Active stroke rehabilitation auxiliary training system

Abstract

The invention belongs to the technical field of rehabilitation training, and particularly relates to an active stroke rehabilitation auxiliary training system which generates a personalized training base line through clinical evaluation data of a patient and guides the patient to cooperatively execute training actions through rehabilitation equipment according to the training base line. Training execution efficiency scores, patient active motion features and equipment auxiliary performance features are analyzed in real time, and rehabilitation equipment auxiliary strength and training task difficulty are dynamically adjusted in the training duration according to the double-feature real-time interaction state and the synchronous training execution efficiency scores; finally, the rehabilitation ability state of the patient is updated according to the multi-dimensional time sequence characteristics of the whole single training process, and a baseline correction instruction of the next training period is output based on the updated rehabilitation ability state, so that the limitation of singly paying attention to patient actions in the past is broken, and the boundary of patient independent effort and equipment assistance in the rehabilitation process is clearly distinguished; and the dynamic adaptability and accuracy of stroke rehabilitation training are effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of rehabilitation training, and in particular relates to an active stroke rehabilitation auxiliary training system. Background Art

[0002] Post-stroke motor dysfunction severely impacts patients' quality of life. Clinical studies have shown that active rehabilitation training can significantly improve functional recovery through neural remodeling. However, in traditional rehabilitation training, the patient's level of voluntary effort is difficult to objectively quantify, resulting in inadequate adaptation of training programs to the patient's actual recovery status. Therefore, incorporating active assessment into the training process is crucial for accurately guiding rehabilitation and improving training efficiency.

[0003] Several stroke rehabilitation training programs that integrate initiative assessment have been proposed in the prior art. For example, Chinese Patent Publication No. CN111161835A describes a method for estimating patient initiative in robot-assisted rehabilitation training. This method calculates the baseline work done by the robot in a single motion state and compares it with the total work done by the human-machine system when the patient participates in training. This method infers the patient's real-time work to assess initiative, avoiding complex dynamic modeling and making it more suitable for clinical application.

[0004] Another Chinese patent, CN120340759A, is a method and device for preventing slackness in rehabilitation training based on AAN challenge adjustment. It determines the challenge level based on the main human power and the driven force of the previous human-machine hybrid system, constrains the auxiliary force range through a virtual force field, and generates non-model robust auxiliary force in combination with time delay estimation. It reasonably provides machine assistance to prevent slackness in training, encourages active participation, and improves the effect of rehabilitation training.

[0005] Although existing technologies attempt to solve the problem of initiative assessment, they still have the following limitations: 1. Existing technologies already have a variety of ways to assess the initiative of patients in rehabilitation training, such as fuzzy algorithms, work volume estimation, trajectory deviation detection, etc., but they all focus on the patient's unilateral movement output characteristics, and do not remove the interference of the auxiliary effect of rehabilitation equipment on the data, resulting in the evaluation results being unable to accurately distinguish the boundary between the patient's independent efforts and equipment assistance, and the evaluation accuracy is significantly limited.

[0006] 2. Existing technologies often refer to the surface effects of training execution to dynamically implement training control, ignoring the dual interactive factors of patient initiative and equipment assistance in the effects of training execution movements. In addition, although there are existing solutions that focus on adjusting the auxiliary force of equipment according to the patient's active effort status, such as increasing or decreasing the virtual auxiliary force in the above-mentioned solution, it does not coordinately optimize the difficulty parameters of the training task. When the patient's muscle strength increases but the motor control ability does not improve, reducing the auxiliary force but maintaining high precision requirements will increase the sense of frustration of training and lead to insufficient training adaptability. Summary of the Invention

[0007] In order to overcome the shortcomings of the background technology, the embodiments of the present invention provide an active stroke rehabilitation auxiliary training system, which can effectively solve the problems involved in the above background technology.

[0008] The purpose of the present invention can be achieved through the following technical solutions: An active stroke rehabilitation auxiliary training system includes: a baseline generation module, a training execution module, a dynamic adjustment module and an iterative optimization module.

[0009] The baseline generation module is connected to the training execution module, the training execution module is connected to the dynamic adjustment module, and the dynamic adjustment module is connected to the iterative optimization module.

[0010] The baseline generation module generates a personalized training baseline based on the patient's clinical assessment data. The training baseline includes the training goals and training plan for the current training cycle.

[0011] The training execution module guides patients to perform training movements collaboratively through rehabilitation equipment based on the training baseline, and analyzes the training execution efficiency score, patient active movement characteristics, and equipment-assisted performance characteristics in real time.

[0012] The dynamic adjustment module dynamically adjusts the auxiliary strength of the rehabilitation equipment and the difficulty of the training task during the training period based on the real-time interaction status of the active movement characteristics and the auxiliary performance characteristics, combined with the training execution efficiency score, in the direction of continuously improving the patient's autonomous movement contribution.

[0013] The iterative optimization module updates the patient's rehabilitation ability status according to the multi-dimensional time series characteristics of the entire single training process, and outputs the baseline correction instructions for the next training cycle based on the updated rehabilitation ability status.

[0014] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention simultaneously analyzes the patient's active movement characteristics and equipment-assisted performance characteristics based on the patient's training performance, realizes the comprehensive capture and linkage analysis of key information in the rehabilitation process, breaks the previous limitation of focusing solely on the patient's movements, and thus clearly distinguishes the boundary between the patient's independent efforts and equipment assistance in the rehabilitation process, providing an accurate basis for dynamic adjustment.

[0015] (2) The present invention uses the dual-feature contribution ratio to clearly reflect the dynamic balance between the patient's active movement and equipment assistance, and the efficiency score to quantify the quality of the training effect. Based on the combination strategy of the dual-feature contribution ratio and the efficiency score, the present invention accurately captures the patient's ability changes and actual needs at different training stages, thereby adjusting the assistance strength and task difficulty in a targeted manner, and improving the dynamic adaptability and scientific nature of the rehabilitation training process.

[0016] (3) The present invention updates the patient's rehabilitation ability status through the full-process time series characteristics and directly outputs the baseline correction instructions for the next cycle, realizing clinical-level adaptive training without human intervention, solving the problem of disconnection between evaluation and execution in existing technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0018] Figure 1 Schematic diagram of module connection of the present invention.

[0019] Figure 2 This is a schematic diagram of the analytical logic of the patient's active movement characteristics in the training execution module of the present invention.

[0020] Figure 3 Schematic diagram of the parsing logic of the device-assisted performance characteristics in the training execution module of the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] Reference Figure 1 As shown, the present invention provides an active stroke rehabilitation auxiliary training system, including: a baseline generation module, a training execution module, a dynamic adjustment module and an iterative optimization module.

[0023] The baseline generation module is connected to the training execution module, the training execution module is connected to the dynamic adjustment module, and the dynamic adjustment module is connected to the iterative optimization module.

[0024] The baseline generation module generates a personalized training baseline based on the patient's clinical assessment data, and the training baseline includes the training goals and training plan of the current training cycle.

[0025] In a preferred embodiment of the present invention, the training baseline generation process includes: extracting stroke pathology parameters from clinical assessment data, and calibrating the severity level of the patient's symptoms against a preset stroke symptom assessment standard.

[0026] It should be noted that the construction of the above-mentioned preset stroke symptom assessment standards is based on the consensus of evidence-based medicine, and its data comes from the integrated analysis of neurological impairment scales, medical imaging parameters, and physiological and biochemical indicators. The standards contain two core contents: one is the numerical interval division standard for each indicator of stroke pathological parameters, which clarifies the quantitative boundaries of different indicators in pathological assessment; the other is the correspondence between the severity level of each stroke symptom and the numerical interval of the pathological parameter indicator, that is, the numerical range that each indicator must meet to correspond to a specific severity level.

[0027] The calibration of the severity level of the above-mentioned patients' symptoms requires retrieving the actual numerical range of each indicator of their stroke pathological parameters, and taking the highest severity level reached as the final calibration result.

[0028] The motor function parameters of the clinical assessment data are compared with the preset clinical norms of healthy people of the same age group as the patient to identify the patient's functional defects.

[0029] It should be noted that the above-mentioned preset clinical norms are the statistical reference ranges for healthy people of the same age group in standardized functional tests, which can be obtained based on relevant medical standards and guidelines for stroke rehabilitation, including the range of joint motion, movement completion time and peak muscle strength in motor function parameters.

[0030] The process of identifying the patient's functional impairment includes the following steps: matching the patient's age with a normative data set of the corresponding age group, wherein the normative data set contains the mean and standard deviation of each motor function index of a healthy population.

[0031] A standardized deviation value calculation is performed on each functional indicator in the motor function parameters, specifically, the actual measured value of the indicator is subtracted from the mean of the functional norm, and the difference is further ratioed with the norm standard deviation.

[0032] If the standardized deviation value of a certain functional indicator is greater than a preset value, the function is identified as a functional defect item.

[0033] According to the severity level of the disease and the disease recovery stage of the current training cycle, the training target of the functional deficiency item is determined through stage adaptation rules.

[0034] It should be noted that the above-mentioned disease recovery stage includes the acute phase, the recovery phase, and the sequelae phase. The acute phase can be exemplarily defined as within 2 weeks after the onset of the disease, the recovery phase is defined as the 2nd to 12th week after the onset of the disease, and the sequelae phase is defined as more than 12 weeks after the onset of the disease.

[0035] The stage adaptation rules are as follows: When the patient is in the acute phase: if the severity level is severe, the goal is to suppress abnormal movement patterns; if the severity level is moderate or mild: the goal is to control symptom progression and suppress abnormal movement patterns.

[0036] When the patient is in the recovery stage: if the severity level is severe, the goal is to establish basic joint mobility; if the severity level is moderate, the goal is to improve the range of autonomous movement; if the severity level is mild, the goal is to restore functional coordination.

[0037] When the patient is in the sequelae stage: if the severity level is severe, the goal is to achieve compensation for basic life functions; if the severity level is moderate, the goal is to establish compensation for fine motor functions; if the severity level is mild, the goal is to optimize movement efficiency and adaptive compensation.

[0038] The training plan bound to the training goal in the preset clinical rule library is called, and the training plan includes the following elements: I. The type of rehabilitation equipment and its initial parameter configuration.

[0039] II. The standard path trajectory of the training action and its permitted trajectory deviation distance limit.

[0040] III. The locations of key path nodes of training actions and their standard pose tolerance limits.

[0041] IV. Requirements for the execution cycle of complete training actions and the transition window time limit of adjacent critical path nodes.

[0042] The training execution module guides the patient to perform training movements in coordination with the rehabilitation equipment with reference to the training baseline, and analyzes the training execution efficiency score, the patient's active movement characteristics and the equipment-assisted performance characteristics in real time.

[0043] In a preferred embodiment of the present invention, the training execution effectiveness scoring and analysis process includes: real-time collection of limb kinematic data of the patient performing the training movements.

[0044] When the following conditions are met at the same time, the full score value of the execution efficiency of the current training action is given: a) the real-time motion trajectory of the patient's limb end is spatially aligned with the standard path trajectory, and the action trajectory execution deviation is quantified by dynamic time warping distance, and the deviation meets the allowable trajectory deviation distance limit.

[0045] It should be noted that the above dynamic time warping processing is intended to match the two spatially aligned trajectories in unequal time series, and calculate the minimum warping path distance through the standard dynamic time warping distance formula as the execution deviation.

[0046] b) The deviation of the actual posture of the patient's limb end when it reaches the critical path node relative to the standard posture of the node is within the tolerance limit.

[0047] It should be noted that the quantification process of the deviation of the above-mentioned actual posture relative to the standard posture of the node is as follows: the standard posture of the node is imported into professional drawing software as the bottom layer, and then the actual posture is imported as the second layer. The spatial position relationship between each unit point of the actual posture and the corresponding point of the standard posture is located through layer comparison, and the closest distance of each unit point relative to the standard posture is retrieved. The posture distance deviation is obtained by taking the average, and the angle difference between the actual posture and the standard posture at the corresponding joints is simultaneously extracted, and the maximum value is taken as the posture angle deviation.

[0048] c) The total execution time of the complete training action meets the execution cycle requirements.

[0049] d) The arrival time interval of adjacent key nodes meets the transition window time limit.

[0050] If there are any unsatisfied conditions, the full score of the performance is deducted accordingly according to the type of unsatisfied condition to generate a training execution performance score.

[0051] It should be noted that when the full score of efficiency is deducted accordingly based on the type of unmet conditions, the deduction score is determined by the weight of the impact of each condition on the training execution efficiency, specifically the product of the impact weight and the full score of efficiency.

[0052] The weight distribution of the impact of various conditions on training execution efficiency can be preset based on industry experience, or obtained by deduction through a limited number of experimental data. For example, first collect the manual pre-evaluation scores of training execution efficiency when different types of conditions are missing, quantify the correlation coefficients of the impact of different types of missing conditions on training execution efficiency, and then determine the contribution of various conditions through regression analysis or logistic regression analysis. Finally, normalize the contribution and convert it into impact weight, where the total impact weight is required to be 1.

[0053] Reference Figure 2 As shown, in a preferred embodiment of the present invention, the patient active movement feature analysis process includes: capturing the original electromyographic signals of the patient's muscle groups through a surface electrode array, and generating an electromyographic amplitude envelope through rectification and filtering.

[0054] The motion trajectory and speed of the patient's limb extremities are collected synchronously, and the kinetic energy of the limb extremities is calculated based on this.

[0055] It should be noted that the above-mentioned calculation process of kinetic energy of limb extremity motion is: obtaining the limb weight through the gravity sensor bound to the patient's limb, combining it with the limb extremity motion speed, and substituting them into the existing standard kinetic energy formula to obtain the kinetic energy of limb extremity motion.

[0056] The integral result of the electromyographic amplitude envelope is analyzed in time domain correlation with the kinetic energy of the limb end movement, and an autonomous drive contribution index representing the degree of coupling between muscle activation and limb movement is output.

[0057] It should be noted that the above-mentioned time domain correlation analysis can be exemplified as a Pearson correlation coefficient analysis of the integral result of the myoelectric amplitude envelope and the rate of change of kinetic energy of the limb end movement.

[0058] Based on the phase synchronization detection of multiple muscle groups, the co-activation period is identified, and the joint angle data are integrated within the co-activation period to construct a theoretical physiological trajectory. According to the difference between the patient's limb end motion trajectory and the theoretical physiological trajectory, the autonomous drive contribution index is calibrated to output the patient's active motion characteristics.

[0059] It should be noted that the above-mentioned phase synchronization detection is to perform Hilbert transform on the electromyographic signal of each muscle group to obtain the instantaneous phase and quantify the variance of the phase difference between muscle groups. When the variance is lower than the preset coordination standard variance threshold, it indicates a state of coordinated activation of multiple muscle groups.

[0060] It should also be noted that the above-mentioned calibration process of the autonomous drive contribution index based on the difference between the patient's limb end motion trajectory and the theoretical physiological trajectory is as follows: the patient's limb end motion trajectory and the theoretical physiological trajectory are converted into coordinate point sets, and the distance from each trajectory point in the limb end motion trajectory coordinate point set to the nearest trajectory point in the theoretical physiological trajectory coordinate point set is obtained, and the maximum value of the distance is recorded as the one-way reference distance 1. Similarly, the distance from each trajectory point in the theoretical physiological trajectory coordinate point set to the nearest trajectory point in the limb end motion trajectory coordinate point set is obtained, and the maximum value of the distance is recorded as the one-way reference distance 2. The maximum value of the two one-way reference distances is taken as the Hausdorff distance of the two trajectories.

[0061] If the Hausdorff distance is less than the first preset distance, the autonomous driving contribution index is calibrated to increase its value according to a reduction ratio of the Hausdorff distance relative to the first preset distance.

[0062] If the Hausdorff distance is greater than the second preset distance, the autonomous driving contribution index is calibrated to reduce its value according to the excess ratio of the Hausdorff distance relative to the second preset distance.

[0063] If the Hausdorff distance is within the closed interval defined by the first and second preset distances, the autonomous driving contribution indicator is only marked without being calibrated.

[0064] The first preset distance is the critical distance that represents the ideal degree of trajectory matching. When the calculated Hausdorff distance is less than the first preset distance, it indicates that the degree of matching between the patient's limb end motion trajectory and the theoretical physiological trajectory is high, which has a positive promoting effect on the autonomous driving process, that is, it produces a positive contribution.

[0065] The second preset distance is the critical distance that indicates that the trajectory deviation is at the upper limit of the acceptable range. When the Hausdorff distance is greater than the second preset distance, it indicates that the deviation between the patient's limb end motion trajectory and the theoretical physiological trajectory is too large, which has an adverse effect on the autonomous driving process, that is, it produces a reverse contribution.

[0066] The first preset distance is smaller than the second preset distance, and both are obtained through calibration before system development after a large number of experimental tests, data statistics and analysis, and can objectively reflect the correlation between the degree of trajectory matching and the contribution of autonomous driving.

[0067] Reference Figure 3 As shown, in a preferred embodiment of the present invention, the device-assisted performance feature analysis process includes: real-time acquisition of the joint space auxiliary torque vector output by the rehabilitation device through an embedded torque sensor, and calculation of the instantaneous auxiliary power based on the motor current and rotor angular velocity of the rehabilitation device.

[0068] The target joint torque is derived based on the allowable trajectory deviation distance limit of the training action standard path trajectory in the training plan, and the vector norm ratio of the auxiliary torque collected in real time to the target joint torque is used as the auxiliary force ratio of the rehabilitation equipment.

[0069] It should be noted that the above-mentioned target joint torque derivation process is as follows: decomposing the allowable trajectory deviation distance limit into three-dimensional Cartesian space to generate a position deviation vector, combining the mapping relationship between the auxiliary torque in the joint space of the rehabilitation equipment and the position deviation in the task space to construct the task space stiffness matrix, and introducing the Jacobian matrix to convert the torque requirement obtained in the task space based on the position deviation vector and the stiffness matrix to the joint space to generate the target joint torque.

[0070] The corresponding relationship between the assist torque energy consumption and the patient trajectory execution deviation is established to determine the power density required for the device to maintain the trajectory.

[0071] It should be noted that the above power density is specifically the result of a ratio operation with the cumulative energy consumption of the assisting torque as the numerator and the integral of the patient trajectory execution deviation over time as the denominator.

[0072] The auxiliary force ratio is subjected to an associated processing based on the power density, and an auxiliary performance feature of the output device is output.

[0073] It should be noted that the above-mentioned association processing process can be exemplified as a linear association correction, such as superimposing the power density converted by the preset power density influence coefficient on the auxiliary force ratio, or exemplified by a piecewise nonlinear association correction. Its logical principle is consistent with the logical principle of calibrating the autonomous drive contribution index based on the difference between the patient's limb end motion trajectory and the theoretical physiological trajectory, that is, judging the positive and negative influence of the numerical value of the power density on the auxiliary force ratio, which will not be repeated here.

[0074] The embodiments of the present invention simultaneously analyze the patient's active movement characteristics and equipment-assisted performance characteristics based on the patient's training performance, realize the comprehensive capture and linkage analysis of key information in the rehabilitation process, break the previous limitation of focusing solely on the patient's movements, and thus clearly distinguish the boundary between the patient's independent efforts and equipment assistance in the rehabilitation process, providing an accurate basis for dynamic adjustment.

[0075] The dynamic adjustment module dynamically adjusts the auxiliary strength of the rehabilitation equipment and the difficulty of the training task during the training period based on the real-time interaction status of the active movement characteristics and the auxiliary performance characteristics, combined with the training execution efficiency score, and the adjustment direction is to continuously improve the patient's autonomous movement contribution.

[0076] In a preferred embodiment of the present invention, the dynamic adjustment process of the auxiliary strength and task difficulty of the rehabilitation equipment includes: during the training period, periodically monitoring the training execution efficiency score, the patient's active movement characteristics and the equipment auxiliary performance characteristics according to the preset adjustment response time points, and recording the time period defined by adjacent adjustment response time points as the monitoring period.

[0077] According to the expected synergy ratio range defined by the clinical rehabilitation strategy, the relative contribution relationship between the patient's active movement characteristics and the device-assisted performance characteristics during the monitoring period is determined.

[0078] Based on the combination of the relative contribution relationship and the training execution efficiency standard status, an adjustment strategy is executed, and the adjustment strategy includes: based on the training execution efficiency standard status, if the patient's active movement characteristics dominate, the task difficulty is increased; if the equipment-assisted performance characteristics dominate, the assistance strength is reduced.

[0079] Based on the fact that the training execution efficiency does not meet the standard, if the patient's active movement characteristics are dominant, the task difficulty is reduced; if the equipment-assisted performance characteristics are dominant, the assistance strength is increased.

[0080] In a preferred embodiment of the present invention, the relative contribution relationship between the patient's active motion characteristics and the device-assisted performance characteristics is determined by normalizing the patient's active motion characteristics and the device-assisted performance characteristics during the monitoring period and calculating the feature contribution ratio.

[0081] It should be noted that the above-mentioned feature contribution ratio distance refers to the ratio of the patient's active motion feature to the device-assisted performance feature after normalization.

[0082] If the feature contribution ratio is within the expected synergy ratio range, it is determined that the patient actively and the device assist in achieving the expected synergy state, and there is no dominant object.

[0083] If the feature contribution ratio exceeds the expected synergy ratio range and the patient's active motion feature is significantly higher than the device-assisted performance feature, the patient's active motion feature is determined to be dominant.

[0084] If the feature contribution ratio exceeds the expected synergy ratio range and the device-assisted performance feature is significantly higher than the patient's active movement feature, the device-assisted performance feature is determined to be dominant.

[0085] It should be noted that the trigger condition for the above-mentioned significantly higher value is that the absolute difference between the two features is greater than a preset reasonable value.

[0086] In a preferred embodiment of the present invention, the adjustment strategy execution process further includes: the auxiliary force adjustment is achieved by updating the initial parameter configuration of the rehabilitation device, changing the joint space auxiliary torque parameters and the motor operation parameters.

[0087] The task difficulty adjustment is achieved by updating at least one of the following elements in the training plan, including the allowable trajectory deviation distance limit, the standard posture tolerance limit of the critical path node, the execution cycle requirement of the complete training action, and the transition window time limit of adjacent critical path nodes.

[0088] The adjustment amplitude is positively correlated with the degree to which the characteristic contribution ratio deviates from the expected synergy ratio range.

[0089] The embodiment of the present invention uses the dual-feature contribution ratio to clearly reflect the dynamic balance relationship between the patient's active movement and equipment assistance, and the efficiency score to quantify the quality of the training effect. Based on the combination strategy of the dual-feature contribution ratio and the efficiency score, it accurately captures the patient's ability changes and actual needs at different training stages, thereby adjusting the assistance strength and task difficulty in a targeted manner, and improving the dynamic adaptability and scientific nature of the rehabilitation training process.

[0090] The iterative optimization module updates the patient's rehabilitation ability status according to the multi-dimensional time series characteristics of the entire single training process, and outputs the baseline correction instruction for the next training cycle based on the updated rehabilitation ability status.

[0091] In a preferred embodiment of the present invention, the patient rehabilitation ability status update process includes: extracting a training execution efficiency score sequence of the entire single training session, introducing a time decay factor for weighted fusion to output a functional progress score benchmark.

[0092] The fluctuation variance of the patient's active movement characteristics during a single training session and the evolution trend direction of the device-assisted performance characteristics are obtained respectively.

[0093] It should be noted that the evolution trend direction of the above-mentioned device-assisted performance characteristics depends on the positive or negative direction of the slope value of the characteristic linear fitting time series curve. If the slope is positive, it means that the rehabilitation device-assisted performance characteristics show a positive change trend. If the slope value is negative, it means that the rehabilitation device-assisted performance characteristics show a negative change trend.

[0094] When the functional progress score benchmark reaches the preset clinical advancement standard, the fluctuation degree of the patient's active movement characteristics meets the preset stability requirements, and the auxiliary performance characteristics of the rehabilitation equipment show a negative change trend, the patient's rehabilitation ability status is updated to the pre-advancement status.

[0095] When the functional progress score benchmark is lower than the preset clinical maintenance standard, the fluctuation degree of the patient's active movement characteristics exceeds the preset sensitivity requirement, and the auxiliary performance characteristics of the rehabilitation equipment show a positive change trend, the patient's rehabilitation ability status is updated to the ability degradation warning state.

[0096] When the functional progress score benchmark is between the preset clinical advancement standard and the maintenance standard, and the fluctuation degree of the patient's active movement characteristics is between the preset stability requirement and the sensitivity requirement, the patient's rehabilitation ability status is updated to the maintenance training status.

[0097] In a preferred embodiment of the present invention, the baseline correction instruction output process for the next training cycle includes: when the patient's rehabilitation ability status is in an advanced preparation state, selecting a movement function that meets the advanced requirements of the current rehabilitation stage from the functional defect items as a new training target, and feeding it back to the next training cycle.

[0098] When the ability degradation warning state is reached, the current training goal is broken down into low-level sub-action goals and fed back to the next training cycle.

[0099] When the training state is maintained, the current training baseline parameters are kept unchanged and applied to the next training cycle.

[0100] The embodiment of the present invention updates the patient's rehabilitation ability status through the full-process time series characteristics and directly outputs the baseline correction instructions for the next cycle, realizing clinical-level adaptive training without human intervention, and solving the problem of disconnection between evaluation and execution in existing technologies.

[0101] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. An active stroke rehabilitation auxiliary training system, characterized in that: include: A baseline generation module generates a personalized training baseline based on the patient's clinical assessment data, wherein the training baseline includes the training goals and training plan for the current training cycle; The training execution module guides patients to perform training movements in coordination with rehabilitation equipment based on the training baseline, and analyzes the training execution efficiency score, patient active movement characteristics, and equipment-assisted performance characteristics in real time; A dynamic adjustment module dynamically adjusts the auxiliary strength of the rehabilitation equipment and the difficulty of the training task during the training period based on the real-time interaction between the active movement characteristics and the auxiliary performance characteristics, combined with the training execution efficiency score, in order to continuously improve the patient's independent movement contribution; The iterative optimization module updates the patient's rehabilitation ability status according to the multi-dimensional time series characteristics of the entire single training process, and outputs the baseline correction instructions for the next training cycle based on the updated rehabilitation ability status.

2. The active stroke rehabilitation auxiliary training system according to claim 1, characterized in that: The training baseline generation process includes: Extract stroke pathological parameters from clinical assessment data and calibrate the severity of the patient's symptoms against the pre-set stroke symptom assessment criteria; Compare the motor function parameters of the clinical assessment data with the preset clinical norms of healthy people of the same age group as the patient to identify the patient's functional deficits; Determining the training target for the functional impairment item using a stage adaptation rule based on the severity of the symptom and the symptom recovery stage of the current training cycle; Calling a training plan bound to the training goal in a preset clinical rule library, wherein the training plan includes the following elements: I. Rehabilitation equipment type and initial parameter configuration; II. The standard path trajectory of the training movement and the permitted trajectory deviation distance limit; III. The location of key path nodes of training actions and their standard pose tolerance limits; IV. Requirements for the execution cycle of complete training actions and the transition window time limit of adjacent critical path nodes.

3. The active stroke rehabilitation auxiliary training system according to claim 2, characterized in that: The training execution performance score analysis process includes: Real-time collection of limb kinematic data of patients performing training movements; When the following conditions are met at the same time, the current training action execution efficiency is given a full score: a) spatially aligning the real-time motion trajectory of the patient's limb extremity with the canonical path trajectory, and quantifying the motion trajectory execution deviation using dynamic time warping distance, wherein the deviation satisfies the permitted trajectory deviation distance limit; b) The actual posture of the patient's limb end when it reaches the critical path node meets the tolerance limit of the node standard posture; c) The total execution time of the complete training action meets the execution cycle requirements; d) The arrival time interval of adjacent key nodes meets the transition window time limit; If there are any unsatisfied conditions, the full score of the performance is deducted accordingly according to the type of unsatisfied condition to generate a training execution performance score.

4. The active stroke rehabilitation auxiliary training system according to claim 1, characterized in that: The patient's active motion feature analysis process includes: The original electromyographic signals of the patient's muscle groups are captured by the surface electrode array, and the electromyographic amplitude envelope is generated after rectification and filtering; Synchronously collect the motion trajectory and speed of the patient's limb extremities, and calculate the kinetic energy of the limb extremities based on this; Performing a time-domain correlation analysis on the integral result of the electromyographic amplitude envelope and the kinetic energy of the limb end movement, and outputting an autonomous drive contribution index representing the degree of coupling between muscle activation and limb movement; Based on the phase synchronization detection of multiple muscle groups, the co-activation period is identified, and the joint angle data are integrated within the co-activation period to construct a theoretical physiological trajectory. According to the difference between the patient's limb end motion trajectory and the theoretical physiological trajectory, the autonomous drive contribution index is calibrated to output the patient's active motion characteristics.

5. The active stroke rehabilitation auxiliary training system according to claim 2, characterized in that: The device-assisted performance feature analysis process includes: The embedded torque sensor collects the joint space auxiliary torque vector output by the rehabilitation device in real time, and calculates the instantaneous auxiliary power based on the motor current and rotor angular velocity of the rehabilitation device; The target joint torque is derived based on the allowable trajectory deviation distance limit of the training action standard path trajectory in the training plan, and the vector norm ratio of the assisting torque collected in real time to the target joint torque is used as the assisting force ratio of the rehabilitation device; Establish the corresponding relationship between the assist torque energy consumption and the patient trajectory execution deviation to determine the power density required for the device to maintain the trajectory; The auxiliary force ratio is subjected to an associated processing based on the power density, and an auxiliary performance feature of the output device is output.

6. The active stroke rehabilitation auxiliary training system according to claim 2, characterized in that: The dynamic adjustment process of the assisting force and task difficulty of the rehabilitation device includes: During the training period, the training execution efficiency score, the patient's active movement characteristics, and the device-assisted performance characteristics are periodically monitored according to the preset adjustment response time points, and the period defined by adjacent adjustment response time points is recorded as the monitoring period; According to the expected synergy ratio range defined by the clinical rehabilitation strategy, the relative contribution relationship between the patient's active movement characteristics and the device-assisted performance characteristics during the monitoring period is determined; Based on the combination of the relative contribution relationship and the training execution efficiency reaching the target state, an adjustment strategy is executed, and the adjustment strategy includes: Based on the training execution efficiency reaching the target status, if the patient's active movement characteristics are dominant, the task difficulty is increased; if the device-assisted performance characteristics are dominant, the assistance strength is reduced; Based on the fact that the training execution efficiency does not meet the standard, if the patient's active movement characteristics are dominant, the task difficulty is reduced; if the equipment-assisted performance characteristics are dominant, the assistance strength is increased.

7. The active stroke rehabilitation auxiliary training system according to claim 6, characterized in that: The relative contribution relationship between the patient's active motion characteristics and the device-assisted performance characteristics is determined by: The patient's active movement characteristics and device-assisted performance characteristics during the monitoring period are normalized and the feature contribution ratio is calculated; If the feature contribution ratio is within the expected synergy ratio range, it is determined that the patient actively and the device assist to achieve the expected synergy state, and there is no dominant object; If the feature contribution ratio exceeds the expected synergy ratio range, and the patient's active motion feature is significantly higher than the device-assisted performance feature, the patient's active motion feature is determined to be dominant; If the feature contribution ratio exceeds the expected synergy ratio range and the device-assisted performance feature is significantly higher than the patient's active movement feature, the device-assisted performance feature is determined to be dominant.

8. The active stroke rehabilitation auxiliary training system according to claim 7, characterized in that: The adjustment strategy execution process also includes: The auxiliary force adjustment is achieved by updating the initial parameter configuration of the rehabilitation equipment, changing the joint space auxiliary torque parameters and motor operating parameters; The task difficulty adjustment is achieved by updating at least one of the following elements in the training plan, including the allowable trajectory deviation distance limit, the standard posture tolerance limit of the key path node, the execution cycle requirement of the complete training action, and the transition window time limit of adjacent key path nodes; The adjustment amplitude is positively correlated with the degree to which the characteristic contribution ratio deviates from the expected synergy ratio range.

9. The active stroke rehabilitation auxiliary training system according to claim 2, characterized in that: The patient rehabilitation ability status update process includes: Extract the training execution efficiency score sequence of the entire training process of a single training session, introduce the time decay factor for weighted fusion to output the functional progress score benchmark; Obtain the fluctuation variance of the patient's active movement characteristics throughout a single training session, as well as the evolution trend direction of the device-assisted performance characteristics; When the functional progress score benchmark reaches the preset clinical advancement standard, the fluctuation degree of the patient's active movement characteristics meets the preset stability requirements, and the auxiliary performance characteristics of the rehabilitation equipment show a negative change trend, the patient's rehabilitation ability status is updated to the pre-advancement status; When the functional progress score benchmark is lower than the preset clinical maintenance standard, the fluctuation degree of the patient's active movement characteristics exceeds the preset sensitivity requirement, and the auxiliary performance characteristics of the rehabilitation equipment show a positive change trend, the patient's rehabilitation ability status is updated to the ability degradation warning state; When the functional progress score benchmark is between the preset clinical advancement standard and the maintenance standard, and the fluctuation degree of the patient's active movement characteristics is between the preset stability requirement and the sensitivity requirement, the patient's rehabilitation ability status is updated to the maintenance training status.

10. The active stroke rehabilitation auxiliary training system according to claim 9, characterized in that: The baseline correction instruction output process of the next training cycle includes: When the patient's rehabilitation ability status is in the advanced preparation state, a movement function that meets the advanced requirements of the current rehabilitation stage is selected from the functional deficiency items as a new training target and fed back to the next training cycle; When the capability degradation warning state is reached, the current training goal is broken down into low-level sub-action goals and fed back to the next training cycle; When the training state is maintained, the current training baseline parameters are kept unchanged and applied to the next training cycle.

Images