded deep learning engine, which can self-learn and optimize according to the user's physiological data. It monitors the driver's physical condition in real time and provides preventive or relieving electrical stimulation in time, thereby effectively preventing and relieving cervical and lumbar muscle pain. In addition, the deep learning engine improves the intelligence level of the system, making the electrical stimulation more accurate and personalized, and enhancing the user experience.

[0028] 2. In the present invention, the data preprocessing module and feature extraction module can convert the original signal into valid data that can be used for analysis; and predict the possible events in the future through the CNN model, and continuously optimize the electrical stimulation strategy using the DQN algorithm. Noise interference is removed, the accuracy and reliability of data analysis are improved, and the effectiveness of subsequent processing is ensured. In addition, by predicting potential problems in advance and taking preventive measures, the predictability and adaptability of the system are improved, and the discomfort of users is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a system architecture diagram of the real-time intervention system for cervical and lumbar muscle pain proposed in the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] like Figure 1 As shown, the real-time intervention system for cervical and lumbar myalgia proposed by the present invention comprises:

[0032] An acceleration sensor for detecting acceleration changes of the driver's body;

[0033] an electrical stimulation unit for providing electrical stimulation according to the acceleration change;

[0034] An intelligent control module, used for adjusting the working parameters of the electrical stimulation unit according to the data detected by the acceleration sensor;

[0035] The intelligent control module includes a microprocessor and a deep learning engine;

[0036] The electrical stimulation unit includes multiple independently controlled electrodes and an adaptive intensity adjustment mechanism;

[0037] The acceleration sensor includes a multi-dimensional sensor fusion module and a bio-signal sensor;

[0038] The modules work in coordination through the intelligent control module.

[0039] In one embodiment, the intelligent control module includes: a data preprocessing module, which is used to convert time domain signals into frequency domain signals and remove noise; a feature extraction module, which is used to extract key features from the processed data and simplify the model complexity; an event prediction module, which is used to predict possible future events through a trained CNN model; a strategy optimization module, which is used to continuously optimize the electrical stimulation strategy based on user feedback data; and a dynamic adjustment module, which is used to dynamically adjust the electrical stimulation parameters.

[0040] In one embodiment, it includes: a touch screen for displaying the current working status and allowing the user to adjust the settings through simple gestures; a mobile application that connects to a smartphone via Bluetooth or Wi-Fi, so that the user can view detailed historical data reports on the phone and customize a personalized electrical stimulation plan; a voice recognition module for supporting the user to control the device through voice commands; a natural language processing module for understanding the user's natural language expression and adjusting the electrical stimulation strategy according to the user's needs.

[0041] In one embodiment, it includes: an overheating protection mechanism, which automatically disconnects the electrical stimulation when local overheating is detected to prevent burns; an emergency stop button, which is used to quickly interrupt the electrical stimulation under any circumstances; and a user adaptability test program, which is used to guide the user to complete the adaptability test before the first use to ensure that the electrical stimulation parameters are in line with the individual's physique.

[0042] In one embodiment, it includes: a user portrait building module, which is used to build a user portrait by collecting the user's behavior data and health data; a personalized recommendation system module, which is used to combine the user portrait and the deep learning model to provide the user with the electrical stimulation intensity and frequency recommendations that best suit the current state.

[0043] In one embodiment, it includes: a user interface and interaction design module, which is used to provide touch screen operation, mobile application integration and voice control support; a graphical user interface (GUI), which is used to display various operation instructions and real-time status; and a voice assistant, which is used to provide voice prompts and receive user voice instructions.

[0044] In one embodiment, it includes: a safety consideration module for implementing overheat protection, emergency stop function and user adaptability test; a sensor fault detection mechanism for detecting whether the sensor is working properly; a hardware protection circuit for preventing short circuit and overload at the hardware level; a user safety training module for educating users to use the system correctly and avoid misoperation.

[0045] In one embodiment, the intelligent control module also includes: an FFT transformation module, which is used to convert time domain signals into frequency domain signals and remove noise; a PCA algorithm module, which is used to extract key features from processed data and simplify model complexity; a CNN model module, which is used to predict possible future events through a trained CNN model; a DQN algorithm module, which is used to continuously optimize the electrical stimulation strategy based on user feedback data; and a Ka lman filtering algorithm module, which is used to dynamically adjust electrical stimulation parameters to adapt to different environments and individual differences.

[0046] In one embodiment, it includes: a user behavior analysis module for analyzing user usage habits; a recommendation algorithm optimization module for improving the accuracy of the recommendation algorithm; and a user feedback collection module for collecting user usage feedback and adjusting the recommendation strategy.

[0047] In one embodiment, it includes: a user health monitoring module, which is used to monitor the user's health status in real time and remind the user to take measures when abnormalities occur; and a user personalization setting module, which is used to allow the user to set electrical stimulation parameters according to their own preferences.

[0048] In one embodiment, the system architecture

[0049] Intelligent control module:

[0050] Hardware platform: It uses ARM Cortex-A72 processor as the core, integrates 4GB LPDDR4 memory and 32GB eMMC flash memory, supports efficient data processing and storage. The processor has a main frequency of 1.8GHz and can quickly process data from sensors.

[0051] Operating system: Equipped with FreeRTOS real-time operating system to ensure the real-time responsiveness and stability of the system.

[0052] Deep learning framework: Integrates the TensorFlowLite lightweight deep learning framework to support model reasoning and online learning.

[0053] Encryption mechanism: Built-in SecureEnc lave encryption module, using AES-256 encryption algorithm to ensure data security.

[0054] Sensor components:

[0055] Multi-dimensional sensor: Bosch BNO055 nine-axis IMU (inertial measurement unit) is used, which integrates accelerometer, gyroscope and magnetometer to provide accurate motion data in three-dimensional space. The sampling rate of the sensor is 100Hz, which means that data can be obtained 100 times per second.

[0056] Biosignal sensor: Integrates MaximMAX86140 optical heart rate sensor and SpO2 module to monitor heart rate and blood oxygen saturation. The accuracy of the heart rate sensor can reach ±2bpm (beats per minute).

[0057] Environmental sensor: Texas Instruments TMP117 high-precision temperature sensor and Sensirion SHTC3 temperature and humidity sensor are used to ensure a suitable wearing environment. The accuracy of the temperature sensor is ±0.2°C.

[0058] Electrical stimulation unit:

[0059] Flexible electrodes: Flexible electrodes are made of conductive silicone material to ensure good contact with the skin and improve the efficiency of electrical stimulation.

[0060] Multi-band electrical stimulation: supports adjustable frequencies of 1-100Hz, suitable for different types of muscle stimulation. For example, medium and high frequency electrical stimulation (50-100Hz) is used to provide preload, and low frequency electrical stimulation (1-30Hz) is used to relieve muscle fatigue.

[0061] Intensity adjustment: Using a digitally adjustable current source, the intensity of electrical stimulation can be automatically adjusted according to the instructions output by the algorithm. The intensity adjustment range is 0-50mA.

[0062] Power Management System:

[0063] Energy recovery: The integrated TI BQ25570 energy recovery chip converts the kinetic energy generated by the wearer's movement into electrical energy. It is estimated that about 0.1 mJ of energy can be recovered per walk.

[0064] Smart charging: Using TI BQ24195 smart charging controller, supporting USB PD fast charging protocol, automatically adjusting charging strategy. It takes about 2 hours to fully charge a 1000mAh lithium battery.

[0065] In one embodiment, the workflow and logic

[0066] initialization:

[0067] System startup: After the device is started, it will perform a self-test to ensure that each module is working properly. The self-test time is about 5 seconds.

[0068] User Configuration: The user is guided through the initial setup via the touch screen or mobile app, including stimulation preferences, emergency contact information, etc. The user can set the default intensity of stimulation to 20mA.

[0069] Data collection:

[0070] Real-time monitoring: The IMU sensor continuously collects the driver's body movement data, and the heart rate and blood oxygen sensors monitor physiological indicators. The data collection interval is 0.01 seconds.

[0071] Data transmission: The sensor data is sent to the intelligent control center for processing via the BLE (Bluetooth Low Energy) module. The data transmission delay does not exceed 0.1 seconds.

[0072] Data Analysis:

[0073] Data preprocessing: Use FFT transformation to filter the original data and remove noise. For example, the original signal can be converted into a frequency domain signal through FFT, and then high-frequency noise can be filtered out by setting a threshold (such as above 50Hz).

[0074] formula:

[0075] Explanation: Here x(n) is the time series data, N is the number of data points, and f is the frequency variable. Through FFT transformation, we can get the components of the signal at different frequencies.

[0076] Feature extraction: Use the PCA algorithm to extract key features from the processed data, such as acceleration peak, heart rate change trend, etc. PCA can reduce the dimension of multiple features and retain the most important ones.

[0077] Formula: X pca =XW

[0078] Explanation: Here X is the original data matrix, W is the PCA transformation matrix, X pca is the feature matrix after dimensionality reduction.

[0079] Electrical stimulation control:

[0080] Preload start: When the system predicts an impending acceleration change through the CNN model, medium- and high-frequency electrical stimulation (50-100 Hz) is immediately initiated for 0.5 seconds.

[0081] formula: Explanation: Here x is the input data, is the model output, representing the prediction of the motion pattern.

[0082] Fatigue relief: In non-emergency situations, the system switches manually or automatically to low-frequency electrical stimulation mode (1-30Hz) for 30 seconds depending on the driver's fatigue level.

[0083] Adaptive adjustment: The system has self-learning capabilities and continuously optimizes the electrical stimulation strategy based on user feedback through the DQN algorithm. For example, users can rate the comfort of electrical stimulation through the mobile app, and the system adjusts the intensity of the next electrical stimulation based on the score.

[0084] Formula: Q(s,a)=r+γmax a′ Q ′ (s ′ ,a ′ ) Explanation: Here Q(s,a) is the value function of the state-action pair, r is the immediate reward, γ is the discount factor, s ′ is the next state, a ′ It’s the next move.

[0085] User feedback:

[0086] Multi-modal reminder: The device's built-in speaker plays a sound reminder, the LED light flashes, or the vibration motor vibrates to remind the driver to pay attention to safety. The sound reminder volume is adjustable, with a maximum volume of 80dB.

[0087] Mobile app synchronization: The device status is synchronized through the mobile app, and users can check health data at any time and adjust driving behavior according to the suggestions. The mobile app can display historical curves of data such as heart rate and blood oxygen saturation.

[0088] In one embodiment, data processing and algorithms

[0089] Preprocessing:

[0090] Digital signal processing: FFT transform is used to filter and smooth the raw sensor data to eliminate noise interference. For example, the raw acceleration signal may contain a lot of high-frequency noise, which can be converted into a frequency domain signal through FFT, and the high-frequency noise can be filtered out by setting a threshold (such as above 100Hz).

[0091] formula: Feature Engineering: Use feature selection algorithms such as PCA and LDA to extract key features from the processed data and simplify the model complexity. For example, the features extracted from acceleration data may include maximum, minimum, average, etc.

[0092] Formula: X pca =XW

[0093] Feature extraction:

[0094] Motion pattern recognition: CNN models are used to analyze sensor data such as acceleration and angular velocity to identify the driver’s motion pattern. For example, a trained CNN model can identify whether the driver is accelerating, decelerating, or maintaining a constant speed.

[0095] formula: Health status assessment: Combined with biosignal data such as heart rate and blood oxygen saturation, the system assesses the driver's health status. For example, if the heart rate is continuously higher than 100bpm, the system may prompt the driver to take a rest.

[0096] formula: Explanation: Here HR represents heart rate (unit: beats / minute), and I is the time interval between two adjacent R waves (unit: seconds).

[0097] Decision logic:

[0098] Event prediction: Predict possible future events (such as sudden braking) through the trained CNN model. For example, when the model detects a sudden increase in acceleration value, it may predict sudden braking.

[0099] Formula: p = softmax(CNN(x)) Explanation: Here p is the predicted probability distribution, and the softmax function converts the model output into a probability form.

[0100] Strategy optimization: The DQN algorithm is integrated to allow the system to continuously learn the user's preferences and physical reactions during use, and gradually improve the electrical stimulation strategy. For example, through user feedback data, the system can learn which electrical stimulation intensity is most comfortable in a specific situation.

[0101] Formula: Q(s,a)=r+γmax a′ Q ′ (s ′ ,a ′ ) Dynamic adjustment: Use the Kalman filter algorithm to dynamically adjust the electrical stimulation parameters to adapt to different environments and individual differences. For example, when the system detects that the ambient temperature rises, the electrical stimulation intensity may be appropriately reduced to avoid overstimulation.

[0102] formula: Explanation: Here is the state estimate, A is the state transfer matrix, K k is the Kalman gain, z k is the observation value, and H is the observation matrix.

[0103] Personalized recommendations:

[0104] User portrait construction: Build user portraits by collecting user behavior data and health data. For example, user age, gender, health status and other information can be used to build user portraits.

[0105] Formula: u=[age,gender,health,...] T

[0106] Intelligent recommendation system: Combines user portraits and deep learning models to provide users with recommendations on the intensity and frequency of electrical stimulation that best suits their current state. For example, for users who often drive long distances, the system may recommend a higher frequency of electrical stimulation to relieve fatigue.

[0107] Formula: recommendation=model(u,context)

[0108] In one embodiment, the user interface and interaction design

[0109] Touch screen operation:

[0110] Intuitive display: The device is equipped with a color touch screen with a size of 2.4 inches, a resolution of 320x240 pixels, and supports multi-touch. The screen displays the current working status, such as electrical stimulation mode, intensity, frequency and other information.

[0111] Simple gesture operation: Users can adjust settings with simple gestures, such as sliding the screen to adjust the intensity of electrical stimulation and tapping the buttons on the screen to switch between different electrical stimulation modes.

[0112] Graphical interface: The interface design uses graphical elements, such as icons, progress bars, etc., to make it easier for users to understand the current device status and operation steps.

[0113] Mobile App Integration:

[0114] Real-time synchronization: Connect to smartphones via Bluetooth or Wi-Fi, and users can view the device’s working status and historical data reports in real time on their phones.

[0115] Personalized settings: Users can set personalized electrical stimulation plans in the mobile application, including parameters such as the time, frequency, and intensity of electrical stimulation.

[0116] Data Visualization: The mobile app provides data visualization capabilities in the form of charts and graphs to help users better understand their health status and usage.

[0117] Voice control support:

[0118] Voice Recognition Module: Integrates a high-sensitivity microphone and advanced voice recognition technology to support users to control the device through voice commands.

[0119] Common commands: The device supports common voice commands, such as "turn on electrical stimulation", "increase intensity", "check status", etc.

[0120] Natural language processing: Through natural language processing technology, the device can understand more natural voice expressions, such as "I feel a little tired now, please help me relax."

[0121] In one embodiment, security considerations

[0122] Overheat protection:

[0123] Temperature sensor: The device has a built-in high-precision temperature sensor to monitor temperature changes inside the device.

[0124] Overheating power off: When it is detected that the device temperature exceeds the preset safety threshold (such as 40°C), the system automatically cuts off the electrical stimulation output to prevent burns caused by overheating.

[0125] Cooling mechanism: Designed with heat sinks and vents to ensure the device remains within a safe temperature range during extended use.

[0126] Emergency stop button:

[0127] Physical button: Provide an obvious physical button on the device that the user can press in any situation to immediately stop the electrical stimulation.

[0128] Double-click confirmation: In order to prevent misoperation, the emergency stop button is designed with a double-click confirmation mechanism. The user needs to press the button twice in succession to trigger the emergency stop function.

[0129] User adaptability test:

[0130] Adaptability test procedure: Before the first use, the system guides the user to complete a series of adaptability tests, including gradually increasing the intensity of electrical stimulation, allowing the user to feel the sensations at different intensities and choose the intensity that best suits them.

[0131] Personalized settings: Based on the user's adaptability test results, the system automatically adjusts the electrical stimulation parameters to ensure that it suits the individual's physique.

[0132] Continuous monitoring: During use, the system continuously monitors the user's response and dynamically adjusts the electrical stimulation strategy based on feedback data.

[0133] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A real-time intervention system for cervical and lumbar muscle pain, characterized in that: include: An acceleration sensor for detecting acceleration changes of the driver's body; an electrical stimulation unit for providing electrical stimulation according to the acceleration change; An intelligent control module, used for adjusting the working parameters of the electrical stimulation unit according to the data detected by the acceleration sensor; The intelligent control module includes a microprocessor and a deep learning engine; The electrical stimulation unit includes a plurality of independently controlled electrodes and an adaptive intensity adjustment mechanism; The acceleration sensor includes a multi-dimensional sensor fusion module and a bio-signal sensor; The modules work in coordination through the intelligent control module.

2. The real-time intervention system for cervical and lumbar muscle pain according to claim 1, characterized in that: The intelligent control module includes: a data preprocessing module, which is used to convert time domain signals into frequency domain signals and remove noise; a feature extraction module, which is used to extract key features from the processed data and simplify the model complexity; an event prediction module, which is used to predict possible future events through a trained CNN model; a strategy optimization module, which is used to continuously optimize the electrical stimulation strategy based on user feedback data; and a dynamic adjustment module, which is used to dynamically adjust the electrical stimulation parameters.

3. The real-time intervention system for cervical and lumbar muscle pain according to claim 1, characterized in that: include: A touch screen that displays the current working status and allows users to adjust settings through simple gestures; The mobile application connects to a smartphone via Bluetooth or Wi-Fi, allowing users to view detailed historical data reports on their phones and customize personalized electrical stimulation plans; the voice recognition module is used to support users to control the device through voice commands; the natural language processing module is used to understand the user's natural language expression and adjust the electrical stimulation strategy according to the user's needs.

4. The real-time intervention system for cervical and lumbar muscle pain according to claim 1, characterized in that: include: Emergency stop button to quickly interrupt electrical stimulation in any situation; The user adaptability test program is used to guide users to complete the adaptability test before first use to ensure that the electrical stimulation parameters are suitable for their personal physique.

5. The real-time intervention system for cervical and lumbar muscle pain according to claim 1, characterized in that: include: User portrait building module, used to build user portraits by collecting user behavior data and health data; The personalized recommendation system module is used to combine user portraits and deep learning models to provide users with recommendations on the electrical stimulation intensity and frequency that best suits their current state.

6. The real-time intervention system for cervical and lumbar muscle pain according to claim 1, characterized in that: include: User interface and interaction design module, used to provide touch screen operation, mobile application integration and voice control support; Graphical user interface (GUI), used to display various operation instructions and real-time status; voice assistant, used to provide voice prompts and receive user voice instructions.

7. The real-time intervention system for cervical and lumbar myalgia according to claim 1, characterized in that: include: Safety consideration module, used to implement overheat protection, emergency stop function and user adaptability test; Sensor fault detection mechanism, used to detect whether the sensor is working properly; Hardware protection circuit to prevent short circuit and overload at the hardware level; User safety training module is used to educate users on how to use the system correctly and avoid misoperation.

8. The real-time intervention system for cervical and lumbar muscle pain according to claim 1, characterized in that: The intelligent control module also includes: an FFT transformation module, which is used to convert time domain signals into frequency domain signals and remove noise; a PCA algorithm module, which is used to extract key features from processed data and simplify model complexity; a CNN model module, which is used to predict possible future events through a trained CNN model; a DQN algorithm module, which is used to continuously optimize the electrical stimulation strategy based on user feedback data; and a Kalman filtering algorithm module, which is used to dynamically adjust electrical stimulation parameters to adapt to different environments and individual differences.

9. The real-time intervention system for cervical and lumbar muscle pain according to claim 1, characterized in that: include: User behavior analysis module, used to analyze user usage habits; Recommendation algorithm optimization module, used to improve the accuracy of recommendation algorithm; The user feedback collection module is used to collect user usage feedback and adjust the recommendation strategy.

10. The real-time intervention system for cervical and lumbar muscle pain according to claim 1, characterized in that: include: User health monitoring module, used to monitor the user's health status in real time and remind the user to take measures when abnormalities occur; The user personalized setting module is used to allow the user to set the electrical stimulation parameters according to their own preferences.

Images