Assisted stroke rehabilitation method and device based on multi-source physiological signal wearable equipment

Abstract

The invention discloses an auxiliary stroke rehabilitation method and device based on a multi-source physiological signal wearable device. The method comprises the steps that the pulse waveform variation rate and sublingual vein feature parameters of a subject are monitored through a self-powered five-hidden monitoring wrist strap; dynamically evaluating the internal organ imbalance index of the subject according to the pulse waveform variation rate and the sublingual vein characteristic parameters; generating personalized rehabilitation adjustment parameters according to the internal organ imbalance index of the subject; synchronously acquiring an electroencephalogram signal of a subject and a surface electromyogram signal of a target muscle, and generating an acupoint activation time sequence map of preset hand actions; the acupoint activation time sequence map is optimized according to the personalized rehabilitation adjustment parameters so as to adjust acupoint selection, stimulation intensity and stimulation time sequence; and presenting a built-in foot yangming stomach meridian virtual acupuncture scene to the subject through the VR guide instrument. According to the apoplexy rehabilitation method, electroencephalogram and myoelectricity cooperative decoding, personalized parameter adjustment, VR and a viscera imbalance traditional Chinese medicine diagnosis method are integrated into a rehabilitation scheme, and the apoplexy rehabilitation effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of stroke rehabilitation assistance, and particularly to an assisted stroke rehabilitation method, device and computing device based on a multi-source physiological signal wearable device. Background Art

[0002] Traditional stroke rehabilitation methods mainly rely on physical therapy and occupancy therapy (such as muscle stretching, joint movement and functional training). Due to the lack of personalized and precise rehabilitation methods, the rehabilitation effect is poor. Although some modern rehabilitation devices (such as robot-assisted rehabilitation systems, electrical stimulation devices, etc.) have improved the rehabilitation effect to a certain extent, they still lack the ability to monitor the physiological state of patients in real time and make dynamic adjustments, and cannot comprehensively reflect the overall health status of patients. In addition, the application of traditional Chinese medicine theory in the field of rehabilitation mainly focuses on traditional techniques such as acupuncture and massage, lacking the combination with modern medical technologies. In particular, the concept of "visceral imbalance" in traditional Chinese medicine theory is of great significance in rehabilitation, but there is a lack of scientific quantitative evaluation methods.

[0003] To solve the above problems, the present invention proposes an assisted stroke rehabilitation method based on a multi-source physiological signal wearable device, integrating brain-muscle electrical co-decoding, personalized parameter adjustment, VR, and the traditional Chinese medicine diagnosis method of visceral imbalance into the rehabilitation plan to improve the rehabilitation effect of stroke rehabilitation. Summary of the Invention

[0004] In view of the above problems, the present invention provides an assisted stroke rehabilitation method, device and computing device based on a multi-source physiological signal wearable device.

[0005] According to one aspect of the present invention, there is provided an assisted stroke rehabilitation method based on a multi-source physiological signal wearable device, including:

[0006] Monitoring the pulse wave variability rate and sublingual vein characteristic parameters of a subject through a self-powered five-viscera monitoring wristband, where the self-powered five-viscera monitoring wristband includes a flexible piezoelectric sensor, a photoplethysmogram (PPG) sensor, and a tongue image acquisition module;

[0007] Dynamically evaluating the visceral imbalance index of the subject according to the pulse wave variability rate and sublingual vein characteristic parameters; generating personalized rehabilitation adjustment parameters according to the visceral imbalance index of the subject, where the personalized rehabilitation adjustment parameters include the acupoint selection, stimulation intensity, stimulation timing, electrical pulse stimulation intensity, stimulation frequency, action time in the collaborative training closed loop, and VR scene interaction method of the acupoint activation timing map;

[0008] Synchronously collect the electroencephalogram (EEG) signals of the subject and the surface electromyogram (sEMG) signals of the target muscle, analyze the non-linear coupling relationship between the motor imagery potential of the EEG signals and the sEMG signals through an EEG-myoelectricity collaborative decoding module, and generate an acupoint activation timing map corresponding to a preset hand movement.

[0009] Optimize the acupoint activation timing map according to the personalized rehabilitation adjustment parameters to adjust acupoint selection, stimulation intensity, and stimulation timing; present a virtual acupuncture scene of the Stomach Meridian of Foot-Yangming built-in to the subject through a portable VR guide, and provide real-time tactile feedback corresponding to the preset hand movement through a bone conduction headset to guide the subject to perform the preset rehabilitation movement.

[0010] In an alternative way, the presenting of the virtual acupuncture scene of the Stomach Meridian of Foot-Yangming built-in to the subject through the portable VR guide further includes:

[0011] When the subject completes the preset hand movement in the VR scene and meets the triggering condition based on the heart rate variability (HRV) rhythm, trigger personalized electrical pulse stimulation according to the viscera imbalance index to stimulate the preset acupoints.

[0012] Meanwhile, present the dynamic qi and blood flow path corresponding to the preset acupoints through the portable VR guide.

[0013] In an alternative way, the calculation formula of the viscera imbalance index is:

[0014]

[0015] where w i is the weight coefficient of the i-th viscera; P i is the pulse waveform variability rate monitored in real time; P norm,i is the normal variability rate threshold of the corresponding viscera; TongueBaseline i is the tongue image feature value of the i-th viscera; TongueFeature i is the tongue image baseline value of the i-th viscera; P crit,i is the critical variability rate threshold of the i-th viscera; Θ(.) is the Heaviside step function; t is the current time; τ is the time integration variable.

[0016] In an alternative way, the VR scene interaction method renders the light and shadow changes of the qi and blood flow path in real time through the Shader Graph method, where the color gradient of the qi and blood flow path is positively correlated with the current heart rate variability frequency domain energy ratio.

[0017] And, spatialized audio is output through bone conduction headphones, where the phase difference between the left / right channels has a linear relationship with the EEG μ-rhythm energy offset. When the patient's motor imagery potential is enhanced, the audio sound image automatically shifts to the opposite side;

[0018] The action trajectory is captured by an inertial measurement unit (IMU) and mapped in real time as the kinematic parameters of a virtual limb in a VR scenario to form a proprioceptive-visual closed loop.

[0019] In an optional manner, the state space of the preset rehabilitation action includes PWV, HRV, the entropy value of the myoelectric signal, and the action completion degree parameter;

[0020] The action space of the preset rehabilitation action includes the acupoint activation parameter, the VR scene complexity parameter, and the electrical stimulation parameter;

[0021] The reward function of the preset rehabilitation action is:

[0022]

[0023] where ΔFuglMeyerScore is the increment of the scoring scale; StandardTime is the standard time required for the rehabilitation action; ActualTime is the time actually spent to complete the rehabilitation action; and NumberOfAbnormalAlerts is the number of abnormal alerts.

[0024] In an optional manner, the electrical pulse stimulation parameter adopts a heart rate variability (HRV) feedback model, where the expression of the heart rate variability (HRV) feedback model is:

[0025]

[0026] where I(t) is the electrical pulse stimulation intensity at time t; Kp is the proportional gain coefficient; is the center frequency; φ HRV (t) is the HRV phase modulation function; HRV LF / HF (t) is the low-frequency / high-frequency (LF / HF) ratio of the heart rate variability; PWV(t) is the pulse wave velocity at time t; PWV base is the PWV value of the patient in the normal state; f c is the center frequency.

[0027] In an optional manner, the acupoint activation timing map obtains a dynamic gain function by real-time modeling of the phase-locking value (PLV) between the μ-rhythm of the surface electromyogram (sEMG) and the motor imagery potential through the recursive least squares (RLS) method; where the dynamic gain function is:

[0028]

[0029] Among them, G base is the basic gain coefficient; k is the PLV gain adjustment coefficient; PLV max is the preset maximum phase-locked value; HRV LF / HF,base is the baseline value of the heart rate variability of the patient at rest;

[0030] The electric pulse stimulation intensity parameter is adjusted in real time according to the dynamic gain function, and the adjustment formula is:

[0031]

[0032] Among them, t onset is the stimulation start time; τ adapt is the adaptive adjustment time constant, which is used to smooth the instantaneous impact of the gain change on the stimulation intensity; I(t) is the unadjusted electric pulse stimulation intensity at time t; τ adapt is the adaptive adjustment time constant.

[0033] In an optional manner, the electroencephalogram-myoelectricity collaborative decoding module analyzes the sublingual vein texture features output by the tongue image acquisition module in real time through a convolutional neural network CNN to extract the tongue image attention weight map and obtain the tongue image feature attention vector;

[0034] Performs a tensor product operation on the attention vector and the EEG motor imagery potential to generate an enhanced motor imagery feature matrix;

[0035] Performs spatio-temporal sequence modeling on the enhanced feature matrix through a long short-term memory network LSTM, and outputs an acupoint activation time series map corresponding to a preset hand movement.

[0036] According to another aspect of the present invention, there is provided an auxiliary stroke rehabilitation device based on a multi-source physiological signal wearable device, including:

[0037] A physiological signal monitoring module, which is used to monitor the pulse wave variability rate and sublingual vein characteristic parameters of the subject through a self-powered five-viscera monitoring wristband, and the self-powered five-viscera monitoring wristband includes a flexible piezoelectric sensor, a photoplethysmogram PPG sensor and a tongue image acquisition module;

[0038] A personalized rehabilitation parameter generation module, which is used to dynamically evaluate the viscera imbalance index of the subject according to the pulse wave variability rate and sublingual vein characteristic parameters; generate personalized rehabilitation adjustment parameters according to the viscera imbalance index of the subject, wherein the personalized rehabilitation adjustment parameters include the acupoint selection, stimulation intensity, stimulation time sequence, electric pulse stimulation intensity, stimulation frequency, action time and VR scene interaction mode in the acupoint activation time series map;

[0039] A brain-muscle electrical signal collaborative decoding module, which is used to synchronously collect the electroencephalogram (EEG) signals of a subject and the surface electromyogram (sEMG) signals of the target muscle, analyze the non-linear coupling relationship between the motor imagery potential of the EEG signals and the sEMG signals through the brain-muscle electrical signal collaborative decoding module, and generate an acupoint activation timing map corresponding to a preset hand movement.

[0040] A VR guidance and acupoint stimulation module, which is used to optimize the acupoint activation timing map according to the personalized rehabilitation adjustment parameters so as to adjust acupoint selection, stimulation intensity and stimulation timing; present a virtual acupuncture scene of the Stomach Meridian of Foot-Yangming built in to the subject through a portable VR guidance device, and provide real-time tactile feedback corresponding to the preset hand movement through a bone conduction headset to guide the subject to perform the preset rehabilitation movement.

[0041] According to another aspect of the present invention, a computing device is provided, including: a processor, a memory, a communication interface and a communication bus, and the processor, the memory and the communication interface complete communication with each other through the communication bus;

[0042] The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operations corresponding to the above-mentioned auxiliary stroke rehabilitation method based on a multi-source physiological signal wearable device.

[0043] According to the solution provided by the present invention, the pulse wave variability rate and sublingual vein characteristic parameters of a subject are monitored by a self-powered five-viscera monitoring wristband, and the self-powered five-viscera monitoring wristband includes a flexible piezoelectric sensor, a photoplethysmogram (PPG) sensor, and a tongue image acquisition module; the viscera imbalance index of the subject is dynamically evaluated according to the pulse wave variability rate and sublingual vein characteristic parameters; personalized rehabilitation adjustment parameters are generated according to the viscera imbalance index of the subject, wherein the personalized rehabilitation adjustment parameters include the acupoint selection, stimulation intensity, stimulation timing in the acupoint activation timing map, the electrical pulse stimulation intensity, stimulation frequency, action time in the co-training closed loop, and the VR scene interaction method; the electroencephalogram (EEG) signal and the surface electromyogram (sEMG) signal of the target muscle of the subject are synchronously collected, and the non-linear coupling relationship between the motor imagery potential of the EEG signal and the sEMG signal is analyzed by an EEG-EMG co-decoding module to generate an acupoint activation timing map corresponding to a preset hand movement; the acupoint activation timing map is optimized according to the personalized rehabilitation adjustment parameters to adjust the acupoint selection, stimulation intensity, and stimulation timing; a virtual acupuncture scene of the Stomach Meridian of Foot-Yangming is presented to the subject through a portable VR guide, and real-time tactile feedback corresponding to the preset hand movement is provided through a bone conduction headset to guide the subject to perform the preset rehabilitation movement. The present invention integrates EEG-EMG co-decoding, personalized parameter adjustment, VR, and the traditional Chinese medicine diagnosis method of viscera imbalance into the rehabilitation plan, improving the rehabilitation effect of stroke rehabilitation. Specifically, the viscera imbalance index is dynamically evaluated according to the pulse wave variability rate and sublingual vein characteristic parameters of the subject, and personalized rehabilitation adjustment parameters are generated based on this, ensuring the pertinence of the rehabilitation plan. By analyzing the non-linear coupling relationship between EEG and sEMG through the EEG-EMG co-decoding module, the connection between motor imagery and actual movement can be understood more effectively, so as to generate the acupoint activation timing map corresponding to the preset hand movement more accurately and improve the efficiency of rehabilitation training. Optimizing the acupoint activation timing map according to the personalized rehabilitation adjustment parameters and adjusting the acupoint selection, stimulation intensity, and stimulation timing can be dynamically adjusted according to the real-time state of the patient to achieve a better therapeutic effect. Presenting the virtual acupuncture scene through the portable VR guide and providing tactile feedback through the bone conduction headset can improve the patient's participation and the immersion of training, enhance the patient's motivation, and help the patient complete the rehabilitation movement better. The traditional Chinese medicine concept of "viscera imbalance" is introduced and the traditional Chinese medicine diagnosis methods such as tongue image and pulse condition are integrated into the rehabilitation plan, reflecting the idea of integrating traditional Chinese and Western medicine and better meeting the needs of Chinese patients.

[0044] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention are hereinafter specifically exemplified. Brief Description of the Drawings

[0045] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0046] Figure 1 A flowchart showing the method for assisting stroke rehabilitation based on a multi-source physiological signal wearable device according to an embodiment of the present invention is shown;

[0047] Figure 2 A schematic diagram showing the assistance for stroke rehabilitation according to an embodiment of the present invention is shown Figure 1 ;

[0048] Figure 3 A schematic diagram showing the assistance for stroke rehabilitation according to an embodiment of the present invention is shown Figure 2 ;

[0049] Figure 4 A framework diagram showing the device for assisting stroke rehabilitation based on a multi-source physiological signal wearable device according to an embodiment of the present invention is shown;

[0050] Figure 5 A structural diagram showing the computing device according to an embodiment of the present invention is shown. Detailed Embodiments

[0051] The exemplary embodiments of the present invention will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be fully conveyed to those skilled in the art.

[0052] Figure 1 A flowchart showing the method for assisting stroke rehabilitation based on a multi-source physiological signal wearable device according to an embodiment of the present invention is shown. Specifically, as Figure 1 shown, the following steps are included:

[0053] Step S101, monitoring the pulse wave variability rate and sublingual vein characteristic parameters of the subject through a self-powered five-organ monitoring wristband, where the self-powered five-organ monitoring wristband includes a flexible piezoelectric sensor, a photoplethysmogram (PPG) sensor, and a tongue image acquisition module.

[0054] In this embodiment, the flexible piezoelectric sensor is used to monitor the pulse wave variability rate, and reflects the health status of the cardiovascular system by capturing the minute changes in the blood vessel wall. The photoplethysmogram (PPG) sensor is used to monitor the blood oxygen saturation and heart rate variability, and provides real-time data on blood circulation. The tongue image acquisition module includes a high-resolution camera and a light source, and is used to acquire the sublingual vein image to extract the characteristic parameters of the sublingual vein. The flexible piezoelectric sensor, the PPG sensor and the tongue image acquisition module are integrated into a wearable device through a wristband. For example, the flexible piezoelectric sensor is arranged on the inner side of the wristband at the position where the radial artery pulsation is obvious, usually on the side of the wrist joint close to the thumb. In this embodiment, the piezoelectric sensor in the self-powered five-viscera monitoring wristband uses a PVDF piezoelectric film with a thickness of 50 microns, which is cut into strips of 5 mm x 20 mm and attached to a flexible polyimide substrate. The PPG sensor selects the SFH 7050 PPG sensor of Osram, and integrates a red light LED (660 nm) and a photodiode. The light source of the tongue image acquisition module is a ring-shaped LED lamp, which includes 12 warm white LEDs (color temperature 4000K). The camera and the LED lamp are fixed on a rotatable bracket, and the user can adjust the angle and transmit the image to the mobile phone APP via Bluetooth. 36 AWG silver-plated copper wires are used to connect all the sensors, and epoxy resin is used for insulation encapsulation. A flexible solar cell with a size of 5 cm x 5 cm is integrated on the surface of the wristband to supply power to part of the circuits of the PPG sensor and the tongue image acquisition module. At the same time, energy is collected through a micro electromagnetic generator using wrist movement and stored in a supercapacitor. The mobile phone APP displays the pulse waveform, heart rate, blood oxygen saturation and tongue image.

[0055] Step S102, dynamically evaluate the viscera imbalance index of the subject according to the pulse wave variability rate and the characteristic parameters of the sublingual vein; generate personalized rehabilitation adjustment parameters according to the viscera imbalance index of the subject, wherein the personalized rehabilitation adjustment parameters include the acupoint selection, stimulation intensity, stimulation timing in the acupoint activation timing map, the electric pulse stimulation intensity, stimulation frequency, action time in the cooperative training closed loop, and the VR scene interaction mode.

[0056] In this embodiment, the pulse waveform contains rich cardiovascular physiological information, and its variability reflects the dynamic changes of cardiac function, vascular elasticity, and neurohumoral regulation. By analyzing the pulse waveform, the functional states of the heart, liver, spleen, lungs, kidneys and other internal organs can be objectively and quantitatively evaluated. The morphology, color, thickness, and varicosity characteristics of the sublingual veins are closely related to the movement of qi and blood. By using image recognition technology to extract the objective characteristic parameters of the sublingual veins, it can assist in judging the pathological states of qi stagnation and blood stasis, and phlegm-dampness obstruction. By continuously monitoring the changes in the pulse waveform and sublingual veins, the dynamic change trend of the internal organ functions can be understood, so as to more accurately grasp the evolution law of the disease condition. Traditional acupuncture emphasizes syndrome differentiation and treatment, and selecting acupoints along the meridians. By combining with the internal organ imbalance index, a personalized acupoint activation time sequence map is generated to clarify the acupoint selection, stimulation intensity, and stimulation time sequence parameters, improving the effectiveness of acupoint stimulation. By combining electrical pulse stimulation with VR scene interaction, the active participation of the patient is mobilized to promote the recovery of neuromuscular function. According to the patient's real-time physiological response, the intensity and frequency of electrical pulse stimulation are dynamically adjusted to achieve precise intervention. Since stroke patients often have disorders of the functions of the heart, liver, spleen, kidneys and other internal organs (such as insufficient heart qi leading to palpitations and fatigue, liver qi transforming into fire leading to mood swings, and spleen deficiency with excessive dampness leading to limb heaviness), this embodiment can objectively and quantitatively evaluate the functional states of the internal organs of stroke patients, providing a basis for formulating personalized rehabilitation programs. Aiming at the common problems of limb motor disorders, language disorders, and cognitive disorders in stroke patients, by combining with the internal organ imbalance index to generate a personalized acupoint activation time sequence map and a collaborative training program, the rehabilitation effect is further improved. Among them, for limb motor disorders, acupoints such as Jianyu, Quchi, Shousanli, and Hegu on the upper limb, and Huantiao, Fengshi, Zusanli, and Yanglingquan on the lower limb are selected. For language disorders, acupoints such as Lianquan, Yamen, and Tongli are selected. For cognitive disorders, acupoints such as Baihui, Sishencong, and Shenmen are selected. At the same time, according to the internal organ imbalance index, corresponding supplementary acupoints are selected. For heart qi deficiency, the stimulation of acupoints such as Xinshu and Neiguan is strengthened. For liver yang hyperactivity, the stimulation of acupoints such as Taichong and Xingjian is strengthened. For phlegm-dampness obstruction of the collaterals, the stimulation of acupoints such as Fenglong and Yinlingquan is strengthened. For the stimulation intensity, the appropriate intensity of acupoint stimulation is determined according to factors such as the patient's age, constitution, and disease condition. Stroke patients may have dull sensations, so it is necessary to pay attention that the stimulation intensity should not be too large to avoid causing discomfort. According to the principles of "opening acupoints" and "reinforcing and reducing" in traditional Chinese medicine, a time sequence plan for acupoint stimulation is formulated. For example, first stimulate the acupoints at the distal end of the limb, and then stimulate the acupoints at the proximal end to promote blood circulation. The intensity of electrical pulse stimulation is 1-3 mA (adjusted according to the patient's tolerance, starting from a low intensity and gradually increasing), the frequency is 20-50 Hz (to promote muscle contraction) or 2 Hz (for sedation and pain relief), and the action time is 20-30 minutes. For limb motor disorders, VR scenes such as the kitchen, living room, and park are selected. For language rehabilitation, dialogue scenes such as shopping, asking for directions, and seeing a doctor are simulated. For cognitive rehabilitation, memory games, attention training, etc. are simulated.The patient completes tasks in the VR scenario by controlling limb movements. For example, picking up and placing items, walking, going up and down stairs, etc. The patient has conversations with virtual characters in the VR scenario to practice pronunciation, speech rate, and expression ability. Also, the patient completes tasks such as memory matching and spatial reasoning in the VR scenario. For example. Figure 2 , Figure 3 As shown, a stroke patient has hemiplegia in the right limb, accompanied by symptoms of qi deficiency of the heart and qi stagnation and blood stasis. The acupoints selected are Jianyu (right side), Quchi (right side), Shousanli (right side), Hegu (right side), Huantiao (right side), Fengshi (right side), Zusanli (right side), Yanglingquan (right side), Xinshu, and Neiguan. The stimulation intensity is 1 - 2 mA (electrical pulse), and finger pressure massage is applied until the patient feels soreness and distension. The stimulation sequence is to first stimulate the acupoints at the distal ends of the upper and lower limbs (such as Hegu and Yanglingquan), then stimulate the proximal acupoints (such as Jianyu and Huantiao), and finally stimulate Xinshu and Neiguan. The intensity of the electrical pulse stimulation is 1.5 mA, the frequency is 30 Hz, and the action time is 25 minutes. The VR scenario simulates a kitchen scenario, and the patient needs to use the right hand to complete simple cooking tasks (picking up and placing bowls and chopsticks, pouring water, stirring ingredients). The interaction method is as follows: The patient wears a motion capture device to map limb movements to the VR scenario, controls the virtual character to complete cooking tasks, records the patient's movement trajectory and completion time, and provides feedback. The patient undergoes acupoint stimulation and VR scenario interaction training according to the above rehabilitation plan. The patient's heart rate, blood pressure, and muscle activity are monitored in real time, and the motor function of the patient's right limb is regularly evaluated (such as using the Fugl - Meyer assessment scale). The rehabilitation plan is adjusted according to the evaluation results. If the patient's limb motor function improves, the difficulty of the VR scenario can be increased, for example, increasing the complexity of the task or reducing assistance.

[0057] In an optional manner, the calculation formula for the viscera imbalance index is:

[0058]

[0059] where w i is the weight coefficient of the i - th viscera; P i is the pulse waveform variability rate monitored in real time; P norm,i is the normal variability rate threshold of the corresponding viscera; TongueBaseline i is the tongue image feature value of the i - th viscera; TongueFeature i is the tongue image baseline value of the i - th viscera; P crit,i is the critical variability rate threshold of the i - th viscera; Θ(.) is the Heaviside step function; t is the current time; τ is the time integration variable.

[0060] In this embodiment, for stroke patients, the weight coefficients can be adjusted. For example, the weights of the heart and liver can be increased because stroke is usually related to cardiovascular and cerebrovascular diseases and liver dysfunction. At the same time, according to the specific conditions of the patient, the normal threshold and the critical threshold are adjusted.

[0061] In an alternative way, the electrical pulse stimulation parameters adopt a heart rate variability HRV feedback model, where the expression of the heart rate variability HRV feedback model is:

[0062]

[0063] where I(t) is the electrical pulse stimulation intensity at time t; Kp is the proportional gain coefficient; is the center frequency; φ HRV (t) is the HRV phase modulation function; HRV LF / HF (t) is the low-frequency LF / high-frequency HF ratio of the heart rate variability; PWV(t) is the pulse wave velocity at time t; PWV base is the PWV value of the patient in the normal state; f c is the center frequency.

[0064] In this embodiment, through HRV feedback, the autonomic nervous system can be effectively regulated, the activities of the sympathetic and parasympathetic nerves can be balanced, which helps to improve cerebral blood circulation and promote the recovery of nerve function. This embodiment constitutes a closed-loop control system, which adjusts the stimulation parameters according to the real-time monitoring of the patient's physiological indicators to ensure that the stimulation effect is always in the best state. By adjusting the proportional gain coefficient, the intensity of the electrical pulse stimulation is limited to avoid damage to the patient caused by excessive stimulation.

[0065] In an alternative way, the acupoint activation timing map obtains a dynamic gain function by recursively least squares RLS real-time modeling of the phase-locking value PLV between the μ rhythm of the surface electromyogram sEMG and the movement imagination potential; where the dynamic gain function is:

[0066]

[0067] where G base is the basic gain coefficient; κ is the PLV gain adjustment coefficient; PLV max is the preset maximum phase-locking value; HRV LF / HF,base is the baseline value of the heart rate variability of the patient at rest;

[0068] The electrical pulse stimulation intensity parameter is adjusted in real time according to the dynamic gain function, and the adjustment formula is:

[0069]

[0070] where t onset is the stimulation start time; τ adapt is the adaptive adjustment time constant, which is used to smooth the instantaneous impact of the gain change on the stimulation intensity; I(t) is the unadjusted electrical pulse stimulation intensity at time t; τ adapt is the adaptive adjustment time constant.

[0071] In this embodiment, the phase-locking value (PLV) between the μ rhythm of the surface electromyogram signal (sEMG) and the movement imagination potential is modeled in real time by the recursive least squares method (RLS), and the electrical pulse stimulation intensity is dynamically adjusted to more precisely respond to the changes in the physiological state of the patient. The dynamic gain function takes into account the patient's basic gain coefficient, PLV gain adjustment coefficient, and heart rate variability (HRV) personalized parameters, making the treatment plan more targeted. By introducing an adaptive adjustment time constant, the instantaneous impact of the gain change on the stimulation intensity is smoothed, avoiding violent fluctuations in the stimulation intensity and improving the safety of the treatment.

[0072] Step S103, synchronously collect the electroencephalogram signal EEG of the subject and the surface electromyogram signal sEMG of the target muscle, and analyze the non-linear coupling relationship between the movement imagination potential of the electroencephalogram signal EEG and the surface electromyogram signal sEMG through the brain-muscle electrocoordination decoding module to generate an acupoint activation timing map corresponding to the preset hand movement.

[0073] In this embodiment, the electroencephalogram signal (EEG) and the surface electromyogram signal (sEMG) of the target muscle are synchronously collected, and the non-linear coupling relationship between the movement imagination potential of the EEG and the sEMG is analyzed in combination with the brain-muscle electrocoordination decoding module to more precisely identify the movement intention of the patient. The acupoint activation timing map generated by analyzing the brain-muscle electrocoordination relationship based on the patient's own physiological data better matches the individual differences of the patient, thereby realizing a personalized treatment plan. Movement imagination combined with acupoint activation stimulation promotes the activation of the motor area of the cerebral cortex and strengthens the connection between the nerve and muscle, which helps to restore motor function. In addition, both EEG and sEMG are non-invasive technologies and are non-invasive to the patient.

[0074] In an optional manner, the brain-muscle electrocoordination decoding module analyzes the sublingual vein texture features output by the tongue image acquisition module in real time through a convolutional neural network CNN to extract a tongue image attention weight map to obtain a tongue image feature attention vector;

[0075] Perform a tensor product operation on the attention vector and the EEG movement imagination potential to generate an enhanced movement imagination feature matrix;

[0076] Perform spatio-temporal sequence modeling on the enhanced feature matrix through a long short-term memory network LSTM, and output an acupoint activation timing map corresponding to the preset hand movement.

[0077] In this embodiment, the tongue image attention vector and the EEG motor imagery potential are subjected to a tensor product operation to generate an enhanced motor imagery feature matrix, effectively integrating tongue image information and improving the performance of motor intention decoding. Tongue image acquisition also belongs to a non-invasive method. Combining non-invasive electroencephalogram and electromyogram, the overall solution places less burden on patients and has high compliance. For example, for stroke patients with impaired motor function in the left limb, electroencephalogram and electromyogram cooperative decoding combined with acupoint activation stimulation assisted by tongue image features are required to promote rehabilitation. An electroencephalogram cap is placed on the patient's scalp to collect EEG signals, and sEMG electrodes are placed on the flexor carpi radialis and flexor carpi ulnaris of the patient's left forearm to collect sEMG signals. A tongue image acquisition module is used to photograph the patient's tongue image, and the patient is instructed to perform a specific motor imagery task (such as imagining clenching or stretching the left hand). A pre-trained CNN model is used to analyze the patient's tongue image, extract the sublingual vein texture features, and generate a tongue image attention weight map and a tongue image feature attention vector. The tongue image feature attention vector and the EEG motor imagery potential are subjected to a tensor product operation to generate an enhanced motor imagery feature matrix. A trained LSTM model is used to perform spatio-temporal sequence modeling on the enhanced feature matrix to predict the acupoint activation time series map corresponding to the left hand clenching action, which indicates first stimulating the Laogong acupoint on the hand, then stimulating the Hegu acupoint, and specifying the stimulation time and intensity of each acupoint. An electrical stimulation device is used to perform electrical stimulation on the Laogong acupoint and Hegu acupoint of the patient's left hand according to the generated acupoint activation time series map. During the stimulation process, the patient continues to perform motor imagery and tries to clench the fist. The patient's EEG, sEMG signals, and tongue image changes are monitored in real time, and the stimulation effect is analyzed through the electroencephalogram and electromyogram cooperative decoding module. If it is found that the stimulation effect is not good, the acupoint activation time series map is adjusted, such as adjusting the stimulation intensity or changing the stimulation order.

[0078] Step S104, optimize the acupoint activation time series map according to the personalized rehabilitation adjustment parameters to adjust acupoint selection, stimulation intensity, and stimulation timing; present the built-in virtual acupuncture scene of the Stomach Meridian of Foot-Yangming to the subject through a portable VR guide, and provide real-time tactile feedback related to the preset hand movement through a bone conduction headset to guide the subject to perform the preset rehabilitation movement.

[0079] In this embodiment, a portable VR guide is used to present the built-in virtual acupuncture scene of the Stomach Meridian of Foot-Yangming, enhancing the patient's immersion, improving the quality of motor imagery, and promoting the activation of the motor area of the cerebral cortex. Real-time tactile feedback related to the preset hand movement is provided through a bone conduction headset, providing a real movement experience for the patient and promoting the remodeling of the sensorimotor cortex. Combining vision (VR), hearing (bone conduction headset), and touch (electrical stimulation) forms multi-sensory stimulation, which can more effectively activate the cerebral cortex and improve the rehabilitation effect. VR guidance and tactile feedback enhance the patient's sense of participation and interest, and improve the compliance of rehabilitation training. The portable VR guide and the bone conduction headset facilitate the patient to perform rehabilitation training in the home or community scenario.

[0080] In an alternative approach, the step of presenting the virtual acupuncture scenario of the Stomach Meridian of Foot-Yangming built-in to the subject through the portable VR guide further includes:

[0081] When the subject completes a preset hand movement in the VR scenario and meets the triggering conditions based on the heart rate variability (HRV) rhythm, personalized electrical pulse stimulation is triggered according to the visceral imbalance index to stimulate the preset acupoints;

[0082] Meanwhile, the portable VR guide presents the dynamic qi and blood flow path corresponding to the preset acupoints.

[0083] In this embodiment, by combining the heart rate variability (HRV) rhythm and the visceral imbalance index, personalized electrical pulse stimulation is triggered, realizing the transformation from "one prescription for all" to "one prescription for one person", and improving the accuracy of treatment. The hand movement in the VR scenario serves as the input, HRV as the physiological feedback, electrical pulse stimulation as the intervention, and the dynamic qi and blood flow path as the visual feedback, forming a closed-loop control system, which helps the patient enhance the confidence in treatment.

[0084] In an alternative approach, the VR scenario interaction method renders the light and shadow changes of the qi and blood flow path in real time through the Shader Graph method, wherein the color gradient of the qi and blood flow path is positively correlated with the current heart rate variability frequency domain energy ratio;

[0085] In addition, spatialized audio is output through bone conduction headphones, wherein the left / right channel phase difference has a linear relationship with the EEG μ rhythm energy offset. When the patient's movement imagination potential increases, the audio sound image automatically shifts to the opposite side;

[0086] The action trajectory is captured by the inertial measurement unit (IMU) and mapped in real time as the kinematic parameters of the virtual limb in the VR scenario to form a proprioception-vision closed loop.

[0087] In this embodiment, Shader Graph allows developers to create complex shaders in a graphical manner, enabling the rendering of the blood flow path to be more realistic and delicate, and more intuitively showing the state of blood circulation. The color of the blood flow path is associated with the HRV frequency domain energy ratio, allowing patients to intuitively understand the state of their own neural autonomic regulation through visual feedback. For example, the color is reddish when the sympathetic nerve is active and bluish when the parasympathetic nerve is active. Bone conduction headphones directly transmit sound to the inner ear, reducing the interference of environmental noise. Associating the spatialization of audio with the EEG μ rhythm and using the patient's motor imagery to control the sound image of the audio can enhance the patient's sense of active participation. When the motor imagery potential increases, the audio sound image automatically shifts to the contralateral side, encouraging the patient to actively perform motor imagery training. When the patient imagines the movement of the left limb, the audio sound image will shift to the right, and vice versa, which helps to promote the neuroplasticity of the cerebral cortex. The IMU can accurately capture information such as the patient's movements, positions, postures, and speeds. Mapping the movements captured by the IMU to the virtual limbs in the VR scene in real time allows the patient to feel that their limbs are moving, even if the actual limb movement is restricted, promoting the brain's perception of the limbs and helping to improve motor control and coordination abilities. Among them, the VR headset is a high-refresh-rate and low-latency VR headset, and the hand motion capture device selects Leap Motion or a VR controller for capturing hand movements. The heart rate sensor uses a heart rate belt or a finger pulse sensor for collecting heart rate data. The electroencephalogram acquisition device (EEG) can be a dry electrode or a wet electrode. The inertial measurement unit (IMU) uses multiple IMU sensors, which are respectively worn on the patient's limbs for capturing movement trajectories. The bone conduction headphones are used to output spatialized audio. As Figure 3 shown, the post-stroke sequelae patient has motor impairment in the left limb. The VR scene simulates a kitchen scene, and the patient needs to complete tasks such as washing vegetables, cutting vegetables, and stir-frying in the VR scene, that is, the patient needs to imagine that the left hand completes actions such as washing vegetables, cutting vegetables, and stir-frying. The patient tries to complete the corresponding actions with the left hand, and the IMU sensor captures the movement trajectory. The patient sees the virtual left hand completing the corresponding actions in the VR scene. When the patient imagines the movement of the left hand, the audio sound image shifts to the right, encouraging the patient to continue with the motor imagery. According to the HRV frequency domain energy ratio, the color and light and shadow of the blood flow path of the virtual left hand are adjusted in real time. Through the combination of motor imagery, action execution, visual feedback, and auditory feedback, the motor function recovery of the left limb is promoted, and the patient's self-care ability is improved.

[0088] In an optional manner, the state space of the preset rehabilitation action includes PWV, HRV, myoelectric signal entropy value, and action completion degree parameter;

[0089] The action space of the preset rehabilitation action includes acupoint activation parameter, VR scene complexity parameter, and electrical stimulation parameter;

[0090] The reward function for the preset rehabilitation movement is as follows:

[0091]

[0092] where ΔFuglMeyerScore is the increment of the scoring scale; StandardTime is the standard time required for the rehabilitation movement; ActualTime is the time taken to actually complete the rehabilitation movement; and NumberOfAbnormalAlerts is the number of abnormal alerts.

[0093] In this embodiment, the parameters of the rehabilitation movement are automatically adjusted according to the patient's real-time state and movement feedback. The state space includes PWV (pulse wave velocity, reflecting vascular elasticity), HRV (heart rate variability, reflecting the function of the autonomic nervous system), the entropy value of the electromyogram signal (reflecting the complexity of muscle activity), and the movement completion parameter, which can comprehensively reflect the patient's physiological state and movement quality. The movement space includes acupoint activation parameters (frequency, intensity, and duration of electrical stimulation), VR scene complexity parameters (task difficulty, visual stimulation), and electrical stimulation parameters, providing rich adjustment options. The reward function takes into account the Fugl-Meyer score increment, movement completion efficiency, and safety, guiding the reinforcement learning algorithm to optimize in the direction of improving the rehabilitation effect, increasing efficiency, and reducing risks. By adjusting the VR scene complexity parameters, the rehabilitation difficulty is adaptively adjusted according to the patient's ability, maintaining the patient's participation and enthusiasm. For example, for a patient with sequelae of stroke and right upper limb movement disorder. State space: PWV = 0.8, HRV_LFHF = 1.5, EMG_Entropy = 0.6, Movement_Accuracy = 0.4; Acupoint activation parameters: Electrical stimulation frequency = 20 Hz, Electrical stimulation intensity = 5 mA, Electrical stimulation duration = 0.5 s; VR scene complexity parameters: Task difficulty = medium, Visual stimulation = high; Electrical stimulation parameters: The same as the acupoint activation parameters; Reward function: After one rehabilitation training, the increment of the Fugl-Meyer score is 2. The standard time required for the rehabilitation movement is 10 seconds, and the actual completion time is 12 seconds. There are no abnormal alerts, then the reward value is: R = 2 + (1 - 10 / 12) - 0 = 2.167. Using the DQN algorithm to train the reinforcement learning model, the patient completes the task of grasping an object in the VR scene while receiving electrical stimulation. According to the patient's real-time state and movement feedback, the DQN algorithm is used to select the best movement parameters and update the model.

[0094] According to the solution provided by the present invention, the pulse wave variability rate and sublingual vein characteristic parameters of a subject are monitored by a self-powered five-organ monitoring wristband, and the self-powered five-organ monitoring wristband includes a flexible piezoelectric sensor, a photoplethysmogram (PPG) sensor, and a tongue image acquisition module; the viscera imbalance index of the subject is dynamically evaluated according to the pulse wave variability rate and sublingual vein characteristic parameters; according to the viscera imbalance index of the subject, personalized rehabilitation adjustment parameters are generated, wherein the personalized rehabilitation adjustment parameters include the acupoint selection, stimulation intensity, stimulation timing in the acupoint activation timing map, the electrical pulse stimulation intensity, stimulation frequency, action time in the co-training closed loop, and the VR scene interaction mode; the electroencephalogram (EEG) signal and the surface electromyogram (sEMG) signal of the target muscle of the subject are synchronously collected, and the non-linear coupling relationship between the motor imagery potential of the EEG signal and the sEMG signal is analyzed by an EEG-EMG co-decoding module to generate an acupoint activation timing map corresponding to a preset hand movement; the acupoint activation timing map is optimized according to the personalized rehabilitation adjustment parameters to adjust the acupoint selection, stimulation intensity, and stimulation timing; a virtual acupuncture scene of the Stomach Meridian of Foot-Yangming is presented to the subject through a portable VR guide, and real-time tactile feedback corresponding to the preset hand movement is provided through a bone conduction headset to guide the subject to perform the preset rehabilitation movement. The present invention integrates EEG-EMG co-decoding, personalized parameter adjustment, VR, and the traditional Chinese medicine diagnosis method of viscera imbalance into the rehabilitation plan, improving the rehabilitation effect of stroke rehabilitation. Specifically, the viscera imbalance index is dynamically evaluated according to the pulse wave variability rate and sublingual vein characteristic parameters of the subject, and personalized rehabilitation adjustment parameters are generated based on this, ensuring the pertinence of the rehabilitation plan. By analyzing the non-linear coupling relationship between EEG and sEMG through the EEG-EMG co-decoding module, the connection between motor imagery and actual movement can be more effectively understood, so as to more accurately generate an acupoint activation timing map corresponding to the preset hand movement and improve the efficiency of rehabilitation training. Optimizing the acupoint activation timing map according to the personalized rehabilitation adjustment parameters and adjusting the acupoint selection, stimulation intensity, and stimulation timing can be dynamically adjusted according to the real-time state of the patient to achieve a better treatment effect. Presenting the virtual acupuncture scene through the portable VR guide and providing tactile feedback through the bone conduction headset can improve the patient's participation and the immersion of the training, enhance the patient's motivation, and help the patient better complete the rehabilitation movement. The traditional Chinese medicine concept of "viscera imbalance" is introduced and traditional Chinese medicine diagnosis methods such as tongue image and pulse condition are integrated into the rehabilitation plan, reflecting the idea of integrating traditional Chinese and Western medicine and better meeting the needs of Chinese patients.

[0095] Figure 4 Fig. shows a schematic framework diagram of an auxiliary stroke rehabilitation device based on a multi-source physiological signal wearable device according to an embodiment of the present invention. The auxiliary stroke rehabilitation device based on a multi-source physiological signal wearable device includes:

[0096] The physiological signal monitoring module 410 is used to monitor the pulse wave variability rate and sublingual vein characteristic parameters of the subject through the self-powered five-organ monitoring wristband, and the self-powered five-organ monitoring wristband includes a flexible piezoelectric sensor, a photoplethysmogram (PPG) sensor, and a tongue image acquisition module;

[0097] The personalized rehabilitation parameter generation module 420 is used to dynamically evaluate the viscera imbalance index of the subject according to the pulse wave variability rate and sublingual vein characteristic parameters; and generate personalized rehabilitation adjustment parameters according to the viscera imbalance index of the subject, wherein the personalized rehabilitation adjustment parameters include the acupoint selection, stimulation intensity, stimulation timing in the acupoint activation timing map, the electrical pulse stimulation intensity, stimulation frequency, action time in the collaborative training closed loop, and the VR scene interaction mode;

[0098] The brain-muscle electrophysiology collaborative decoding module 430 is used to synchronously collect the electroencephalogram (EEG) signal of the subject and the surface electromyogram (sEMG) signal of the target muscle, analyze the non-linear coupling relationship between the motor imagery potential of the EEG signal and the sEMG signal through the brain-muscle electrophysiology collaborative decoding module, and generate an acupoint activation timing map corresponding to a preset hand movement;

[0099] The VR guidance and acupoint stimulation module 440 is used to optimize the acupoint activation timing map according to the personalized rehabilitation adjustment parameters to adjust the acupoint selection, stimulation intensity, and stimulation timing; present the built-in virtual acupuncture scene of the Stomach Meridian of Foot-Yangming to the subject through a portable VR guidance device, and provide real-time tactile feedback corresponding to the preset hand movement through a bone conduction headset to guide the subject to perform the preset rehabilitation movement.

[0100] Figure 5 The structure diagram of the computing device embodiment of the present invention is shown, and the specific implementation of the computing device is not limited in the specific embodiment of the present invention.

[0101] As Figure 5 shown, the computing device may include: a processor 502, a communication interface 504, a memory 506, and a communication bus 508.

[0102] Wherein: the processor 502, the communication interface 504, and the memory 506 communicate with each other through the communication bus 508. The communication interface 504 is used to communicate with network elements of other devices such as clients or other servers. The processor 502 is used to execute the program 510, and specifically can execute the relevant steps in the above-mentioned embodiment of the auxiliary stroke rehabilitation method based on the multi-source physiological signal wearable device.

[0103] Specifically, the program 510 may include program code that includes computer operation instructions.

[0104] The processor 502 may be a central processing unit (CPU), or a specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors included in the computing device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0105] The memory 506 is used to store the program 510. The memory 506 may include high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0106] According to the solution provided by the present invention, the pulse wave variability rate and the characteristic parameters of the sublingual vein of the subject are monitored by a self-powered five-viscera monitoring wristband, and the self-powered five-viscera monitoring wristband includes a flexible piezoelectric sensor, a photoplethysmogram (PPG) sensor, and a tongue image acquisition module; the viscera imbalance index of the subject is dynamically evaluated according to the pulse wave variability rate and the characteristic parameters of the sublingual vein; according to the viscera imbalance index of the subject, personalized rehabilitation adjustment parameters are generated, wherein the personalized rehabilitation adjustment parameters include the acupoint selection, stimulation intensity, stimulation timing in the acupoint activation timing map, the electrical pulse stimulation intensity, stimulation frequency, action time in the co-training closed loop, and the VR scene interaction mode; the electroencephalogram (EEG) signal of the subject and the surface electromyogram (sEMG) signal of the target muscle are synchronously collected, and the non-linear coupling relationship between the motor imagery potential of the EEG signal and the sEMG signal is analyzed by an electroencephalogram and electromyogram co-decoding module to generate an acupoint activation timing map corresponding to a preset hand movement; the acupoint activation timing map is optimized according to the personalized rehabilitation adjustment parameters to adjust the acupoint selection, stimulation intensity, and stimulation timing; a virtual acupuncture scene of the Stomach Meridian of Foot-Yangming is presented to the subject through a portable VR guide, and real-time tactile feedback corresponding to the preset hand movement is provided through a bone conduction headset to guide the subject to perform the preset rehabilitation movement. The present invention integrates electroencephalogram and electromyogram co-decoding, personalized parameter adjustment, VR, and the traditional Chinese medicine diagnosis method of viscera imbalance into the rehabilitation plan, improving the rehabilitation effect of stroke rehabilitation. Specifically, the viscera imbalance index is dynamically evaluated according to the pulse wave variability rate and the characteristic parameters of the sublingual vein of the subject, and personalized rehabilitation adjustment parameters are generated based on this, ensuring the pertinence of the rehabilitation plan. By analyzing the non-linear coupling relationship between EEG and sEMG through an electroencephalogram and electromyogram co-decoding module, the connection between motor imagery and actual movement can be more effectively understood, so as to more accurately generate an acupoint activation timing map corresponding to the preset hand movement and improve the efficiency of rehabilitation training. The acupoint activation timing map is optimized according to the personalized rehabilitation adjustment parameters to adjust the acupoint selection, stimulation intensity, and stimulation timing, which can be dynamically adjusted according to the patient's real-time state to achieve a better treatment effect. By presenting a virtual acupuncture scene through a portable VR guide and providing tactile feedback through a bone conduction headset, the patient's participation and the immersion of training are improved, enhancing the patient's motivation and helping to better complete the rehabilitation movement. The traditional Chinese medicine concept of "viscera imbalance" is introduced and traditional Chinese medicine diagnosis methods such as tongue image and pulse condition are integrated into the rehabilitation plan, reflecting the idea of integrating traditional Chinese and Western medicine and better meeting the needs of Chinese patients.

[0107] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise explicitly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature that provides the same, equivalent, or similar purpose. In addition, those skilled in the art can understand that although some of the embodiments herein include certain features included in other embodiments rather than other features, the combination of the features of different embodiments means that it is within the scope of the present invention and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination. The present invention can be implemented by means of hardware including several different elements and by means of a properly programmed computer. In the unit claims listing several devices, several of these devices can be embodied by the same hardware item. The steps in the above embodiments, unless otherwise specified, should not be construed as a limitation on the execution order.

Claims

1. A method for assisting stroke rehabilitation based on a multi-source physiological signal wearable device, characterized in that: include: The pulse waveform variability and sublingual vein characteristic parameters of the subject are monitored by a self-powered five-organ monitoring wristband, wherein the self-powered five-organ monitoring wristband includes a flexible piezoelectric sensor, a photoelectric volumetric pulse wave (PPG) sensor, and a tongue image acquisition module; Dynamically evaluating the subject's viscera imbalance index according to the pulse waveform variability and the sublingual vein characteristic parameters; generating personalized rehabilitation adjustment parameters according to the subject's viscera imbalance index, wherein the personalized rehabilitation adjustment parameters include acupoint selection, stimulation intensity, stimulation timing, electric pulse stimulation intensity, stimulation frequency, action time and VR scene interaction mode in the acupoint activation timing map; Synchronously collect the subject's EEG signal and the target muscle's surface electromyography signal (sEMG), analyze the nonlinear coupling relationship between the motor imagery potential of the EEG signal and the surface electromyography signal (sEMG) through the EEG-EMG collaborative decoding module, and generate a time-series graph of acupoint activation corresponding to the preset hand movement; The acupoint activation timing map is optimized according to the personalized rehabilitation adjustment parameters to adjust acupoint selection, stimulation intensity and stimulation timing; a built-in virtual acupuncture scene of the Stomach Meridian of Foot-Yangming is presented to the subject through a portable VR guide device, and real-time tactile feedback with the preset hand movements is provided through bone conduction headphones to guide the subject to perform the preset rehabilitation movements.

2. The method for assisting stroke rehabilitation based on a multi-source physiological signal wearable device according to claim 1, characterized in that: The presenting of a built-in virtual acupuncture scene of the Stomach Meridian of Foot-Yangming to the subject through the portable VR guide device further includes: When the subject completes the preset hand movements in the VR scene and meets the triggering conditions based on the heart rate variability (HRV) rhythm, personalized electrical pulse stimulation is triggered according to the viscera imbalance index to stimulate the preset acupoints; At the same time, the portable VR guiding instrument presents the dynamic Qi and blood flow path corresponding to the preset acupuncture points.

3. The method for assisting stroke rehabilitation based on a multi-source physiological signal wearable device according to claim 1, characterized in that: The calculation formula of the viscera imbalance index is: Among them, w i is the weight coefficient of the i-th organ; P i P is the real-time monitored pulse waveform variation rate; norm,i TongueBaseline is the normal variation rate threshold of the corresponding viscera; i TongueFeature is the tongue feature value of the i-th organ; i The tongue image baseline value of the i-th organ; P crit,i is the critical variation rate threshold of the i-th organ; Θ(.) is the Heaviside step function; t is the current time; τ is the time integral variable.

4. The method for assisting stroke rehabilitation based on a multi-source physiological signal wearable device according to claim 1, characterized in that: The VR scene interaction method uses the Shader Graph method to render the light and shadow changes of the blood flow path in real time, wherein the color gradient of the blood flow path is positively correlated with the current heart rate variability frequency domain energy ratio; And, spatialized audio is output through bone conduction headphones, where the left / right channel phase difference is linearly related to the EEG μ rhythm energy offset, and when the patient's motor imagery potential increases, the audio image automatically shifts to the contralateral side; The motion trajectory is captured by the inertial measurement unit (IMU) and mapped into the kinematic parameters of the virtual limbs in real time in the VR scene to form a proprioception-vision closed loop.

5. The method for assisting stroke rehabilitation based on a multi-source physiological signal wearable device according to claim 1, characterized in that: The state space of the preset rehabilitation action includes PWV, HRV, electromyographic signal entropy value and action completion parameter; The preset action space of the rehabilitation action includes acupoint activation parameters, VR scene complexity parameters and electrical stimulation parameters; The preset reward function of the rehabilitation action is: Among them, ΔFuglMeyerScore is the increment of the scoring scale; StandardTime is the standard time required for rehabilitation action; ActualTime is the time actually spent on completing the rehabilitation action; NumberOfAbnormalAlerts is the number of abnormal alerts.

6. The method for assisting stroke rehabilitation based on a multi-source physiological signal wearable device according to claim 2, characterized in that: The electrical pulse stimulation parameters adopt the heart rate variability HRV feedback model, wherein the expression of the heart rate variability HRV feedback model is: Where, I(t) is the electrical pulse stimulation intensity at time t; Kp is the proportional gain coefficient; is the center frequency; φ HRV (t) is the HRV phase modulation function; HRV LF / HF PWV(t) is the pulse wave velocity at time t. base is the PWV value of the patient in normal state; f c is the center frequency.

7. The method for assisting stroke rehabilitation based on a multi-source physiological signal wearable device according to claim 1, characterized in that: The acupoint activation time series spectrum is modeled by the recursive least squares method RLS real-time modeling of the μ rhythm of the electromyographic signal sEMG and the phase locking value PLV between the motor imagery potential to obtain a dynamic gain function; wherein, the dynamic gain function is: Among them, G base is the basic gain coefficient; κ is the PLV gain adjustment coefficient; PLV max is the preset maximum phase lock value; HRV LF / HF,base is the baseline value of the patient's heart rate variability at rest; The electrical pulse stimulation intensity parameter is adjusted in real time according to the dynamic gain function, and the adjustment formula is: Among them, t onset is the stimulus start time; τ adapt is the adaptive adjustment time constant, which is used to smooth the instantaneous impact of gain change on stimulation intensity; I(t) is the unadjusted electrical pulse stimulation intensity at time t; τ adapt It is the time constant for adaptive adjustment.

8. The method for assisting stroke rehabilitation based on a multi-source physiological signal wearable device according to claim 1, characterized in that: The brain electromyography collaborative decoding module analyzes the sublingual vein texture features output by the tongue image acquisition module in real time through a convolutional neural network (CNN) to extract the tongue image attention weight map to obtain a tongue image feature attention vector; Performing a tensor product operation on the attention vector and the EEG motor imagery potential to generate an enhanced motor imagery feature matrix; The enhanced feature matrix is ​​subjected to spatiotemporal sequence modeling through a long short-term memory network (LSTM), and a time series graph of acupoint activation corresponding to preset hand movements is output.

9. An auxiliary stroke rehabilitation device based on a multi-source physiological signal wearable device, characterized in that: include: A physiological signal monitoring module, used to monitor the pulse waveform variability and sublingual vein characteristic parameters of the subject through a self-powered five-organ monitoring wristband, wherein the self-powered five-organ monitoring wristband includes a flexible piezoelectric sensor, a photoelectric volumetric pulse wave (PPG) sensor, and a tongue image acquisition module; A personalized rehabilitation parameter generation module, used for dynamically evaluating the subject's viscera imbalance index according to the pulse waveform variability rate and the sublingual vein characteristic parameters; generating personalized rehabilitation adjustment parameters according to the subject's viscera imbalance index, wherein the personalized rehabilitation adjustment parameters include acupoint selection, stimulation intensity, stimulation timing, electric pulse stimulation intensity, stimulation frequency, action time and VR scene interaction mode in the acupoint activation timing map; The brain-electromyography collaborative decoding module is used to synchronously collect the EEG signal of the subject and the surface electromyography signal sEMG of the target muscle, analyze the nonlinear coupling relationship between the motor imagery potential of the EEG signal and the surface electromyography signal sEMG through the brain-electromyography collaborative decoding module, and generate acupoint activation timing diagram corresponding to the preset hand movement; The VR guidance and acupoint stimulation module is used to optimize the acupoint activation timing map according to the personalized rehabilitation adjustment parameters to adjust the acupoint selection, stimulation intensity and stimulation timing; the built-in virtual acupuncture scene of the Stomach Meridian of Foot-Yangming is presented to the subject through a portable VR guidance device, and real-time tactile feedback with the preset hand movements is provided through bone conduction headphones to guide the subject to perform the preset rehabilitation movements.

10. A computing device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the above-mentioned method for assisting stroke rehabilitation based on a multi-source physiological signal wearable device.

Images