Multi-signal fusion massage glove teaching system and control method

Abstract

The invention provides a multi-signal fusion massage glove teaching system and a control method, and the system comprises a glove body, and a pressure sensing module, a motion sensing module and a myoelectricity sensing module which are disposed on the glove body, and is in electric signal connection with the pressure sensing module, the motion sensing module and the myoelectricity sensing module through a control unit. The control unit is used for analyzing the collected massage pressure, motion trail and electromyographic signals, and synchronous and in-situ collection of force-motion-physiology multi-dimensional information of massage manipulation in a real clinical environment is achieved. The design overcomes the limitation that in the prior art, a real operation scene is separated, and only single-aspect measurement can be carried out, and a hardware foundation is laid for comprehensive and objective quantitative evaluation of the massage manipulation. The integrated structure greatly facilitates the use of an operator, and the system can evaluate the manipulation quality online and give guidance immediately, thereby greatly improving the teaching efficiency and the training effect.

Description

Technical Field

[0001] This invention relates to a multi-signal fusion massage glove teaching system and control method. Background Technology

[0002] The transmission and evaluation of massage techniques have long relied on the subjective feelings of the master and the comprehension of the student, lacking objective and quantifiable standards. This has severely restricted the standardization, scientification, and internationalization of the discipline of massage. While some massage technique measuring instruments exist, they have significant shortcomings: Firstly, the teaching often takes place on simulation platforms, detached from real clinical environments. This results in insufficient student engagement and a lack of immersive learning experience, leading to slow learning progress. Secondly, the reliance on single-type sensors fails to comprehensively capture the evenness, gentleness, persistence, strength, and depth of massage techniques. It also prevents students from experiencing the force application characteristics of the massage process from different perspectives and from analyzing technique deficiencies from multiple angles, resulting in low teaching efficiency. Therefore, in view of the above problems, the present invention proposes a multi-signal fusion massage glove teaching system and control method. Summary of the Invention

[0003] This invention provides a multi-signal fusion massage glove teaching system and control method, which can effectively solve the above problems.

[0004] This invention is implemented as follows: A multi-signal fusion massage glove teaching system includes: The glove body includes a palm portion adapted to the wearer's hand, a finger portion located on the outer side of the palm portion, a back of the hand located opposite the palm portion, and a forearm portion located on the side of the palm portion away from the finger portion. The pressure sensing module is set in the corresponding areas of the fingers and the fingertips of the operator, as well as the corresponding areas of the palm and the thenar, hypothenar, and palmar areas of the operator's palm. The pressure sensing module is used to detect the massage pressure during the massage process. A motion sensing module is installed on the back of the hand and in the corresponding area in the center of the back of the operator's hand. The motion sensing module is used to detect the movement trajectory of the operator during the massage process. An electromyography (EMG) sensing module is installed on the forearm and in corresponding areas on the inner and outer sides of the operator's forearm. The EMG sensing module is used to detect EMG signals during the operator's massage. The control unit is located at the junction of the palm and fingers. It is electrically connected to the pressure sensing module, motion sensing module, and electromyography (EMG) sensing module. The control unit is used to analyze the collected massage pressure, motion trajectory, and EMG signals.

[0005] As a further improvement, the pressure sensing module includes a pressure sensor and a pressure data processor. The pressure sensor and the pressure data processor are electrically connected in sequence to a pressure signal operational amplifier module, a pressure signal filtering module, and a pressure signal analog-to-digital converter module. The pressure signal operational amplifier module is used to amplify the pressure micro-signal collected by the pressure sensor. The pressure signal filtering module is used to filter and reduce noise in the pressure signal. The pressure signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The pressure data processor transmits the signal to the control unit.

[0006] As a further improvement, the pressure sensor collects the pressure peak, pressure average, pressure symmetry, and pressure distribution center during the operator's massage process.

[0007] As a further improvement, the motion sensing module includes an integrated accelerometer, gyroscope, magnetometer, and motion data processor. The accelerometer, gyroscope, and magnetometer are each independently electrically connected to the motion data processor. The motion data processor converts the collected data signals into corresponding displacement changes and angular velocity values ​​and transmits them to the control unit.

[0008] As a further improvement, the accelerometer and the motion data processor are electrically connected in sequence to a displacement signal operational amplifier module, a displacement signal filtering module, and a displacement signal analog-to-digital converter module. The displacement signal operational amplifier module is used to amplify the displacement micro-signal collected by the accelerometer, the displacement signal filtering module is used to filter and reduce noise in the displacement signal, and the displacement signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The gyroscope and the motion data processor are electrically connected in sequence to an angular velocity signal operational amplifier module, an angular velocity signal filtering module, and an angular velocity signal analog-to-digital converter module. The angular velocity signal operational amplifier module is used to amplify the angular velocity micro-signal collected by the gyroscope. The angular velocity signal filtering module is used to filter and reduce noise in the angular velocity signal. The angular velocity signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The magnetometer and the motion data processor are electrically connected in sequence to a magnetic signal operational amplifier module, a magnetic signal filtering module, and a magnetic signal analog-to-digital converter module. The magnetic signal operational amplifier module is used to amplify the magnetic micro-signal collected by the magnetometer. The magnetic signal filtering module is used to filter and reduce noise in the magnetic motion signal. The magnetic signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal.

[0009] As a further improvement, the motion sensing module collects the operator's lifting and pinching frequency, lifting and pinching displacement, smoothness of movement trajectory, and hand stability during the massage process.

[0010] As a further improvement, the electromyography (EMG) sensing module includes an EMG sensor and an EMG data processor. The EMG sensor and the EMG data processor are electrically connected in sequence to an EMG signal operational amplifier module, an EMG signal filtering module, and an EMG signal analog-to-digital converter module. The EMG signal operational amplifier module is used to amplify the EMG micro-signals collected by the EMG sensor. The EMG signal filtering module is used to filter and reduce noise in the EMG signal. The EMG signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The EMG data processor transmits the signal to the control unit.

[0011] As a further improvement, the electromyography sensing module collects the muscle activation sequence, muscle activation intensity, synergistic contraction rate, and muscle fatigue during the operator's massage process.

[0012] A control method for a multi-signal fusion massage glove teaching system, applied to a multi-signal fusion massage glove teaching system, includes the following steps: S1: Initialize the system. The operator, wearing gloves, performs specific calibration actions to complete the baseline calibration of the sensor signals. S2: The operator selects the target massage technique and retrieves the standard technique model corresponding to that technique; S3; The operator performs massage training. The pressure sensing module, motion sensing module, and electromyography sensing module simultaneously collect pressure, motion, and electromyography signals. The electrical signals are filtered, noise-reducing preprocessed, and converted into digital signals. S4: Compare the real-time feature parameters extracted in step S3 with the standard method model loaded in step S2, and calculate the degree of difference between the current method and the standard method in a single dimension. Difference based on a single dimension Calculate the overall difference ΔG; S5: Based on the comprehensive difference degree and specific deviation characteristic parameters calculated in step S4, generate specific control instructions and output them through the real-time feedback module.

[0013] Furthermore, the overall difference ΔG satisfies the following relationship: ; in, These are the weighting coefficients for each feature parameter.

[0014] The beneficial effects of this invention are: (1) This invention organically combines pressure, motion, and electromyography (EMG) sensor modules with the glove body, enabling the synchronous acquisition of multi-dimensional information on the force, motion, and physiology of massage techniques in a real clinical environment. This invention overcomes the limitations of existing technologies that are detached from real-world operating scenarios and can only perform single-aspect measurements, laying a hardware foundation for a comprehensive and objective quantitative evaluation of massage techniques. Its integrated structure greatly facilitates the use of operators and improves teaching effectiveness.

[0015] (2) This invention not only includes multi-signal synchronous acquisition, but more importantly, it includes the steps of comparing with the standard technique model and generating real-time control instructions. It transforms the system from a passive data recorder into an active coach, which can evaluate the quality of techniques online and provide immediate guidance, greatly improving teaching efficiency and training effect. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the structure of the massage gloves of the present invention. Figure 1 .

[0018] Figure 2 This is a schematic diagram of the structure of the massage gloves of the present invention. Figure 1 .

[0019] Figure 3 This is a schematic diagram of the sensor process provided in an embodiment of the present invention.

[0020] Figure 4 This is a schematic diagram of the control method provided in an embodiment of the present invention.

[0021] The attached diagram is labeled as follows: 11. Glove body; 12. Palm; 13. Fingers; 14. Back of hand; 15. Forearm; 20. Pressure sensing module; 30. Motion sensing module; 40. Electromyography (EMG) sensing module; 50. Control unit. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention.

[0023] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0024] Reference Figures 1-2 As shown, a multi-signal fusion massage glove teaching system includes: The glove body 10 includes a palm portion 11 adapted to the wearer's hand, a finger portion 12 disposed on the outside of the palm portion 11, a back of the hand 13 disposed opposite to the palm portion 11, and a forearm portion 14 disposed on the side of the palm portion 11 away from the finger portion 12. The pressure sensing module 20 is set in the corresponding area of ​​the finger part 12 and the fingertip of the operator, and the corresponding area of ​​the palm part 11 and the thenar eminence, hypothenar eminence and palm center of the operator's palm. The pressure sensing module 20 is used to detect the massage pressure during the massage process. A motion sensing module 30 is disposed on the back of the hand 13 and the corresponding area in the center of the back of the operator's hand. The motion sensing module 30 is used to detect the movement trajectory of the operator during the massage process. An electromyography (EMG) sensing module 40 is disposed on the forearm 14 and in the corresponding areas of the inner and outer sides of the operator's forearm. The EMG sensing module 40 is used to detect EMG signals during the operator's massage. The control unit 50 is located at the connection between the palm part 11 and the finger part 12. The control unit 50 is electrically connected to the pressure sensing module 20, the motion sensing module 30, and the electromyography sensing module 40. The control unit 50 is used to analyze the collected massage pressure, motion trajectory, and electromyography signals.

[0025] Reference Figures 1-3As shown, the pressure sensing module 20 includes a pressure sensor and a pressure data processor. The pressure sensor and the pressure data processor are electrically connected in sequence to a pressure signal operational amplifier module, a pressure signal filtering module, and a pressure signal analog-to-digital converter module. The pressure signal operational amplifier module is used to amplify the pressure micro-signal collected by the pressure sensor. The pressure signal filtering module is used to filter and reduce noise in the pressure signal. The pressure signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The pressure data processor transmits the signal to the control unit 50.

[0026] Reference Figure 3 As shown, the pressure sensors collect the pressure peak, average pressure, pressure symmetry, and pressure distribution center during the operator's massage process. The pressure peak is the maximum pressure during pinching, the average pressure is the average pressure within one pinching cycle, the pressure symmetry is the ratio or difference between the pressure of the thumb and the other four fingers, and the pressure distribution center is whether the pressure is evenly distributed on the fingertips. The pressure peak, average pressure, and pressure symmetry are measured using miniature single-point pressure sensors. In this embodiment, a pressure sensor of model FSR402 is used. This pressure sensor is located in the fingertips of the thumb, index finger, and middle finger. The sensor's range is 0-50N, which can cover the range of human strength. The software reads the sum of the pressure of the three fingertips in real time. The formula for calculating pressure symmetry is Symmetry = thumb pressure / index finger pressure + middle finger pressure. A ratio close to 1 indicates good symmetry; a ratio much greater than 1 indicates that the thumb is too heavy; and a ratio much less than 1 indicates that the other fingers are too heavy. The pressure distribution center is measured using a flexible pressure array sensor, which covers the thenar and hypothenar eminences and the palm area.

[0027] Reference Figure 3 As shown, the motion sensing module 30 includes an integrated accelerometer, gyroscope, magnetometer, and motion data processor. The accelerometer, gyroscope, and magnetometer are each independently electrically connected to the motion data processor. The motion data processor converts the collected data signals into corresponding displacement changes and angular velocity values ​​and transmits them to the control unit 50.

[0028] As a further improvement, the accelerometer and the motion data processor are electrically connected in sequence to a displacement signal operational amplifier module, a displacement signal filtering module, and a displacement signal analog-to-digital converter module. The displacement signal operational amplifier module is used to amplify the displacement micro-signal collected by the accelerometer, the displacement signal filtering module is used to filter and reduce noise in the displacement signal, and the displacement signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The gyroscope and the motion data processor are electrically connected in sequence to an angular velocity signal operational amplifier module, an angular velocity signal filtering module, and an angular velocity signal analog-to-digital converter module. The angular velocity signal operational amplifier module is used to amplify the angular velocity micro-signal collected by the gyroscope. The angular velocity signal filtering module is used to filter and reduce noise in the angular velocity signal. The angular velocity signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The magnetometer and the motion data processor are electrically connected in sequence to a magnetic signal operational amplifier module, a magnetic signal filtering module, and a magnetic signal analog-to-digital converter module. The magnetic signal operational amplifier module is used to amplify the magnetic micro-signal collected by the magnetometer. The magnetic signal filtering module is used to filter and reduce noise in the magnetic motion signal. The magnetic signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal.

[0029] As a further improvement, the motion sensing module 30 collects the lifting and pinching frequency, lifting and pinching displacement, motion trajectory smoothness, and hand stability during the operator's massage process. The lifting and pinching frequency is the number of lifting and pinching operations completed per unit time; the lifting and pinching displacement is the change in height when lifting and lowering the hand; the motion trajectory smoothness is the rate of change of acceleration, with a lower value indicating smoother movement; and the hand stability is whether there is unnecessary hand shaking during the operation. The lifting and pinching frequency, lifting and pinching displacement, motion trajectory smoothness, and hand stability all use a 9-axis IMU, including an accelerometer, a gyroscope, and a magnetometer. The lifting and pinching frequency is measured by fixing the IMU to the center of the back of the hand, specifically the back of the third metacarpal bone. A fast Fourier transform is performed on the Z-axis signal of the accelerometer to find the dominant frequency. The lifting and pinching displacement is obtained by performing a second integration on the Z-axis signal of the accelerometer. The motion trajectory smoothness is obtained by analyzing the acceleration of the hand's motion trajectory, and the hand stability is obtained by calculating the amplitude of the angular velocity vector measured by the IMU when the hand is stationary or maintains a certain posture.

[0030] As a further improvement, the electromyography (EMG) sensing module 40 includes an EMG sensor and an EMG data processor. The EMG sensor and the EMG data processor are electrically connected in sequence to an EMG signal operational amplifier module, an EMG signal filtering module, and an EMG signal analog-to-digital converter module. The EMG signal operational amplifier module is used to amplify the EMG micro-signals collected by the EMG sensor. The EMG signal filtering module is used to filter and reduce noise in the EMG signal. The EMG signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The EMG data processor transmits the signal to the control unit 50.

[0031] As a further improvement, the electromyography (EMG) sensing module 40 collects the muscle activation sequence, muscle activation intensity, synergistic contraction rate, and muscle fatigue during the operator's massage process. Muscle activation sequence refers to when the flexor and extensor muscles begin to exert force and when they relax. Muscle activation intensity refers to the degree of force exertion by the flexor and extensor muscles. Synergistic contraction rate refers to the degree of simultaneous activation of the flexor and extensor muscles; high synergistic contraction indicates muscle stiffness and low efficiency. Muscle fatigue is the rate at which the median EMG frequency decreases over time. The EMG sensing module 40 uses a bipolar dry electrode sEMG sensor, located on the inner and outer sides of the forearm. The muscle activation sequence involves bandpass filtering, full-wave rectification, and linear envelope processing of the original sEMG signal. A baseline threshold is set; exceeding the threshold indicates the start of activation, and falling below the threshold indicates the end of activation. Muscle activation intensity is calculated as the root mean square value of the rectified sEMG signal. Synergistic contraction rate is the percentage of the antagonist muscle integral EMG value to the sum of the agonist and antagonist muscle integral EMG values ​​within one action cycle. A higher percentage indicates more severe synergistic contraction and lower efficiency. Muscle fatigue is determined by performing a short-time Fourier transform on the original sEMG signal and then calculating the median frequency, which is the frequency point in the power spectrum that divides the total power in half. During fatigue, the spectrum shifts to the left, and the median frequency decreases over time. The faster the rate of decrease, the higher the degree of fatigue.

[0032] Reference Figure 4 As shown, a control method for a multi-signal fusion massage glove teaching system, applied to a multi-signal fusion massage glove teaching system, includes the following steps: S1: Initialize the system. The operator, wearing gloves, performs specific calibration actions to complete the baseline calibration of the sensor signals. S2: The operator selects the target massage technique and retrieves the corresponding standard technique model. First, we need a reference point. We invite several renowned massage masters, who, wearing the equipment, perform what they consider the most standard and effective "grasping" technique, recording a large amount of standard operation data. Using machine learning algorithms, we learn the coordinated change patterns of all the above quantitative indicators over time, ultimately forming one or more standard technique models. This defines how pressure, movement, and electromyography (EMG) signals should coordinately change over time under ideal conditions. This invention constructs the standard massage technique model using a Gaussian mixture model. First, we invite several industry-recognized renowned massage masters as standard technique providers. Under standardized operating conditions, they wear the massage glove system described in this invention to perform the target massage technique. The system continuously and synchronously collects and records the original pressure, movement, and EMG signals generated by each expert during the operation, using hardware synchronization. It collects multiple operation cycle data generated by multiple target massage experts when performing specific techniques. For each operation cycle, a set of d-dimensional feature parameters is extracted from the synchronously collected pressure, movement, and EMG signals to form a feature vector x. The feature parameters include, but are not limited to, peak pressure, average pressure, pressure symmetry, pressure distribution center, pinching frequency, pinching displacement, smoothness of movement trajectory, and hand stability. Assuming a total of N valid operation cycles are collected, the training dataset is obtained. Each of them Given a d-dimensional vector, the probability density function of a Gaussian mixture model is composed of a mixture of K Gaussian distribution components, and its mathematical expression is: ; K: The total number of Gaussian distribution components in the Gaussian mixture model, which is a preset hyperparameter; The mixing weights for the k-th Gaussian component satisfy the following condition: ; The mean is The covariance matrix is The multidimensional Gaussian probability density function; The set of model parameters to be optimized; The training process involves iteratively executing an E-step (calculating the posterior probability of a sample belonging to each component) and an M-step (updating the model parameters θ) until the model's log-likelihood function converges, ultimately yielding the optimal parameters θ*. This set of θ* constitutes the standard technique digital model for the massage expert. Finally, cross-validation is used to evaluate the performance of the trained Gaussian mixture model. The trained model parameters θ* are associated with the corresponding expert information and technique type, and then encrypted and stored in the system's model database for real-time evaluation.

[0033] S3; The operator performs massage training. The pressure sensing module, motion sensing module, and electromyography sensing module simultaneously collect pressure, motion, and electromyography signals. The electrical signals are filtered, noise-reducing preprocessed, and converted into digital signals. S4: Compare the real-time feature parameters extracted in step S3 with the standard method model loaded in step S2, and calculate the normalized absolute difference between the current method and the standard method in a single dimension. Difference based on a single dimension Calculate the overall difference ΔG; S5: Based on the comprehensive difference and specific deviation characteristic parameters calculated in step S4, specific control instructions are generated and output through the real-time feedback module. Typical problems that the system can diagnose include: stiffness, i.e., rigid force exertion, which is manifested by electromyography showing an extremely high rate of coordinated contraction of flexor and extensor muscles, and the muscles cannot fully relax throughout the cycle. Pressure signals show stiff force changes, and motion signals show poor smoothness of movement. The underlying cause is excessive tension on the part of the operator, with agonist and antagonist muscles competing simultaneously, resulting in wasted energy and insufficient force penetration.

[0034] Insufficient or excessive grip strength will result in a pressure signal that is significantly lower or higher than the standard range. The underlying cause is inaccurate perception and control of force. "Incoordination": The signals manifest as incorrect muscle activation timing (e.g., failure to relax when it should) in electromyography (EMG). Motor signals show unstable pinching frequency and insufficient displacement. The underlying cause is lack of proficiency in the movements and poor neuromuscular control.

[0035] "Imminent fatigue" is manifested by a continuous decrease in the average power frequency of electromyography (EMG) signals. The underlying cause is excessive local muscle load, which is about to lead to exhaustion and affects the sustainability of the manipulation technique.

[0036] In this embodiment, the overall difference ΔG satisfies the following relationship: ; in, These are the weighting coefficients for each feature parameter.

[0037] The comprehensive difference model is the core decision-making algorithm of this system. Its goal is to fuse multiple heterogeneous feature parameters extracted from multimodal signals into a unified, quantifiable scalar value, used to objectively and comprehensively evaluate the overall deviation between the current operational method and the pre-stored standard method model. Let the set of feature parameters extracted by the current operational method be denoted as... Let the reference set of feature parameters for the standard method model be . First, calculate the normalized absolute dissimilarity for each feature parameter. ,in, This is the reasonable dynamic range of the characteristic parameter under the standard model, used to eliminate dimensions and make all differences on the same order of magnitude.

[0038] Then, calculate the overall difference degree. ΔG is the calculated overall difference, a dimensionless scalar value. The smaller ΔG is, the closer the current technique is to the standard technique; the larger ΔG is, the greater the deviation. These are the weighting coefficients for each feature parameter. These weighting coefficients reflect the importance of that feature to the quality of the evaluation method. The assignment of values ​​is crucial to the scientific validity of the model. It is not subjectively set, but determined through the following method: First, several experts in the field of massage were invited to construct a judgment matrix by comparing the importance of each feature to the quality of the massage technique pairwise. After a consistency check, the weights of each feature were calculated. This method fully utilizes expert experience. Second, a large number of standard data samples from expert operations were collected, and the entropy value of each feature parameter across all samples was calculated. The smaller the entropy value of a feature, the less volatile and more stable the data, and the stronger its ability to distinguish between good and bad massage techniques; therefore, it should be given a greater weight. Finally, the results of the AHP method and the entropy weight method were combined to obtain a final weight set that respects expert experience and conforms to the objective laws of data. An example weight allocation is shown in the table below:

[0039] The output of the overall difference ΔG can be divided into multiple levels for intuitive evaluation and to trigger different levels of feedback, as shown in the table below:

[0040] By organically integrating pressure, motion, and electromyography (EMG) sensing modules with the glove body, the system achieves synchronous, in-situ acquisition of multi-dimensional "force-motion-physiology" information of massage techniques in a real clinical environment. After analysis and conclusions, the system provides specific adjustment instructions, displaying three real-time curves on the software interface: pressure, lifting and pinching displacement, and EMG activation intensity. Green indicates within the standard range, and red indicates abnormality. Text prompts are also provided, such as "Too much grip force, please reduce the force by 10%", "Insufficient lifting height, please lift 2cm higher", "Insufficient relaxation! Note that your fingers should be completely relaxed after lifting", and "Too much synergistic contraction, imagine your forearm as soft as water". Auditory feedback can also be provided, using different tones or rhythmic sounds to guide the rhythm. For example, a "lift-release-lift-release" beat sound can help the operator stabilize the frequency. A "humming" warning sound is emitted when a serious error occurs. In another embodiment, a micro-vibration motor is integrated into the glove body through tactile feedback. When the grip force is too great, the motor at the thumb vibrates; when relaxation is needed, the motor at the wrist vibrates. Provides intuitive feedback without requiring you to look away.

[0041] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the invention by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the invention should be included within the scope of protection of the invention.

Claims

1. A multi-signal fusion massage glove teaching system, characterized in that, include: The glove body (10) includes a palm part (11) adapted to the wearer's hand, a finger part (12) located on the outside of the palm part (11), a back of the hand (13) located opposite to the palm part (11), and a forearm part (14) located on the side of the palm part (11) away from the finger part (12). The pressure sensing module (20) is set in the corresponding area of ​​the finger (12) and the fingertip of the operator, and in the corresponding area of ​​the palm (11) and the thenar eminence, hypothenar eminence and palm center of the operator's palm. The pressure sensing module (20) is used to detect the massage pressure during the massage process. A motion sensing module (30) is set on the back of the hand (13) and the corresponding area in the center of the back of the operator's hand. The motion sensing module (30) is used to detect the movement trajectory of the operator during the massage process. An electromyography (EMG) sensor module (40) is set in the forearm (14) and the corresponding areas of the inner and outer sides of the operator's forearm. The EMG sensor module (40) is used to detect the EMG signals during the operator's massage. The control unit (50) is located at the connection between the palm (11) and the fingers (12). The control unit (50) is electrically connected to the pressure sensing module (20), the motion sensing module (30), and the electromyography sensing module (40). The control unit (50) is used to analyze the collected massage pressure, motion trajectory, and electromyography signals.

2. The multi-signal fusion massage glove teaching system according to claim 1, characterized in that, The pressure sensing module (20) includes a pressure sensor and a pressure data processor. The pressure sensor and the pressure data processor are electrically connected in sequence to a pressure signal operational amplifier module, a pressure signal filtering module, and a pressure signal analog-to-digital converter module. The pressure signal operational amplifier module is used to amplify the pressure micro-signal collected by the pressure sensor. The pressure signal filtering module is used to filter and reduce noise in the pressure signal. The pressure signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The pressure data processor transmits the signal to the control unit (50).

3. The multi-signal fusion massage glove teaching system according to claim 2, characterized in that, The pressure sensors respectively collect the pressure peak value, pressure average value, pressure symmetry, and pressure distribution center during the operator's massage process.

4. The multi-signal fusion massage glove teaching system according to claim 1, characterized in that, The motion sensing module (30) includes an integrated accelerometer, gyroscope, magnetometer and motion data processor. The accelerometer, gyroscope and magnetometer are electrically connected to the motion data processor independently. The motion data processor converts the collected data signals into corresponding displacement changes and angular velocity values ​​and transmits them to the control unit (50).

5. The multi-signal fusion massage glove teaching system according to claim 4, characterized in that, The accelerometer and the motion data processor are electrically connected in sequence to a displacement signal operational amplifier module, a displacement signal filtering module, and a displacement signal analog-to-digital converter module. The displacement signal operational amplifier module is used to amplify the displacement micro-signal collected by the accelerometer, the displacement signal filtering module is used to filter and reduce noise in the displacement signal, and the displacement signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The gyroscope and the motion data processor are electrically connected in sequence to an angular velocity signal operational amplifier module, an angular velocity signal filtering module, and an angular velocity signal analog-to-digital converter module. The angular velocity signal operational amplifier module is used to amplify the angular velocity micro-signal collected by the gyroscope. The angular velocity signal filtering module is used to filter and reduce noise in the angular velocity signal. The angular velocity signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The magnetometer and the motion data processor are electrically connected in sequence to a magnetic signal operational amplifier module, a magnetic signal filtering module, and a magnetic signal analog-to-digital converter module. The magnetic signal operational amplifier module is used to amplify the magnetic micro-signal collected by the magnetometer. The magnetic signal filtering module is used to filter and reduce noise in the magnetic motion signal. The magnetic signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal.

6. The multi-signal fusion massage glove teaching system according to claim 4, characterized in that, The motion sensing module (30) collects the operator's lifting and pinching frequency, lifting and pinching displacement, smoothness of movement trajectory, and hand stability during the massage process.

7. The multi-signal fusion massage glove teaching system according to claim 1, characterized in that, The electromyography (EMG) sensing module (40) includes an EMG sensor and an EMG data processor. The EMG sensor and the EMG data processor are electrically connected in sequence to an EMG signal operational amplifier module, an EMG signal filtering module, and an EMG signal analog-to-digital converter module. The EMG signal operational amplifier module is used to amplify the EMG micro-signals collected by the EMG sensor. The EMG signal filtering module is used to filter and reduce noise in the EMG signal. The EMG signal analog-to-digital converter module is used to convert the filtered and noise-reduced electrical signal into a digital signal. The EMG data processor transmits the signal to the control unit (50).

8. The multi-signal fusion massage glove teaching system according to claim 7, characterized in that, The electromyography sensing module (40) collects the muscle activation sequence, muscle activation intensity, synergistic contraction rate, and muscle fatigue during the operator's massage process.

9. A control method for a multi-signal fusion massage glove teaching system, applied to the multi-signal fusion massage glove teaching system as described in any one of claims 1 to 8, comprising the following steps: S1: Initialize the system. The operator, wearing gloves, performs specific calibration actions to complete the baseline calibration of the sensor signals. S2: The operator selects the target massage technique and retrieves the standard technique model corresponding to that technique; S3; The operator performs massage training. The pressure sensing module, motion sensing module, and electromyography sensing module simultaneously collect pressure, motion, and electromyography signals. The electrical signals are filtered, noise-reducing preprocessed, and converted into digital signals. S4: Compare the real-time feature parameters extracted in step S3 with the standard method model loaded in step S2, and calculate the degree of difference between the current method and the standard method in a single dimension. Based on the degree of difference in a single dimension Calculate the overall difference ΔG; S5: Based on the comprehensive difference degree and specific deviation characteristic parameters calculated in step S4, generate specific control instructions and output them through the real-time feedback module.

10. The control method for a multi-signal fusion massage glove teaching system according to claim 9, wherein the comprehensive difference degree ΔG satisfies the following relationship: ； in, These are the weighting coefficients for each feature parameter.

Images