Gait feedback rehabilitation training system data processing method and device and medium

Abstract

This application discloses a data processing method, device, and medium for a gait feedback rehabilitation training system, relating to the field of rehabilitation training technology. It collects plantar pressure data and accelerometer data during the training process, addressing the lack of quantitative data. It calculates total plantar pressure and the coordinates of the plantar pressure center using plantar pressure data, and plots gait lines and total plantar pressure curves to reflect the interaction of force on the foot. A report is generated by combining the temporal, mechanical, and symmetry parameters extracted from the collected data. The entire process is based on real-time collected dynamic and motion data, and all extracted parameters are calculated from measured data, eliminating subjective human judgment bias. An evaluation report is generated by integrating various parameters, replacing experience-based judgments with quantitative data results. This achieves effective monitoring and standardized processing of training process data, ensuring objectivity throughout the entire process from data source and parameter calculation to result output, and improving the accuracy and reliability of subsequent related evaluation results.

Description

Technical Field

[0001] This application relates to the field of rehabilitation training technology, and in particular to a data processing method, device and medium for a gait feedback rehabilitation training system. Background Technology

[0002] Current lower limb rehabilitation training techniques are mainly based on two modes. Therapist-led manual training: A rehabilitation therapist assists the patient one-on-one in standing, weight transfer, and gait training. The therapist manually guides the patient's movements through visual observation and touch, and judges the patient's muscle tone, balance, and force exertion based on experience. Equipment-driven programmed passive training: Utilizing motor-driven devices, the patient's body performs repetitive, upright alternating stepping movements along a fixed trajectory. These devices typically provide basic postural changes and uniform reciprocating motion patterns; their core is to achieve automated, large-scale repetitive training.

[0003] Despite the widespread use of these technologies, they suffer from the following drawbacks: therapist assessments rely on personal experience and subjective feelings, making it impossible to objectively and quantitatively measure data during training. This results in a lack of objective basis for judging patients' gait status and low accuracy of assessment results. Existing training equipment operates in a blind state, lacking the ability to monitor and process training effects, particularly lacking the ability to collect dynamic data on the direct interaction between the foot and the ground.

[0004] How to monitor and process data during the training process in order to improve the accuracy of subsequent evaluation results is a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a data processing method, device, and medium for a gait feedback rehabilitation training system, which addresses the problems of therapists' assessments relying on personal experience and subjective feelings, resulting in low accuracy of assessment results, and existing training equipment operating in a blind state, lacking the ability to monitor and process training effects.

[0006] To address the aforementioned technical problems, this application provides a data processing method for a gait feedback rehabilitation training system, comprising: Acquire real-time plantar pressure data from the plantar pressure sensor array and real-time accelerometer data from the triaxial accelerometer; The total plantar pressure and the coordinates of the plantar pressure center are determined based on the plantar pressure data. The movement trajectory of the coordinates of the plantar pressure center is continuously tracked within a preset gait cycle to obtain a gait line. The total plantar pressure curve within the preset gait cycle is generated based on the total plantar pressure. Based on the gait line, the total plantar pressure curve, and the accelerometer data, temporal parameters, mechanical parameters, and symmetry parameters are extracted; wherein, the temporal parameters include the duration of the support phase, the proportion of the support phase, the duration of the swing phase, and the gait frequency; the mechanical parameters include the maximum pressure, the average pressure, and the rate of pressure change; and the symmetry parameters include the gait symmetry index. A report is generated by combining the timing parameters, the mechanical parameters, and the symmetry parameters.

[0007] In one optional embodiment, determining the total plantar pressure and the coordinates of the plantar pressure center based on the plantar pressure data includes: The total pressure on the sole of the foot is calculated according to the first preset formula; The first preset formula is: F_total = Σ(P_i); Where F_total is the total plantar pressure, and P_i is the plantar pressure data of the i-th sensor; The abscissa of the plantar pressure center coordinate is calculated according to the second preset formula; The second preset formula is: X_cop = Σ(P_i X_i) / F_total; Where X_cop is the abscissa of the center coordinate of the plantar pressure, P_i is the plantar pressure data of the i-th sensor, X_i is the abscissa of the i-th sensor, and F_total is the total plantar pressure. The ordinate of the plantar pressure center coordinates is calculated according to the third preset formula; The third preset formula is: Y_cop = Σ(P_i Y_i) / F_total; Where Y_cop is the ordinate of the plantar pressure center coordinate, P_i is the plantar pressure data of the i-th sensor, Y_i is the ordinate of the i-th sensor, and F_total is the total plantar pressure.

[0008] In one optional embodiment, extracting time-series parameters based on the gait curve, the total plantar pressure curve, and the accelerometer data includes: The gait curve, the total plantar pressure curve, and the accelerometer data are combined to divide the preset gait cycle into a support phase and an oscillation phase, and the duration of the support phase and the duration of the oscillation phase are determined. The proportion of the support phase is determined based on the duration of the single-leg support phase and the total gait cycle duration. The first ground contact event and toe-off event are identified based on the gait line, the total plantar pressure curve, and the accelerometer data, and the total number of steps during the training process is determined based on the first ground contact event and toe-off event. The step frequency is calculated based on the total number of steps and the training duration.

[0009] In one alternative embodiment, extracting mechanical parameters includes: The maximum pressure and the rate of pressure change are determined based on the total plantar pressure curve. The average pressure is calculated according to the fourth preset formula; The fourth preset formula is: P_mean = (Σ F_total(t)) / N_samples; Wherein, P_mean is the average pressure, F_total(t) is the total plantar pressure at time t, and N_samples is the number of sampling points within the set time window.

[0010] In one alternative embodiment, extracting the symmetry parameter includes: The gait symmetry index is calculated according to the fifth preset formula; The fifth preset formula is: SI_Time = |(T_left - T_right)| / (0.5) (T_left +T_right)) 100%; Wherein, SI_Time is the gait symmetry index, T_left is the duration of the support phase of the left foot, and T_right is the duration of the support phase of the right foot.

[0011] In an optional embodiment, after extracting timing parameters, mechanical parameters, and symmetry parameters based on the gait curve, the total plantar pressure curve, and the accelerometer data, the method further includes: The plantar pressure data is rendered in real time as a heatmap to show the plantar pressure distribution. The gait line is displayed in real time as a dynamic trajectory line; The total plantar pressure curve is displayed as a waveform diagram; The gait symmetry index is displayed on the dashboard.

[0012] In one optional embodiment, generating a report by combining the timing parameters, the mechanical parameters, and the symmetry parameters includes: The mean, standard deviation, and slope of the time-varying trend of the time-series parameter, the mechanical parameter, and the symmetry parameter are calculated respectively to generate the report; The report also includes trend graphs of the time series parameters, mechanical parameters, and symmetry parameters, comparison graphs of the time series parameters, mechanical parameters, and symmetry parameters with their respective historical data, and an evaluation summary.

[0013] In an optional embodiment, after extracting timing parameters, mechanical parameters, and symmetry parameters based on the gait curve, the total plantar pressure curve, and the accelerometer data, the method further includes: If the gait line of the left foot is located to the left of the preset gait line and the gait line of the right foot is located to the right of the preset gait line, it is marked as an abnormal gait event of foot inversion. If the coordinates of the plantar pressure center are outside the preset plantar center area, it is marked as an abnormal gait event of center of gravity shift; If the gait symmetry index is greater than a preset value, it is marked as an abnormal gait event with asymmetric support time.

[0014] This application also provides a data processing device for a gait feedback rehabilitation training system, including a memory for storing computer programs; A processor is used to implement the data processing method of the gait feedback rehabilitation training system when executing the computer program.

[0015] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the data processing method of the gait feedback rehabilitation training system.

[0016] The data processing method of the gait feedback rehabilitation training system provided in this application uses a plantar pressure sensor array and a triaxial accelerometer to collect plantar pressure data and accelerometer data in real time during the patient's rehabilitation training process. This enables real-time capture of raw motion-related data throughout the training process, overcoming the shortcomings of traditional rehabilitation training methods that lack quantifiable measured data. Based on the collected plantar pressure data, the total plantar pressure and the coordinates of the plantar pressure center are calculated. The positional movement trajectory of the pressure center within the gait cycle is continuously tracked to form a gait line. Simultaneously, a total plantar pressure curve is constructed based on the continuously changing total plantar pressure, intuitively reproducing the mechanical interaction between the patient's foot and the contact surface during training. Based on gait curves, total plantar pressure curves, and accelerometer data, multi-dimensional parameter extraction is performed. From a temporal motion perspective, temporal parameters such as stance phase duration, stance phase percentage, swing phase duration, and cadence are extracted to divide the duration and rhythm of each gait phase. From a foot force perspective, biomechanical parameters such as maximum pressure, average pressure, and pressure change rate are extracted to quantify the actual force exerted and its changes during patient training. Simultaneously, a gait symmetry index is calculated as a symmetry parameter to objectively assess the degree of gait coordination between both limbs. This entire data processing workflow abandons the traditional rehabilitation model that relies on therapists' visual observation, tactile perception, and subjective judgment based on personal experience. It uses real-time collected objective dynamic and motion data as the basis for calculations, and all extracted parameters are derived from measured data, eliminating any bias from subjective judgment. Finally, the timing parameters, mechanical parameters, and symmetry parameters are integrated to generate an assessment report. Quantitative data results replace empirical judgment criteria, and all status information throughout the training process is fully preserved. This enables effective monitoring and standardized processing of training process data. The objectivity of the entire process, from data source and parameter calculation to result output, is guaranteed, significantly improving the accuracy and reliability of subsequent assessments of patient gait status and rehabilitation training effects.

[0017] The beneficial effects and methods of the data processing device and medium for the gait feedback rehabilitation training system provided in this application are as described above. Attached Figure Description

[0018] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a data processing method for a gait feedback rehabilitation training system provided in this application embodiment; Figure 2 A schematic diagram of a host computer software interface provided in an embodiment of this application; Figure 3 A heat map of pressure distribution in the left foot is provided for an embodiment of this application; Figure 4 A heat map of pressure distribution in the right foot is provided for an embodiment of this application; Figure 5 A schematic diagram of a display interface for left foot plantar pressure data and acceleration data provided in an embodiment of this application; Figure 6 A schematic diagram of a display interface for right foot plantar pressure data and acceleration data provided in an embodiment of this application; Figure 7 A schematic diagram of the average gait line of the left foot provided in an embodiment of this application; Figure 8 A schematic diagram of the average gait line of the right foot provided in an embodiment of this application; Figure 9 A schematic diagram of a left foot's dynamic trajectory provided in an embodiment of this application; Figure 10 A schematic diagram of a right foot's dynamic trajectory provided in an embodiment of this application; Figure 11 A schematic diagram of a total pressure curve of the left foot provided in an embodiment of this application; Figure 12 A schematic diagram of a total pressure curve of the right foot plantar surface provided for an embodiment of this application; Figure 13 A left-foot support phase diagram provided in an embodiment of this application; Figure 14 A right foot support phase diagram provided in an embodiment of this application; Figure 15 A left-foot stepping phase diagram provided for an embodiment of this application; Figure 16 A right-foot stepping phase diagram provided for an embodiment of this application; Figure 17 A graph showing the change in left foot acceleration provided in an embodiment of this application; Figure 18 A graph showing the change in right foot acceleration provided in an embodiment of this application; Figure 19 A structural diagram of a data processing device for a gait feedback rehabilitation training system provided in this application embodiment; Figure 20 This is a structural diagram of a data processing device for another gait feedback rehabilitation training system provided in an embodiment of this application. Detailed Implementation

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

[0021] The core of this application is to provide a data processing method, device, and medium for a gait feedback rehabilitation training system, used to monitor and process data during the training process in order to improve the accuracy of subsequent evaluation results.

[0022] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] Figure 1 A flowchart illustrating a data processing method for a gait feedback rehabilitation training system provided in this application embodiment is shown below. Figure 1 As shown, the data processing methods of the gait feedback rehabilitation training system include: S10: Acquire plantar pressure data collected in real time by the plantar pressure sensor array and accelerometer data collected in real time by the triaxial accelerometer.

[0024] S11: Determine the total plantar pressure and the coordinates of the plantar pressure center based on plantar pressure data, continuously track the movement trajectory of the plantar pressure center coordinates within a preset gait cycle to obtain the gait line, and generate the total plantar pressure curve within the preset gait cycle based on the total plantar pressure.

[0025] S12: Extract time-series parameters, mechanical parameters, and symmetry parameters based on gait lines, total plantar pressure curves, and accelerometer data; among which, time-series parameters include support phase duration, support phase percentage, swing phase duration, and gait frequency; mechanical parameters include maximum pressure, average pressure, and pressure change rate; and symmetry parameters include gait symmetry index.

[0026] S13: Generate a report by combining timing parameters, mechanical parameters, and symmetry parameters.

[0027] To better understand this application, a brief introduction to the gait feedback rehabilitation training system is provided below. The gait feedback rehabilitation training system mainly includes a main frame structure, a suspension weight-reduction mechanism, a lower limb drive mechanism, and a control device. Based on these existing devices, this application adds a pair (left / right) flexible pressure insoles that can be embedded in the patient's shoe and a triaxial accelerometer. Each insole integrates a 16-channel plantar pressure sensor array for detecting real-time pressure values ​​in 16 zones of the foot and calculating the total plantar pressure. A triaxial accelerometer is used to detect the acceleration and angle changes of the foot in the X, Y, and Z directions; hereinafter, the acceleration and angle in the X, Y, and Z directions are collectively referred to as accelerometer data. The control device is used to execute the steps in the above data processing method.

[0028] Before step S10, the patient stands on the device pedal with the insole close to the sole of the foot; the device is started, and the lower limb drive mechanism begins to drive the lower limb to perform reciprocating stepping movements; the pressure sensor array synchronously collects real-time plantar pressure data of 16 zones on both feet at high frequency; the triaxial accelerometer synchronously collects the motion state data of the foot in three-dimensional space (accelerometer data).

[0029] In step S10, plantar pressure data collected by each sensor in the plantar pressure sensor array and accelerometer data collected in real time by the triaxial accelerometer are acquired. The accelerometer data includes the acceleration and angle of the foot in the X, Y, and Z directions. Further, the plantar pressure data and accelerometer data can be preprocessed, such as filtered and denoised, to eliminate signal interference.

[0030] In step S11, based on the plantar pressure data collected by sensors in 16 zones, the coordinates of the plantar pressure center at each moment are calculated in real time using a formula. Within a complete preset gait cycle, the movement trajectory of the plantar pressure center coordinates is continuously tracked, dynamically forming a complete path from initial ground contact to toe liftoff, i.e., the gait line. Determining the total plantar pressure and the coordinates of the plantar pressure center based on the plantar pressure data includes: calculating the total plantar pressure according to a first preset formula; the first preset formula is: F_total = Σ(P_i); where F_total is the total plantar pressure, and P_i is the plantar pressure data from the i-th sensor; calculating the abscissa of the plantar pressure center coordinates according to a second preset formula; the second preset formula is: X_cop = Σ(P_i) X_i) / F_total; where X_cop is the x-coordinate of the plantar pressure center coordinate, P_i is the plantar pressure data of the i-th sensor, X_i is the x-coordinate of the i-th sensor, and F_total is the total plantar pressure; the y-coordinate of the plantar pressure center coordinate is calculated according to the third preset formula; the third preset formula is: Y_cop = Σ(P_i) / F_total; Y_i) / F_total; where Y_cop is the ordinate of the plantar pressure center coordinate, P_i is the plantar pressure data of the i-th sensor, Y_i is the ordinate of the i-th sensor, and F_total is the total plantar pressure.

[0031] In step S12, timing parameters are extracted based on gait lines, total plantar pressure curves, and accelerometer data, including: dividing the preset gait cycle into support and swing phases by combining gait lines, total plantar pressure curves, and accelerometer data, and determining the duration of the support and swing phases; determining the proportion of the support phase based on the duration of the single-foot support phase and the total gait cycle duration; identifying the first ground contact event and toe-off event based on gait lines, total plantar pressure curves, and accelerometer data, and determining the total number of steps during the training process based on the first ground contact event and toe-off event; and calculating the step frequency based on the total number of steps and the training duration.

[0032] The preset gait cycle is divided into support and swing phases by combining gait curves, total plantar pressure curves, and accelerometer data. Specifically, when the total plantar pressure in the total plantar pressure curve is greater than or equal to a set value, it is classified as a support phase. When the total plantar pressure in the total plantar pressure curve is less than the set value (e.g., the patient lightly touches the ground or lands on the edge of inversion), the support and swing phases can be defined based on the gait curve. If the gait curve shows that the direction of continuous movement of the plantar pressure center coordinate is from heel to toe (the foot is indeed in contact with the ground and rolling), it is determined to be a support phase. The support phase can also be defined based on accelerometer data. If the vertical acceleration fluctuation amplitude is less than a preset value (no large fluctuations), indicating that the foot has landed stably, it is also determined to be a support phase. If the vertical acceleration fluctuation amplitude is greater than or equal to a preset value (with obvious and violent fluctuations / sudden peak changes, the foot is in a lifted or swinging state), it is determined to be a swing phase. After defining the swing and support phases, the duration of the support phase and the duration of the swing phase can be calculated separately.

[0033] The proportion of the stance phase is determined based on the duration of the single-leg stance phase and the total gait cycle duration. The formula is: Stance_Ratio = T_stance / T_cycle 100%; where Stance_Ratio is the percentage of the support phase, T_stance is the duration of the single-leg support phase, and T_cycle is the total gait cycle duration.

[0034] The first ground contact (FPT) and toe-off events are identified based on gait curves, total plantar pressure (TP) curves, and accelerometer data. The total number of steps during training is determined based on these events. Specifically: the first ground contact event is identified when the vertical acceleration of the foot in the accelerometer data suddenly changes from downward to upward (due to deceleration upon impact), resulting in a steep inflection point in the waveform. Simultaneously, the total plantar pressure in the TPT curve rises rapidly from near zero. The toe-off event is identified when the center of plantar pressure in the gait curve moves to the very tip of the toe area and disappears. Simultaneously, the total plantar pressure in the TPT curve rapidly decreases to near zero. Each step from the first ground contact event to the toe-off event constitutes one step, allowing for the calculation of the total number of steps during the entire training process.

[0035] The formula for calculating cadence based on total steps and training duration is: Cadence = (Number of Steps) / Training Duration; where Cadence is the cadence, Number of Steps is the total number of steps, and Training Duration is the training duration.

[0036] Extract mechanical parameters, including: determining the maximum pressure and pressure change rate based on the total plantar pressure curve; calculating the average pressure according to the fourth preset formula; the fourth preset formula is: P_mean = (Σ F_total(t)) / N_samples; where P_mean is the average pressure, F_total(t) is the total plantar pressure at time t, and N_samples is the number of sampling points within the set time window.

[0037] Extracting symmetry parameters includes: calculating the gait symmetry index according to the fifth preset formula; the fifth preset formula is: SI_Time = |(T_left - T_right)| / (0.5) (T_left + T_right)) 100%; where SI_Time is the gait symmetry index, T_left is the duration of the support phase of the left foot, and T_right is the duration of the support phase of the right foot.

[0038] Based on the above embodiments, after extracting time-series parameters, mechanical parameters, and symmetry parameters from gait lines, total plantar pressure curves, and accelerometer data, this application embodiment further includes: rendering plantar pressure distribution in real time in the form of a heatmap; displaying gait lines in real time as dynamic trajectory lines; displaying total plantar pressure curves as waveform diagrams; and displaying gait symmetry index through an instrument panel.

[0039] The above data is mapped onto the screen in real time using intuitive formats such as heatmaps, gait lines, and total plantar pressure curves. The color depth C_i of the heatmap is proportional to the plantar pressure data P_i: C_i = f(P_i), typically using a linear or non-linear color mapping function f.

[0040] In step S13, a report is generated by combining time-series parameters, mechanical parameters, and symmetry parameters, including: calculating the mean, standard deviation, and slope of the time-series parameters, mechanical parameters, and symmetry parameters respectively to generate a report; wherein the report also includes trend graphs of the time-series parameters, mechanical parameters, and symmetry parameters, comparison graphs of the time-series parameters, mechanical parameters, and symmetry parameters with their respective historical data, and an evaluation summary.

[0041] This application records and stores time-series parameters, mechanical parameters, and symmetry parameters: automatically encrypts and stores all original data and derived parameters for each training session.

[0042] The therapist clicks to generate a report, and the system automatically outputs a standardized, visualized rehabilitation assessment report. The report includes: a trend chart showing the changing trends of key parameters (such as gait symmetry index and maximum pressure) during the current training period; a comparison chart comparing the parameters of this training period with historical parameters, clearly demonstrating rehabilitation progress; and a summary and recommendations: based on data analysis, an objective assessment summary is automatically generated (e.g., the average duration of the affected side's stance phase increased by 15% this week, but the center trajectory of plantar pressure still shows lateral deviation). This supports clinical decision-making; therapists can use this report, rather than solely relying on experience, to accurately judge the rehabilitation effect of the week and scientifically formulate or adjust the training plan for the following week (e.g., the next training session should emphasize reminding the patient to keep their foot flat and reduce weight-bearing support by 5% to increase weight-bearing on the affected side). This application uses sensors to sense gait, extracting temporal, biomechanical, and symmetry parameters, providing feedback through a vivid interface, and ultimately generating a report. This report bridges the gap between equipment training and clinical decision-making, making therapists' decisions data-driven and verifiable. It provides precise data support for therapists to adjust parameters such as weight loss ratio and training speed, thus achieving evidence-based rehabilitation.

[0043] Based on the above embodiments, after extracting timing parameters, mechanical parameters, and symmetry parameters from gait lines, total plantar pressure curves, and accelerometer data in this application embodiment, the method further includes: if the gait line of the left foot is located to the left of a preset gait line and the gait line of the right foot is located to the right of the preset gait line, it is marked as an abnormal gait event of foot inversion; if the coordinates of the plantar pressure center are outside the preset plantar center area, it is marked as an abnormal gait event of center of gravity shift; if the gait symmetry index is greater than a preset value, it is marked as an abnormal gait event of asymmetric support time. By marking abnormal gait events, the repeated reinforcement of incorrect movement patterns is avoided, improving the safety of training and the rehabilitation effect. The preset gait line is typically located in the middle area of ​​the sole.

[0044] This application provides a data processing method for a gait feedback rehabilitation training system, comprising: acquiring plantar pressure data collected in real time by a plantar pressure sensor array and accelerometer data collected in real time by a triaxial accelerometer; determining total plantar pressure and plantar pressure center coordinates based on the plantar pressure data; continuously tracking the movement trajectory of the plantar pressure center coordinates within a preset gait cycle to obtain a gait line; and generating a total plantar pressure curve within the preset gait cycle based on the total plantar pressure; extracting temporal parameters, mechanical parameters, and symmetry parameters based on the gait line, total plantar pressure curve, and accelerometer data; wherein the temporal parameters include the duration of the support phase, the proportion of the support phase, the duration of the swing phase, and the cadence; the mechanical parameters include the maximum pressure, the average pressure, and the rate of pressure change; and the symmetry parameters include the gait symmetry index; and generating a report by combining the temporal parameters, mechanical parameters, and symmetry parameters. This application utilizes a plantar pressure sensor array and a triaxial accelerometer to synchronously collect plantar pressure and accelerometer data in real time during patient rehabilitation training. This enables real-time capture of raw motion-related data throughout the training process, overcoming the shortcomings of traditional rehabilitation training methods that lack quantifiable measured data. Based on the collected plantar pressure data, the total plantar pressure and the coordinates of the plantar pressure center are calculated. The trajectory of the pressure center's movement within the gait cycle is continuously tracked to form a gait curve. Simultaneously, a total plantar pressure curve is constructed based on the continuously changing total plantar pressure, visually recreating the biomechanical interaction between the patient's foot and the contact surface during training. Based on gait curves, total plantar pressure curves, and accelerometer data, multi-dimensional parameter extraction is performed. From a temporal motion perspective, temporal parameters such as stance phase duration, stance phase percentage, swing phase duration, and cadence are extracted to divide the duration and rhythm of each gait phase. From a foot force perspective, biomechanical parameters such as maximum pressure, average pressure, and pressure change rate are extracted to quantify the actual force exerted and its changes during patient training. Simultaneously, a gait symmetry index is calculated as a symmetry parameter to objectively assess the degree of gait coordination between both limbs. This entire data processing workflow abandons the traditional rehabilitation model that relies on therapists' visual observation, tactile perception, and subjective judgment based on personal experience. It uses real-time collected objective dynamic and motion data as the basis for calculations, and all extracted parameters are derived from measured data, eliminating any bias from subjective judgment. Finally, the timing parameters, mechanical parameters, and symmetry parameters are integrated to generate an assessment report. Quantitative data results replace empirical judgment criteria, and all status information of the entire training process is fully preserved. This enables effective monitoring and standardized processing of training process data. The objectivity of the entire process, from data source and parameter calculation to result output, is guaranteed, significantly improving the accuracy and reliability of assessment results related to patient gait status and rehabilitation training effects.

[0045] This application introduces a real-time sensing mechanism for plantar pressure distribution in a gait feedback rehabilitation training system. By integrating a multi-channel plantar pressure sensor array into the insoles of the patient's left and right feet, it collects pressure distribution information from different areas of the sole in real time and simultaneously acquires the force distribution status of both feet. This overcomes the limitations of existing rehabilitation training equipment that relies solely on mechanical parameters or subjective observation, enabling the system to objectively reflect the patient's true plantar force distribution during training and providing a reliable data foundation for gait analysis and training evaluation.

[0046] This application achieves quantitative analysis of key gait parameters based on plantar pressure data: Based on real-time collected plantar pressure data, this application calculates the plantar pressure center trajectory (gait line) and further extracts key gait parameters such as stance phase time, gait frequency, and left-right gait symmetry. This enables a quantitative description of the patient's gait characteristics, transforming the assessment of rehabilitation training effects from qualitative to quantifiable and comparable objective evaluation, which is beneficial for accurately judging rehabilitation progress.

[0047] This application constructs a real-time feedback mechanism based on gait analysis results: the plantar pressure distribution and pressure center trajectory obtained from gait analysis are visualized and fed back to the patient and therapist in real time, guiding the patient to adjust their force application and training posture. This transforms rehabilitation training from traditional open-loop passive training to guided training with immediate feedback, increasing patient participation and enhancing the effectiveness of neuromuscular control training.

[0048] This application enables the identification and alerting of abnormal gait patterns: By analyzing the characteristics of plantar pressure distribution and gait parameters, this application identifies abnormal gait patterns such as foot inversion, insufficient support, and left-right asymmetry, and provides alerts or markings during training. This allows for the timely detection of potential abnormal gait risks during rehabilitation training, preventing the repeated reinforcement of incorrect movement patterns and improving the safety and effectiveness of training.

[0049] This application establishes a rehabilitation assessment and recording mechanism based on plantar pressure data: This application records and organizes plantar pressure data and gait analysis results during training to form standardized rehabilitation assessment data. This facilitates long-term tracking and cross-sectional comparison of the patient's rehabilitation process, provides objective evidence for adjusting treatment plans, and improves the scientific nature and continuity of rehabilitation management.

[0050] To better understand this application, the process of the scheme will be further described below.

[0051] Step 1: Equipment preparation and patient placement.

[0052] The therapist securely positions the patient on the upright bed of the rehabilitation training system and puts on specialized rehabilitation shoes with built-in high-precision pressure insoles. The insoles connect to the system's main control computer wirelessly (e.g., via Bluetooth) or via wired connection. The system performs a self-test to confirm that all sensor signals are being transmitted normally.

[0053] Step 2: Parameter initialization and training start-up.

[0054] Figure 2 This is a schematic diagram of a host computer software interface provided in an embodiment of this application, such as... Figure 2 As shown, the therapist sets initial training parameters on the host computer software interface, such as the target angle of the standing bed (e.g., 70°), the weight-reduction support ratio, the movement speed and amplitude of the lower limb drive motor, treatment time, spasticity rest time, stepping speed, and stepping angle. The device is then started, and the bed rises smoothly to the set angle. The motor then begins to drive the patient's lower limbs in simulated stepping movements according to the preset mode.

[0055] Step 3: Real-time data acquisition and transmission.

[0056] During training, the pressure insoles of both feet begin to work at high speed and continuously: the piezoresistive sensor array collects pressure data from 16 zones on the sole of the foot in real time. The triaxial accelerometer synchronously collects the acceleration and angular changes of the foot in three-dimensional space. All raw data is initially processed and packaged by the microprocessor built into the insole before being transmitted to the host computer in real time.

[0057] Figure 3 A heat map of pressure distribution in the left foot is provided as an embodiment of this application. Figure 4 A thermal map of pressure distribution in the right foot is provided for an embodiment of this application, such as... Figure 3 and Figure 4 As shown, the darker the color, the greater the pressure, and the plus sign (+) indicates the center of pressure on the sole of the foot. Figure 5 This is a schematic diagram of a display interface for left foot plantar pressure data and acceleration data provided in an embodiment of this application. Figure 6 A schematic diagram of a display interface for right foot plantar pressure data and acceleration data provided in an embodiment of this application, as shown below. Figure 5 and Figure 6 As shown, the interface displays the total plantar pressure collected by the plantar pressure sensor array and the acceleration data collected in real time by the triaxial accelerometer.

[0058] Step 4: Calculation and analysis of core gait parameters.

[0059] After receiving the data, the host computer software calls the built-in algorithm module to perform real-time calculations and calculates the following key gait parameters: Plantar pressure center coordinates: The precise location of the pressure center at each moment is calculated based on the total plantar pressure of 16 zones.

[0060] Gait Line: By continuously tracking the movement of the center of pressure of the foot during a complete gait cycle, the complete path from the first heel contact with the ground (starting point) to the toe leaving the ground (ending point) is dynamically drawn. Figure 7 This is a schematic diagram of the average gait line of the left foot provided in an embodiment of this application. Figure 8 This is a schematic diagram of the average gait line of the right foot provided in an embodiment of this application. Figure 9 This is a schematic diagram of a left foot's dynamic trajectory provided in an embodiment of this application. Figure 10 This application provides a schematic diagram of a right foot's dynamic trajectory as an embodiment of the present application; for example... Figure 7 As shown, the gait line in the middle (blue trajectory line) is the average gait line of the left and right gait lines; as Figure 8 As shown, the gait line in the middle (red trajectory line) is the average gait line of the left and right gait lines; as Figure 9 As shown, the gait trajectory corresponding to each step of the left foot is displayed; as... Figure 10 As shown, the gait trajectory corresponding to each step of the right foot is displayed.

[0061] Support Phase Time vs. Pressure Curve: Accurately calculate the duration of the single-leg support phase and plot the curve showing the change in total pressure over time during this period, such as... Figure 11 and Figure 12 As shown, Figure 11 This is a schematic diagram of a total pressure curve of the left foot plantar surface provided in an embodiment of this application. Figure 12This is a schematic diagram of a right plantar total pressure curve provided in an embodiment of this application. Based on the plantar total pressure curve, indicators such as average pressure and peak pressure are obtained. Basic indicators: total steps, cadence; Gait cycle: average cycle, average cycle of the left foot, average cycle of the right foot; Standing phase (support phase) / stepping phase (swing phase): average standing phase of the left foot (seconds), average standing phase of the right foot (seconds), average stepping phase of the left foot (seconds), average stepping phase of the right foot (seconds); Gait line indicators: average total force of the left foot during the standing phase, average total force of the right foot during the standing phase, average maximum force of the left foot during the standing phase, average maximum force of the right foot during the standing phase. The average total force of the left foot during the standing phase refers to the sum of the total plantar pressure (the sum of values ​​from 16 sensors) measured at each moment during the time from the left foot touching the ground to leaving the ground (i.e., the standing phase), and then divided by the duration of the standing phase. The same applies to the right foot. Simply put, it is the average weight-bearing capacity of the left foot during the ground-planting phase. By comparing this value of the left and right feet, the symmetrical weight-bearing capacity of the patient's two legs can be quantified, and the recovery status of the support capacity of the affected side can be judged. Standard deviation indicators: standard deviation of left foot stance line length, standard deviation of left foot stance line width, standard deviation of right foot stance line length, standard deviation of right foot stance line width, standard deviation of left foot starting point X / Y, standard deviation of left foot ending point X / Y, standard deviation of right foot starting point X / Y, standard deviation of right foot ending point X / Y, standard deviation of total force of left foot standing phase, standard deviation of total force of right foot standing phase, standard deviation of left foot stepping phase, standard deviation of right foot stepping phase.

[0062] Step frequency and symmetry analysis: Step frequency is calculated based on stepping rhythm, and gait symmetry is quantified by comparing data such as the support phase duration and peak pressure of the left and right feet. Figure 13 This application provides a left-foot support phase diagram as an embodiment. Figure 14 This application provides a right foot support phase diagram in an embodiment. Figure 15 A left-foot stepping phase diagram is provided as an embodiment of this application. Figure 16 This application provides a right foot stepping phase diagram for an embodiment of the present application; the stepping phase is the swinging phase. Based on Figure 13 and Figure 16 It can calculate the state symmetry index.

[0063] Step 5: Multimodal biofeedback and interaction.

[0064] The calculated parameters are transformed into intuitive feedback information and presented to patients and therapists in real time. Figure 17 This application provides a graph showing the change in left foot acceleration as an embodiment of the present application. Figure 18 A graph illustrating the change in right foot acceleration is provided for an embodiment of this application, such as... Figure 17 and 18As shown, acceleration is displayed as a curve. The main screen can also dynamically display plantar pressure distribution as a heatmap, and the gait line showing the movement of the plantar pressure center in real time as a dynamic trajectory line; real-time pressure changes and symmetry indices are displayed as waveforms and on a digital dashboard.

[0065] Step 6: Closed-loop control and adaptive adjustment.

[0066] Based on real-time analysis results, closed-loop control can be formed to optimize training.

[0067] Step 7: Data recording and report generation.

[0068] All data throughout the training process is automatically recorded and stored by the system. After treatment, a report can be generated with one click to track the patient's long-term recovery progress and provide accurate data for adjusting subsequent treatment plans.

[0069] In the above embodiments, the data processing method of the gait feedback rehabilitation training system has been described in detail. This application also provides embodiments corresponding to the data processing device of the gait feedback rehabilitation training system. It should be noted that this application describes the embodiments of the device part from two perspectives: one is based on the functional module, and the other is based on the hardware.

[0070] Figure 19 A structural diagram of a data processing device for a gait feedback rehabilitation training system provided in this application embodiment is shown below. Figure 19 As shown, the data processing device of the gait feedback rehabilitation training system includes: The acquisition module 10 is used to acquire plantar pressure data collected in real time by the plantar pressure sensor array and accelerometer data collected in real time by the triaxial accelerometer. The calculation module 11 is used to determine the total plantar pressure and the coordinates of the plantar pressure center based on the plantar pressure data, continuously track the movement trajectory of the coordinates of the plantar pressure center within a preset gait cycle to obtain the gait line, and generate the total plantar pressure curve within the preset gait cycle based on the total plantar pressure. Processing module 12 is used to extract time-series parameters, mechanical parameters, and symmetry parameters based on gait lines, total plantar pressure curves, and accelerometer data. Among them, the time-series parameters include the duration of the support phase, the proportion of the support phase, the duration of the swing phase, and the gait frequency; the mechanical parameters include the maximum pressure, the average pressure, and the rate of pressure change; and the symmetry parameters include the gait symmetry index. Module 13 is used to generate a report by combining timing parameters, mechanical parameters, and symmetry parameters.

[0071] Based on the above embodiments, in one optional embodiment, the computing module includes: The first calculation unit is used to calculate the total plantar pressure according to the first preset formula; the first preset formula is: F_total = Σ(P_i); where F_total is the total plantar pressure and P_i is the plantar pressure data of the i-th sensor; The second calculation unit is used to calculate the abscissa of the plantar pressure center coordinate according to the second preset formula; the second preset formula is: X_cop = Σ(P_i X_i) / F_total; where X_cop is the x-coordinate of the plantar pressure center, P_i is the plantar pressure data of the i-th sensor, X_i is the x-coordinate of the i-th sensor, and F_total is the total plantar pressure. The third calculation unit is used to calculate the ordinate of the plantar pressure center coordinates according to the third preset formula; the third preset formula is: Y_cop = Σ(P_i Y_i) / F_total; where Y_cop is the ordinate of the plantar pressure center coordinate, P_i is the plantar pressure data of the i-th sensor, Y_i is the ordinate of the i-th sensor, and F_total is the total plantar pressure.

[0072] Based on the above embodiments, in one optional embodiment, the processing module includes: The division unit is used to divide the support phase and swing phase of the preset gait cycle by combining the gait line, total plantar pressure curve and accelerometer data, and to determine the duration of the support phase and the duration of the swing phase. The first determining unit is used to determine the proportion of the support phase based on the duration of the single-leg support phase and the total gait cycle duration. The recognition unit is used to identify the first ground contact event and toe-off event based on gait lines, total plantar pressure curves, and accelerometer data, and to determine the total number of steps during the training process based on the first ground contact event and toe-off event. The fourth calculation unit is used to calculate the step frequency based on the total number of steps and the training duration.

[0073] Based on the above embodiments, in one optional embodiment, the processing module includes: The second determining unit is used to determine the maximum pressure and the rate of pressure change based on the total plantar pressure curve. The fifth calculation unit is used to calculate the average pressure according to the fourth preset formula; the fourth preset formula is: P_mean =(Σ F_total(t)) / N_samples; where P_mean is the average pressure, F_total(t) is the total pressure of the foot at time t, and N_samples is the number of sampling points within the set time window.

[0074] Based on the above embodiments, in one optional embodiment, the processing module includes: The sixth calculation unit is used to calculate the gait symmetry index according to the fifth preset formula; the fifth preset formula is: SI_Time = |(T_left - T_right)| / (0.5) (T_left + T_right)) 100%; where SI_Time is the gait symmetry index, T_left is the duration of the support phase of the left foot, and T_right is the duration of the support phase of the right foot.

[0075] Based on the above embodiments, in an optional embodiment, it further includes: The first display module is used to render the plantar pressure data in the form of a heat map in real time to show the plantar pressure distribution. The second display module is used to display the gait line in real time as a dynamic trajectory line; The third display module is used to display the total pressure curve of the foot in a waveform diagram. The fourth display module is used to display the gait symmetry index via the dashboard.

[0076] Based on the above embodiments, in one optional embodiment, the generation module includes: The generation unit is used to calculate the mean, standard deviation, and slope of the time-series parameters, mechanical parameters, and symmetry parameters, respectively, to generate a report. The report also includes trend graphs of the time-series parameters, mechanical parameters, and symmetry parameters, comparison graphs of the time-series parameters, mechanical parameters, and symmetry parameters with their respective historical data, and an evaluation summary.

[0077] Based on the above embodiments, in an optional embodiment, it further includes: The first marking unit is used to mark an abnormal gait event of foot inversion if the gait line of the left foot is located to the left of the preset gait line and the gait line of the right foot is located to the right of the preset gait line. The second marking unit is used to mark an abnormal gait event of center of gravity shift if the coordinates of the center of pressure on the sole of the foot are located outside the preset center area of ​​the sole of the foot. The third marking unit is used to mark an abnormal gait event with asymmetric support time if the gait symmetry index is greater than a preset value.

[0078] Since the embodiments of the apparatus and the embodiments of the method correspond to each other, please refer to the description of the embodiments of the method for the embodiments of the apparatus, which will not be repeated here.

[0079] Figure 20 A structural diagram of the data processing device for another gait feedback rehabilitation training system provided in this application embodiment is shown below. Figure 20As shown, the data processing device of the gait feedback rehabilitation training system includes: a memory 20 for storing computer programs; The processor 21 is used to execute a computer program to implement the steps of the data processing method of the gait feedback rehabilitation training system as described in the above embodiment.

[0080] The data processing device for the gait feedback rehabilitation training system provided in this embodiment may include, but is not limited to, smartphones, tablets, laptops, or desktop computers.

[0081] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an Artificial Intelligence (AI) processor, which handles computational operations related to machine learning.

[0082] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 20 is used to store at least the following computer program 201, which, after being loaded and executed by the processor 21, is capable of implementing the relevant steps of the data processing method of the gait feedback rehabilitation training system disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, and the storage method may be temporary or permanent storage. The operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, plantar pressure data, accelerometer data, etc.

[0083] In some embodiments, the data processing device of the gait feedback rehabilitation training system may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0084] Those skilled in the art will understand that Figure 20 The structure shown does not constitute a limitation on the data processing device of the gait feedback rehabilitation training system and may include more or fewer components than shown.

[0085] This application provides a data processing device for a gait feedback rehabilitation training system, including a memory and a processor. When the processor executes a program stored in the memory, it can perform the following methods: acquiring plantar pressure data collected in real time by a plantar pressure sensor array and accelerometer data collected in real time by a triaxial accelerometer; determining the total plantar pressure and the coordinates of the plantar pressure center based on the plantar pressure data; continuously tracking the movement trajectory of the plantar pressure center coordinates within a preset gait cycle to obtain a gait line; and generating a total plantar pressure curve within the preset gait cycle based on the total plantar pressure; extracting temporal parameters, mechanical parameters, and symmetry parameters based on the gait line, the total plantar pressure curve, and the accelerometer data; wherein the temporal parameters include the duration of the support phase, the proportion of the support phase, the duration of the swing phase, and the cadence; the mechanical parameters include the maximum pressure, the average pressure, and the rate of pressure change; and the symmetry parameters include the gait symmetry index; and generating a report by combining the temporal parameters, mechanical parameters, and symmetry parameters.

[0086] Finally, this application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the data processing method of the gait feedback rehabilitation training system in the above-described method embodiment.

[0087] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0088] The foregoing provides a detailed description of the data processing method, apparatus, and medium for a gait feedback rehabilitation training system provided in this application. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0089] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A data processing method for a gait feedback rehabilitation training system, characterized in that, include: Acquire real-time plantar pressure data from the plantar pressure sensor array and real-time accelerometer data from the triaxial accelerometer; The total plantar pressure and the coordinates of the plantar pressure center are determined based on the plantar pressure data. The movement trajectory of the coordinates of the plantar pressure center is continuously tracked within a preset gait cycle to obtain a gait line. The total plantar pressure curve within the preset gait cycle is generated based on the total plantar pressure. Based on the gait line, the total plantar pressure curve, and the accelerometer data, temporal parameters, mechanical parameters, and symmetry parameters are extracted; wherein, the temporal parameters include the duration of the support phase, the proportion of the support phase, the duration of the swing phase, and the gait frequency; the mechanical parameters include the maximum pressure, the average pressure, and the rate of pressure change; and the symmetry parameters include the gait symmetry index. A report is generated by combining the timing parameters, the mechanical parameters, and the symmetry parameters.

2. The data processing method for the gait feedback rehabilitation training system according to claim 1, characterized in that, Determining the total plantar pressure and the coordinates of the plantar pressure center based on the plantar pressure data includes: The total pressure on the sole of the foot is calculated according to the first preset formula; The first preset formula is: F_total = Σ(P_i); Where F_total is the total plantar pressure, and P_i is the plantar pressure data of the i-th sensor; The abscissa of the plantar pressure center coordinate is calculated according to the second preset formula; The second preset formula is: X_cop = Σ(P_i X_i) / F_total; Where X_cop is the abscissa of the center coordinate of the plantar pressure, P_i is the plantar pressure data of the i-th sensor, X_i is the abscissa of the i-th sensor, and F_total is the total plantar pressure. The ordinate of the plantar pressure center coordinates is calculated according to the third preset formula; The third preset formula is: Y_cop = Σ(P_i Y_i) / F_total; Where Y_cop is the ordinate of the plantar pressure center coordinate, P_i is the plantar pressure data of the i-th sensor, Y_i is the ordinate of the i-th sensor, and F_total is the total plantar pressure.

3. The data processing method for the gait feedback rehabilitation training system according to claim 1, characterized in that, Based on the gait curve, the total plantar pressure curve, and the accelerometer data, time-series parameters are extracted, including: The gait curve, the total plantar pressure curve, and the accelerometer data are combined to divide the preset gait cycle into a support phase and an oscillation phase, and the duration of the support phase and the duration of the oscillation phase are determined. The proportion of the support phase is determined based on the duration of the single-leg support phase and the total gait cycle duration. The first ground contact event and toe-off event are identified based on the gait line, the total plantar pressure curve, and the accelerometer data, and the total number of steps during the training process is determined based on the first ground contact event and toe-off event. The step frequency is calculated based on the total number of steps and the training duration.

4. The data processing method for the gait feedback rehabilitation training system according to claim 1, characterized in that, Extract mechanical parameters, including: The maximum pressure and the rate of pressure change are determined based on the total plantar pressure curve. The average pressure is calculated according to the fourth preset formula; The fourth preset formula is: P_mean = (Σ F_total(t)) / N_samples; Wherein, P_mean is the average pressure, F_total(t) is the total plantar pressure at time t, and N_samples is the number of sampling points within the set time window.

5. The data processing method for the gait feedback rehabilitation training system according to claim 3, characterized in that, Extract symmetry parameters, including: The gait symmetry index is calculated according to the fifth preset formula; The fifth preset formula is: SI_Time = |(T_left - T_right)| / (0.5) (T_left + T_right)) 100%; Wherein, SI_Time is the gait symmetry index, T_left is the duration of the support phase of the left foot, and T_right is the duration of the support phase of the right foot.

6. The data processing method for the gait feedback rehabilitation training system according to claim 1, characterized in that, After extracting time-series parameters, mechanical parameters, and symmetry parameters based on the gait curve, the total plantar pressure curve, and the accelerometer data, the method further includes: The plantar pressure data is rendered in real time as a heatmap to show the plantar pressure distribution. The gait line is displayed in real time as a dynamic trajectory line; The total plantar pressure curve is displayed as a waveform diagram; The gait symmetry index is displayed on the dashboard.

7. The data processing method for the gait feedback rehabilitation training system according to claim 1, characterized in that, A report is generated by combining the time parameters, the mechanical parameters, and the symmetry parameters, including: The mean, standard deviation, and slope of the time-varying trend of the time-series parameter, the mechanical parameter, and the symmetry parameter are calculated respectively to generate the report; The report also includes trend graphs of the time series parameters, mechanical parameters, and symmetry parameters, comparison graphs of the time series parameters, mechanical parameters, and symmetry parameters with their respective historical data, and an evaluation summary.

8. The data processing method for the gait feedback rehabilitation training system according to claim 5, characterized in that, After extracting time-series parameters, mechanical parameters, and symmetry parameters based on the gait curve, the total plantar pressure curve, and the accelerometer data, the method further includes: If the gait line of the left foot is located to the left of the preset gait line and the gait line of the right foot is located to the right of the preset gait line, it is marked as an abnormal gait event of foot inversion. If the coordinates of the plantar pressure center are outside the preset plantar center area, it is marked as an abnormal gait event of center of gravity shift; If the gait symmetry index is greater than a preset value, it is marked as an abnormal gait event with asymmetric support time.

9. A data processing device for a gait feedback rehabilitation training system, characterized in that, Includes memory used to store computer programs; A processor, configured to execute the computer program to implement the data processing method of the gait feedback rehabilitation training system as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the data processing method of the gait feedback rehabilitation training system as described in any one of claims 1 to 8.

Images