Method, system and device for visual and auditory stimulation assisted walking training

Abstract

The present invention relates to the field of rehabilitation training technology, and specifically discloses a method, system, and device for visual and auditory stimulation-assisted walking training. The present invention generates visual and auditory data with the help of auxiliary training equipment to guide the user's walking training, adjusts parameters according to the user's physical condition, obtains limb coordination characteristics and muscle group coordination characteristics based on multiple joint motion trajectory information, and calculates gait parameters based on the limb coordination characteristics and muscle group coordination characteristics to obtain accurate limb gait information. Then, it is determined whether the limb gait information meets preset conditions. If not, posture auxiliary information is generated based on the analysis results, and the parameters of the auxiliary training equipment itself are adjusted according to the posture auxiliary information, and the joint motion trajectory information is re-acquired; if it meets the conditions, the equipment parameters are fixed to form a complete and scientific home rehabilitation training system to ensure stable and coherent training.

Description

Technical Field

[0001] The present invention relates to the technical field of rehabilitation training, and in particular to a method, system and device for visual and auditory stimulation assisted walking training. Background Art

[0002] Parkinson's disease is a degenerative disorder of the central nervous system. Its typical motor symptoms include bradykinesia, involuntary tremors, muscle stiffness, and gait imbalance. These symptoms severely impair patients' walking function and significantly reduce their quality of life. Currently, rehabilitation training is one of the important means to improve the motor function of Parkinson's patients.

[0003] Existing rehabilitation training methods use rhythmic auditory stimulation, which can improve patients' walking ability and balance ability. Rhythmic auditory stimulation is a rehabilitation training method that enables patients to listen to music while feedbacking the gait rhythm under music stimulation, thereby increasing the stimulation connection of brain areas, making brain nerve activity active, and improving the coordination and regularity of limb movements. When patients are discharged from the hospital, it is difficult for them to train under the guidance of a rehabilitation doctor for a long time because their residence is far away from the rehabilitation center, coupled with labor costs, time pressure and transportation problems.

[0004] When patients engage in self-rehabilitation training at home, the lack of professional guidance can easily lead to non-standard gait movements (such as premature gastrocnemius contraction), which can cause foot dragging. These problems are difficult for patients to detect themselves. Therefore, a method, system, and device for visual and auditory stimulation-assisted walking training are needed to address these issues. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, system and device for visual and auditory stimulation assisted walking training to solve the technical problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for visual and auditory stimulation-assisted walking training is applied to a rehabilitation training area, wherein the rehabilitation training area is provided with auxiliary training equipment, including:

[0008] Acquiring, within a first preset time period, information on multiple joint motion trajectories generated by a user performing walking training following audiovisual data, wherein the audiovisual data is generated by an auxiliary training device, the audiovisual data including sound data generated by the auxiliary training device based on adjustment of its own parameters and light source data that matches the sound data and is reflected in a rehabilitation training area;

[0009] Acquire coordination features between multiple joints according to the multiple joint motion trajectory information, wherein the coordination features include limb coordination features and muscle group coordination features;

[0010] Acquiring limb gait information according to a plurality of the coordination features;

[0011] Determining whether the limb gait information meets a preset condition;

[0012] If the limb gait information does not meet the preset conditions, generating posture auxiliary information according to the limb gait information;

[0013] Adjusting the parameters of the auxiliary training device according to the posture auxiliary information, and after the adjustment is completed, returning to the step of obtaining multiple joint motion trajectory information generated when the user follows the visual and auditory data for walking training within the first preset time period;

[0014] If the limb gait information meets the preset conditions, the auxiliary training device fixes its own parameters.

[0015] Preferably, the step of generating the audiovisual data by the auxiliary training device comprises:

[0016] The auxiliary training device obtains its own initial projection light source and guiding audio;

[0017] During the second preset time period, the auxiliary training device obtains the stride information of the user during walking training, and adjusts the moving speed and moving distance of its own projection light source according to the stride information;

[0018] Acquire the stride beat characteristics of the user during walking training based on the stride information;

[0019] Acquire sound data according to the guide audio and the stride beat feature, and generate audiovisual data according to the sound data, the moving speed and the moving distance of the projection light source.

[0020] Preferably, the step of obtaining coordination features between multiple joints based on the multiple joint motion trajectory information includes:

[0021] Acquire multiple ankle joint movement trajectories and multiple hip joint movement trajectories according to the joint movement trajectory information;

[0022] Obtaining an initial movement timestamp and an end movement timestamp according to each ankle joint movement trajectory and each hip joint movement trajectory, constructing a plurality of first position nodes during the movement process according to each ankle joint movement trajectory, constructing a plurality of second position nodes during the movement process according to each hip joint movement trajectory, and obtaining a phase difference between each ankle joint movement trajectory and each hip joint movement trajectory according to the plurality of first position nodes and the plurality of second position nodes within a third preset time;

[0023] The synchronization of each ankle joint movement trajectory and each hip joint movement trajectory is obtained according to the phase difference, the initial movement timestamp and the terminal movement timestamp;

[0024] Acquire limb coordination features based on the phase difference and synchronization of each ankle joint movement trajectory and each hip joint movement trajectory during movement;

[0025] Obtain corresponding agonist muscle variable features and antagonist muscle variable features according to each ankle joint movement trajectory and each hip joint movement trajectory;

[0026] Obtaining a muscle contraction time period according to the variable characteristics of the agonist muscle and the variable characteristics of the antagonist muscle, and obtaining an agonist muscle activation time and an antagonist muscle activation time according to the muscle contraction time period;

[0027] Obtain a muscle activation sequence table based on the activation time of the agonist muscle and the activation time of the antagonist muscle during the muscle contraction period, and use the muscle activation sequence table as a muscle group coordination feature;

[0028] The coordination features between multiple joints are obtained based on the limb coordination features and muscle group coordination features.

[0029] Preferably, the step of generating posture auxiliary information according to the limb gait information comprises:

[0030] Acquire a plurality of light beams of different brightness and flickering frequencies matching the light beams of different brightness according to the light source data, generate a light beam brightness change trend graph according to the plurality of light beams of different brightness, and generate a visual stimulation change gradient graph according to the light beam brightness change trend graph and the flickering frequencies;

[0031] Acquiring multiple audio time periods according to the sound data, extracting corresponding audio decibel values ​​according to the multiple audio time periods, and generating an auditory stimulation change gradient map according to the multiple audio decibel values;

[0032] The visual stimulus change gradient map and the auditory stimulus change gradient map are used to generate posture auxiliary information.

[0033] Preferably, the step of generating posture auxiliary information according to the limb gait information comprises:

[0034] acquiring pulse information according to the limb gait information;

[0035] Acquire multiple current stimulation peaks within a preset time and the time interval between each of the current stimulation peaks according to the pulse information;

[0036] Obtain stimulation frequency based on multiple time intervals;

[0037] Extract the microampere current in the pulse information and convert the microampere current into a voltage signal;

[0038] Collecting a frequency spectrum of a voltage signal obtained by Fourier transform within a preset time, extracting a plurality of peak points according to the frequency spectrum, and generating a main frequency component according to the plurality of peak points;

[0039] Posture auxiliary information is obtained based on the current stimulation peak, stimulation frequency and main frequency component.

[0040] Preferably, the step of obtaining coordination features between multiple joints based on limb coordination features and muscle group coordination features, and judging whether the limb gait information meets preset conditions includes:

[0041] According to the limb gait information, the activation time range of the agonist muscles, the activation time range of the antagonist muscles, the ankle joint motion trajectory and the hip joint motion trajectory are obtained;

[0042] Determining whether the agonist muscle activation time range and the antagonist muscle activation time range are both greater than a maximum value of a preset interval;

[0043] If the agonist muscle activation time range and the antagonist muscle activation time range are both greater than the maximum value of the preset interval, it is determined that the preset condition is not met;

[0044] If the agonist muscle activation time range and the antagonist muscle activation time range are both smaller than the minimum value of the preset interval, it is determined that the preset condition is not met;

[0045] If the agonist muscle activation time range and the antagonist muscle activation time range are both within the range values ​​of the preset interval, it is determined that the preset condition is met, and it is determined whether the phase difference between the ankle joint motion trajectory and the hip joint motion is less than a preset value;

[0046] If the phase difference between the ankle joint motion trajectory and the hip joint motion trajectory is less than a preset value, it is determined that the preset condition is not met;

[0047] If the phase difference between the ankle joint motion trajectory and the hip joint motion trajectory is not less than a preset value, it is determined that the preset condition is met.

[0048] Preferably, the step of generating posture auxiliary information according to the limb gait information comprises:

[0049] Acquire multiple respiratory rates and heel strike timestamps based on limb gait information;

[0050] generating a respiratory spectrum according to the plurality of respiratory frequencies, wherein the respiratory spectrum comprises a plurality of peaks and a plurality of troughs;

[0051] The time period from each peak to each trough is set as the exhalation period. The shortest exhalation period between two adjacent exhalation periods is obtained based on multiple exhalation periods. The exhalation start timestamp in the shortest exhalation period is extracted, and the exhalation start timestamp is synchronized with the heel touchdown timestamp.

[0052] The present application also provides a system for visual and auditory stimulation-assisted walking training, comprising:

[0053] a first acquisition module for acquiring, within a first preset time period, information on multiple joint motion trajectories generated by a user performing walking training following audiovisual data, wherein the audiovisual data is generated by an auxiliary training device, and includes sound data generated by the auxiliary training device based on adjustment of its own parameters, and light source data that matches the sound data and is reflected in a rehabilitation training area;

[0054] a second acquisition module, which acquires coordination features between multiple joints according to the multiple joint motion trajectory information, wherein the coordination features include limb coordination features and muscle group coordination features;

[0055] a third acquisition module, acquiring limb gait information according to the plurality of coordination features;

[0056] A judgment module, judging whether the limb gait information meets a preset condition;

[0057] A generating module, which generates posture auxiliary information according to the limb gait information if the limb gait information does not meet the preset conditions;

[0058] an adjustment module, adjusting the parameters of the auxiliary training device according to the posture auxiliary information, and returning to the step of obtaining multiple joint motion trajectory information generated when the user follows the visual and auditory data for walking training within the first preset time period after the adjustment is completed;

[0059] If the limb gait information meets the preset conditions, the auxiliary training device fixes its own parameters.

[0060] Preferably, the first acquisition module includes:

[0061] A first acquisition unit assists the training device in acquiring its own initial projection light source and guidance audio;

[0062] a second acquiring unit, wherein the auxiliary training device acquires stride information of the user during walking training within a second preset time period, and adjusts the moving speed and moving distance of its own projection light source according to the stride information;

[0063] a third acquiring unit, for acquiring a stride beat feature of the user during walking training according to the stride information;

[0064] The generating unit acquires sound data according to the guiding audio and the stride beat feature, and generates audiovisual data according to the sound data, the moving speed and the moving distance of the projection light source.

[0065] The present application also provides a device for visual and auditory stimulation-assisted walking training, the device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements any of the above-described methods when executing the computer program.

[0066] The beneficial effects of the present application are as follows: the present invention first generates diversified audiovisual data by means of auxiliary training equipment to attract users to actively participate in training, and adjusts parameters according to the user's physical condition, such as reducing the intensity of sound and light stimulation for users with poor balance, and increasing the complexity of stimulation for those with strong athletic ability. At the same time, high-precision sensors are used to obtain the joint movement trajectory information of users when following audiovisual data training, to ensure the accuracy and completeness of the data, and to make the training more targeted and adjustable. Then, the limb coordination characteristics are evaluated by calculating the phase difference and time delay of the joint movement, the muscle group activation sequence and intensity are analyzed to obtain the muscle group coordination characteristics, and the two are combined to calculate the gait parameters such as step frequency and stride length, and comprehensive optimization and adjustment are made to obtain accurate limb gait information. In view of the defects of traditional training effect evaluation standards that are not unified and rely on subjective judgment. When an abnormal gait is found in the user, the root cause is analyzed based on the joint coordination characteristics and muscle group coordination characteristics, and targeted posture assistance information is pushed using visualization or voice prompts to help users improve the problem that traditional equipment parameters are fixed and cannot be adjusted in real time. The equipment parameters are dynamically optimized based on the posture assistance information, such as strengthening the user's balance training by changing the light source data. When the limb gait information meets the preset conditions, the equipment parameters are fixed to ensure stable and coherent training, forming a complete and scientific home rehabilitation training system. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a schematic diagram of a method flow chart according to an embodiment of the present application.

[0068] Figure 2 This is a schematic diagram of the system structure of an embodiment of the present application.

[0069] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0070] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0071] like Figure 1-2 As shown, the present application provides a method for visual and auditory stimulation assisted walking training, which is applied to a rehabilitation training area, wherein the rehabilitation training area is provided with auxiliary training equipment, including:

[0072] S1. Acquiring, within a first preset time period, information on multiple joint motion trajectories generated by a user performing walking training following audiovisual data, wherein the audiovisual data is generated by an auxiliary training device, the audiovisual data including sound data generated by the auxiliary training device based on adjustment of its own parameters and light source data that matches the sound data and is reflected in a rehabilitation training area;

[0073] S2. Acquire coordination features between multiple joints based on the multiple joint motion trajectory information, wherein the coordination features include limb coordination features and muscle group coordination features;

[0074] S3. Acquiring limb gait information based on the plurality of coordination features;

[0075] S4, determining whether the limb gait information meets a preset condition;

[0076] S5. If the limb gait information does not meet the preset conditions, generate posture auxiliary information according to the limb gait information;

[0077] S6, adjusting the parameters of the auxiliary training device according to the posture auxiliary information, and after the adjustment is completed, returning to the step of obtaining multiple joint motion trajectory information generated when the user follows the visual and auditory data for walking training within the first preset time period;

[0078] S7. If the limb gait information meets the preset conditions, the auxiliary training device fixes its own parameters.

[0079] As described in steps S1-S7 above, when a user performs self-rehabilitation training at home, the user's movement state is first comprehensively and accurately captured by acquiring multiple joint motion trajectory information generated by the user following audiovisual data during walking training within a first preset time period. The user's movement state is then comprehensively and accurately captured using the auxiliary training device to generate diverse audiovisual data to encourage the user to actively participate in the training. The auxiliary training device adjusts its parameters based on the user's different physical conditions. For example, for users with poor balance, the sound frequency and light source movement speed are reduced to provide a more stable stimulation environment, while for users with stronger athletic ability, the complexity and intensity of the stimulation are increased. When acquiring joint motion trajectory information, high-precision sensors are used to ensure data accuracy and completeness, thereby making the training targeted and adjustable. Then, through comprehensive analysis of the multiple joint motion trajectory information, limb coordination characteristics are evaluated by calculating phase differences and time delays in joint motion. Muscle coordination characteristics are obtained by analyzing the activation sequence and intensity of different muscle groups during exercise. The cadence is calculated by analyzing the joint motion phase differences in the limb coordination characteristics and combining them with time information. The stride length is then inferred based on the muscle contraction force and time in the muscle coordination characteristics. The interactions among multiple coordination features are simultaneously considered, and the gait parameters are comprehensively optimized and adjusted to obtain more accurate limb gait information.

[0080] In the past, the evaluation of training effects lacked a unified standard and mostly relied on the subjective judgment of doctors or trainers. This was easily influenced by personal experience and observation angles, resulting in inaccurate evaluation results. When formulating preset conditions, it may be necessary to comprehensively consider multiple factors, such as the user's age, physical condition, and disease type. When a user's gait is found to be abnormal, it is difficult for the user to make clear and effective improvements due to the lack of professional rehabilitation training knowledge. This application uses the acquired joint coordination characteristics and muscle group coordination characteristics to deeply analyze the root cause of the problem. For example, if it is detected that the user's stride is too small due to insufficient hip flexion and extension, then the posture assistance information real-time action feedback will push targeted suggestions, such as increasing hip joint range of motion training, performing specific muscle strength training, etc. At the same time, posture assistance information is fed back to the user in real time through visualization or voice prompts, making it easier for the user to understand and implement it. The training parameters set in traditional auxiliary training equipment are often fixed and cannot be adjusted in real time according to the user's movement status and training progress, resulting in poor training results. Furthermore, inappropriate training parameters can cause discomfort or even injury to the user. By adjusting the training device's parameters based on posture assistance information, the system dynamically optimizes the training plan. For example, if posture assistance information indicates a need for increased balance training, the device's light source data can be adjusted to exhibit an erratic flickering pattern, increasing visual distraction while walking and thereby enhancing the intensity of balance training. Simultaneously, based on user feedback and changes in training data, the device parameters are continuously fine-tuned to ensure optimal training results. When the system determines that the gait information meets preset conditions, it records the current training device parameter settings and fixes them. Simultaneously, a notification is sent to the user and trainer, informing them that the training has achieved the desired goal and that the current parameter settings will remain stable. In subsequent training sessions, unless further anomalies arise, the device will continue to operate according to the fixed parameters, ensuring training stability and continuity.

[0081] In one embodiment, step S2 in which the audiovisual data is generated by the auxiliary training device includes:

[0082] S201, the auxiliary training device obtains its own initial projection light source and guidance audio;

[0083] S202: During a second preset time period, the auxiliary training device obtains stride information of the user during walking training, and adjusts the moving speed and moving distance of its own projection light source according to the stride information;

[0084] S203, obtaining stride rhythm characteristics of the user during walking training according to the stride information;

[0085] S204: Acquire sound data according to the guiding audio and the stride rhythm feature, and generate audiovisual data according to the sound data, the moving speed and the moving distance of the projection light source.

[0086] As described in steps S201-S204 above, the auxiliary training device in the present invention is a projector capable of playing designated guidance audio and projecting a light source. The projection light source settings include light color, projection angle, and trajectory shape. For example, it can be set to a green, straight light trajectory. The guidance audio settings include frequency, rhythm, and pitch. For example, a metronome similar to a normal walking rhythm can be set. This lays the foundation for subsequent training. A pre-designed light pattern is projected onto the floor of the rehabilitation training area to create a clear walking guidance mark. Simultaneously, the auxiliary training device plays the generated guidance audio. The guidance audio can be a steady rhythmic metronome; for rehabilitation training, it can be a rhythmic audio with a prompt tone, reminding the user when to lift their leg, when to take a step, etc. The start and end nodes of a stride are determined based on the user's gait. A node graph of the multiple start and end nodes is generated according to a fourth preset time sequence. The start and end nodes of a stride are accurately determined. Based on this, these nodes are arranged in an orderly manner according to the fourth preset time sequence and a node graph is plotted. The node curve diagram intuitively presents the dynamic changes of the user's stride action during walking, including the distribution density of nodes, time intervals and other information, which becomes the key basis for subsequent analysis. The stride time period and node curve are obtained according to two adjacent nodes in the node curve diagram, and the moving distance of the projection light source is obtained according to the node curve. Starting from the node curve, with the help of kinematic principles, the moving distance of the projection light source in the corresponding process can be accurately obtained, and the moving speed of the projection light source can be obtained according to the stride time period and the moving distance of the projection light source. The stride time period is obtained by recording the time interval between adjacent start nodes and end nodes. According to the two core data of the stride time period and the moving distance of the projection light source, the moving speed of the projection light source can be smoothly calculated according to the basic speed calculation formula (speed = distance ÷ time).The moving speed of the projection light source reflects the movement rate that the projection light source should have to adapt to the stride during the user's stride. The stride information is obtained through the stride time period and the moving distance of the projection light source, and the moving speed and moving distance of the projection light source are adjusted according to the stride information. The information contained in the stride time period and the moving distance of the projection light source covers multiple dimensions such as stride size (related to the moving distance of the projection light source), stride rhythm (related to the stride time period) and the coordination between the two. Through in-depth mining of stride information, the auxiliary training equipment can fully understand the user's current gait characteristics and walking habits, obtain the stride time average based on multiple stride time periods, and obtain the stride time average based on the stride time average. The stride beat feature is determined by statistically analyzing multiple stride time periods, calculating the stride time period average, summarizing the data of multiple consecutive stride time periods, and then calculating the stride time average by the arithmetic average method. Based on the stride time average, its stability and change trend are further analyzed to determine the stride beat feature. For example, if the stride time average is relatively stable and the fluctuation range is within the normal range, it means that the user's walking rhythm is relatively regular; if the average fluctuates greatly, it may indicate that there is a problem with the user's walking rhythm. The auxiliary training equipment adjusts and optimizes the guiding audio according to the stride beat feature, such as adjusting the audio rhythm, frequency and other parameters to match the user's actual walking rhythm.

[0087] In one embodiment, the step S3 of acquiring coordination features between multiple joints based on the multiple joint motion trajectory information includes:

[0088] S301, acquiring a plurality of ankle joint movement trajectories and a plurality of hip joint movement trajectories according to a plurality of joint movement trajectory information;

[0089] S302, obtaining an initial movement timestamp and an end movement timestamp according to each ankle joint movement trajectory and each hip joint movement trajectory, constructing a plurality of first position nodes during the movement process according to each ankle joint movement trajectory, constructing a plurality of second position nodes during the movement process according to each hip joint movement trajectory, and obtaining a phase difference between each ankle joint movement trajectory and each hip joint movement trajectory according to the plurality of first position nodes and the plurality of second position nodes within a third preset time;

[0090] S303, obtaining synchronization of each ankle joint movement trajectory and each hip joint movement trajectory according to the phase difference, the initial movement timestamp, and the final movement timestamp;

[0091] S304, obtaining limb coordination features according to the phase difference and synchronization of each ankle joint movement trajectory and each hip joint movement trajectory during movement;

[0092] S305, acquiring corresponding agonist muscle variable features and antagonist muscle variable features according to each ankle joint movement trajectory and each hip joint movement trajectory;

[0093] S306, obtaining a muscle contraction time period according to the agonist muscle variable characteristics and the antagonist muscle variable characteristics, and obtaining an agonist muscle activation time and an antagonist muscle activation time according to the muscle contraction time period;

[0094] S307, obtaining a muscle activation sequence table based on the activation time of the agonist muscle and the activation time of the antagonist muscle during the muscle contraction period, and using the muscle activation sequence table as a muscle group coordination feature;

[0095] S308. Acquire coordination features between multiple joints based on limb coordination features and muscle group coordination features.

[0096] As described in the above steps S301-S308, the present invention accurately screens out the ankle joint movement trajectory and the hip joint movement trajectory from the information of multiple joint movement trajectories. The ankle joint and the hip joint are the key hubs of the human lower limb movement, and their movement trajectories can intuitively reflect the movement pattern and mechanical characteristics of the lower limbs. Analyzing the ankle joint movement trajectory and the hip joint movement trajectory can reduce the interference of irrelevant information, making the analysis more targeted and efficient. Acquiring data on multiple ankle joint movement trajectories and hip joint movement trajectories can comprehensively cover different movement states and individual differences, providing rich and representative data samples for subsequent analysis, ensuring the reliability and universality of the analysis results, and identifying and marking the initial movement timestamp and the terminal movement timestamp of each movement of the ankle joint movement trajectory and the hip joint movement trajectory. Then, at fixed time intervals (such as every 10 milliseconds), the corresponding position information is extracted from the ankle joint movement trajectory and the hip joint movement trajectory to construct multiple first position nodes and second position nodes. Within a third preset time (such as a complete gait cycle), the position node data of the ankle joint movement trajectory and the hip joint movement trajectory are processed using Fourier transform to calculate the phase difference between them. The synchronization of the ankle and hip joint movement trajectories is evaluated based on the phase difference, initial movement timestamp and terminal movement timestamp. This can comprehensively and objectively evaluate the coordination and synchronization of the ankle and hip joints during movement. It is an important indicator for measuring the quality of joint coordinated movement.

[0097] By quantifying synchronization, it is possible to accurately determine whether the ankle and hip joint trajectories are well coordinated, providing a key basis for analyzing motor function and diagnosing movement abnormalities. Combined with timestamp information, synchronization assessment not only considers the phase relationship of joint movement but also incorporates the time dimension, making it more consistent with the actual human movement. Limb coordination characteristics are obtained based on the phase difference and synchronization of the ankle and hip joint trajectories, achieving a macro-level overview from the microscopic parameters of joint movement to the overall coordination of limb movement. Based on anatomical and biomechanical knowledge, the main agonist and antagonist muscles of the ankle and hip joint trajectories during movement are determined. Then, using surface electromyography signal acquisition equipment, the electrical activity signals of these agonist and antagonist muscles are synchronously collected during walking training. At the same time, the muscle electrical activity signal is time-synchronized with the ankle joint movement trajectory data and the hip joint movement trajectory data, and the agonist muscle variable characteristics and antagonist muscle variable characteristics are extracted from the electromyographic signal. The agonist muscle variable characteristics are the process of the agonist muscle transforming from stretching and relaxation to contraction and tension, and the antagonist muscle variable characteristics are the process of the antagonist muscle transforming from stretching and relaxation to contraction and tension. By analyzing the relationship between the agonist muscle variable characteristics and antagonist muscle variable characteristics and the ankle joint movement trajectory data and the hip joint movement trajectory data, an important basis is provided for analyzing motor function, evaluating muscle status and formulating rehabilitation training plans. Then, a preset threshold is set, and the start and end time of muscle contraction is determined according to the amplitude change of the electromyographic signal, thereby obtaining the muscle contraction time period. Next, by analyzing the changing characteristics of the electromyographic signals during the contraction period, such as the slope of the rising and falling edges and the amplitude trend, combined with the principles of kinematics and biomechanics, the activation times of the agonist and antagonist muscles are precisely determined. These activation times are then arranged in chronological order to form a muscle activation sequence table. During this arrangement process, the activation time points, activation durations, and temporal relationships of the agonist and antagonist muscles with other muscles are recorded in detail. This activation sequence table is then visually displayed using a graph for easier analysis and understanding. Furthermore, the activation sequence table is further analyzed and verified based on the ankle and hip joint movement trajectories to determine whether it conforms to normal movement biomechanics and whether there are any abnormal activation sequences. The coordination characteristics of multiple joints are then derived by integrating the coordination characteristics of the limb and muscle groups. This achieves a comprehensive integration of the microscopic level of joint movement to the macroscopic level of overall limb movement, and from local muscle activity to the overall coordination of muscle groups. The coordination characteristics between multiple joints can comprehensively reflect the overall functional state of the human movement system during movement, covering joint movement, muscle activity and the relationship between them.

[0098] In one embodiment, the step S4 of generating posture auxiliary information according to the limb gait information includes:

[0099] S401, acquiring a plurality of light beams of different brightness and flickering frequencies matching the light beams of different brightness according to the light source data, generating a light beam brightness change trend graph according to the plurality of light beams of different brightness, and generating a visual stimulation change gradient graph according to the light beam brightness change trend graph and the flickering frequencies;

[0100] S402, acquiring multiple audio time periods according to the sound data, extracting corresponding audio decibel values ​​according to the multiple audio time periods, and generating an auditory stimulation change gradient map according to the multiple audio decibel values;

[0101] S403: Generate posture auxiliary information from the visual stimulation change gradient map and the auditory stimulation change gradient map.

[0102] As described in steps S401-S403 above, the present invention extracts information about multiple light beams of varying brightness and their corresponding flicker frequencies from the light source data using the auxiliary training device. This is accomplished through the light source control module and sensor built into the auxiliary training device. The sensor monitors the brightness and flicker of the light source in real time and transmits the data to a data processing system. The data processing system organizes and analyzes this data, creating a chronological graph of the light beam brightness trends. Using the light beam brightness change trend graph, with time as the horizontal axis and light beam brightness as the vertical axis, the brightness data at different times are connected into a curve to intuitively display the brightness change trend over time. By analyzing the light beam brightness change trend graph, you can intuitively see whether the brightness of the light source is gradually increasing, decreasing, or fluctuating periodically. Combined with the flicker frequency, when the brightness of the light source is gradually increasing, the flicker frequency becomes faster and faster, and when the brightness of the light source is gradually decreasing, the flicker frequency becomes slower and slower. The visual stimulation change gradient graph generated by the flicker frequency can further quantify the degree of dynamic change of visual stimulation, providing an objective and accurate basis for subsequent training and evaluation. By calculating the brightness change rate between adjacent time points, the dynamic change gradient of visual stimulation can be quantified. If the posture assistance information indicates that the user needs to strengthen balance training, by increasing the brightness of the projected light beam and making the projected light beam flicker, the visual interference of the user during walking is increased, thereby improving the intensity of the user's balance ability training.

[0103] By acquiring multiple audio time segments and extracting the corresponding audio decibel values, an auditory stimulus change gradient map is generated, achieving precise quantification and visualization of auditory stimuli. Similar to visual stimulus analysis, this process comprehensively considers the temporal and intensity variations of auditory stimuli. By analyzing the temporal variations in audio decibel values, fluctuations in sound intensity can be clearly understood, such as whether the sound suddenly increases, gradually decreases, or remains stable. The generated auditory stimulus change gradient map further quantifies the extent of this variation, making the characteristics of auditory stimuli more intuitive and easier to understand. This provides a scientific basis for tailoring auditory stimulation programs to user needs and training goals, helping to improve the relevance and effectiveness of training. The visual and auditory stimulus change gradient maps are integrated to generate posture-assisted information, achieving the fusion and sublimation of multimodal stimulation information. This fusion not only leverages the respective strengths of visual and auditory stimulation, but also complements and synergizes them to provide users with more comprehensive, rich, and effective training guidance. Posture-assisted information comprehensively reflects the dynamic characteristics of visual and auditory stimuli, providing users with more targeted exercise guidance. If posture assistance information indicates that the user needs to strengthen balance training, suddenly increasing the audio decibel level and volume will impact the user's auditory system, thereby disrupting the user's sensory system. This approach can also improve the user's balance ability, helping them better adapt to the training environment and complete the training task. At the same time, this fusion of multimodal information helps to improve user attention and training participation, enhancing training effectiveness.

[0104] In one embodiment, the step S5 of generating posture auxiliary information according to the limb gait information includes:

[0105] S501, obtaining pulse information according to the limb gait information;

[0106] S502, acquiring multiple current stimulation peaks within a preset time and the time interval between each of the current stimulation peaks according to the pulse information;

[0107] S503, obtaining stimulation frequencies according to multiple time intervals;

[0108] S504, extracting the microampere current in the pulse information and converting the microampere current into a voltage signal;

[0109] S505, collecting a frequency spectrum of the voltage signal obtained by Fourier transform within a preset time, extracting multiple peak points from the frequency spectrum, and generating a main frequency component based on the multiple peak points;

[0110] S506: Acquire posture auxiliary information according to the current stimulation peak value, stimulation frequency, and main frequency component.

[0111] As described in steps S501-S505 above, the present invention uses an inertial measurement unit sensor to collect real-time gait information from the user. When pulse information is linked to gait information, it provides a personalized foundation for subsequent electrical stimulation assistance. Gait information can reflect an individual's unique movement patterns and states. By extracting pulse information from it, the generated pulse information can be precisely adapted to each user's specific situation. This means that electrical stimulation can closely follow the user's actual gait, improving the targetedness and effectiveness of stimulation. By detecting the amplitude of the pulse signal, the current stimulation peak is identified. At the same time, the time point of each current stimulation peak is recorded, and the time interval between adjacent peaks is calculated. To ensure data accuracy, multiple sampling and statistical analysis may be performed to filter and correct outliers. For example, a sliding window method is used to continuously analyze the pulse signal within a certain time range to extract stable current stimulation peak and time interval data. The stimulation frequency is a key parameter of electrical stimulation, which directly affects the rhythm of muscle contraction and relaxation. By calculating the stimulation frequency based on multiple time intervals, the rhythm of electrical stimulation can be accurately grasped and matched to the human body's physiological rhythm. The appropriate stimulation frequency can effectively activate muscle fibers, improving muscle reaction speed and power output. For example, different muscle types (such as fast-twitch fibers and slow-twitch fibers) have different optimal stimulation frequencies. By precisely controlling the stimulation frequency, different muscle types can be trained in a targeted manner, improving training effectiveness. The peak current output by the stimulation frequency on the user's muscle group to be stimulated can help the user contract the muscle group and adjust the walking posture to improve gait. The formula for extracting the microampere current in the pulse information through the damping amplifier is:

[0112] ;

[0113] Among them, V a Indicates the output voltage, I in Represents the output current, R f Represents the feedback resistor.

[0114] The voltage signal is then processed using a Fourier transform algorithm, converting it from the time domain to the frequency domain to produce a spectrogram. The spectrogram uses frequency as the horizontal axis and signal amplitude as the vertical axis, visually displaying the intensity of each frequency component in the signal. A peak detection algorithm then identifies multiple peaks in the spectrogram, representing frequency components with high energy. Finally, based on the frequency and amplitude information of these peaks, the dominant frequency components are generated. The dominant frequency components can be represented by one or more primary frequencies and their corresponding amplitudes, reflecting the dominant frequency characteristics of the electrical stimulation signal. Microcurrent therapy is applied to the user's fast and slow twitch fibers using a microampere current of 50–200 μA (below the pain threshold) and a frequency of 0.5–10 Hz (simulating physiological electrical activity) to improve the clearance of post-exercise lactate accumulation. By comprehensively considering multiple key parameters, such as the current stimulation peak, stimulation frequency, and dominant frequency components, posture-related information is generated, enabling comprehensive evaluation and precise application of the electrical stimulation effect. These parameters reflect the characteristics of electrical stimulation from different perspectives, and their combination can more accurately describe the impact of electrical stimulation on human posture and movement. Posture assistance information can provide users with personalized exercise guidance, helping them adjust their posture, improve their gait, and enhance their athletic ability. For example, based on different combinations of current stimulation peaks, stimulation frequencies, and dominant frequency components, it can be determined whether electrical stimulation is effectively activating the relevant muscles, and how to adjust stimulation parameters to achieve the optimal posture assistance effect.

[0115] In one embodiment, the step S6 of determining whether the limb gait information meets a preset condition further includes:

[0116] S601, obtaining an agonist muscle activation time range, an antagonist muscle activation time range, an ankle joint motion trajectory, and a hip joint motion trajectory based on limb gait information;

[0117] S602: Determine whether the agonist muscle activation time range and the antagonist muscle activation time range are both greater than a maximum value of a preset interval;

[0118] If the agonist muscle activation time range and the antagonist muscle activation time range are both greater than the maximum value of the preset interval, it is determined that the preset condition is not met;

[0119] If the agonist muscle activation time range and the antagonist muscle activation time range are both smaller than the minimum value of the preset interval, it is determined that the preset condition is not met;

[0120] S603: If the agonist muscle activation time range and the antagonist muscle activation time range are both within the range values ​​of the preset interval, it is determined that the preset condition is met, and it is determined whether the phase difference between the ankle joint motion trajectory and the hip joint motion trajectory is less than a preset value;

[0121] If the phase difference between the ankle joint motion trajectory and the hip joint motion trajectory is less than a preset value, it is determined that the preset condition is not met;

[0122] If the phase difference between the ankle joint motion trajectory and the hip joint motion trajectory is not less than a preset value, it is determined that the preset condition is met.

[0123] As described in the above steps S601-S603, the present invention first synchronously collects data based on the optical motion capture device and the electromyographic signal acquisition device when the user is performing walking training. The optical motion capture device records the three-dimensional motion trajectory of the ankle joint and hip joint in real time, captures the position changes of the joints in space through multiple sensors and generates the ankle joint motion trajectory and the hip joint motion trajectory. At the same time, the electromyographic signal acquisition device collects the electrical activity signals of the muscles through electrodes attached to the surfaces of the agonist and antagonist muscles to analyze the electromyographic signals. According to the characteristics such as the amplitude change of the signal, the activation start time and end time of the agonist and antagonist muscles are determined, thereby obtaining the agonist muscle activation time range and the antagonist muscle activation time range. By setting a preset interval, the agonist muscle activation time range and the antagonist muscle activation time range are strictly judged, and it is possible to quickly and accurately identify whether the muscle function is normal. In the actual evaluation process, the agonist muscle activation time range and the antagonist muscle activation time range are compared with the preset interval. If both the agonist and antagonist activation time ranges are greater than the maximum value of the preset interval, it indicates overactivation of the muscles, which may result in muscle spasm or abnormal neural control. If both the agonist and antagonist activation time ranges are less than the minimum value of the preset interval, it indicates underactivation of the muscles, which may be caused by decreased muscle strength or neural conduction disorders. Once the preset conditions are determined to be unsatisfactory, the auxiliary training device issues an abnormality prompt for further inspection and intervention. After confirming that the agonist and antagonist activation time ranges are normal, the phase difference between the ankle and hip joint motion trajectories is further determined, achieving a comprehensive and systematic assessment from muscle activity to joint movement. The phase difference of joint movement reflects the coordination between joints, and the appropriate phase difference is one of the key factors in ensuring normal gait. By comparing the phase difference between the ankle and hip joint motion trajectories with the preset value, an accurate quantitative assessment of the coordination of lower limb joint movement is achieved. Phase difference is a key indicator reflecting the temporal and spatial relationship of joint movement. Compared with traditional assessment methods that rely solely on visual observation or simple measurement of joint angles, this quantitative comparison method is more objective and accurate. It can detect subtle incoordination issues in joint movement, and by prioritizing the steps of determining muscle activation time range and complementing each other, it forms a complete assessment system from muscle function to joint movement. Normal muscle activation is the foundation of joint movement, and coordinated joint movement is the key to achieving a good gait. Only by further evaluating the phase difference of joint movement under the premise of a normal muscle activation time range can we comprehensively and systematically determine whether the gait is normal. This hierarchical, multi-dimensional assessment method greatly improves the comprehensiveness and accuracy of gait assessment and can more effectively identify potential gait abnormalities.

[0124] In one embodiment, after the step of generating posture auxiliary information according to the limb gait information S7, the method further includes:

[0125] S701, obtaining multiple respiratory rates and heel touchdown timestamps based on limb gait information;

[0126] S702: Generate a respiratory spectrum according to the multiple respiratory frequencies, wherein the respiratory spectrum includes multiple peaks and multiple troughs;

[0127] S703: Set the time period from each peak to each trough as an exhalation time period, obtain the shortest exhalation time period between two adjacent exhalation time periods based on the multiple exhalation time periods, extract the exhalation start timestamp within the shortest exhalation time period, and synchronize the exhalation start timestamp with the heel strike timestamp.

[0128] As described in steps S701-S703 above, the present invention first monitors the chest's fluctuations during breathing in real time by wearing a piezoelectric respiratory sensor, converting the sensor's fluctuations into electrical signals. The signal is then converted into respiratory rate using a signal processing algorithm. Simultaneously, a pressure sensor is installed in the shoe. When the heel strikes the ground, the pressure sensor detects the pressure change and generates an electrical signal. The system records the timestamp at this moment, generating a heel strike timestamp. Combining respiratory rate with heel strike timestamps provides a multi-dimensional data foundation for analyzing human motion. Respiratory rate reflects the body's respiratory rhythm and cardiopulmonary function during exercise, while heel strike timestamps accurately record key events in the gait cycle. This combination overcomes the limitations of traditional methods that focus solely on either gait or respiration, converting discrete respiratory rate data into an intuitive spectrum graph. The multiple peaks and troughs contained within clearly demonstrate the periodic changes and fluctuations in respiratory rate. This visual representation, compared to simply listing numerical values, makes it easier for analysts to quickly capture the changing trends, patterns, and abnormal fluctuations in respiratory rate. Analysis of the respiratory spectrum provides a deeper understanding of the dynamic process of respiratory regulation during exercise and allows for judgment of reasonable breathing patterns. This provides an intuitive and effective means for assessing respiratory function and exercise adaptability. In the respiratory spectrum, the horizontal axis represents frequency, and the vertical axis represents the amplitude of the corresponding frequency. The position and height of the peaks and troughs reflect the contribution and intensity of different frequency components in respiratory frequency changes. By synchronizing the exhalation period with the heel strike timestamp, a temporal correlation between respiration and gait is established, revealing the synergistic relationship between the two during exercise. When a user experiences gait abnormalities that lead to respiratory disturbances, the shortest exhalation period between two adjacent exhalation periods is identified and the exhalation start timestamp within the shortest exhalation period is extracted. Synchronizing this exhalation start timestamp with the heel strike timestamp allows for precise location of the corresponding moments of key respiratory and gait events. This helps to improve joint stability, reduce the risk of sports injuries, and enhance sports safety by synchronizing gait with exhalation and utilizing changes in intra-abdominal pressure.

[0129] The present application also provides a system for visual and auditory stimulation-assisted walking training, comprising:

[0130] A first acquisition module 1 acquires, within a first preset time period, information on multiple joint motion trajectories generated by a user performing walking training following audiovisual data, wherein the audiovisual data is generated by an auxiliary training device, and includes sound data generated by the auxiliary training device based on adjustment of its own parameters, and light source data that matches the sound data and is reflected in a rehabilitation training area;

[0131] A second acquisition module 2 acquires coordination features between multiple joints based on the multiple joint motion trajectory information, wherein the coordination features include limb coordination features and muscle group coordination features;

[0132] A third acquisition module 3 acquires limb gait information according to the plurality of coordination features;

[0133] Determination module 4, determining whether the limb gait information meets the preset conditions;

[0134] Generating module 5, generating posture auxiliary information according to the limb gait information if the limb gait information does not meet the preset conditions;

[0135] Adjustment module 6 adjusts the parameters of the auxiliary training device according to the posture auxiliary information, and after the adjustment is completed, returns to the step of obtaining multiple joint motion trajectory information generated when the user follows the visual and auditory data for walking training within the first preset time period;

[0136] If the limb gait information meets the preset conditions, the auxiliary training device fixes its own parameters.

[0137] In one embodiment, the first acquisition module 1 includes:

[0138] A first acquisition unit assists the training device in acquiring its own initial projection light source and guidance audio;

[0139] a second acquiring unit, wherein the auxiliary training device acquires stride information of the user during walking training within a second preset time period, and adjusts the moving speed and moving distance of its own projection light source according to the stride information;

[0140] a third acquiring unit, for acquiring a stride beat feature of the user during walking training according to the stride information;

[0141] The generating unit acquires sound data according to the guiding audio and the stride beat feature, and generates audiovisual data according to the sound data, the moving speed and the moving distance of the projection light source.

[0142] The present application also provides a device for visual and auditory stimulation-assisted walking training, the device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements any of the above-described methods when executing the computer program.

[0143] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct RAM bus dynamic RAM (DRDRAM), and RAM bus dynamic RAM (RDRAM).

[0144] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0145] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for visual and auditory stimulation assisted walking training, applied to a rehabilitation training area, wherein the rehabilitation training area is provided with auxiliary training equipment, characterized in that: include: Acquiring, within a first preset time period, information on multiple joint motion trajectories generated by a user performing walking training following audiovisual data, wherein the audiovisual data is generated by an auxiliary training device, the audiovisual data including sound data generated by the auxiliary training device based on adjustment of its own parameters and light source data that matches the sound data and is reflected in a rehabilitation training area; Acquire multiple ankle joint movement trajectories and multiple hip joint movement trajectories according to the multiple joint movement trajectory information; Obtaining an initial movement timestamp and an end movement timestamp according to each ankle joint movement trajectory and each hip joint movement trajectory, constructing a plurality of first position nodes during the movement process according to each ankle joint movement trajectory, constructing a plurality of second position nodes during the movement process according to each hip joint movement trajectory, and obtaining a phase difference between each ankle joint movement trajectory and each hip joint movement trajectory according to the plurality of first position nodes and the plurality of second position nodes within a third preset time; The synchronization of each ankle joint movement trajectory and each hip joint movement trajectory is obtained according to the phase difference, the initial movement timestamp and the terminal movement timestamp; Acquire limb coordination features based on the phase difference and synchronization of each ankle joint movement trajectory and each hip joint movement trajectory during movement; Obtain corresponding agonist muscle variable features and antagonist muscle variable features according to each ankle joint movement trajectory and each hip joint movement trajectory; Obtaining a muscle contraction time period according to the variable characteristics of the agonist muscle and the variable characteristics of the antagonist muscle, and obtaining an agonist muscle activation time and an antagonist muscle activation time according to the muscle contraction time period; Obtain a muscle activation sequence table based on the activation time of the agonist muscle and the activation time of the antagonist muscle during the muscle contraction period, and use the muscle activation sequence table as a muscle group coordination feature; Acquire coordination features between multiple joints based on limb coordination features and muscle group coordination features; Acquiring limb gait information according to a plurality of the coordination features; Determining whether the limb gait information meets a preset condition; If the limb gait information does not meet the preset conditions, generating posture auxiliary information according to the limb gait information; Adjusting the parameters of the auxiliary training device according to the posture auxiliary information, and after the adjustment is completed, returning to the step of obtaining multiple joint motion trajectory information generated when the user follows the visual and auditory data for walking training within the first preset time period; If the limb gait information meets the preset conditions, the auxiliary training device fixes its own parameters.

2. The method of visual and auditory stimulation assisted walking training according to claim 1, characterized in that: The step of generating the audiovisual data by the auxiliary training device comprises: The auxiliary training device obtains its own initial projection light source and guiding audio; During the second preset time period, the auxiliary training device obtains the stride information of the user during walking training, and adjusts the moving speed and moving distance of its own projection light source according to the stride information; Acquire the stride beat characteristics of the user during walking training based on the stride information; Acquire sound data according to the guide audio and the stride beat feature, and generate audiovisual data according to the sound data, the moving speed and the moving distance of the projection light source.

3. The method of visual and auditory stimulation assisted walking training according to claim 1, characterized in that: The step of generating posture auxiliary information according to the limb gait information comprises: Acquire a plurality of light beams of different brightness and flickering frequencies matching the light beams of different brightness according to the light source data, generate a light beam brightness change trend graph according to the plurality of light beams of different brightness, and generate a visual stimulation change gradient graph according to the light beam brightness change trend graph and the flickering frequencies; Acquiring multiple audio time periods according to the sound data, extracting corresponding audio decibel values ​​according to the multiple audio time periods, and generating an auditory stimulation change gradient map according to the multiple audio decibel values; The visual stimulus change gradient map and the auditory stimulus change gradient map are used to generate posture auxiliary information.

4. The method of visual and auditory stimulation assisted walking training according to claim 1, characterized in that: The step of generating posture auxiliary information according to the limb gait information comprises: acquiring pulse information according to the limb gait information; Acquire multiple current stimulation peaks within a preset time and the time interval between each of the current stimulation peaks according to the pulse information; Obtain stimulation frequency based on multiple time intervals; Extract the microampere current in the pulse information and convert the microampere current into a voltage signal; Collecting a frequency spectrum of a voltage signal obtained by Fourier transform within a preset time, extracting a plurality of peak points according to the frequency spectrum, and generating a main frequency component according to the plurality of peak points; Posture auxiliary information is obtained based on the current stimulation peak, stimulation frequency and main frequency component.

5. The method of visual and auditory stimulation assisted walking training according to claim 1, characterized in that: The step of determining whether the limb gait information meets a preset condition includes: According to the limb gait information, the activation time range of the agonist muscles, the activation time range of the antagonist muscles, the ankle joint motion trajectory and the hip joint motion trajectory are obtained; Determining whether the agonist muscle activation time range and the antagonist muscle activation time range are both greater than a maximum value of a preset interval; If the agonist muscle activation time range and the antagonist muscle activation time range are both greater than the maximum value of the preset interval, it is determined that the preset condition is not met; If the agonist muscle activation time range and the antagonist muscle activation time range are both smaller than the minimum value of the preset interval, it is determined that the preset condition is not met; If the agonist muscle activation time range and the antagonist muscle activation time range are both within the range values ​​of the preset interval, it is determined that the preset condition is met, and it is determined whether the phase difference between the ankle joint motion trajectory and the hip joint motion is less than a preset value; If the phase difference between the ankle joint motion trajectory and the hip joint motion trajectory is less than a preset value, it is determined that the preset condition is not met; If the phase difference between the ankle joint motion trajectory and the hip joint motion trajectory is not less than a preset value, it is determined that the preset condition is met.

6. The method of visual and auditory stimulation assisted walking training according to claim 1, characterized in that: After the step of generating posture auxiliary information according to the limb gait information, the method further comprises: Acquire multiple respiratory rates and heel strike timestamps based on limb gait information; generating a respiratory spectrum according to the plurality of respiratory frequencies, wherein the respiratory spectrum comprises a plurality of peaks and a plurality of troughs; The time period from each peak to each trough is set as the exhalation period. The shortest exhalation period between two adjacent exhalation periods is obtained based on multiple exhalation periods. The exhalation start timestamp in the shortest exhalation period is extracted, and the exhalation start timestamp is synchronized with the heel touchdown timestamp.

7. A system for visual and auditory stimulation assisted walking training, characterized in that: include: a first acquisition module for acquiring, within a first preset time period, information on multiple joint motion trajectories generated by a user performing walking training following audiovisual data, wherein the audiovisual data is generated by an auxiliary training device, and includes sound data generated by the auxiliary training device based on adjustment of its own parameters, and light source data that matches the sound data and is reflected in a rehabilitation training area; a second acquisition module, acquiring a plurality of ankle joint movement trajectories and a plurality of hip joint movement trajectories according to the plurality of joint movement trajectory information; Obtaining an initial movement timestamp and an end movement timestamp according to each ankle joint movement trajectory and each hip joint movement trajectory, constructing a plurality of first position nodes during the movement process according to each ankle joint movement trajectory, constructing a plurality of second position nodes during the movement process according to each hip joint movement trajectory, and obtaining a phase difference between each ankle joint movement trajectory and each hip joint movement trajectory according to the plurality of first position nodes and the plurality of second position nodes within a third preset time; The synchronization of each ankle joint movement trajectory and each hip joint movement trajectory is obtained according to the phase difference, the initial movement timestamp and the terminal movement timestamp; Acquire limb coordination features based on the phase difference and synchronization of each ankle joint movement trajectory and each hip joint movement trajectory during movement; Obtain corresponding agonist muscle variable features and antagonist muscle variable features according to each ankle joint movement trajectory and each hip joint movement trajectory; Obtaining a muscle contraction time period according to the variable characteristics of the agonist muscle and the variable characteristics of the antagonist muscle, and obtaining an agonist muscle activation time and an antagonist muscle activation time according to the muscle contraction time period; Obtain a muscle activation sequence table based on the activation time of the agonist muscle and the activation time of the antagonist muscle during the muscle contraction period, and use the muscle activation sequence table as a muscle group coordination feature; Acquire coordination features between multiple joints based on limb coordination features and muscle group coordination features; a third acquisition module, acquiring limb gait information according to the plurality of coordination features; A judgment module, judging whether the limb gait information meets a preset condition; A generating module, which generates posture auxiliary information according to the limb gait information if the limb gait information does not meet the preset conditions; an adjustment module, adjusting the parameters of the auxiliary training device according to the posture auxiliary information, and returning to the step of obtaining multiple joint motion trajectory information generated when the user follows the visual and auditory data for walking training within the first preset time period after the adjustment is completed; If the limb gait information meets the preset conditions, the auxiliary training device fixes its own parameters.

8. The system for visual and auditory stimulation assisted walking training according to claim 7, characterized in that: The first acquisition module includes: A first acquisition unit assists the training device in acquiring its own initial projection light source and guidance audio; a second acquiring unit, wherein the auxiliary training device acquires stride information of the user during walking training within a second preset time period, and adjusts the moving speed and moving distance of its own projection light source according to the stride information; a third acquiring unit, for acquiring a stride beat feature of the user during walking training according to the stride information; The generating unit acquires sound data according to the guiding audio and the stride beat feature, and generates audiovisual data according to the sound data, the moving speed and the moving distance of the projection light source.

9. A device for visual and auditory stimulation assisted walking training, characterized in that: include: The device adopts the steps of the method for visual and auditory stimulation-assisted walking training as described in any one of claims 1-6.

Images