Brain-computer interface lower limb feedback training adjustment device monitoring method and system

Abstract

This invention relates to the field of brain-computer interface (BCI) technology, specifically to a monitoring method and system for a lower limb feedback training and adjustment device using a BCI. The method includes: real-time acquisition of EEG signals related to the patient's lower limb movement intention via an EEG signal acquisition unit, combined with lower limb movement posture data obtained via a posture sensing module, and synchronous transmission to a data processing center; the data processing center performs fusion analysis on the EEG signals and posture data to identify the accuracy of movement intention, compliance of movement execution, and muscle load status; based on the analysis results, real-time feedback instructions are generated, and multimodal feedback information is output to the patient through a feedback adjustment unit to dynamically adjust the parameters of the training device; abnormal data is monitored throughout the training process, triggering corresponding safety warnings and emergency adjustment mechanisms. This invention improves the accuracy, safety, and effectiveness of lower limb rehabilitation training through the coordinated monitoring of EEG signals and movement postures, multi-dimensional data fusion analysis, and real-time feedback adjustment.

Description

Technical Field

[0001] This invention relates to the field of brain-computer interface technology, specifically to a monitoring method and system for a brain-computer interface lower limb feedback training and adjustment device. Background Technology

[0002] With the application of brain-computer interface (BCI) technology in rehabilitation medicine, lower limb feedback training devices have become an important tool to help patients with stroke, spinal cord injury, and other conditions regain lower limb motor function. However, existing monitoring methods for lower limb training devices using BCI still have many technical shortcomings: Insufficient accuracy in EEG signal recognition: Existing methods mostly use single-band EEG signals for motor intention recognition, which is easily affected by power frequency interference and electromyography artifacts, resulting in low matching degree between intention and actual movement and poor training guidance. The data monitoring dimension is limited: it only focuses on EEG signals or single motor posture data, and fails to achieve coordinated monitoring of EEG intention and action execution effect, thus failing to comprehensively evaluate training quality. The feedback is limited and delayed: it is mainly visual feedback, lacking real-time multimodal feedback such as auditory and tactile feedback, which makes it difficult for patients to quickly perceive movement deviations and affects training efficiency. Fixed training parameters: The resistance, movement trajectory threshold and other parameters of the training equipment are mostly preset fixed values. They cannot be dynamically adjusted according to the patient's real-time muscle load and intention recognition ability, which can easily lead to insufficient training or over-fatigue, or even secondary injury. The safety monitoring mechanism is inadequate: there is a lack of comprehensive monitoring of abnormal EEG signals, out-of-range postures, and equipment malfunctions. The safety early warning and emergency response capabilities are weak, and there are training risks.

[0003] Therefore, there is an urgent need for a brain-computer interface method for monitoring lower limb feedback training that features multi-dimensional collaborative monitoring, real-time feedback adjustment, and safety and controllability, in order to address the shortcomings of existing technologies and improve the accuracy, safety, and effectiveness of lower limb rehabilitation training. Summary of the Invention

[0004] To address the aforementioned technical shortcomings, this invention provides a monitoring method and system for a brain-computer interface-based lower limb feedback training and adjustment device. Through the coordinated acquisition of electroencephalogram (EEG) signals and motor postures, multi-dimensional data fusion analysis, multi-modal real-time feedback, and dynamic parameter adjustment, it achieves precise monitoring and intelligent adjustment of lower limb rehabilitation training.

[0005] This invention is achieved through the following technical solution: A method for monitoring a brain-computer interface lower limb feedback training and adjustment device is provided, the method comprising the following steps: Step S10: The EEG signal acquisition unit collects the EEG signals related to the patient's lower limb movement intention in real time, and the posture sensing unit collects the lower limb posture data, including joint angle, movement trajectory, movement speed and muscle tension data. The two types of data are transmitted to the data processing center simultaneously. Step S20: The data processing center preprocesses the received EEG signals and posture data, extracts key features and performs fusion analysis to determine the accuracy of movement intention, compliance of movement execution and muscle load status. Step S30: Generate real-time feedback instructions based on the fusion analysis results, output multimodal feedback information to the patient through the feedback adjustment unit, and dynamically adjust the resistance parameters, motion trajectory thresholds and training intensity levels of the training equipment according to the analysis results; Step S40: Monitor abnormal fluctuations in EEG signals, out-of-limit posture data, and equipment malfunctions throughout the training process. When an abnormality is detected, trigger the corresponding safety warning and emergency adjustment mechanism. Steps S10-S40 form a closed-loop monitoring and adjustment process, completing data acquisition, analysis, feedback, and parameter adjustment every 100ms to ensure the real-time performance and dynamic adaptability of the training process.

[0006] Preferably, the EEG signal acquisition unit in step S10 includes an implantable EEG electrode or a non-invasive high-density EEG cap, and the acquired EEG signals include μ waves, β waves and event-related potentials related to the motor cortex, with a sampling frequency of not less than 250 Hz. The posture sensing unit includes an inertial measurement unit (IMU) and a muscle surface electromyography (EMG) sensor installed at the hip, knee and ankle joints of the lower limbs, and the acquired data includes joint flexion angle, motion trajectory coordinates, instantaneous motion speed and EMG signal amplitude during muscle contraction, with the joint flexion angle acquisition range being 0°-180°.

[0007] Preferably, the step S20, in which the data processing center preprocesses the received EEG signals and posture data, includes: EEG signal preprocessing: Adaptive filtering algorithm is used to remove power frequency interference, electromyography artifacts and electrooculography artifacts. Wavelet transform is used to denoise the EEG signal. Independent component analysis (ICA) is used to separate motor-related EEG components and extract the characteristic frequency band signal corresponding to the motor intention. Attitude data preprocessing: Kalman filtering is performed on the joint angle data collected by the inertial measurement unit to smooth the data and correct sensor drift error. Full-wave rectification, low-pass filtering and normalization are performed on the electromyography signal to eliminate data deviation caused by individual muscle strength differences. Data spatiotemporal calibration: Based on timestamp-synchronized EEG signals and posture data, the time difference caused by signal transmission delay is corrected and controlled within 5ms to ensure accurate correspondence between motor intention and action execution data.

[0008] Preferably, the step of extracting key features and performing fusion analysis in step S20 includes: EEG feature extraction: Based on power spectral density analysis, energy change features of μ waves and β waves are extracted. The range of μ waves is 8-13Hz and the range of β waves is 14-30Hz. The motion intention feature vector is extracted by linear discriminant analysis (LDA), including intention recognition features of lower limb extension / flexion and left / right movement. Posture feature extraction: Extract the maximum angle of joint movement, the rate of change of angle, the smoothness of the movement trajectory, and the integrated electromyography (IEMG) value and root mean square (RMS) value of muscle electromyography signals to form a motion execution feature vector; Fusion analysis: The weighted Naive Bayes algorithm is used to fuse EEG feature vectors and posture feature vectors to calculate the accuracy of movement intention. A match between intention and actual movement of ≥85% is considered acceptable. By using a preset standard movement template, the deviation between the actual movement trajectory and the standard trajectory is compared. A deviation of ≤10° is considered compliant. Based on the RMS value of electromyography signal and movement duration, the muscle load index is calculated. A load index of ≤0.7 is considered safe.

[0009] Preferably, the multimodal feedback information in step S30 includes visual feedback, auditory feedback, and tactile feedback. Visual feedback displays the deviation of the movement trajectory and the degree of intention matching in real time on the display screen. Auditory feedback outputs prompts of different frequencies through a speaker. If the matching degree is qualified, it is a high-frequency sound, and if it is unqualified, it is a low-frequency sound. Tactile feedback outputs vibration intensity through a vibration module worn on the wrist. The greater the deviation, the stronger the vibration. The dynamic adjustment strategy is to dynamically adjust the device parameters according to the accuracy of the movement intention, the compliance of the movement execution, and the muscle load index.

[0010] Preferably, the monitoring of abnormal fluctuations in EEG signals, exceeding limits in posture data, and equipment malfunction information during the entire training process in step S40 includes: Abnormal EEG signal: When the amplitude of the EEG signal suddenly exceeds the set normal threshold, such as ±3 times the standard deviation, or when the energy of the motion-related frequency band signal continues to decay beyond the set threshold, such as 50%, it is judged as an abnormal EEG signal. Posture data exceeds limits: When the maximum angle of joint movement exceeds the set range, or the smoothness of the movement trajectory is greater than the set threshold, it is judged that the posture data exceeds limits. Equipment malfunctions include abnormal resistance output of the training equipment and interruption of sensor data transmission. Abnormal resistance output of the training equipment is defined as a deviation from the set value >15%, and interruption of sensor data transmission is defined as a data transmission time exceeding 2 seconds.

[0011] Preferably, the safety warning and emergency adjustment mechanism in step S40 includes issuing an audible and visual alarm signal, immediately stopping the resistance output of the training equipment and resetting it to the initial position, outputting a strong vibration prompt from the feedback adjustment unit, and simultaneously uploading abnormal data to the medical terminal in real time.

[0012] Furthermore, to achieve the above objectives, the present invention also proposes a monitoring system for a brain-computer interface lower limb feedback training and adjustment device, wherein the brain-computer interface lower limb feedback training and adjustment device monitoring system comprises: EEG signal and lower limb posture data acquisition module: It is used to acquire EEG signals related to the patient's lower limb movement intention in real time through the EEG signal acquisition unit, and to acquire lower limb posture data, including joint angle, movement trajectory, movement speed and muscle tension data, through the posture sensing unit, and to transmit the two types of data to the data processing center simultaneously. EEG signal and posture data fusion analysis module: used by the data processing center to preprocess the received EEG signals and posture data, extract key features and perform fusion analysis to determine the accuracy of movement intention, compliance of movement execution and muscle load status. Real-time feedback adjustment module: used to generate real-time feedback instructions based on the fusion analysis results, output multimodal feedback information to the patient through the feedback adjustment unit, and dynamically adjust the resistance parameters, motion trajectory thresholds and training intensity levels of the training equipment according to the analysis results; Training monitoring, safety warning and emergency adjustment module: used to monitor abnormal fluctuations in EEG signals, out-of-limit posture data and equipment malfunction information throughout the training process, and trigger corresponding safety warning and emergency adjustment mechanisms when abnormalities are detected; The EEG signal and lower limb posture data acquisition module forms a closed-loop monitoring and adjustment process with the training monitoring, safety early warning and emergency adjustment module. Data acquisition, analysis, feedback and parameter adjustment are completed every 100ms to ensure the real-time and dynamic adaptability of the training process.

[0013] Furthermore, to achieve the above objectives, the present invention also proposes a monitoring device for a brain-computer interface lower limb feedback training and adjustment device. The device includes: a memory, a processor, and a brain-computer interface lower limb feedback training and adjustment program stored in the memory and executable on the processor. The brain-computer interface lower limb feedback training and adjustment program is the step of implementing the brain-computer interface lower limb feedback training and adjustment device monitoring method described above.

[0014] In addition, to achieve the above objectives, the present invention also provides a computer program product, which includes programs such as brain-computer interface lower limb feedback training and adjustment programs. When the brain-computer interface lower limb feedback training and adjustment programs are executed by a processor, they implement a brain-computer interface lower limb feedback training and adjustment device monitoring method as described above.

[0015] The advantages and effects of this invention are: This invention proposes a monitoring method and system for a brain-computer interface (BCI) lower limb feedback training and adjustment device. By simultaneously collecting EEG signals and lower limb movement posture and muscle activity data, it achieves coordinated evaluation of movement intention and action execution effect, avoiding the one-sidedness caused by single data monitoring. Integrating visual, auditory, and tactile feedback, patients can perceive movement deviations and training status through multiple senses, and quickly adjust movement intention and action execution methods, improving training efficiency compared to single visual feedback. Based on real-time monitoring evaluation indicators, the resistance, trajectory threshold, and training intensity of the training device are dynamically adjusted to adapt to the functional status of patients at different rehabilitation stages, avoiding undertraining or overtraining and reducing the risk of secondary injury. This invention effectively solves the problems of inaccurate intention recognition, single feedback, fixed parameters, and insufficient safety in existing BCI lower limb training device monitoring methods, providing a more accurate, safe, and efficient technical solution for lower limb rehabilitation training for patients with stroke, spinal cord injury, etc., and has significant clinical application value. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a monitoring method for a brain-computer interface lower limb feedback training and adjustment device according to the present invention.

[0018] Figure 2 This is a schematic diagram of the monitoring system structure of a brain-computer interface lower limb feedback training and adjustment device according to the present invention.

[0019] Figure 3 This is a schematic block diagram of the monitoring electronic device structure of a brain-computer interface lower limb feedback training and adjustment device according to the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] like Figure 1As shown, in one embodiment of the present invention, a monitoring method for a brain-computer interface lower limb feedback training and adjustment device includes the following steps: Step S10: The EEG signal acquisition unit collects the EEG signals related to the patient's lower limb movement intention in real time, and the posture sensing unit collects the lower limb posture data, including joint angle, movement trajectory, movement speed and muscle tension data. The two types of data are transmitted to the data processing center simultaneously.

[0022] Specifically, in step S10, the EEG signal acquisition unit uses a non-invasive high-density EEG cap (≥32 channels of electrodes) or implantable EEG electrodes to acquire μ waves (8-13Hz), β waves (14-30Hz), and event-related potentials in the motor cortex region. The sampling frequency is set to 250Hz-500Hz to ensure signal integrity. The posture sensing unit includes an inertial measurement unit (IMU) installed at the patient's three key joints (hip, knee, and ankle) and electromyography (EMG) sensors on the surface of the thigh and calf muscles. The IMU acquires the joint bending angle, three-dimensional coordinates of the motion trajectory, and instantaneous motion velocity. The joint bending angle measurement range is 0°-180° with an accuracy of ±0.5°. The EMG sensors acquire the amplitude of the EMG signal during muscle contraction, with a measurement range of 0-10mV. The sampling frequency is consistent with that of the EEG signal acquisition unit to ensure data synchronization.

[0023] Step S20: The data processing center preprocesses the received EEG signals and posture data, extracts key features and performs fusion analysis to determine the accuracy of movement intention, compliance of movement execution and muscle load status.

[0024] Specifically, step S20, in which the data processing center preprocesses the received EEG signals and posture data, includes the following steps: EEG signal preprocessing: Adaptive filtering algorithm is used to remove power frequency interference (50Hz / 60Hz), electromyography artifacts and electrooculography artifacts. Wavelet transform is used to denoise the EEG signal. Independent component analysis (ICA) is used to separate motor-related EEG components and extract the characteristic frequency band signals corresponding to motor intention. Attitude data preprocessing: Kalman filtering is performed on the joint angle data collected by the inertial measurement unit to smooth the data and correct sensor drift error. Full-wave rectification, low-pass filtering (cutoff frequency 10Hz) and normalization are performed on the electromyography signal to eliminate data deviation caused by individual muscle strength differences. Data spatiotemporal calibration: Based on timestamp-synchronized EEG signals and posture data, the time difference caused by signal transmission delay is corrected and controlled within 5ms to ensure accurate correspondence between motor intention and action execution data.

[0025] Specifically, step S20, which involves extracting key features and performing fusion analysis, includes: EEG feature extraction: Based on power spectral density analysis, energy change features of μ waves and β waves are extracted. The range of μ waves is 8-13Hz and the range of β waves is 14-30Hz. The motion intention feature vector is extracted by linear discriminant analysis (LDA), including intention recognition features of lower limb extension / flexion and left / right movement. Posture feature extraction: Extract the maximum angle of joint movement, the rate of change of angle, and the smoothness of the movement trajectory. Combine the integral electromyography (IEMG) value and root mean square (RMS) value of the electromyography (EMG) signal to form a motion execution feature vector. The rate of change of angle is used to reflect the speed of movement. The smoothness of the movement trajectory is calculated by the curvature variance of the trajectory curve. The integral EMG value of the EMG signal reflects the total muscle contraction and the RMS value reflects the intensity of muscle contraction. Fusion Analysis: A weighted Naive Bayes algorithm is used to fuse EEG feature vectors and action execution feature vectors, outputting three core evaluation indicators: accuracy of motor intention (calculating the degree of matching between the identified motor intention and the actual executed action, with a matching degree ≥85% considered acceptable); compliance of action execution (comparing the actual action trajectory and joint angles with a preset standard training template, with a deviation ≤10° considered acceptable); and muscle load index (calculating the real-time muscle load based on the RMS value of the EMG signal, the duration of the action, and the patient's weight and muscle mass parameters, with a load index ≤0.7 considered safe).

[0026] Step S30: Generate real-time feedback instructions based on the fusion analysis results, output multimodal feedback information to the patient through the feedback adjustment unit, and dynamically adjust the resistance parameters, motion trajectory thresholds and training intensity levels of the training equipment according to the analysis results.

[0027] Specifically, the multimodal feedback information in step S30 includes visual feedback, auditory feedback, and tactile feedback. Visual feedback displays the deviation of the movement trajectory and the degree of intention matching in real time on the screen. Auditory feedback outputs different frequencies of prompts through the speaker. The matching degree is qualified and the sound is high frequency, while the matching degree is unqualified and the sound is low frequency. Tactile feedback outputs the vibration intensity through the vibration module worn on the wrist. The greater the deviation, the stronger the vibration. The dynamic adjustment strategy is to dynamically adjust the device parameters according to the accuracy of the movement intention, the compliance of the movement execution, and the muscle load index. The data processing center generates two types of instructions, including sending multimodal feedback instructions to the feedback adjustment unit and sending parameter adjustment instructions to the training device to realize the closed-loop adjustment of the training process.

[0028] Specifically, the multimodal feedback output involves the feedback adjustment unit simultaneously outputting visual, auditory, and tactile feedback information to help patients correct their movements in real time, including: Visual feedback: The display screen on the training equipment shows the accuracy of the movement intention, the deviation curve of the movement trajectory from the standard template, and the muscle load index in real time, with different colors indicating the status, such as green for qualified, yellow for needing improvement, and red for unqualified. Auditory feedback: Prompt sounds are output through the speaker. A high-frequency, crisp prompt sound is played when the accuracy of the movement intention is ≥85% at a frequency of 1000Hz. A low-frequency prompt sound is played when the accuracy is not up to standard at a frequency of 500Hz. The greater the movement deviation, the shorter the interval between prompt sounds. Tactile feedback: Vibration is output through a vibration module worn on the patient's wrist. The vibration intensity is proportional to the deviation of the movement. There is no vibration when the deviation is ≤5°, weak vibration when the deviation is 5°-10°, and strong vibration when the deviation is >10°.

[0029] Specifically, dynamic parameter adjustment refers to the data processing center dynamically adjusting the key parameters of the training equipment based on three core evaluation indicators to achieve personalized training, including: Resistance parameter adjustment: When the accuracy of the movement intention is <85%, reduce the equipment resistance by 10%-20% to reduce the difficulty of the movement; when the accuracy is ≥90% for 3 consecutive times, increase the resistance by 5%-10% to increase the training intensity. Movement trajectory threshold adjustment: When the compliance rate of movement execution is <90%, reduce the trajectory threshold range by 5°-8° to guide the patient to complete the movement accurately; when the compliance rate is ≥95% for 5 consecutive times, expand the threshold range by 3°-5° to gradually improve the flexibility of movement. Training intensity level adjustment: When the muscle load index is ≤0.5, increase the training intensity level by 1 level, increase the number of repetitions or extend the duration of a single movement; when the load index is >0.7, maintain the current parameters and extend the rest interval by 20%-30%; when the load index is >0.8, pause training for 1-2 minutes to avoid excessive muscle fatigue.

[0030] Step S40: Monitor abnormal fluctuations in EEG signals, out-of-limit posture data, and equipment malfunctions throughout the training process. When an abnormality is detected, trigger the corresponding safety warning and emergency adjustment mechanism.

[0031] Specifically, step S40, which involves monitoring abnormal fluctuations in EEG signals, exceeding limits in posture data, and equipment malfunction information throughout the training process, includes: Abnormal EEG signal: When the amplitude of the EEG signal suddenly exceeds the set normal threshold, such as ±3 times the standard deviation, or when the energy of the motion-related frequency band signal continues to decay beyond the set threshold, such as 50%, it is judged as an abnormal EEG signal. Posture data exceeds limits: When the maximum angle of joint movement exceeds the set range, such as hip joint > 120°, knee joint > 150°, ankle joint > 90° in the set movement angle, or the smoothness of the movement trajectory is greater than the set threshold, such as the set threshold is 0.5m / s, it is judged that the posture data exceeds limits. Equipment malfunctions include abnormal resistance output of the training equipment and interruption of sensor data transmission. Abnormal resistance output of the training equipment is defined as a deviation from the set value >15%, and interruption of sensor data transmission is defined as a data transmission time exceeding 2 seconds.

[0032] Specifically, in step S40, when any of the above-mentioned anomalies are detected, the following operations are performed immediately: Warning prompt: A red warning icon is displayed on the device screen, a continuous buzzing sound is played by the speaker, and the vibration unit outputs continuous strong vibration; Emergency equipment adjustment: The training equipment should immediately stop the resistance output and drive the mechanical structure back to the initial position to ensure that the lower limbs are in a relaxed posture; Data reporting: The abnormality type, occurrence time, and relevant data parameters are uploaded to the medical staff terminal in real time, so that medical staff can intervene and handle the situation in a timely manner; Recovery mechanism: After the abnormality is resolved, if the patient's condition returns to normal and the equipment malfunction is eliminated, the training process must be restarted after confirmation by medical staff, and it will automatically adjust to low-intensity training mode after restarting.

[0033] In addition, such as Figure 2 As shown, in one embodiment of the present invention, a monitoring system for a brain-computer interface lower limb feedback training and adjustment device is proposed. The monitoring system includes: EEG signal and lower limb posture data acquisition module: It is used to acquire EEG signals related to the patient's lower limb movement intention in real time through the EEG signal acquisition unit, and to acquire lower limb posture data, including joint angle, movement trajectory, movement speed and muscle tension data, through the posture sensing unit, and to transmit the two types of data to the data processing center simultaneously. EEG signal and posture data fusion analysis module: used by the data processing center to preprocess the received EEG signals and posture data, extract key features and perform fusion analysis to determine the accuracy of movement intention, compliance of movement execution and muscle load status. Real-time feedback adjustment module: used to generate real-time feedback instructions based on the fusion analysis results, output multimodal feedback information to the patient through the feedback adjustment unit, and dynamically adjust the resistance parameters, motion trajectory thresholds and training intensity levels of the training equipment according to the analysis results; Training monitoring, safety warning and emergency adjustment module: used to monitor abnormal fluctuations in EEG signals, out-of-limit posture data and equipment malfunction information throughout the training process, and trigger corresponding safety warning and emergency adjustment mechanisms when abnormalities are detected; The EEG signal and lower limb posture data acquisition module forms a closed-loop monitoring and adjustment process with the training monitoring, safety early warning and emergency adjustment module. Data acquisition, analysis, feedback and parameter adjustment are completed every 100ms to ensure the real-time and dynamic adaptability of the training process.

[0034] This application provides a monitoring system for a brain-computer interface (BCI) lower limb feedback training and adjustment device, employing a monitoring method for a BCI lower limb feedback training and adjustment device as described in the above embodiments. This system addresses the technical problems of inaccurate intent recognition, limited feedback, fixed parameters, and insufficient security in existing BCI lower limb training device monitoring methods. Compared to the prior art, the beneficial effects of the BCI lower limb feedback training and adjustment device monitoring system provided in this application are the same as those of the monitoring method for a BCI lower limb feedback training and adjustment device provided in the above embodiments. Furthermore, other technical features of the BCI lower limb feedback training and adjustment device monitoring system are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0035] This application provides a monitoring device for a brain-computer interface lower limb feedback training and adjustment device. The monitoring device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform a brain-computer interface lower limb feedback training and adjustment device monitoring method as described in Embodiment 1 above.

[0036] like Figure 3 As shown in the illustration, in one embodiment of the present invention, a structural schematic diagram of a monitoring device suitable for implementing a brain-computer interface lower limb feedback training and adjustment device according to an embodiment of the present application is presented. The monitoring device for a brain-computer interface lower limb feedback training and adjustment device according to an embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), etc., as well as fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The brain-computer interface lower limb feedback training and adjustment device monitoring device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0037] Figure 3The brain-computer interface lower limb feedback training and adjustment device monitoring device shown may include a processor 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a machine-readable storage medium (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the brain-computer interface lower limb feedback training and adjustment device monitoring device. The processor 1001, the read-only memory 1002, and the machine-readable storage medium 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and a communication unit 1009. Communication unit 1009 allows a brain-computer interface lower limb feedback training and adjustment device monitoring device to wirelessly or wiredly communicate with other devices to exchange data. Although the figure shows a brain-computer interface lower limb feedback training and adjustment device monitoring device with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0038] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application 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 a communication unit, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processor 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0039] This application provides a monitoring device for lower limb feedback training and adjustment equipment based on a brain-computer interface (BCI) method described in the above embodiments. This device addresses the technical problems of inaccurate intent recognition, limited feedback, fixed parameters, and insufficient security in existing BCI lower limb training equipment monitoring methods. Compared to the prior art, the beneficial effects of the monitoring device provided in this application are the same as those of the monitoring method described in the above embodiments. Furthermore, other technical features of this monitoring device are identical to those disclosed in the previous embodiment, and will not be elaborated upon here.

[0040] The various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0041] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the brain-computer interface lower limb feedback training and adjustment device monitoring method described above.

[0042] The computer program product provided in this application can solve the technical problems of inaccurate intent recognition, single feedback, fixed parameters, and insufficient security in existing brain-computer interface lower limb training device monitoring methods. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the brain-computer interface lower limb feedback training and adjustment device monitoring method provided in the above embodiments, and will not be repeated here.

[0043] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A monitoring method for a brain-computer interface lower limb feedback training and adjustment device, characterized in that, The method includes the following steps: Step S10: The EEG signal acquisition unit collects the patient's lower limb movement intention EEG signal in real time, and the posture sensing unit collects the lower limb posture data, including joint angle, movement trajectory, movement speed and muscle tension data. The two types of data are transmitted to the data processing center simultaneously. Step S20: The data processing center preprocesses the received EEG signals and posture data, extracts key features and performs fusion analysis to determine the accuracy of movement intention, compliance of movement execution and muscle load status. Step S30: Generate real-time feedback instructions based on the fusion analysis results, output multimodal feedback information to the patient through the feedback adjustment unit, and dynamically adjust the resistance parameters, motion trajectory thresholds and training intensity levels of the training equipment according to the analysis results; Step S40: Monitor abnormal fluctuations in EEG signals, out-of-limit posture data, and equipment malfunctions throughout the training process. When an abnormality is detected, trigger the corresponding safety warning and emergency adjustment mechanism.

2. The monitoring method for a brain-computer interface lower limb feedback training and adjustment device according to claim 1, characterized in that, The EEG signal acquisition unit in step S10 includes implantable EEG electrodes or a non-invasive high-density EEG cap. The acquired EEG signals include μ waves, β waves, and event-related potentials related to the motor cortex. The posture sensing unit includes an inertial measurement unit and a muscle surface electromyography sensor installed at the hip, knee, and ankle joints of the lower limbs. The acquired data includes joint flexion angle, motion trajectory coordinates, instantaneous motion speed, and electromyography signal amplitude during muscle contraction.

3. The monitoring method for a brain-computer interface lower limb feedback training and adjustment device according to claim 1, characterized in that, The step S20, in which the data processing center preprocesses the received EEG signals and posture data, includes: EEG signal preprocessing: Adaptive filtering algorithm is used to remove power frequency interference, electromyography artifacts and electrooculography artifacts. Wavelet transform is used to denoise the EEG signal. Independent component analysis is used to separate motion-related EEG components and extract the characteristic frequency band signal corresponding to the motion intention. Attitude data preprocessing: Kalman filtering is performed on the joint angle data collected by the inertial measurement unit to smooth the data and correct sensor drift error. Full-wave rectification, low-pass filtering and normalization are performed on the electromyography signal to eliminate data deviation caused by individual muscle strength differences. Data spatiotemporal calibration: Based on timestamps, synchronize EEG signals and posture data to correct time differences caused by signal transmission delays.

4. The monitoring method for a brain-computer interface lower limb feedback training and adjustment device according to claim 1, characterized in that, The steps of extracting key features and performing fusion analysis in step S20 include: EEG feature extraction: Based on power spectral density analysis, energy change features of μ waves and β waves are extracted. The range of μ waves is 8-13Hz and the range of β waves is 14-30Hz. The motion intention feature vector is extracted through linear discriminant analysis, including intention recognition features of lower limb extension / flexion and left / right movement. Posture feature extraction: Extract the maximum angle of joint movement, the rate of change of angle, the smoothness of the movement trajectory, and the integrated electromyographic value and root mean square value of muscle electromyographic signal to form a motion execution feature vector; Fusion analysis: The weighted Naive Bayes algorithm is used to fuse EEG features and posture features to calculate the accuracy of movement intention. By using a preset action standard template, the deviation between the actual movement trajectory and the standard trajectory is compared. Based on the root mean square value of the electromyographic signal and the duration of movement, the muscle load index is calculated.

5. The monitoring method for a brain-computer interface lower limb feedback training and adjustment device according to claim 1, characterized in that, The multimodal feedback information in step S30 includes visual feedback, auditory feedback and tactile feedback. The dynamic adjustment strategy is to dynamically adjust the equipment parameters based on the accuracy of the movement intention, the deviation between the actual movement trajectory and the standard trajectory during the movement execution, and the muscle load index.

6. The monitoring method for a brain-computer interface lower limb feedback training and adjustment device according to claim 1, characterized in that, The abnormal fluctuations in EEG signals, out-of-limit posture data, and equipment malfunction information monitored throughout the training process in step S40 include: Abnormal EEG signal: When the amplitude of the EEG signal of the lower limb movement intention exceeds the set normal threshold, or when the energy of the characteristic frequency band signal corresponding to the movement intention continues to decay beyond the set threshold, it is judged as an abnormal EEG signal. Posture data exceeds limits: When the joint angle exceeds the set range, or the movement speed exceeds the set threshold, it is judged that the posture data exceeds limits; Equipment malfunctions include abnormal resistance output from training equipment and interruption of sensor data transmission.

7. The monitoring method for a brain-computer interface lower limb feedback training and adjustment device according to claim 1, characterized in that, The safety warning and emergency adjustment mechanism in step S40 includes issuing an audible and visual alarm signal, immediately stopping the resistance output of the training equipment and resetting it to the initial position, outputting a vibration prompt from the feedback adjustment unit, and simultaneously uploading abnormal data to the medical terminal in real time.

8. A monitoring system for a brain-computer interface lower limb feedback training and adjustment device, characterized in that, The system executes the monitoring method for a brain-computer interface lower limb feedback training and adjustment device as described in claim 1, comprising: EEG signal and lower limb posture data acquisition module: It is used to acquire the patient's lower limb movement intention EEG signal in real time through the EEG signal acquisition unit, and to acquire lower limb posture data, including joint angle, movement trajectory, movement speed and muscle tension data, through the posture sensing unit, and transmit the two types of data to the data processing center simultaneously; EEG signal and posture data fusion analysis module: used by the data processing center to preprocess the received EEG signals and posture data, extract key features and perform fusion analysis to determine the accuracy of movement intention, compliance of movement execution and muscle load status. Real-time feedback adjustment module: used to generate real-time feedback instructions based on the fusion analysis results, output multimodal feedback information to the patient through the feedback adjustment unit, and dynamically adjust the resistance parameters, motion trajectory thresholds and training intensity levels of the training equipment according to the analysis results; Training monitoring, safety warning and emergency adjustment module: used to monitor abnormal fluctuations in EEG signals, out-of-limit posture data and equipment malfunction information throughout the training process, and trigger corresponding safety warning and emergency adjustment mechanisms when abnormalities are detected.

9. A monitoring device for a brain-computer interface lower limb feedback training and adjustment device, characterized in that, include: The device includes a memory, a processor, and a brain-computer interface lower limb feedback training and adjustment device monitoring program stored in the memory and executable on the processor. When the brain-computer interface lower limb feedback training and adjustment device monitoring program is executed by the processor, it implements a brain-computer interface lower limb feedback training and adjustment device monitoring method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a brain-computer interface lower limb feedback training and adjustment device monitoring program, which, when executed by a processor, implements a brain-computer interface lower limb feedback training and adjustment device monitoring method as described in any one of claims 1 to 7.

Images