Intelligent neck muscle drafting device

Abstract

The invention relates to an intelligent neck muscle drafting device, and belongs to the technical field of medical instruments. Comprising a surface electromyogram signal acquisition unit, and a dry electrode and a signal acquisition circuit of the surface electromyogram signal acquisition unit are responsible for acquiring neck electromyogram signals; the signal processing and analysis unit generates a drafting strategy by means of a deep learning algorithm through filtering, amplification, feature extraction and diagnosis modules; the adjustable multi-angle drafting mechanism is composed of a frame main body, translation and rotation joints, a silica gel pad, an air pump and the like, and multi-dimensional movement and comfortable adaptation of the neck are achieved; and a man-machine interaction unit and a touch display screen are also arranged, so that medical staff and patients can operate and feed back conveniently. The main control unit accurately controls the traction mechanism to act according to cooperative work of all the parts, personalized treatment and real-time monitoring, feedback and adjustment can be achieved, the neck muscle rehabilitation effect and the comfort level of a patient are effectively improved, and the neck muscle rehabilitation device is suitable for related rehabilitation scenes of neck muscles.

Description

Technical Field

[0001] The invention relates to the technical field of medical devices, in particular to an intelligent neck muscle stretching device. Background Art

[0002] Chronic nonspecific neck pain has a high incidence in modern people, which has a significant negative impact on patients' quality of life and work efficiency. Its etiology is closely related to long-term poor posture, muscle overuse or strain, etc., which lead to neck muscle tension and abnormal increase in muscle tension.

[0003] Currently, there are many limitations in the diagnosis of neck muscle problems. Physical examinations mainly rely on the doctor's subjective experience and manual palpation, which makes it difficult to accurately quantify subtle muscle lesions; patients' subjective descriptions are often highly subjective and vague, and cannot provide a reliable objective basis for accurate diagnosis; although imaging examinations can present structural information such as bones, it is difficult to effectively detect functional changes in muscles and early microscopic injuries. These traditional diagnostic methods are difficult to accurately determine the site and extent of neck muscle damage, which in turn affects the pertinence and effectiveness of subsequent treatment plans.

[0004] In terms of treatment, traditional neck stretching devices generally lack the ability to accurately perceive the real-time status of the neck muscles and dynamically feedback and adjust them. Most of them can only operate according to preset fixed modes or parameters, and cannot flexibly adjust key parameters such as stretching angle, strength, speed and time according to the actual condition of the patient's individual muscles (such as muscle tension, degree of injury, fatigue state, etc.). This not only easily leads to insufficient or excessive stretching, delaying the treatment process or causing secondary injuries, but also makes it difficult to meet the personalized treatment needs of different patients due to differences in age, gender, physical condition, etc., greatly limiting the improvement of treatment effects and the progress of patient recovery. Therefore, it is particularly urgent and necessary to develop an intelligent device that can accurately diagnose neck muscles and provide personalized stretching therapy. Summary of the invention

[0005] In view of this, the purpose of the present invention is to propose an intelligent neck muscle stretching device, which solves the problems of subjectivity and inaccuracy of traditional diagnosis, inability to monitor muscle status in real time, lack of personalized treatment, and opaque and difficult adjustment of treatment process information in the prior art by providing an intelligent neck muscle stretching device that is equipped with a surface electromyography signal dry electrode device, a signal processing and analysis module, an adjustable multi-angle stretching mechanism and a human-computer interaction interface.

[0006] The present invention is achieved through the following technical solutions:

[0007] An intelligent neck muscle stretching device comprises an adjustable multi-angle stretching mechanism, wherein a surface electromyography signal acquisition unit is externally connected to the adjustable multi-angle stretching mechanism, a signal processing and analysis unit is arranged between the adjustable multi-angle stretching mechanism and the surface electromyography signal acquisition unit, a human-machine interaction unit is externally connected to the adjustable multi-angle stretching mechanism via a line, and the human-machine interaction unit is respectively connected to the surface electromyography signal acquisition unit and the signal processing and analysis unit via lines.

[0008] Further, the adjustable multi-angle stretching mechanism includes a frame body, a horizontal translation joint is fixedly arranged at the bottom of the frame body near the shoulder, a first connecting plate is fixedly arranged on the top of the horizontal translation joint, a vertical translation joint is fixedly arranged on the top of the first connecting plate, a second connecting plate is fixedly arranged on the top of the vertical translation joint, an X-axis rotation joint is fixedly arranged on the top of the second connecting plate, a third connecting plate is fixedly arranged on the top of the X-axis rotation joint, a Y-axis rotation joint is fixedly arranged on the top of the second connecting plate above the X-axis rotation joint, a fourth connecting plate is fixedly arranged on the top of the Y-axis rotation joint, a Z-axis rotation joint is fixedly arranged above the fourth connecting plate, and a skull fixation sleeve is fixedly arranged on the top of the Z-axis rotation joint.

[0009] Furthermore, the first connecting plate, the second connecting plate, the third connecting plate and the fourth connecting plate are all fixedly provided with silicone pads that adapt to the user's body structure, the outer sides of the silicone pads are connected and fixedly provided with air pumps, and air chambers are provided inside the silicone pads. The silicone pads can change shape and hardness by adjusting the air pressure through the air pump.

[0010] Furthermore, the X-axis rotating joint, horizontal electromagnetic sliding joint, Y-axis rotating joint, vertical electromagnetic sliding joint and Z-axis rotating joint are all connected to a control box through lines, and the control box is fixedly arranged on the frame body. A motor driver, a circuit board, a microcontroller fixedly arranged on the circuit board and a data acquisition card fixedly arranged on the circuit board are fixedly arranged inside the control box.

[0011] Furthermore, the X-axis rotating joint, the horizontal electromagnetic sliding joint, the Y-axis rotating joint, the vertical electromagnetic sliding joint and the Z-axis rotating joint are all fixedly provided with an absolute photoelectric encoder and a strain gauge force sensor, and the absolute photoelectric encoder and the strain gauge force sensor are connected to the control box.

[0012] Furthermore, the horizontal translation joint and the vertical translation joint both use electromagnetic sliding sleeves.

[0013] Furthermore, the surface electromyography signal acquisition unit includes a dry electrode and a signal acquisition circuit connected to the dry electrode.

[0014] Furthermore, the signal processing and analysis unit includes a filtering circuit, an amplifying circuit, a time domain feature extraction unit, a frequency domain feature extraction unit and a data analysis and diagnosis module.

[0015] Furthermore, the human-computer interaction unit is configured as a touch display screen.

[0016] The beneficial effects of the present invention are:

[0017] The structural combination of the surface electromyography signal acquisition unit, the signal processing and analysis unit, the adjustable multi-angle drafting mechanism and the human-computer interaction unit is conducive to achieving excellent technical effects in many aspects.

[0018] The surface electromyography signal acquisition unit can accurately capture the electrical activity signals of the neck muscles through the cooperation of dry electrodes and signal acquisition circuits, providing basic data support for subsequent accurate diagnosis. The signal processing and analysis unit can deeply analyze the signal and accurately determine the location and degree of muscle injury through the coordinated operation of filtering circuits, amplification circuits, time domain feature extraction units, frequency domain feature extraction units and data analysis and diagnosis modules, and then generate personalized stretching strategies to achieve the effect of accurate diagnosis and personalized treatment.

[0019] The adjustable multi-angle stretching mechanism uses structures such as the frame body, horizontal translation joint, first connecting plate, vertical translation joint, second connecting plate, X-axis rotation joint, third connecting plate, Y-axis rotation joint, fourth connecting plate, Z-axis rotation joint and skull fixation sleeve to achieve multi-dimensional complex movement simulation of the neck, comprehensively stretch the neck muscles, and improve muscle flexibility and coordination. The silicone pads and air pump combination at each joint ensure the patient's comfortable experience and good adaptability.

[0020] The touch screen of the human-machine interaction unit, combined with the feedback mechanism of the entire device, facilitates medical staff operation and patient feedback, allowing the signal processing and analysis unit to optimize the stretching strategy based on feedback, achieve real-time monitoring and closed-loop control, ensure safe, reliable and effective treatment, and ultimately improve the overall treatment effect and patient satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is the overall device structure diagram;

[0022] Figure 2 This is the front view of the overall structure without the base;

[0023] Figure 3 This is a side view of the overall structure without the base;

[0024] Figure 4 This is a top view of the overall structure without the base;

[0025] Figure 5 This is an enlarged view of the rear side of the adjustable multi-angle drafting mechanism;

[0026] Figure 6 This is the internal structure diagram of the signal processing and analysis unit.

[0027] Description of reference numerals:

[0028] 1. Dry electrode; 2. Signal acquisition circuit; 3. Filter circuit; 4. Amplification circuit; 5. Time domain feature extraction unit; 6. Frequency domain feature extraction unit; 7. Data analysis and diagnosis module; 8. Frame body; 9. Horizontal translation joint; 10. First connecting plate; 11. Vertical translation joint; 12. Second connecting plate; 13. X-axis rotation joint; 14. Third connecting plate; 15. Y-axis rotation joint; 16. Fourth connecting plate; 17. Z-axis rotation joint; 18. Skull top fixation sleeve; 19. Silicone pad; 20. Microcontroller; 21. Data acquisition card; 22. Control box; 23. Absolute photoelectric encoder; 24. Strain gauge force sensor; 25. Human-computer interaction unit; 26. Signal processing and analysis unit. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0030] 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 invention claimed for protection, but merely represents selected embodiments of the present invention. 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] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0032] In the above description of the present invention, it should be noted that the terms "one side", "the other side", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0033] In addition, the term "same" does not mean that the parts must be absolutely the same, but slight differences are allowed. The term "vertical" only means that the positional relationship between the parts is more vertical than "parallel", and does not mean that the structure must be completely vertical, but can be slightly tilted.

[0034] like Figure 1-6 As shown, an embodiment of the present invention provides: an intelligent neck muscle stretching device, comprising the following structure;

[0035] Surface electromyography signal acquisition unit: It is composed of dry electrodes 1 and signal acquisition circuit 2. Dry electrodes 1 are distributed in key muscle groups according to the anatomical structure of human neck muscles, such as bilateral trapezius muscles, sternocleidomastoid muscles, cervical splenius muscles, etc., and collect weak electrical activity signals generated by muscle contraction through close contact with the skin. Signal acquisition circuit 2 uses a specific chip (such as Texas Instruments' ADS1299), which has multi-channel synchronous sampling, high-precision sampling, and filtering and amplification functions. It performs preliminary processing on the collected original signal, removes some noise and amplifies the signal amplitude, and then transmits the processed signal to the signal processing and analysis unit 26.

[0036] Signal processing and analysis unit 26: includes filter circuit 3, amplifier circuit 4, time domain feature extraction unit 5, frequency domain feature extraction unit 6 and data analysis and diagnosis module 7. Filter circuit 3 adopts a combination of FIR and IIR filters to adaptively adjust the filter parameters according to the signal spectrum characteristics, effectively filtering out high-frequency noise and low-frequency baseline drift in the signal. Amplifier circuit 4 adjusts the amplification factor in real time according to the signal strength to ensure that the signal is suitable for subsequent processing. Time domain feature extraction unit 5 calculates time domain feature parameters such as RMS, MAV and zero crossing times through a dedicated digital signal processor (DSP) chip to reflect the intensity, frequency and other information of muscle contraction. Frequency domain feature extraction unit 6 uses a fast Fourier transform (FFT) chip to perform spectrum analysis on the signal, calculates frequency domain feature parameters such as MF and MPF, and assists in judging the degree of muscle fatigue. Data analysis and diagnosis module 7 has a built-in database of neck muscle physiological characteristics based on a large amount of clinical sample data, and uses a convolutional neural network (CNN) combined with a recurrent neural network (RNN) in a deep learning algorithm to build a diagnostic model. CNN extracts the spatial feature information of signal features, and RNN captures the time series relationship of feature parameters. Through model analysis, it determines the location and degree of muscle injury and generates a stretching control strategy represented by digital coding, including different stretching angles, strengths, speeds and time combinations, providing precise instruction basis for the action of the adjustable multi-angle stretching mechanism.

[0037] Adjustable multi-angle drafting mechanism: Based on the frame body 8, it includes multiple joints and connecting parts. The horizontal translation joint 9 and the vertical translation joint 11 are in the form of electromagnetic sliding sleeves, which are respectively installed at the bottom of the frame body 8 near the shoulder and in the vertical direction. The precise displacement of the neck in the horizontal and vertical directions is achieved by electromagnetic force driving. The two are connected to other joints through the first connecting plate 10 and the second connecting plate 12 respectively. The X-axis rotation joint 13 is located in the lower middle part of the device, and rotates around the X-axis to achieve left and right rotation of the neck on the horizontal plane; the Y-axis rotation joint 15 is on the side of the middle part of the device, so that the neck produces lateral flexion or compound movement around the Y-axis; the Z-axis rotation joint 17 is near the head position at the top of the device to control the backward or forward tilt of the head around the Z-axis. These rotation joints are connected in sequence through the third connecting plate 14 and the fourth connecting plate 16, and an absolute photoelectric encoder 23 and a strain gauge force sensor 24 are installed at each joint to monitor the position information and force conditions of the joints, and feed back the information to the data acquisition card 21 in the control box 22. A silicone pad 19 is fixedly installed on each connecting plate and the skull fixing sleeve 18. The air chamber inside the silicone pad 19 adjusts the air pressure through an air pump to change the shape and hardness. When the joint moves, it is in close contact with the human body and transmits force to drive the head and neck to move. A microcontroller 20 and a data acquisition card 21 and a motor driver are fixedly installed in the control box 22. The motor driver receives the control strategy signal of the signal processing and analysis unit 26 to drive the motor of each joint to operate. The microcontroller 20 obtains sensor feedback information through the data acquisition card 21 and uses the PID algorithm to achieve closed-loop control to ensure the accuracy and safety of joint movement.

[0038] Human-computer interaction unit 25: It adopts the form of a touch screen display and is connected to the surface electromyography signal acquisition unit, the signal processing and analysis unit 26 and the adjustable multi-angle stretching mechanism through lines. It can display the electromyography signal characteristic parameters of the neck muscles, the diagnosis results, the working status of the stretching mechanism and the treatment progress in real time. Medical staff can enter the advanced setting interface after password verification and manually adjust the initial parameters of the stretching mechanism according to the individual conditions of the patient (such as age, weight, height, medical history, etc.). Patients can enter their own subjective feelings in the operation interface, such as pain level scores or comfort level descriptions. This information is transmitted to the signal processing and analysis unit 26 so that the stretching control strategy can be adjusted according to feedback, dynamic optimization during the treatment process can be achieved, and the personalization and effectiveness of the treatment can be improved.

[0039] When this embodiment is implemented, the following stages are completed:

[0040] Preparation

[0041] The medical staff first ensures that all parts of the device are intact and connected normally, and checks whether the touch screen displays the initial status information normally, such as the position of each joint, sensor data, etc. (it should be the default initial value at this time).

[0042] The patient takes a comfortable and stable sitting or supine position and relaxes the neck muscles. The medical staff takes out the dry electrode 1 and uses a medical alcohol cotton ball to clean the skin surface that the electrode will contact to remove grease, dirt and stratum corneum. Then the dry electrode 1 is accurately placed on the upper, middle and lower parts of the bilateral trapezius muscles, the bilateral sternocleidomastoid muscles, the bilateral cervical splenius muscles and other key muscle groups according to the anatomical structure of the neck muscles. For example, in the upper part of the bilateral trapezius muscles, the electrode is placed 2-3 cm above the midpoint of the line connecting the outer third of the clavicle and the acromion, and the long axis of the electrode is parallel to the direction of the muscle fibers. Each electrode is connected to the signal acquisition circuit 2 through a wire.

[0043] The signal acquisition circuit 2 is turned on, and the internal ADS1299 chip starts to synchronously sample the neck muscle electrical activity signal with 24-bit accuracy. The built-in low-pass filter (5th-order Butterworth filter structure, cut-off frequency 500Hz) of the chip filters out high-frequency noise, and the high-pass filter (3rd-order Chebyshev filter structure, cut-off frequency 10Hz) removes low-frequency baseline drift, while amplifying the weak electromyographic signal to the order of 0.1-1 volt. The preliminarily processed signal is transmitted to the signal processing and analysis unit 26.

[0044] Signal processing and analysis stage

[0045] After the signal enters the signal processing and analysis unit 26, it first reaches the filter circuit 3. The finite impulse response filter in the filter circuit 3 (using Xilinx's Virtex-6FPGA chip to implement, the number of taps is 64, and the Hamming window function method is used for design) accurately filters the high-frequency noise of the signal. For example, when there are high-frequency signals generated by electromagnetic interference in the environment, it can effectively remove these interferences and ensure the purity of the signal. The infinite impulse response filter (using Analog Devices' ADAU1701 chip, the order is 6, and the bilinear transformation method is used for design) removes the low-frequency baseline drift. The two can be adaptively adjusted by the microcontroller 20 according to the signal spectrum characteristics. Filter parameters.

[0046] The filtered signal enters the amplifier circuit 4, which uses a variable gain amplifier structure composed of a multi-stage operational amplifier (such as the OPA2277 operational amplifier of Texas Instruments). Through the digital potentiometer in the feedback network, the microcontroller 20 dynamically adjusts the amplification factor according to the signal strength to ensure that the signal has a suitable amplitude in subsequent processing. For example, when the collected signal is weak, the microcontroller 20 will instruct the digital potentiometer to adjust the amplification factor to increase the signal strength to a suitable range.

[0047] The adjusted signal enters the time domain feature extraction unit 5, and the root mean square value (RMS), the mean absolute value (MAV) and the number of zero crossings are calculated by a dedicated digital signal processor (DSP) chip (TMS320C6748 of Texas Instruments). The RMS calculation adopts the square sum averaging and square root algorithm, and the MAV calculation is realized by integrating and averaging the absolute value of the signal, with an integration time window of 100ms. The number of zero crossings is based on the accurate detection of the signal crossing the zero level, and a Schmitt trigger (NCS2201 of ONSEMI) is used to shape the signal during detection. The hysteresis voltage range of the Schmitt trigger is 0.1-1 volt, which can improve the accuracy of zero crossing detection and the ability to resist noise interference.

[0048] At the same time, the signal also enters the frequency domain feature extraction unit 6, and uses the fast Fourier transform (FFT) chip (Ana logDevices' ADSP-BF533) to perform spectrum analysis on the signal and calculate the median frequency (MF) and the mean power frequency (MPF). MF is determined by performing an area equal division algorithm on the power spectrum density curve, and MPF is calculated based on the integral of the product of the power spectrum density and the frequency and then divided by the total power. The FFT calculation adopts the base-2 time sampling algorithm, and the number of sampling points is 1024 points.

[0049] The extracted characteristic parameters are sent to the data analysis and diagnosis module 7, which compares the parameters with the database of physiological characteristics of neck muscles stored in the module. The database contains various characteristic parameter ranges and corresponding muscle state labels of neck muscles in rest, contraction, fatigue and other states under different age groups, genders and health conditions. The diagnostic model constructed by the convolutional neural network (CNN) built with the TensorFlow framework combined with the recurrent neural network (RNN) starts to work. CNN extracts spatial characteristic information of signal features, such as extracting features of the signal through the convolution layer (with 3 convolution layers, convolution kernel sizes of 3×3, 5×5 and 7×7, step size of 1, and padding mode of the same). RNN adopts the long short-term memory network (LSTM) structure with 2 hidden layers and 128 neurons in each layer to capture the time series relationship of characteristic parameters. Through model analysis, the location and degree of muscle injury are judged, and the stretching control strategy represented by digital coding is generated, including different stretching angles, strengths, speeds and time combinations. For example, if the patient is diagnosed with moderate tension in the middle of the left trapezius muscle, the model will generate a corresponding stretching strategy, such as rotating the X-axis rotation joint 13 to a certain angle, moving the horizontal translation joint 9 to a suitable position, stretching the area with a specific force and speed, and setting a suitable stretching time.

[0050] Stretch therapy implementation phase

[0051] The motor driver of the adjustable multi-angle drafting mechanism receives the drafting control strategy signal from the data analysis and diagnosis module 7. For example, for the motor driving the X-axis rotating joint 13, the motor driver converts the signal into the control current and pulse signal of the motor. The X-axis rotating joint 13 is located at the bottom of the device near the patient's shoulder, and a connection portion connected to the harmonic reducer is fixedly arranged on its top. The harmonic reducer is connected to the driving motor through a special coupling. When the motor receives the signal, the harmonic reducer reduces the speed, increases the torque and accurately transmits the signal, driving the X-axis rotating joint 13 to rotate according to a predetermined angle, realizing the rotational movement of the neck around the X-axis, and the rotation angle range is -60 degrees to 60 degrees, and the rotation accuracy is within ±0.5 degrees. During the rotation process, the absolute photoelectric encoder 23 (such as the ECN1313 type of Heidenhain) on the X-axis rotating joint 13 measures the position information of the joint in real time, and the strain gauge force sensor 24 (such as the FSG-1 type of Honeywell) detects the force applied to the joint, and this information is transmitted to the microcontroller 20 through the data acquisition card 21.

[0052] Similarly, the Y-axis rotation joint 15 is located on the side of the middle part of the device, and a high-precision angular contact ball bearing is fixed inside it, which can withstand large radial and axial forces. The internal absolute photoelectric encoder 23 and strain gauge force sensor 24 provide feedback information, and are driven by a drive motor (in conjunction with a motor driver) to drive the neck to rotate around the Y-axis or perform a combined lateral flexion and rotation movement.

[0053] The Z-axis rotation joint 17 is located at the top of the device near the patient's head. Its shell is made of lightweight aluminum alloy and has good heat dissipation performance. The internal absolute photoelectric encoder 23 and strain gauge force sensor 24 cooperate with the drive motor and motor driver to realize the rotation movement of the neck around the Z axis, such as the backward or forward tilt of the head.

[0054] The horizontal translation joint 9 is connected to the driving motor through a ball screw nut pair transmission mechanism. The bottom slider slides on a high-hardness stainless steel transverse guide rail. Driven by the motor, the neck is displaced in the horizontal direction. The displacement range is -10 cm to 10 cm, and the displacement accuracy is within ±0.2 cm. Its absolute photoelectric encoder 23 and strain gauge force sensor 24 monitor the displacement and force conditions in real time and provide feedback.

[0055] The vertical translation joint 11 is connected to the driving motor through a ball screw nut pair transmission mechanism. A slider on one side slides on the titanium alloy square tube vertical bracket. Driven by the motor, the neck is displaced in the vertical direction. The internal absolute photoelectric encoder 23 and strain gauge force sensor 24 provide feedback information for precise control.

[0056] A silicone pad 19 with adjustable shape and hardness is installed at each joint that contacts the patient's neck. The air pressure in the air chamber of the silicone pad 19 is adjusted by an air pump to change the shape and hardness to adapt to the contours and movement requirements of different parts of the human body, thereby improving comfort and contact stability. The surface of the silicone pad 19 is made of skin-friendly material, with an air permeability of 100-500 grams per square meter per day and an antibacterial rate of 90%-99%. For example, when the patient's neck is thin, the air pressure of the silicone pad 19 can be appropriately reduced to make it fit the neck better and avoid excessive pressure.

[0057] Human-computer interaction and feedback adjustment stage

[0058] Medical staff can enter the advanced settings interface after password verification and manually adjust the initial parameters of the stretching mechanism according to the individual conditions of the patient (such as age, weight, height, medical history, etc.). For example, for elderly patients or patients with weak bodies, they can operate on the touch screen to appropriately reduce the initial setting value of the stretching force, or adjust the stretching time according to the special needs of the patient.

[0059] The patient can input his or her subjective feelings in a specific area of ​​the operation interface. For example, by clicking on the pain level scoring option (0-10 points) or inputting a description of the comfort level (such as comfortable, slightly uncomfortable, painful, etc.), this information is transmitted to the signal processing and analysis unit 26 in the form of text or voice. When the patient reports that the pain is aggravated or uncomfortable, the signal processing and analysis unit 26 re-evaluates and adjusts the stretching control strategy based on the feedback information and the current electromyographic signal characteristics, such as reducing the stretching force, pausing the stretching, or adjusting the stretching angle, and then transmits the new strategy to the drive and control unit of the stretching mechanism to achieve dynamic optimization during the treatment process and improve the personalization and effectiveness of the treatment. For example, if the patient feels that the pain in a certain part of the neck is aggravated during the stretching process and the input pain score is high, the signal processing and analysis module will analyze that the stretching force may be too large or the angle is not appropriate, and regenerate the control strategy, such as reducing the driving motor power of the relevant joint or adjusting the joint movement angle, and then controlling the motor action through the motor driver to adjust the stretching state so that the patient feels more comfortable and can achieve a better treatment effect.

[0060] The technical effects of this embodiment are as follows:

[0061] Precise diagnosis and personalized treatment: The surface electromyography signal acquisition unit accurately collects the electrical activity of the neck muscles, and the advanced filtering, amplification, feature extraction and deep learning diagnostic models in the signal processing and analysis unit 26 can accurately determine the location and degree of muscle damage, and then generate a highly personalized stretching control strategy. This personalized treatment plan can effectively improve the treatment effect and shorten the recovery period according to the specific condition and physical condition of different patients.

[0062] Multi-angle and multi-dimensional stretching adjustment: The unique design of the adjustable multi-angle stretching mechanism includes horizontal translation joint 9, vertical translation joint 11, X-axis rotation joint 13, Y-axis rotation joint 15, and Z-axis rotation joint 17, which can realize the horizontal and vertical translation of the neck and the rotation around three coordinate axes. The joints work together to simulate a variety of complex neck movement postures, comprehensively stretch or treat the neck muscles, meet the stretching needs of different muscle groups in different directions, and effectively improve the flexibility, strength and coordination of the neck muscles.

[0063] Real-time monitoring and closed-loop control: The absolute photoelectric encoder 23 and strain gauge force sensor 24 installed at each joint can monitor the position information and force of the joint in real time, and transmit the information to the microcontroller 20 through the data acquisition card 21. The microcontroller 20 uses the PID algorithm for closed-loop control, compares the sensor feedback information with the target position and force value, and adjusts the output of the motor driver in time to accurately control the movement of the joint. This real-time monitoring and closed-loop control mechanism ensures the accuracy, stability and safety of the stretching process, avoids harm to the patient due to excessive stretching or uneven force, and also ensures that the stretching action is always carried out according to the predetermined strategy, improving the reliability and repeatability of the treatment.

[0064] Comfortable experience and good adaptability: The silicone pads 19 distributed at the joints and the contact parts with the patient have air chambers whose air pressure can be adjusted by an air pump to change the shape and hardness. This design can closely fit the physiological curves of the neck and head of different patients, while providing stable support and effective force transmission, greatly improving the comfort of patients during treatment. Whether it is patients of different body shapes and different neck shapes, or during long-term treatment, they can maintain good wearing comfort, reduce the resistance of patients due to discomfort, and facilitate the smooth progress of treatment.

[0065] Convenient human-computer interaction and dynamic optimization: The touch screen of the human-computer interaction unit 25 provides a convenient operation interface for medical staff and patients. Medical staff can easily set parameters and adjust treatment plans, and patients can provide timely feedback on their feelings. Based on patient feedback information and real-time monitoring data, the signal processing and analysis unit 26 can dynamically optimize the stretching control strategy so that the treatment process can be flexibly adjusted according to the patient's real-time response. This human-computer interaction and dynamic optimization function not only improves the personalization of treatment, but also enhances the patient's sense of participation and self-management ability during the treatment process, which helps to improve the overall treatment effect and patient satisfaction.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. An intelligent neck muscle stretching device, characterized in that: It comprises an adjustable multi-angle drafting mechanism, wherein a surface electromyography signal acquisition unit is externally connected to the adjustable multi-angle drafting mechanism, a signal processing and analysis unit is arranged between the adjustable multi-angle drafting mechanism and the surface electromyography signal acquisition unit, a human-machine interaction unit is externally connected to the adjustable multi-angle drafting mechanism via lines, and the human-machine interaction unit is respectively connected to the surface electromyography signal acquisition unit and the signal processing and analysis unit via lines.

2. The intelligent neck muscle stretching device according to claim 1, characterized in that: The adjustable multi-angle drafting mechanism includes a frame body, a horizontal translation joint is fixedly arranged at the bottom of the frame body near the shoulder, a first connecting plate is fixedly arranged on the top of the horizontal translation joint, a vertical translation joint is fixedly arranged on the top of the first connecting plate, a second connecting plate is fixedly arranged on the top of the vertical translation joint, an X-axis rotation joint is fixedly arranged on the top of the second connecting plate, a third connecting plate is fixedly arranged on the top of the X-axis rotation joint, a Y-axis rotation joint is fixedly arranged on the top of the second connecting plate above the X-axis rotation joint, a fourth connecting plate is fixedly arranged on the top of the Y-axis rotation joint, a Z-axis rotation joint is fixedly arranged above the fourth connecting plate, and a skull fixation sleeve is fixedly arranged on the top of the Z-axis rotation joint.

3. The intelligent neck muscle stretching device according to claim 2, characterized in that: The first connecting plate, the second connecting plate, the third connecting plate and the fourth connecting plate are all fixedly provided with silicone pads that adapt to the user's body structure, the outer sides of the silicone pads are connected and fixedly provided with air pumps, and the interior of the silicone pads is provided with air chambers, and the silicone pads can change shape and hardness by adjusting the air pressure through the air pump.

4. The intelligent neck muscle stretching device according to claim 3, characterized in that: The X-axis rotating joint, the horizontal electromagnetic sliding joint, the Y-axis rotating joint, the vertical electromagnetic sliding joint and the Z-axis rotating joint are all connected to a control box through lines. The control box is fixedly arranged on the frame body. A motor driver, a circuit board, a microcontroller fixedly arranged on the circuit board and a data acquisition card fixedly arranged on the circuit board are fixedly arranged inside the control box.

5. The intelligent neck muscle stretching device according to claim 4, characterized in that: The X-axis rotating joint, the horizontal electromagnetic sliding joint, the Y-axis rotating joint, the vertical electromagnetic sliding joint and the Z-axis rotating joint are all fixedly provided with an absolute photoelectric encoder and a strain gauge force sensor, and the absolute photoelectric encoder and the strain gauge force sensor are connected to the control box.

6. The intelligent neck muscle stretching device according to claim 5, characterized in that: The horizontal translation joint and the vertical translation joint both adopt electromagnetic sliding sleeves.

7. The intelligent neck muscle stretching device according to claim 1, characterized in that :The surface electromyography signal acquisition unit includes a dry electrode and a signal acquisition circuit connected to the dry electrode.

8. The intelligent neck muscle stretching device according to claim 1, characterized in that The signal processing and analysis unit includes a filtering circuit, an amplifying circuit, a time domain feature extraction unit, a frequency domain feature extraction unit and a data analysis and diagnosis module.

9. The intelligent neck muscle stretching device according to claim 1, characterized in that :The human-computer interaction unit is configured as a touch display screen.

Images