Integrated spinal cord stimulation systems, spinal cord stimulation methods, media and products

Abstract

This disclosure presents an integrated spinal cord stimulation system, method, medium, and product. One specific embodiment of the system includes: a brain-computer interface (BCI), a spinal cord stimulation device, an exoskeleton device, and a main control unit. The BCI is configured to acquire electroencephalogram (EEG) signals. The spinal cord stimulation device is configured to generate electrical pulses and transmit them to a target spinal cord segment via spinal cord stimulation electrodes. The exoskeleton device is configured to activate motors in corresponding joints to perform preset movements. The main control unit is configured to: acquire EEG signals; generate movement intention information; generate control parameter information; control the spinal cord stimulation device to perform spinal cord stimulation operations based on the spinal cord stimulation parameter information; and control the exoskeleton device to perform exoskeleton drive operations based on the exoskeleton movement parameter information. This embodiment allows for parameter adjustment based on the user's movement intention, better coordinating with the mechanical assistance of the exoskeleton, improving user applicability and experience, and simplifying user operation.

Description

Technical Field

[0001] Embodiments of this disclosure relate to the field of computer technology, and more specifically to an integrated spinal cord stimulation system, spinal cord stimulation method, medium, and product. Background Technology

[0002] Applying specific electrical pulses in specific segments of the epidural space has been shown to effectively activate spinal neural networks, promote the excitability of motor neurons, induce or enhance the contraction of target muscles, and even, to some extent, "awaken" potential motor functions below the level of spinal cord injury, thus offering possibilities for motor reconstruction. Currently, the common approach to spinal cord electrical stimulation is to directly apply electrical stimulation to the target spinal cord segment according to the stimulation parameters, requiring professionals to perform cumbersome parameter settings and mode switching.

[0003] However, when using the above methods, the following technical problems often exist: the user's movement intentions cannot be used for real-time and personalized parameter adjustments, and the mechanical assistance of the exoskeleton cannot be well coordinated, resulting in poor user applicability and user experience. When setting parameters and switching modes, the user learning cost is high, the operation is inconvenient, and it is difficult to promote in home or community rehabilitation environments.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure provide integrated spinal cord stimulation systems, spinal cord stimulation methods, computer-readable media, and computer program products to address one or more of the technical problems mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide an integrated spinal cord stimulation system, comprising: a brain-computer interface (BCI), a spinal cord stimulation device, an exoskeleton device, and a main control unit; the BCI includes EEG electrodes and is configured to acquire EEG signals; the spinal cord stimulation device includes spinal cord stimulation electrodes and a pulse generator, and is configured to generate electrical pulses based on spinal cord stimulation parameter information, via the pulse generator, and transmit them to a target spinal cord segment via the spinal cord stimulation electrodes; the exoskeleton device is configured to activate motors of corresponding joints to perform preset actions based on motion parameter information; the BCI... The aforementioned spinal cord stimulation device and exoskeleton device are communicatively connected to a main control unit, which is configured to perform the following steps: acquiring electroencephalogram (EEG) signals from the brain-computer interface; generating motor intention information based on the EEG signals; generating control parameter information based on the motor intention information, wherein the control parameter information includes spinal cord electrical stimulation parameter information and exoskeleton motion parameter information; controlling the spinal cord stimulation device to perform spinal cord electrical stimulation operations based on the spinal cord electrical stimulation parameter information included in the control parameter information; and controlling the exoskeleton device to perform exoskeleton drive operations based on the exoskeleton motion parameter information included in the control parameter information.

[0008] Optionally, the integrated spinal cord stimulation system further includes an electromyography (EMG) signal acquisition device configured to acquire EMG signals.

[0009] Optionally, the exoskeleton device includes at least one of the following sensors: joint force sensor, joint angle sensor, joint angular velocity sensor, plantar pressure sensor, and trunk posture sensor.

[0010] Optionally, the integrated spinal cord stimulation system further includes a wireless power supply unit, which is configured to power the brain-computer interface, the spinal cord stimulation device, and the main control unit.

[0011] Optionally, the main control unit is further configured to generate motion intention information based on the EEG signal through the following steps: performing a first filtering process on the EEG signal to obtain a first EEG signal; performing a second filtering process on the first EEG signal to obtain a second EEG signal; performing artifact removal processing on the second EEG signal to obtain a third EEG signal; performing motion intention feature extraction processing on the third EEG signal to obtain motion intention feature information; and generating motion intention information based on the motion intention feature information, wherein the motion intention information includes motion type and motion intensity.

[0012] Optionally, the main control unit is further configured to generate control parameter information based on the motion intention information through the following steps: determining the motion state corresponding to the exoskeleton device; matching various control parameters corresponding to the motion type and motion state from the control parameter library based on the motion type and motion state included in the motion intention information, wherein each control parameter includes the target spinal cord segment, stimulation initiation advance, action initiation delay, stimulation parameter information, and action parameter information; generating a stimulation initiation time based on the current time, the stimulation initiation advance, and the motion intensity included in the motion intention information; generating an action initiation time based on the stimulation initiation time and the action initiation delay; determining the target spinal cord segment, the stimulation parameter information, and the stimulation initiation time as spinal cord electrical stimulation parameter information; determining the action parameter information and the action initiation time as exoskeleton action parameter information; and determining the spinal cord electrical stimulation parameter information and the exoskeleton action parameter information as control parameter information.

[0013] Optionally, the main control unit is further configured to generate a stimulus initiation time by means of the following steps based on the current time, the stimulus initiation advance amount, and the motion intensity included in the motion intention information: generating a time compensation amount based on a pre-constructed time compensation function and the motion intensity; determining the difference between the stimulus initiation advance amount and the time compensation amount as the adjusted stimulus initiation advance amount; and determining the sum of the current time and the adjusted stimulus initiation advance amount as the stimulus initiation time.

[0014] Secondly, some embodiments of this disclosure provide a spinal cord stimulation method applied to an integrated spinal cord stimulation system described in any implementation of the first aspect above. The method includes: acquiring electroencephalogram (EEG) signals from a brain-computer interface; generating motor intention information based on the EEG signals; generating control parameter information based on the motor intention information, wherein the control parameter information includes spinal cord stimulation parameter information and motion parameter information; controlling a spinal cord stimulation device to perform spinal cord stimulation operations based on the spinal cord stimulation parameter information included in the control parameter information; and controlling an exoskeleton device to perform exoskeleton drive operations based on the motion parameter information included in the control parameter information.

[0015] Thirdly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the second aspect above.

[0016] Fourthly, some embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the implementations of the second aspect above.

[0017] The above-described embodiments of this disclosure have the following beneficial effects: The integrated spinal cord stimulation system of some embodiments of this disclosure allows for real-time, personalized parameter adjustments based on the user's movement intentions, and effectively coordinates with the mechanical assistance of the exoskeleton, improving user applicability and user experience, simplifying user operation, and facilitating its promotion in home or community rehabilitation environments. Specifically, the reason for poor user applicability and user experience, and the difficulty in promoting it in home or community rehabilitation environments, is that it fails to utilize the user's movement intentions for real-time, personalized parameter adjustments, and cannot effectively coordinate with the mechanical assistance of the exoskeleton. This results in poor user applicability and user experience, high learning costs and inconvenient operation when setting parameters and switching modes, making it difficult to promote in home or community rehabilitation environments. Based on this, some embodiments of the integrated spinal cord stimulation system disclosed herein include a brain-computer interface (BCI), a spinal cord stimulation device, an exoskeleton device, and a main control unit; the BCI includes EEG electrodes and is configured to acquire EEG signals; the spinal cord stimulation device includes spinal cord stimulation electrodes and a pulse generator, and is configured to generate electrical pulses based on spinal cord stimulation parameter information, via the pulse generator, and transmit them to the target spinal cord segment via the spinal cord stimulation electrodes; the exoskeleton device is configured to activate motors of corresponding joints to perform preset actions based on motion parameter information; the BCI, the spinal cord stimulation device, and the exoskeleton device are configured to... The spinal cord stimulation device and the aforementioned exoskeleton device are communicatively connected to a main control unit, which is configured to perform the following steps: acquiring electroencephalogram (EEG) signals from the brain-computer interface; generating motor intention information based on the EEG signals; generating control parameter information based on the motor intention information, wherein the control parameter information includes spinal cord stimulation parameters and exoskeleton motion parameters; controlling the spinal cord stimulation device to perform spinal cord stimulation operations based on the spinal cord stimulation parameters included in the control parameter information; and controlling the exoskeleton device to perform exoskeleton drive operations based on the exoskeleton motion parameters included in the control parameter information. Because the integrated spinal cord stimulation system identifies motor intention information through the acquired EEG signals, it can dynamically determine the control parameter information based on the motor intention information, enabling real-time, personalized parameter adjustments based on the user's motor intention. Simultaneously, the control parameter information, including spinal cord stimulation parameters for controlling the spinal cord stimulation device and exoskeleton motion parameters for controlling the exoskeleton device, can better coordinate the mechanical assistance of the exoskeleton, thereby improving user applicability and user experience. Furthermore, because it eliminates the need for users to manually set control parameters and switch modes, it simplifies user operation and facilitates its promotion in home or community rehabilitation environments. Attached Figure Description

[0018] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0019] Figure 1 This is a schematic diagram of the structure of some embodiments of the integrated spinal cord electrical stimulation system according to the present disclosure;

[0020] Figure 2 This is a flowchart of some embodiments of the spinal cord electrical stimulation method according to the present disclosure;

[0021] Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0022] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0023] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0024] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0025] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0026] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0027] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0028] Figure 1A schematic diagram of the structure of some embodiments of the integrated spinal cord stimulation system according to the present disclosure is shown. The integrated spinal cord stimulation system 100 includes a brain-computer interface 101, a spinal cord stimulation device 102, an exoskeleton device 103, and a main control unit 104.

[0029] In some embodiments, the brain-computer interface device 101 described above can be a device for acquiring electroencephalogram (EEG) signals. The brain-computer interface device can be placed on the user's head. The brain-computer interface device 101 can include EEG electrodes. EEG electrodes can be non-invasive, invasive, or semi-invasive electrodes. Non-invasive electrodes can be fixed with an elastic cap or a custom helmet, and the scalp location can be selected according to the area of ​​motor intention. Invasive electrodes can be placed within the scalp through craniotomy. For example, the EEG electrodes can be Ag / AgCl-conductive fabric composite electrodes with a medical-grade silicone base and a micro-protrusion design on the surface to conform to the curvature of the skull. The EEG electrodes can be implanted under the skull, epidurally, or intracerebrally, covering or penetrating the motor cortex (such as the corresponding areas of C3 / C2 / C4). Semi-invasive electrodes can be between invasive and non-invasive types, implanted under the scalp and attached to the dura mater but without directly penetrating the cerebral cortex to acquire signals. The aforementioned brain-computer interface (BCI) device can have a multi-channel microelectrode array structure, capable of capturing local field potentials (LFP) and high-frequency brain electrical activity. The number of EEG electrodes included in the BCI device is not limited here. The BCI device can be configured to acquire EEG signals. The BCI device may also include a signal transmitting device. The signal transmitting device can be placed intracranially or subcutaneously, responsible for initially amplifying, filtering, and encoding the signals recorded by the acquisition chip, and transmitting them to the main control unit in real time via a wireless communication module (such as BLE or UWB). The signal transmitting device can be equipped with a dedicated power supply module (e.g., powered by wireless charging or a subcutaneous battery). For example, the signal transmitting device may include an analog front-end (AFE) and an analog-to-digital converter (ADC). The AFE can be used to amplify, filter, and convert weak raw EEG signals (μV level) into stable analog signals suitable for processing by the ADC. The AFE may include a low-noise instrumentation amplifier, a programmable filter bank, and a DC servo loop. A low-noise instrumentation amplifier (APA) can be used with an input reference noise of <0.8μVpp (0.5-100Hz), employing chopper zero-stabilization technology to suppress 1 / f noise. The programmable filter bank's dynamic bandpass adjustment supports segmented switching within the 0.5-100Hz range (e.g., delta wave 1-4Hz, alpha wave 8-12Hz). A DC servo loop utilizes a feedback integrator to eliminate electrode polarization voltage (range ±300mV), with an output offset of <10μV, suppressing active drift. The EEG acquisition ADC can convert the analog EEG signals processed by the EEG acquisition AFE into high-precision digital signals. The EEG acquisition ADC can be set with a sampling rate of 1k-2kHz and has a built-in PGA. It supports 256 channels of simultaneous sampling with inter-channel skew of <5ns, ensuring multi-channel phase consistency.

[0030] In some embodiments, the spinal cord stimulation device 102 described above can be a device for applying electrical stimulation to a spinal cord segment. The spinal cord stimulation device 102 can include spinal cord stimulation electrodes and a pulse generator. The spinal cord stimulation electrodes can be disposed in the vertebrae corresponding to the spinal cord segment, and can provide electrical stimulation to the spinal cord corresponding to the spinal cord segment by direct implantation into the vertebrae. For example, the spinal cord stimulation electrodes can be platinum-iridium alloy microwire electrodes with a diameter of 10-50 μm, a contact spacing of 200 μm, a polyimide substrate, a bending radius of <1 mm, and adaptability to the physiological curvature of the spinal cord. The pulse generator can be responsible for generating precisely controlled electrical pulse signals, which are transmitted to the spinal cord nerve tissue through the spinal cord stimulation electrodes to activate or modulate neural pathways. The spinal cord stimulation device 102 can be configured to generate electrical pulses based on spinal cord electrical stimulation parameter information, through the pulse generator, and transmit them to the target spinal cord segment through the spinal cord stimulation electrodes. The target spinal cord segment can be the spinal cord segment where the spinal cord stimulation electrodes are disposed.

[0031] In some embodiments, the exoskeleton device 103 can provide physical support and power assistance to users with limb motor dysfunction, helping them to perform exercises such as standing and walking, and promoting neuroplasticity and muscle strength recovery. The exoskeleton device 103 may include, but is not limited to, at least one of the following: a lower limb exoskeleton, an upper limb exoskeleton, and a controller. The lower limb exoskeleton can be a brace used to provide physical support and power assistance to the user's lower limbs. The upper limb exoskeleton can be a brace used to provide physical support and power assistance to the user's upper limbs. The exoskeleton device may be configured with motors, reducers, sensors, and fixation components corresponding to each joint. For example, the motor may be a brushless motor. The reducer may be a harmonic reducer. The fixation components may include a carbon fiber support and pneumatic straps. The controller can process commands from the main control unit and sensor feedback in real time. The exoskeleton device 103 can be configured to activate the motors of the corresponding joints to perform preset actions based on motion parameter information. The preset actions may correspond to the motion parameter information, that is, the actions represented by the motion parameter information.

[0032] In some embodiments, the brain-computer interface 101, the spinal cord stimulation device 102, and the exoskeleton device 103 can be communicatively connected to the main control unit 104. For example, they can be communicatively connected to the main control unit 104 via wired or wireless connection. The main control unit 104 can be configured to perform the following steps: acquiring electroencephalogram (EEG) signals from the brain-computer interface; generating motor intention information based on the EEG signals; generating control parameter information based on the motor intention information, wherein the control parameter information includes spinal cord stimulation parameter information and exoskeleton motion parameter information; controlling the spinal cord stimulation device to perform spinal cord stimulation operation based on the spinal cord stimulation parameter information included in the control parameter information; and controlling the exoskeleton device to perform exoskeleton drive operation based on the exoskeleton motion parameter information included in the control parameter information.

[0033] In practice, brain-computer interfaces can acquire brain signals at a preset sampling frequency. For example, the preset sampling frequency can be 30 kHz.

[0034] In some optional implementations of certain embodiments, the main control unit may be further configured to generate motor intention information based on the aforementioned EEG signals through the following steps:

[0035] The first step involves performing a first filtering process on the aforementioned EEG signal to obtain a first EEG signal. In practice, bandpass filtering can be applied to the EEG signal to obtain the first EEG signal. For example, bandpass filtering can be performed using a set bandpass filter, with the target frequency band of the bandpass filter set to 8-30Hz to extract μ (typically between 8-13Hz) and β (approximately between 13-30Hz) rhythms. This bandpass filter will allow frequency components within the target frequency band to pass through while reducing or eliminating frequency components outside the target frequency band, helping to remove low-frequency drift and high-frequency noise, thereby focusing on the EEG rhythm of interest.

[0036] The second step involves performing a second filtering process on the first EEG signal to obtain the second EEG signal. In practice, the first EEG signal is subjected to power frequency interference filtering to obtain the second EEG signal. Electromagnetic interference generated by power lines in the environment is typically 50Hz or 60Hz (depending on the country's power grid standards), and this interference can introduce unwanted noise into the EEG signal. To remove this interference, a notch filter can be used, which can significantly reduce the signal strength at a specific frequency (such as 50Hz or 60Hz) without affecting other frequency components. The purpose of a notch filter is to precisely create a "groove" at the interference frequency, significantly attenuating the signal near this frequency without affecting the signal at adjacent frequencies. This improves the quality of the EEG signal.

[0037] The third step involves artifact removal processing of the second EEG signal to obtain the third EEG signal. Here, artifacts refer to interference in the EEG signal caused by body movement (such as blinking or head movements). These artifacts may mask the true characteristics of the EEG signal, thus requiring effective identification and removal methods. In practice, independent component analysis or adaptive filtering techniques can be used to identify and remove artifact interference from the EEG signal.

[0038] The fourth step involves extracting motor intention features from the aforementioned third EEG signal to obtain motor intention feature information. In practice, EEG signals corresponding to various preset channels can be extracted from the aforementioned third EEG signal as target EEG signals. For example, each preset channel can be a channel closely related to limb movement in the sensorimotor cortex region (located near the central sulcus). Then, the aforementioned target EEG signal can be filtered to a first band and a second band to obtain the first target EEG signal and the second target EEG signal. The first band can be the μ band, and the second band can be the β band. The filtering frequency corresponding to the first band can be 8-13Hz. The filtering frequency corresponding to the second band can be 13-30Hz. Next, for the first target EEG signal and the second target EEG signal, the energy value of the EEG signal at each time point can be determined. Here, the energy value can be the power spectral density. For example, the power spectral density can be determined by short-time Fourier transform (STFT) or wavelet transform. Thus, the distribution of the signal in time and frequency can be obtained. Furthermore, the determined energy values ​​can be combined into a motor intention feature vector. The motion intention feature vector can include energy values ​​from various EEG electrodes, different wavelengths, and at different time points. This motion intention feature vector can then be normalized to obtain a normalized motion intention feature vector as the motion intention feature information. For example, the normalization process can be Z-score standardization.

[0039] In practice, the aforementioned EEG signals can first be segmented according to a fixed time window to obtain individual EEG signal segments. For example, the window size of the fixed time window can be 1 second. Then, for each EEG signal segment, the power spectral density can be calculated to obtain the power spectral density of the EEG signal segment at each time point. For example, the Welch method or short-time Fourier transform can be used to calculate the power spectral density. Next, the power spectral density of the first band and the second band at each time point can be extracted to obtain the first power change information and the second power change information. The first power change information includes the power spectral density of the first band at each time point. The second power change information includes the power spectral density of the second band at each time point. Next, the first and second power change information can be compared with the pre-stored power spectral density at each time point in the resting state to calculate the event-related desynchronization (ERD) or synchronization (ERS) percentage, which serves as the first and second frequency domain feature information. The first frequency domain feature information corresponds to the first band. The second frequency domain feature information corresponds to the second band. For the EEG signals of each cortical region corresponding to the above EEG signal segments, cospatial pattern analysis (CSP) can be used to extract the spatial projection components that best distinguish different motor intentions, obtaining spatial feature information. For each frequency band corresponding to the above EEG signal segments, discrete wavelet transform (DWT) is used to extract the energy change characteristics of the above frequency band at each time point, obtaining time-frequency joint feature information. Time-frequency joint features can be used to enhance the recognition ability of transition states (such as starting or stopping intentions). For the EEG signals of each channel corresponding to the above EEG signal segments, the time-domain statistics corresponding to the EEG signals of the above channels can be calculated as statistical feature information. Time-domain statistics may include, but are not limited to: entropy, skewness, kurtosis, and zero-crossing rate. Time-domain statistics can be used to assist classification. Next, the statistical feature information, time-frequency joint feature information, spatial feature information, first frequency domain feature information, and second frequency domain feature information corresponding to the above EEG signal segments can be concatenated into a feature vector. Thus, the feature vector corresponding to each EEG signal segment can be obtained as a motor intention feature vector. Next, the above motion intention feature vector can be normalized to obtain a normalized motion intention feature vector as motion intention feature information. For example, the normalization process can be Z-score standardization.

[0040] Step 5: Based on the aforementioned motion intention feature information, generate motion intention information. This motion intention information includes motion type and motion intensity. Motion type characterizes the user's intended movement. Motion types may include, but are not limited to: standing, walking, turning left, turning right, and stopping. Motion intensity represents the strength of the intention or the desired speed / stride ratio. For example, motion intensity can be a value between 0 and 1. In practice, the aforementioned motion intention feature information can be input into a pre-trained motion intention decoding model to obtain the motion intention information. The motion intention decoding model can be a pre-trained neural network model or machine learning model that takes motion intention feature information as input and outputs motion intention information. For example, the motion intention decoding model may include, but is not limited to: support vector machine, linear discriminant analysis model, and convolutional neural network. Training samples used to train the motion intention decoding model may include sample motion intention feature information and corresponding sample motion intention information. Sample motion intention information may include motion type and motion intensity. Motion type may include, but is not limited to: left leg lift, right leg lift, and stopping.

[0041] In some optional implementations of certain embodiments, the main control unit can be further configured to generate control parameter information based on the motion intent information through the following steps:

[0042] The first step is to determine the motion state corresponding to the exoskeleton device. In practice, the motion state of the exoskeleton device can be determined using sensor data collected by various sensors on the device. Specifically, the joint angles of each joint collected by the joint angle sensors on the exoskeleton device can be matched with the corresponding motion state from a pre-set motion state matching table. For example, each motion state may correspond to at least one joint angle range. If the collected joint angles are all within the range corresponding to the motion state, then the motion state is determined to be a matched motion state. Alternatively, posture data collected by at least one torso posture sensor on the exoskeleton device can be matched with the corresponding motion state from a pre-set motion state matching table. For example, each motion state may correspond to at least one torso position posture range. If the collected posture data are all within the range corresponding to the motion state, then the motion state is determined to be a matched motion state. Motion states may include, but are not limited to: left foot support phase, right foot support phase, both feet support phase, mid-left foot swing phase, and mid-right foot swing phase.

[0043] The second step involves matching the corresponding control parameters from the control parameter library based on the movement type and movement state information provided above. The control parameter library can be a database storing preset control parameters for different movement types and states. For each movement type and state, there may be a target spinal cord segment, stimulation initiation advance, movement initiation delay, stimulation parameter information, and movement parameter information. Each control parameter can include the target spinal cord segment, stimulation initiation advance, movement initiation delay, stimulation parameter information, and movement parameter information. The target spinal cord segment can be the spinal cord region requiring stimulation. Each spinal cord region can correspond to at least one spinal cord stimulation electrode that requires electrical stimulation. Since there is a physiological delay between electrical stimulation and muscle contraction, the stimulation initiation advance can be the baseline time (in milliseconds) at which spinal cord stimulation should begin earlier than the ideal contraction time of the target muscle. Considering nerve conduction time and muscle activation establishment time, the movement initiation delay can be the baseline time (in milliseconds) at which exoskeleton movement should be delayed relative to the spinal cord electrical stimulation initiation time. Stimulation parameters can be basic stimulation parameters (e.g., pulse width, frequency, waveform), which can be fine-tuned based on feedback. Motion parameters can characterize the exoskeleton's motion instruction templates, including at least one target joint motion corresponding to a basic joint torque / angle trajectory. Target joint motions can be the joint movements required to complete the intended movement. For example, when the movement type is left leg lift, the target joint motions could include: left hip flexion, left knee flexion, and ankle dorsiflexion. When the movement type is right leg lift, the target joint motions could include: right hip flexion, right knee flexion, and ankle dorsiflexion. When the movement type is stop, the target joint motions could include: stable leg posture, zero torque output, or rigid mode. The instruction templates can predefine the target angle trajectories or output torque curves for each joint (e.g., hip, knee, ankle) under specific motion types and gait phases, used to drive the exoskeleton motors to achieve physiologically consistent coordinated movements. Each motion type can correspond to a different template. For example, the instruction template for the "walking-left leg swing phase" could include: target hip angle: gradually flexing from -10° to +25°, lasting approximately 400ms; target knee angle: rapidly flexing from 0° to +45°, then slowly extending to 0°, lasting approximately 300ms; ankle torque output: set to a 0–5 Nm dorsiflexion assist curve (ankle dorsiflexion). It should be noted that the stimulation and movement parameters can be sequential to apply sequential electrical stimulation and provide sequential exoskeleton assistance. For example, after applying one electrical stimulus, the exoskeleton can assist the user in walking alternately left and right for a period of time.

[0044] The third step is to generate the stimulus initiation time based on the current time, the aforementioned stimulus initiation advance amount, and the movement intensity included in the aforementioned movement intention information.

[0045] The fourth step is to generate the action initiation time based on the stimulus initiation time and the action initiation delay. In practice, the sum of the stimulus initiation time and the action initiation delay can be used as the action initiation time. Therefore, the action initiation time can be used as the initiation time of the actual exoskeleton movement.

[0046] The fifth step involves defining the target spinal cord segment, the stimulation parameter information, and the stimulation initiation time as spinal cord electrical stimulation parameter information. This parameter information can include the target spinal cord segment, the stimulation parameter information, and the stimulation initiation time. Therefore, the spinal cord electrical stimulation parameter information can serve as control commands for the spinal cord stimulation device.

[0047] The sixth step is to determine the aforementioned motion parameter information and the aforementioned motion initiation time as the exoskeleton motion parameter information. The exoskeleton motion parameter information may include the aforementioned motion parameter information and the aforementioned motion initiation time. Therefore, the exoskeleton motion parameter information can serve as control commands for the exoskeleton device.

[0048] The seventh step involves defining the aforementioned spinal cord stimulation parameters and exoskeleton motion parameters as control parameters. These control parameters can include both the spinal cord stimulation parameters and the exoskeleton motion parameters. This allows for the dynamic generation of timestamped control commands based on the user's intention, enabling time-sequential control of the spinal cord stimulation device and exoskeleton, resulting in more natural user movements. Furthermore, considering the physiological delay between electrical stimulation and muscle contraction, as well as the time required for nerve conduction and muscle activation, a highly efficient and coordinated process conforming to physiological timing—"intention recognition → neural pathway pre-activation (SCS) → muscle contraction preparation → exoskeleton power assistance"—can be achieved. This allows for timely activation of the target muscles before exoskeleton joint movement, effectively superimposing the exoskeleton assistance with the muscle contraction induced by spinal cord stimulation.

[0049] In some optional implementations of certain embodiments, the main control unit may be further configured to generate a stimulus initiation time by means of the following steps: based on the current time, the stimulus initiation advance amount, and the motion intensity included in the motion intent information:

[0050] The first step is to generate a time compensation amount based on the pre-constructed time compensation function and the aforementioned motion intensity. In practice, the aforementioned motion intensity can be input into the aforementioned time compensation function to obtain the time compensation amount. For example, the time compensation function can be f(motion intensity) = k × motion intensity. Here, k can be an empirical coefficient; the stronger the user's intention (i.e., the greater the motion intensity), the faster the desired response. Therefore, reducing the waiting time for spinal cord stimulation initiation increases the value of f(motion intensity), and the stimulation initiation time is closer to the current time.

[0051] The second step is to determine the difference between the above-mentioned stimulus initiation advance amount and the above-mentioned time compensation amount as the adjusted stimulus initiation advance amount.

[0052] The third step is to determine the stimulus initiation time by combining the current time and the adjusted stimulus initiation advance.

[0053] In some alternative implementations of certain embodiments, the spinal cord stimulation device described above can be configured to perform spinal cord electrical stimulation by the following steps:

[0054] The first step is to receive the spinal cord electrical stimulation parameter information sent by the main control unit through the controller included in the spinal cord stimulation device.

[0055] The second step is to synchronize the internal clock of the controller in the spinal cord stimulation device with the master clock of the main control unit. In practice, Network Time Protocol (NTP) or Precision Time Protocol (PTP) can be used for time synchronization.

[0056] The third step involves determining that the current time has reached the stimulation initiation time included in the aforementioned spinal cord electrical stimulation parameter information, and then, according to the stimulation parameters included in the aforementioned spinal cord electrical stimulation parameter information, outputting an electrical pulse sequence generated by a pulse generator through the spinal cord stimulation electrode corresponding to the target spinal cord segment. Thus, an electrical stimulation pulse sequence can be output through the corresponding electrode channel at a precise time point according to the specified target spinal cord segment and stimulation parameters.

[0057] The exoskeleton device described above is configured to perform exoskeleton actuation operations through the following steps:

[0058] The first step is to receive the exoskeleton motion parameter information sent by the main control unit through the controller included in the exoskeleton device.

[0059] The second step is to synchronize the internal clock of the controller in the exoskeleton device with the master clock of the main control unit. In practice, Network Time Protocol (NTP) or Precision Time Protocol (PTP) can be used for time synchronization.

[0060] Third, in response to determining that the current time has reached the action initiation time included in the aforementioned exoskeleton motion parameter information, the motors of at least one corresponding joint are driven to operate according to the motion parameter information included in the aforementioned exoskeleton motion parameter information. Thus, at a precise time point, the motors of the corresponding joints of the exoskeleton can be driven to perform a predetermined action (such as ankle dorsiflexion based on the provided hip flexion torque) according to the motion parameters specified in the instruction.

[0061] In some optional implementations of certain embodiments, the main control unit described above may also be configured to perform the following steps:

[0062] The first step is to determine the muscle activation onset time based on the electromyographic (EMG) signals corresponding to the target spinal cord segment stimulated by the spinal cord stimulation electrodes. In practice, the mean and standard deviation of the EMG signals before spinal cord stimulation can be determined first. Then, a threshold can be determined based on the mean and standard deviation. For example, the mean and three times the standard deviation can be used as the threshold. Next, the point in the EMG signal corresponding to the target spinal cord segment stimulated by the spinal cord stimulation electrodes that first continuously exceeds the preset duration of the threshold can be determined as the activation start point. For example, the preset duration can be 10 ms. Finally, the timestamp corresponding to the activation start point can be determined as the muscle activation start time. Alternatively, a pre-trained machine learning model (such as a support vector machine) can be used to identify activation segments in the EMG signal to determine the activation start point.

[0063] The second step is to determine the difference between the muscle activation start time and the stimulus initiation time as the neuromuscular delay duration.

[0064] The third step involves determining the action response time of the exoskeleton device based on sensor data collected by at least one sensor included in the device. Each action parameter corresponds to a target joint action. The target joint action represents the action required by the command to be performed by the exoskeleton. Each target joint action corresponds to a pre-defined sensor data range for at least one sensor (e.g., a joint angle sensor, a joint force sensor, or a plantar pressure sensor). When all collected sensor data falls within the sensor data range corresponding to the target joint action and persists for a certain period (e.g., 30ms), it can be determined that the exoskeleton device has achieved the required action, and the sensor data acquisition time can be defined as the action response time of the exoskeleton device.

[0065] The fourth step is to determine the difference between the above action response time and the above action start time as the action response time difference.

[0066] The fifth step involves adjusting the stimulus initiation advance corresponding to the aforementioned movement type and movement state in the control parameter library based on the determined neuromuscular delay durations. In practice, a pre-set expected neuromuscular delay duration can be determined first. For example, the expected neuromuscular delay duration can be 50ms. Then, in response to determining that the difference between the average of the aforementioned neuromuscular delay durations and the expected neuromuscular delay duration is greater than or equal to a first preset time difference, the difference between the average of the aforementioned neuromuscular delay durations and the expected neuromuscular delay duration can be determined as a first adjustment amount. For example, the first preset time difference can be 20ms. Finally, the sum of the stimulus initiation advance corresponding to the aforementioned movement type and movement state in the control parameter library and the first adjustment amount can be determined as the updated stimulus initiation advance amount, thereby adaptively adjusting the stimulus initiation advance corresponding to the aforementioned movement type and movement state in the control parameter library. In practice, for each determined neuromuscular delay duration, the difference between the aforementioned neuromuscular delay duration and the preset neuromuscular delay duration can also be determined as the delay time difference. For example, the preset neuromuscular delay duration can be 50ms. Then, the product of the delay difference and a preset coefficient can be used to determine the first adjustment amount. For example, the preset coefficient can be 0.5.

[0067] Step 6: Based on the determined action response time differences, adjust the action start delay amounts corresponding to the aforementioned motion types and motion states in the control parameter library. In practice, in response to the determination that the average of the aforementioned action response time differences is greater than or equal to a second preset time difference, the product of the latest determined action response time difference and a preset learning rate can be used as the second adjustment amount. For example, the second preset time difference can be 30ms. The preset learning rate can range from [0.3, 0.7]. Finally, the difference between the action start delay amounts corresponding to the aforementioned motion types and motion states in the control parameter library and the second adjustment amount can be used as the updated action start delay amount to adaptively adjust the action start delay amounts corresponding to the aforementioned motion types and motion states in the control parameter library. Patients with different spinal cord injuries vary greatly in the degree of injury, residual function, neuroplasticity potential, and muscle condition. Based on the user's muscle response to spinal cord electrical stimulation and the duration of the exoskeleton device's response to movement, the stimulation initiation advance and movement initiation delay in the control parameter library are adaptively adjusted. As an inventive point of this disclosure, this can improve the automated, intelligent, and personalized adaptation mechanism of timing parameters and auxiliary intensity based on individual characteristics (such as sensitivity to spinal cord electrical stimulation, muscle strength, and motor control ability).

[0068] Optionally, the main control unit can also be configured to adjust the motion parameter information corresponding to the motion type and motion state in the control parameter library based on sensor data collected by at least one sensor included in the exoskeleton device. In practice, for the assist torque corresponding to each target joint movement in the motion parameter information, the torque corresponding to the target joint movement in the sensor data is determined as the actual torque. In response to the determined actual torque being consistently lower than the assist torque for a preset duration, and if the plantar pressure center COP significantly deviates from the desired trajectory (e.g., the COP during the support phase deviates more than 10 mm outward), the assist torque corresponding to the target joint movement included in the motion parameter information corresponding to the motion type and motion state in the control parameter library can be increased by a preset torque, and the assist duration can be extended by a preset duration to improve support stability. For example, the preset torque can be 5 Nm. Thus, the magnitude of the assist torque of the exoskeleton can be dynamically adjusted based on mechanical feedback. Thus, dynamic feedback from the exoskeleton (such as joint angle, torque, and plantar pressure) can be effectively integrated to form a fast and precise closed-loop control.

[0069] Optionally, the main control unit can also be configured to update the time compensation function based on sensor data collected by at least one sensor included in the exoskeleton device. In practice, gait events (e.g., heel strike) can be detected using sensor data detected by a torso posture sensor included in the exoskeleton device. Then, the gait symmetry value corresponding to the current gait event can be calculated. Specifically, the absolute value of the difference between the left leg support time and the right leg support time in the current gait event can be determined first, then the sum of the left leg support time and the right leg support time can be determined, then the ratio of the absolute value of the difference to the sum can be determined, and finally, the difference between 1 and the ratio can be determined as the gait symmetry value corresponding to the current gait event. The left leg support time and the right leg support time can refer to the time from the first contact of the left or right foot with the ground to the complete departure from the ground. When the heel strikes the ground, the acceleration signal detected by the torso posture sensor shows a significant peak. When the toes leave the ground, the angular velocity signal (rotation around the ankle joint) changes. The time difference between toe-off and heel-off can be defined as the support time, allowing for the determination of the support time for the left and right legs. Foot pressure sensors can also determine foot contact with the ground; the pressure value initially rises from 0 (foot strike) and drops back to 0 when the toes leave the ground (foot lift). Next, energy expenditure can be determined by collecting the user's heart rate and movement speed. For example, the sum of the product of a first coefficient and heart rate, a second coefficient and movement speed, and a third coefficient can be used to determine the energy expenditure. These coefficients can be pre-defined coefficients of a linear function of heart rate, movement speed, and energy expenditure, and can be pre-calibrated experimentally. Then, the gait symmetry value and energy consumption value can be input into a pre-defined objective function (e.g., J(k) = GSI - λ × CoT, where GSI represents the gait symmetry value, CoT represents the energy consumption value, and λ represents the weighting coefficient used to balance the importance of symmetry and energy consumption) to obtain the objective function value. Next, policy gradient method or Q-learning can be used to update the empirical coefficients of the time compensation function based on the objective function value after each training round to better match the response to the intensity of user intent.

[0070] Optionally, the main control unit can also be configured to perform corresponding safety protection operations in response to the detection of electromyographic signals or sensor data collected by at least one sensor included in the exoskeleton device meeting preset abnormal conditions. In practice, in response to the detection that the activation intensity in the electromyographic signal is greater than or equal to a preset threshold (e.g., 80% of the maximum contraction intensity), the spinal cord stimulation device can be controlled to immediately stop the spinal cord electrical stimulation operation and reduce the output torque of the exoskeleton device by a preset torque to avoid muscle strain. In response to the detection that the actual torque for any joint in the sensor data exceeds the safety limit (e.g., knee joint torque > 45 Nm), the exoskeleton device is controlled to enter the support mode and the exoskeleton power output is stopped. In response to the detection by the plantar pressure sensor that the center of plantar pressure COP deviates significantly from the expected trajectory (e.g., the support phase COP is more than 10 mm outward), or the detection by the trunk posture sensor that postural instability is detected (e.g., the user's tilt angle exceeds 15°), the exoskeleton device is controlled to enter the support mode to prevent falls. This allows for the effective integration of dynamic feedback from the exoskeleton (such as joint angles, torques, and plantar pressure) and electromyographic / biomechanical feedback induced by the SCS, forming a rapid and precise closed-loop control. This ensures a quick response when an abnormality is detected, preventing harm to the user.

[0071] Optionally, the aforementioned integrated spinal cord electrical stimulation system may further include an electromyography (EMG) signal acquisition device. The EMG signal acquisition device can be used to acquire EMG signals at the site where electrical stimulation generated by the spinal cord stimulation electrodes evokes muscle activity. The aforementioned EMG signal acquisition device can be configured to acquire EMG signals. The EMG signal acquisition device may include EMG electrodes. For example, the EMG electrodes may employ a conductive hydrogel substrate (stretchability > 500%), embed Ag / AgCl nanoparticles, adapt to dynamic skin deformation, and use an 8×8 matrix electrode to support high-density acquisition of signals from adjacent muscle groups. The EMG signal acquisition device may further include an EMG acquisition amplifier (AFE) and an EMG acquisition analog-to-digital converter (ADC). The EMG acquisition AFE may employ a dynamic gain amplifier, be configured using needle electrodes or implanted electrodes (bandwidth 20-2kHz), and use an adaptive high-pass filter bank with a programmable filter bank to attenuate low-frequency jitter (<5Hz) and suppress motion artifacts. The EMG acquisition ADC may have a sampling rate of 4kHz and support 16-channel simultaneous sampling.

[0072] Optionally, the exoskeleton device may include at least one of the following sensors: a joint force sensor, a joint angle sensor, a joint angular velocity sensor, a plantar pressure sensor, and a trunk posture sensor. The joint force sensor can be located at the joints of the exoskeleton device, for example, at the hip / knee / ankle joint axis. The joint force sensor can be used to collect force or torque; for example, the joint force sensor can be a six-dimensional force sensor. The joint angle sensor can be located at the joints of the exoskeleton device, for example, at the joint rotation center. The joint angle sensor can be used to collect joint motion angles; for example, the joint angle sensor can be an absolute encoder. The joint angular velocity sensor can be located at the joints of the exoskeleton device, for example, at the proximal end of the joint link. The joint angular velocity sensor can be used to collect the angular velocity of joint motion; for example, the joint angular velocity sensor can be a MEMS gyroscope. The plantar pressure sensor can be located at the sole of the foot of the exoskeleton device, for example, inside the insole; it can be located at the forefoot, heel, or arch. The plantar pressure sensor can be used to collect the pressure distribution on the sole of the foot; for example, the plantar pressure sensor can be a flexible pressure sensor array. Trunk posture sensors can be used for real-time monitoring of a user's trunk posture (such as forward tilt, lateral tilt, and rotation). These sensors can be fixed to the wearer's chest or back, specifically the T10–L2 spinal region, via adhesive patches, elastic bands, or integration into the back structure of the exoskeleton. Placement can be close to the body's central axis of posture (e.g., the midline of the spine) to reduce interference from limb movements. Additional trunk posture sensors can be placed in the pelvis, shoulders, etc., to achieve multi-site posture fusion and improve accuracy. All trunk posture sensors should maintain clock consistency with the controllers of the EEG and spinal stimulation devices via a time synchronization protocol (such as PTP) to ensure millisecond-level feedback control of posture changes. The trunk posture sensors can be mounted on the trunk frame of the exoskeleton device, for example, at the center of the trunk frame on the back. For example, the trunk posture sensor can be an IMU (Integrated Mutual Actuation Unit).

[0073] Optionally, the integrated spinal cord stimulation system may further include a wireless power supply unit. This wireless power supply unit can be configured to power the brain-computer interface (BCI), the spinal cord stimulation device, and the main control unit. The wireless power supply unit can be located within the BCI, the spinal cord stimulation device, or integrated with the main control unit. The wireless power supply unit may include a battery, a wireless charging receiver, and a power management module. For example, the battery may be a lithium polymer battery with high energy density and wireless charging capability; the receiver may be a Qi 1.3 standard (15W) receiving coil, compatible with mainstream wireless chargers; and the power management module may support multi-channel DC-DC conversion to simultaneously meet the needs of the BCI, the spinal cord stimulation device, and the main control unit. When powering the BCI, a flexible wire can be used to run along the neck, or a subcutaneous wire can be used for connection. When powering the spinal cord stimulation device, a subcutaneous wire can be used for connection. When powering the main control unit, internal wiring can be used for connection. It should be noted that the exoskeleton device can be configured with a separate power source, for example, it can be configured with a 48V 10Ah lithium battery (with a battery life of 4 hours), which supports hot-swappable replacement.

[0074] The above-described embodiments of this disclosure have the following beneficial effects: The integrated spinal cord stimulation system of some embodiments of this disclosure allows for real-time, personalized parameter adjustments based on the user's movement intentions, and effectively coordinates with the mechanical assistance of the exoskeleton, improving user applicability and user experience, simplifying user operation, and facilitating its promotion in home or community rehabilitation environments. Specifically, the reason for poor user applicability and user experience, and the difficulty in promoting it in home or community rehabilitation environments, is that it fails to utilize the user's movement intentions for real-time, personalized parameter adjustments, and cannot effectively coordinate with the mechanical assistance of the exoskeleton. This results in poor user applicability and user experience, high learning costs and inconvenient operation when setting parameters and switching modes, making it difficult to promote in home or community rehabilitation environments. Based on this, some embodiments of the integrated spinal cord stimulation system disclosed herein include a brain-computer interface (BCI), a spinal cord stimulation device, an exoskeleton device, and a main control unit; the BCI includes EEG electrodes and is configured to acquire EEG signals; the spinal cord stimulation device includes spinal cord stimulation electrodes and a pulse generator, and is configured to generate electrical pulses based on spinal cord stimulation parameter information, via the pulse generator, and transmit them to the target spinal cord segment via the spinal cord stimulation electrodes; the exoskeleton device is configured to activate motors of corresponding joints to perform preset actions based on motion parameter information; the BCI, the spinal cord stimulation device, and the exoskeleton device are configured to... The spinal cord stimulation device and the aforementioned exoskeleton device are communicatively connected to a main control unit, which is configured to perform the following steps: acquiring electroencephalogram (EEG) signals from the brain-computer interface; generating motor intention information based on the EEG signals; generating control parameter information based on the motor intention information, wherein the control parameter information includes spinal cord stimulation parameters and exoskeleton motion parameters; controlling the spinal cord stimulation device to perform spinal cord stimulation operations based on the spinal cord stimulation parameters included in the control parameter information; and controlling the exoskeleton device to perform exoskeleton drive operations based on the exoskeleton motion parameters included in the control parameter information. Because the integrated spinal cord stimulation system identifies motor intention information through the acquired EEG signals, it can dynamically determine the control parameter information based on the motor intention information, enabling real-time, personalized parameter adjustments based on the user's motor intention. Simultaneously, the control parameter information, including spinal cord stimulation parameters for controlling the spinal cord stimulation device and exoskeleton motion parameters for controlling the exoskeleton device, can better coordinate the mechanical assistance of the exoskeleton, thereby improving user applicability and user experience. Furthermore, because it eliminates the need for users to manually set control parameters and switch modes, it simplifies user operation and facilitates its promotion in home or community rehabilitation environments.

[0075] Figure 2 A flow 200 of some embodiments of the spinal cord stimulation method according to the present disclosure is shown. The flow 200 of the spinal cord stimulation method includes the following steps:

[0076] Step 201: Obtain brain signals from the brain-computer interface device.

[0077] Step 202: Generate motor intention information based on EEG signals.

[0078] Step 203: Generate control parameter information based on motion intention information.

[0079] Step 204: Based on the spinal cord stimulation parameter information included in the control parameter information, control the spinal cord stimulation device to perform spinal cord stimulation operation.

[0080] Step 205: Based on the motion parameter information included in the control parameter information, control the exoskeleton device to perform exoskeleton driving operations.

[0081] In some embodiments, the subject performing the spinal cord stimulation method (e.g., Figure 1 The integrated spinal cord stimulation system (in the context of this text) can employ the following techniques during steps 201-205: Figure 1 The steps performed by the main control unit as described in the corresponding embodiments will not be repeated here.

[0082] The spinal cord electrical stimulation method through some embodiments of this disclosure can make real-time and personalized parameter adjustments based on the user's movement intentions, and can better coordinate with the mechanical assistance of the exoskeleton, improving user applicability and user experience, simplifying user operation, and facilitating promotion in home or community rehabilitation environments.

[0083] The following is for reference. Figure 3 It illustrates electronic devices suitable for implementing some embodiments of this disclosure (e.g., Figure 1 A schematic diagram of the integrated spinal cord stimulation system. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0084] like Figure 3 As shown, the electronic device 300 may include a processing unit 301 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0085] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, brain-computer interfaces, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, spinal stimulation devices, exoskeletons, liquid crystal displays (LCDs), speakers, vibrators, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0086] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0087] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0088] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0089] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire brainwave signals from a brain-computer interface; generate motor intention information based on the brainwave signals; generate control parameter information based on the motor intention information, wherein the control parameter information includes spinal cord stimulation parameter information and motion parameter information; control a spinal cord stimulation device to perform spinal cord stimulation operations based on the spinal cord stimulation parameter information included in the control parameter information; and control an exoskeleton device to perform exoskeleton actuation operations based on the motion parameter information included in the control parameter information.

[0090] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0091] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0092] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0093] Some embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements any of the spinal cord electrical stimulation-based methods described above.

[0094] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. An integrated spinal cord electrical stimulation system, characterized in that, The integrated spinal cord stimulation system includes a brain-computer interface, a spinal cord stimulation device, an exoskeleton device, and a main control unit. The brain-computer interface includes electroencephalogram (EEG) electrodes and is configured to acquire EEG signals. The spinal cord stimulation device includes spinal cord stimulation electrodes and a pulse generator. The spinal cord stimulation device is configured to generate electrical pulses through the pulse generator based on spinal cord electrical stimulation parameter information and transmit them to the target spinal cord segment through the spinal cord stimulation electrodes. The exoskeleton device is configured to activate the motors of the corresponding joints to perform preset actions based on motion parameter information; The brain-computer interface, the spinal cord stimulation device, and the exoskeleton device are communicatively connected to a main control unit, which is configured to perform the following steps: EEG signals are acquired from the brain-computer interface device; Based on the electroencephalogram (EEG) signals, motion intention information is generated; Based on the motion intention information, control parameter information is generated, wherein the control parameter information includes spinal cord stimulation parameter information and exoskeleton motion parameter information, including: Determine the motion state corresponding to the exoskeleton device; Based on the movement type and movement state included in the movement intention information, various control parameters corresponding to the movement type and movement state are matched from the control parameter library. The control parameter library is a database that stores preset control parameters for different movement types and movement states. Each control parameter includes the target spinal cord segment, stimulus initiation advance amount, action initiation delay amount, stimulus parameter information, and action parameter information. The stimulus initiation time is generated based on the current time, the stimulus initiation advance amount, and the movement intensity included in the movement intention information; The action initiation time is generated based on the stimulus initiation time and the action initiation delay. The target spinal cord segment, the stimulation parameter information, and the stimulation initiation time are determined as spinal cord electrical stimulation parameter information; The motion parameter information and the motion start time are determined as the exoskeleton motion parameter information; The spinal cord electrical stimulation parameters and the exoskeleton motion parameters are determined as control parameters. Based on the spinal cord stimulation parameter information included in the control parameter information, the spinal cord stimulation device is controlled to perform spinal cord stimulation operation; Based on the exoskeleton motion parameter information included in the control parameter information, the exoskeleton device is controlled to perform exoskeleton driving operations.

2. The integrated spinal cord stimulation system according to claim 1, characterized in that, The integrated spinal cord electrical stimulation system also includes an electromyography (EMG) signal acquisition device configured to acquire EMG signals.

3. The integrated spinal cord stimulation system according to claim 2, characterized in that, The exoskeleton device includes at least one of the following sensors: joint force sensor, joint angle sensor, joint angular velocity sensor, plantar pressure sensor, and torso posture sensor.

4. The integrated spinal cord stimulation system according to claim 1, characterized in that, The integrated spinal cord stimulation system also includes a wireless power supply unit, which is configured to power the brain-computer interface, the spinal cord stimulation device, and the main control unit.

5. The integrated spinal cord stimulation system according to claim 1, characterized in that, The main control unit is further configured to generate motion intention information based on the EEG signals through the following steps: The EEG signal is subjected to a first filtering process to obtain a first EEG signal; The first EEG signal is subjected to a second filtering process to obtain a second EEG signal; The second EEG signal is subjected to artifact removal processing to obtain the third EEG signal; The third EEG signal is subjected to motion intention feature extraction processing to obtain motion intention feature information; Based on the aforementioned motion intention feature information, motion intention information is generated, wherein the motion intention information includes motion type and motion intensity.

6. The integrated spinal cord stimulation system according to claim 1, characterized in that, The main control unit is further configured to generate a stimulus initiation time based on the current time, the stimulus initiation advance, and the motion intensity included in the motion intent information through the following steps: Based on the pre-built time compensation function and the motion intensity, a time compensation amount is generated; The difference between the stimulus initiation advance amount and the time compensation amount is determined as the adjusted stimulus initiation advance amount; The sum of the current time and the adjusted stimulus initiation advance is determined as the stimulus initiation time.

Images