An optimization method and system based on rehabilitation training strategy

Abstract

The present invention relates to the technical field of training strategy optimization, and in particular to an optimization method and system based on rehabilitation training strategy. The method comprises the following steps: using a wearable device to monitor the patient's physiology and training performance in real time during rehabilitation training, and performing emotional state and motor ability assessment and analysis to obtain the patient's emotional state data and motor ability data; performing rehabilitation goal prediction and analysis based on the emotional state data and the motor ability data to obtain the predicted goal of the patient's rehabilitation training; performing a target feedback gap comparison analysis on the predicted goal and the expected goal to obtain the target gap feedback result; performing strategy optimization analysis on the current rehabilitation training strategy to generate a rehabilitation training strategy optimization plan; performing strategy dynamic optimization and adjustment on the current rehabilitation training strategy to obtain an optimized rehabilitation training strategy. The present invention can improve the efficiency and effect of patient rehabilitation training.

Description

Technical Field

[0001] The present invention relates to the technical field of training strategy optimization, and in particular to an optimization method and system based on rehabilitation training strategy. Background Art

[0002] At present, many rehabilitation training strategies still rely on fixed training plans and lack personalized evaluation and adjustment. Different patients have different needs for rehabilitation training due to their different physical conditions, pathological characteristics and psychological states. The traditional "one-size-fits-all" training model may lead to poor training results for patients and even increase the risk of injury. When formulating training plans, many medical institutions still rely mainly on the experience and judgment of doctors, and use machine learning-based algorithms to formulate personalized rehabilitation training plans for each patient, and dynamically adjust training strategies during the training process. Through the feedback mechanism, patients can obtain timely evaluation and guidance of training effects, and enhance their sense of participation and motivation in training. However, traditional rehabilitation training strategy optimization methods often lack scientific support based on data generated by the patient's training process, making it impossible for patients to understand their emotional feelings and motor skills during training in a timely manner, thereby limiting the improvement of patients' rehabilitation training efficiency. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide an optimization method and system based on a rehabilitation training strategy to solve at least one of the above technical problems.

[0004] To achieve the above purpose, an optimization method based on rehabilitation training strategy includes the following steps:

[0005] Step S1: monitoring the patient's physiology and training performance in real time during rehabilitation training through a wearable device to obtain the patient's real-time physiological data and real-time sports performance data; evaluating and analyzing the patient's emotional state and sports ability based on the real-time physiological data and the real-time sports performance data to obtain the patient's emotional state data and sports ability data;

[0006] Step S2: performing rehabilitation goal prediction analysis based on the emotional feeling state data and the motor ability data and the current rehabilitation training strategy to obtain a predicted goal for the patient's rehabilitation training; performing a target feedback gap comparison analysis between the predicted goal and the expected goal to obtain a target gap feedback result;

[0007] Step S3: performing strategy optimization analysis on the current rehabilitation training strategy according to the target gap feedback result, so as to provide corresponding rehabilitation training strategy optimization suggestions for different target gap situations of the target gap feedback result by using a decision tree or optimization algorithm, and generate a rehabilitation training strategy optimization plan;

[0008] Step S4: dynamically optimizing and adjusting the current rehabilitation training strategy according to the rehabilitation training strategy optimization scheme to obtain an optimized rehabilitation training strategy. The specific operations of the dynamic optimization and adjustment of the strategy include redesigning the training course and adjusting the parameter settings of the training process.

[0009] Furthermore, the emotional state and athletic ability evaluation and analysis of the patient is performed based on the real-time physiological data and the real-time athletic performance data to obtain the patient's emotional state data and athletic ability data, including:

[0010] Step S13: performing statistical analysis on the patient's training fatigue level based on the real-time physiological data to obtain the patient's fatigue level;

[0011] Step S14: evaluating and analyzing the patient's training emotional state according to the fatigue perception level to obtain the patient's emotional perception state data;

[0012] Step S15: Based on the real-time sports performance data, the patient's rehabilitation training sports ability evaluation and analysis are performed to obtain the patient's sports ability data.

[0013] Further, step S13 includes the following steps:

[0014] Step S131: extracting the patient's resting heart rate at the start of training, the heart rate during training, and the heart rate at the end of training from the real-time physiological data, and performing an inter-frame change amplitude analysis of the patient's heart rate during rehabilitation training based on the resting heart rate at the start of training, the resting heart rate at the end of training, and the resting heart rate at the end of training, to obtain the patient's inter-frame increase amplitude before training and the patient's inter-frame decrease amplitude after training;

[0015] Step S132: calculating the heart rate recovery index of the patient based on the rehabilitation training process according to the increase variation range between frames before the rehabilitation training of the patient and the decrease variation range between frames after the rehabilitation training of the patient, so as to obtain the heart rate recovery index of the patient;

[0016] Step S133: acquiring the patient's muscle activity during rehabilitation training according to the real-time physiological data, and performing muscle force contraction attenuation analysis according to the muscle activity to obtain the patient's muscle activity force contraction attenuation ratio during training; calculating the patient's muscle fatigue index based on the rehabilitation training process according to the muscle activity force contraction attenuation ratio to obtain the patient's muscle fatigue index of rehabilitation training;

[0017] Step S134: extracting the patient's joint range of motion and the duration of the motion according to the real-time physiological data; calculating the joint flexibility reduction index based on the rehabilitation training process according to the joint range of motion and the duration of the joint motion, to obtain the joint flexibility reduction index of the patient's rehabilitation training;

[0018] Step S135: Perform statistical analysis on the training fatigue level based on the heart rate recovery index, the muscle fatigue index and the joint mobility flexibility reduction index to obtain the patient's fatigue level during rehabilitation training.

[0019] Further, the analysis of the amplitude of the inter-frame changes in the patient's heart rate during rehabilitation training before and after training based on the resting heart rate change at the start of the training, the resting heart rate change at the end of the training, and the resting heart rate change at the end of the patient's rehabilitation training described in step S131 includes the following steps:

[0020] Performing time coordinate system dimension synchronization processing based on the resting heart rate change at the start of training, the heart rate change during training, and the resting heart rate change at the end of training to obtain the resting heart rate change at the start of training, the heart rate change during training, and the resting heart rate change at the end of training in the same time series coordinate dimension;

[0021] Divide the resting heart rate change at the beginning of training and the heart rate change during training in the same time series coordinate dimension into the pre-training time frame, and obtain the resting heart rate before training and the heart rate during training at different time frame points during the rehabilitation training;

[0022] Based on the pre-training resting heart rate at different time frame points, the pre-training time frame change amplitude analysis is performed to obtain the pre-training frame increase change amplitude of the patient;

[0023] The heart rate change during training and the resting heart rate change after training in the same time series coordinate dimension are divided into the post-training time frame to obtain the heart rate during training and the resting heart rate after training corresponding to different time frame points during the rehabilitation training process;

[0024] The post-training inter-frame change amplitude analysis is performed based on the post-training resting heart rate at different time frame points to obtain the post-training inter-frame decline amplitude of the patient.

[0025] Further, step S133 includes the following steps:

[0026] Extracting the patient's muscle activity frequency and muscle activity change duration during training from the real-time physiological data, and performing muscle activity measurement calculation based on the muscle activity change duration and the muscle activity frequency to obtain the patient's muscle activity during rehabilitation training;

[0027] Performing muscle force contraction statistical analysis on each muscle activity contraction during the rehabilitation training based on the muscle activity, and obtaining an estimated muscle activity contraction force corresponding to each contraction process;

[0028] Performing muscle force contraction attenuation analysis based on the estimated muscle activity contraction force to obtain the muscle activity force contraction attenuation ratio during the patient's training;

[0029] Based on the estimated muscle activity contraction force, the contraction fatigue cumulative effect is evaluated and analyzed for each muscle activity contraction during the rehabilitation training to obtain a contraction fatigue cumulative effect factor;

[0030] The muscle fatigue index is calculated based on the muscle activity force contraction attenuation ratio and the contraction fatigue cumulative effect factor using the muscle contraction fatigue index calculation formula to obtain the patient's rehabilitation training muscle fatigue index.

[0031] Furthermore, the muscle contraction fatigue index calculation formula is specifically as follows:

[0032] ;

[0033] In the formula, The muscle fatigue index for patients' rehabilitation training, is the total time of the rehabilitation training process, For time, For time The muscle activity force contraction attenuation ratio at For time The cumulative effect factor of contraction fatigue at For time External load on muscle activity at For time The muscle activity recovery ability of is the muscle force contraction attenuation constant, It is the correction factor of muscle fatigue index.

[0034] Furthermore, the calculation of the joint flexibility reduction index based on the joint range of motion and the joint activity duration during the rehabilitation training process includes the following steps:

[0035] Performing joint motion variation analysis on the joint motion range to obtain the patient's joint motion variation range;

[0036] Quantitatively calculate the joint movement rate based on the joint movement duration and the joint movement change amplitude to obtain the joint movement rate of the patient during rehabilitation training;

[0037] The joint flexibility reduction index is calculated according to the joint motion range and the joint motion rate to obtain the joint flexibility reduction index of the patient's rehabilitation training.

[0038] Further, step S2 includes the following steps:

[0039] Step S22: performing feature engineering preprocessing on the emotional state data and the motor ability data to obtain the emotional state characteristics and motor ability characteristics of the patient's rehabilitation training; performing feature time series correlation mining analysis on the emotional state characteristics and the motor ability characteristics to obtain the time series correlation relationship between the emotional state and the motor ability;

[0040] Step S23: designing rehabilitation time sequence effect conditions according to the time sequence association relationship combined with the emotional feeling state data and the motor ability data, and generating effect conditions of the current rehabilitation training strategy under different time sequence conditions;

[0041] Step S24: performing rehabilitation target prediction analysis based on the effect condition and the current rehabilitation training strategy to obtain a predicted rehabilitation training target for the patient;

[0042] Step S25: performing a target feedback gap comparison analysis based on the expected target of the patient's rehabilitation training and the predicted target, and obtaining a target gap comparison feedback result corresponding to the current rehabilitation training strategy.

[0043] Further, step S25 includes the following steps:

[0044] Step S251: constructing a target evaluation index system according to the expected target and the predicted target of the patient's rehabilitation training to generate a target evaluation index system for the patient's rehabilitation training, wherein the target evaluation index system includes the functional recovery rate, pain relief efficiency and activity ability improvement rate of the rehabilitation training;

[0045] Step S252: performing target reward and punishment gap comparison calculation on the expected target and the predicted target based on the target evaluation index system to obtain reward and punishment gap comparison data;

[0046] Step S253: performing gap cause feedback analysis on the reward and punishment gap comparison data to obtain a target gap comparison feedback result corresponding to the current rehabilitation training strategy.

[0047] Furthermore, the present invention also provides an optimization system based on a rehabilitation training strategy, which is used to execute the above-mentioned optimization method based on a rehabilitation training strategy. The optimization system based on a rehabilitation training strategy includes:

[0048] The rehabilitation training process evaluation and analysis module is used to monitor the patient's physiology and training performance in real time during the rehabilitation training process through wearable devices to obtain the patient's real-time physiological data and real-time sports performance data; based on the real-time physiological data and the real-time sports performance data, the patient's emotional state and sports ability evaluation and analysis are performed to obtain the patient's emotional state data and sports ability data;

[0049] A rehabilitation training target feedback comparison and analysis module is used to perform rehabilitation target prediction analysis based on the emotional feeling state data and the motor ability data based on the current rehabilitation training strategy to obtain the predicted target of the patient's rehabilitation training; and to perform target feedback gap comparison analysis between the predicted target and the expected target to obtain the target gap feedback result;

[0050] A rehabilitation training strategy optimization suggestion module is used to perform strategy optimization analysis on the current rehabilitation training strategy according to the target gap feedback result, so as to adopt a decision tree or an optimization algorithm to provide corresponding rehabilitation training strategy optimization suggestions for different target gap situations of the target gap feedback result, thereby generating a rehabilitation training strategy optimization plan;

[0051] The training strategy dynamic optimization and adjustment module is used to dynamically optimize and adjust the current rehabilitation training strategy according to the strategy optimization scheme, so as to obtain an optimized rehabilitation training strategy. The specific operations of the strategy dynamic optimization and adjustment include redesigning the training course and adjusting the parameter settings of the training process.

[0052] Beneficial effects of the present invention:

[0053] 1. The optimization method based on rehabilitation training strategy proposed by the present invention, compared with the prior art, has the beneficial effect of using wearable devices to monitor the patient's physiology and training performance in real time during rehabilitation training, which can provide an important basis for the subsequent statistical analysis of training data. These physiological data include the patient's heart rate, muscle activity and range of motion, etc., which can reflect the patient's physiological state and physiological response during rehabilitation training, and can realize personalized training fatigue emotional state analysis process, reduce the risk of sports injuries, improve training effects, and improve the patient's overall rehabilitation efficiency. In addition, by obtaining the patient's training performance data, including the number of rehabilitation trainings, the amount of exercise and the duration of each training, a direct basis for evaluating the patient's rehabilitation progress is provided for the subsequent processing process. These data can help professionals understand the patient's motor ability and adaptability in a timely manner and identify potential problems in training. The accumulation of these data can also be used to track the patient's long-term progress, thereby providing basic data guarantee for the subsequent motor ability evaluation process. At the same time, by evaluating and analyzing the emotional state of training based on the patient's real-time physiological data, psychological support can be provided for the subsequent processing process. The emotional state is closely related to the patient's training performance. A positive emotional state can motivate patients to participate in rehabilitation training more actively, while negative emotions cause patients to give up training or reduce the training effect. By evaluating the emotional state data, the patient's psychological barriers during rehabilitation training can be identified, which has a significant promoting effect on the optimization of rehabilitation training strategies. In addition, by evaluating and analyzing the motor ability of rehabilitation training based on real-time sports performance data, important support can be provided for the optimization process of personalized rehabilitation training strategies for patients. This evaluation not only helps to understand the patient's current motor ability level, but also guides the design and adjustment of subsequent rehabilitation training. For example, by analyzing the patient's sports performance data, professionals can clearly identify the aspects of motor ability that patients need to focus on in rehabilitation training, such as strength, flexibility or coordination. Such evaluation results can make the rehabilitation training strategy plan more precise, so that patients can achieve the best training effect during the rehabilitation process, so that patients can timely understand their emotional feelings and motor ability during rehabilitation training. Secondly, by performing rehabilitation goal prediction analysis based on the current rehabilitation training strategy according to the emotional state data and the motor ability data, the patient's rehabilitation goal can be predicted. By evaluating the impact of each training strategy on the rehabilitation effect under specific conditions based on the emotional state and rehabilitation training motor ability data obtained in the previous analysis, this predictive analysis not only provides a scientific basis for the patient's rehabilitation, but also helps determine the corresponding rehabilitation goals at different rehabilitation training time points. By adjusting the training plan to adapt to the patient's specific needs and reactions, the patient's confidence can be enhanced and the sense of control over the rehabilitation training process can be strengthened, thereby improving the effectiveness of rehabilitation training.By comparing and analyzing the target feedback gap between the predicted target and the expected target, important rehabilitation target feedback information can be provided. This process enables timely identification of the deficiencies of the rehabilitation plan and further optimization of the training strategy. During the implementation process, through systematic evaluation and feedback, the training content and intensity can be adjusted in a targeted manner to better meet the patient's corresponding expected rehabilitation goals. This step not only helps to improve the success rate of rehabilitation training, but also can promote the improvement of patients' self-efficacy through a continuous feedback mechanism, enhance the positive attitude and motivation required in the rehabilitation process, so that the effect of their rehabilitation training is more significant, and the patient's overall satisfaction and quality of life will also be significantly improved. Then, by performing a strategy optimization analysis on the current rehabilitation training strategy based on the target gap feedback results, the effectiveness and deficiencies of the current rehabilitation program can be identified, and corresponding optimization suggestions can be put forward. These suggestions involve adjustments in training intensity, frequency, type or rehabilitation means to ensure that rehabilitation training is more in line with the actual needs of patients, so that more personalized rehabilitation programs can be designed, patient participation and satisfaction can be improved, and the rehabilitation efficiency and effect of the rehabilitation training process can be improved. Finally, by dynamically optimizing and adjusting the current rehabilitation training strategy according to the strategy optimization plan, it is possible to ensure that the patient's rehabilitation process is always in the best state. Dynamic optimization and adjustment means that the rehabilitation training strategy plan can be modified at any time according to the patient's real-time performance and feedback, rather than being fixed. This flexibility greatly improves the adaptability of rehabilitation training and enables a quick response to changes in the patient during the rehabilitation training process. For example, when the patient shows great progress at a certain stage, the training intensity or difficulty can be increased in a timely manner to promote faster rehabilitation training; conversely, if the patient encounters difficulties at a certain stage, the training content can be adjusted to reduce the burden. This dynamic optimization strategy ensures that the patient can get appropriate challenges at each stage of rehabilitation training without feeling overly tired or frustrated, thereby maintaining a good training state and positive emotions, and will help patients achieve their rehabilitation goals more effectively.

[0054] 2. The optimization system based on rehabilitation training strategy proposed in the present invention is generally composed of a rehabilitation training process evaluation and analysis module, a rehabilitation training target feedback comparison and analysis module, a rehabilitation training strategy optimization suggestion module and a training strategy dynamic optimization adjustment module. It can realize any optimization method based on rehabilitation training strategy described in the present invention, and is used to combine the operations between computer programs running on each module to realize the optimization method based on rehabilitation training strategy. The internal structures of the system cooperate with each other, which can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient optimization process based on rehabilitation training strategy, thereby simplifying the operation process of the optimization system based on rehabilitation training strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0056] Figure 1 It is a schematic diagram of the steps of the optimization method based on the rehabilitation training strategy of the present invention;

[0057] Figure 2 for Figure 1 Detailed step flow diagram of step S2;

[0058] Figure 3 for Figure 3 Detailed step flow chart of step S25. DETAILED DESCRIPTION

[0059] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0060] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0061] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0062] To achieve this, please refer to Figures 1 to 3 The present invention provides an optimization method based on a rehabilitation training strategy, the method comprising the following steps:

[0063] Step S1: monitoring the patient's physiology and training performance in real time during rehabilitation training through a wearable device to obtain the patient's real-time physiological data and real-time sports performance data; evaluating and analyzing the patient's emotional state and sports ability based on the real-time physiological data and the real-time sports performance data to obtain the patient's emotional state data and sports ability data;

[0064] Step S2: performing rehabilitation goal prediction analysis based on the emotional feeling state data and the motor ability data and the current rehabilitation training strategy to obtain a predicted goal for the patient's rehabilitation training; performing a target feedback gap comparison analysis between the predicted goal and the expected goal to obtain a target gap feedback result;

[0065] Step S3: performing strategy optimization analysis on the current rehabilitation training strategy according to the target gap feedback result, so as to provide corresponding rehabilitation training strategy optimization suggestions for different target gap situations of the target gap feedback result by using a decision tree or optimization algorithm, and generate a rehabilitation training strategy optimization plan;

[0066] Step S4: dynamically optimizing and adjusting the current rehabilitation training strategy according to the rehabilitation training strategy optimization scheme to obtain an optimized rehabilitation training strategy. The specific operations of the dynamic optimization and adjustment of the strategy include redesigning the training course and adjusting the parameter settings of the training process.

[0067] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of the steps of the optimization method based on the rehabilitation training strategy of the present invention. In this example, the optimization method based on the rehabilitation training strategy includes the following steps:

[0068] Step S1: monitoring the patient's physiology and training performance in real time during rehabilitation training through a wearable device to obtain the patient's real-time physiological data and real-time sports performance data; evaluating and analyzing the patient's emotional state and sports ability based on the real-time physiological data and the real-time sports performance data to obtain the patient's emotional state data and sports ability data;

[0069] In an embodiment of the present invention, during the rehabilitation training, wearable devices are used to monitor the patient's physiological data in real time, including heart rate, muscle activity and range of motion. In specific implementation, a smart bracelet or smart chest strap equipped with a heart rate monitoring sensor is selected to transmit real-time heart rate data to a rehabilitation training management system through wireless transmission. Muscle activity monitoring is performed through surface electromyography sensors installed on key parts of the patient's body (such as thighs, upper arms, etc.). The sensor reflects the intensity and frequency of muscle activity by measuring the electrical activity of the muscles, thereby providing data for subsequent fatigue analysis. The range of motion is monitored by wearing angle sensors (such as gyroscope sensors) on the patient's joints to capture changes in motion angles, thereby achieving accurate monitoring of the range of joint motion. During the rehabilitation training process, all monitoring data will be uploaded to the cloud platform in real time to obtain the patient's real-time physiological data. Wearable devices are also used to monitor the patient's exercise performance during rehabilitation training in real time. During specific operations, smart bracelets or sports tracking devices with accelerometers and gyroscopes are used to accurately calculate the patient's exercise volume. The number of exercises is counted through the built-in counting function of the device. When the device detects that a specific movement (such as lifting or squatting an upper limb) reaches the preset standard, it automatically records an exercise completion. The amount of exercise is monitored based on the acceleration and exercise duration measured by the device, combined with a specific algorithm, to calculate the patient's exercise intensity and consumption in each training session in real time. The training duration is recorded by the system automatically identifying the start and end time points of the training. All these data are synchronized to the rehabilitation training data platform in real time via the wireless network, thereby obtaining the patient's real-time exercise performance data.At the same time, by combining the real-time physiological data obtained from previous real-time monitoring (including the patient's heart rate, muscle activity and range of motion), a statistical analysis of the fatigue perception level of the corresponding patient during the rehabilitation training process is performed. Specifically, the heart rate changes and electromyographic activity data are used for analysis. When the heart rate exceeds a certain threshold and remains at this high value for a period of time, it indicates that the patient's physiological load is large and fatigue may occur. In addition, the increase in the frequency and intensity of muscle electrical activity is also usually related to training intensity and fatigue perception. The correlation between heart rate and electromyographic data is analyzed through an algorithm, combined with a physiological model, the patient's fatigue perception level is calculated, and the rehabilitation training process of the corresponding patient is further trained. Assessment of emotional state: Emotional assessment is carried out by monitoring physiological signals such as heart rate variability (HRV) and galvanic skin response (GSR). There is a certain correlation between fatigue and negative emotions. Therefore, the patient's emotional state is reflected by the fluctuation degree of heart rate and the change of galvanic skin response. When the heart rate fluctuates greatly and the galvanic skin response increases, it indicates that the patient feels uncomfortable or is in a negative emotional state. Conversely, a stable heart rate and a lower galvanic skin response may indicate that the patient is in a more relaxed emotional state. In addition, the patient's subjective feedback data (such as analyzing the patient's tone and speech speed changes through voice recognition technology) is combined to further supplement and optimize the emotion assessment results, thereby obtaining the patient's emotional feeling state data. Then, by combining the real-time sports performance data obtained from previous real-time monitoring (including the number of rehabilitation training sessions, the amount of rehabilitation training, and the duration of each rehabilitation training session), the rehabilitation training motor ability of the corresponding patient is evaluated and calculated. This step relies on the sports data generated by the patient during the rehabilitation training process, including the number of exercises, the amount of exercise, the duration, and the intensity of exercise. Based on these data, an evaluation algorithm based on a sports biomechanical model is used to quantitatively evaluate the patient's motor ability. Specifically, the patient's performance in each training session will be evaluated by comparing with standard motor ability data. If the patient can maintain a high amount of exercise and a long exercise time in multiple training sessions, it indicates that his or her motor ability is better. On the contrary, if the patient's motor ability fails to meet the expected standard, corresponding rehabilitation adjustment suggestions will be provided, thereby comparing and calculating the patient's motor performance ability score during the training process, and finally obtaining the patient's motor ability data.

[0070] Step S2: performing rehabilitation goal prediction analysis based on the emotional feeling state data and the motor ability data and the current rehabilitation training strategy to obtain a predicted goal for the patient's rehabilitation training; performing a target feedback gap comparison analysis between the predicted goal and the expected goal to obtain a target gap feedback result;

[0071] In an embodiment of the present invention, data cleaning is performed on the emotional feeling state data and motor ability data obtained by previous statistical analysis to remove invalid data and outliers, and standardization and normalization techniques are used to process the emotional feeling state data (such as emotional indicators such as anxiety, depression, optimism, etc.) and motor ability data (such as strength and endurance indicators) to ensure data consistency. At the same time, representative feature data are extracted from the emotional feeling state data and motor ability data through feature extraction algorithms, such as principal component analysis (PCA) and autoencoders, including emotional feeling state change trends, gait, muscle strength, endurance, etc., to obtain the emotional state characteristics and motor ability characteristics of the patient's rehabilitation training, and the patient's emotional state characteristics and motor ability characteristics are aligned according to the training time series to observe the law of feature changes at each time point, and dynamic time warping (DTW) and other algorithms are used to perform time series analysis to extract the time series correlation between the emotional state and the motor ability. The correlation between the emotional state and the motor ability characteristics is evaluated through statistical analysis methods, such as correlation coefficients and covariance matrices. At the same time, the corresponding emotional feeling state and motor ability at the corresponding rehabilitation training time stage are analyzed by combining the time series correlation obtained by the previous analysis. The design of rehabilitation effect conditions is to determine key time nodes, such as before, in the middle and after the training, which correspond to different training strategies and intensities. At these time nodes, targeted training plans are formulated. For example, at the beginning of training, interesting activities are set up with the goal of stimulating positive emotions; in the middle, focus on ability improvement and set higher intensity exercises; after the end, evaluate the effect, adjust the emotional state, and maintain positive feedback. By designing different training time sequence condition points, the effect of rehabilitation training strategies under the conditions of each time stage can be clarified, that is, the corresponding emotional feeling state and motor ability in each time stage. In addition, by combining the effect conditions determined by previous analysis, the rehabilitation training goals corresponding to the current rehabilitation training strategy are predicted and analyzed, so as to use machine learning models (such as random forests or support vector machines) to train the strategy effect data previously collected in the corresponding training time sequence stage to achieve the prediction of the patient's rehabilitation training goals. The input of the model includes emotional state characteristics, motor ability characteristics and corresponding training conditions. The prediction accuracy of the model is evaluated through cross-validation and other methods, so as to generate a prediction report, indicating the rehabilitation goals that each patient may achieve under different training conditions, thereby obtaining the predicted goals of the patient's rehabilitation training.Then, by comparing and analyzing the corresponding predicted goals of patient rehabilitation training according to the expected goals of the patient's rehabilitation training, the specific method includes adopting the target reward and punishment analysis method to calculate the contrast difference of training parameters between the expected goals and the predicted goals, including the contrast difference corresponding to the functional recovery rate, pain relief efficiency and activity ability improvement rate, to quantify the target gap and analyze the reasons behind it, further understand the relationship between the patient's emotion and motor ability during the rehabilitation training process, and adjust and optimize the rehabilitation training strategy based on the analysis results to ensure that the patient's actual rehabilitation effect is as close to its expected goal as possible, and finally obtain the target gap comparison feedback result corresponding to the current rehabilitation training strategy.

[0072] Step S3: performing strategy optimization analysis on the current rehabilitation training strategy according to the target gap feedback result, so as to provide corresponding rehabilitation training strategy optimization suggestions for different target gap situations of the target gap feedback result by using a decision tree or optimization algorithm, and generate a rehabilitation training strategy optimization plan;

[0073] In an embodiment of the present invention, an optimization suggestion analysis is performed on the corresponding current rehabilitation training strategy by combining the previously obtained target gap comparison feedback results, so as to adopt a decision tree or optimization algorithm to provide corresponding rehabilitation training strategy optimization suggestions for different target gap situations. For example, for patients with low target achievement, it can be recommended to increase the training frequency or adjust the training intensity; and for patients with low emotional state, it can be recommended to add more elements such as social interaction or music therapy, so as to form a detailed rehabilitation training strategy optimization suggestion plan, list specific training adjustment measures and implementation steps, and finally generate a rehabilitation training strategy optimization plan.

[0074] Step S4: dynamically optimizing and adjusting the current rehabilitation training strategy according to the rehabilitation training strategy optimization scheme to obtain an optimized rehabilitation training strategy. The specific operations of the dynamic optimization and adjustment of the strategy include redesigning the training course and adjusting the parameter settings of the training process.

[0075] In an embodiment of the present invention, the current rehabilitation training strategy is dynamically optimized and adjusted by generating a rehabilitation training strategy optimization plan based on previous suggestions. Specific operations include redesigning the training course and adjusting the parameter settings of the training process. For example, when the patient shows great progress at a certain stage, the training intensity or difficulty can be increased in a timely manner to promote faster rehabilitation training; conversely, if the patient encounters difficulties at a certain stage, the training content can be adjusted to reduce the burden. This dynamic optimization strategy ensures that the patient can receive appropriate challenges at each stage of rehabilitation training, so that when executing a new rehabilitation training plan, the patient's physiological reactions and motor performance are continuously monitored, and the training effects are recorded and fed back to the system in a timely manner to ensure real-time optimization and adjustment of the rehabilitation strategy, thereby achieving more efficient rehabilitation effects and ultimately obtaining an optimized rehabilitation training strategy.

[0076] Furthermore, the emotional state and athletic ability evaluation and analysis of the patient is performed based on the real-time physiological data and the real-time athletic performance data to obtain the patient's emotional state data and athletic ability data, including:

[0077] Step S13: performing statistical analysis on the patient's training fatigue level based on the real-time physiological data to obtain the patient's fatigue level;

[0078] In an embodiment of the present invention, a statistical analysis of the fatigue perception level of the corresponding patient during the rehabilitation training process is performed based on the real-time physiological data (including the patient's heart rate, the patient's muscle activity and the patient's range of motion) obtained by combining previous real-time monitoring. Specifically, the heart rate change and electromyographic activity data are used for analysis. When the heart rate exceeds a certain threshold and remains at this high value for a period of time, it indicates that the patient's physiological load is large and fatigue may occur. In addition, the increase in the frequency and intensity of muscle electrical activity is also generally related to training intensity and fatigue perception. The correlation between heart rate and electromyographic data is analyzed by an algorithm, and combined with a physiological model, the patient's fatigue perception level is calculated. Statistics can be performed based on the fluctuations and changing trends of physiological parameters to obtain a real-time fatigue perception value, and finally the patient's fatigue perception level is obtained.

[0079] Step S14: evaluating and analyzing the patient's training emotional state according to the fatigue perception level to obtain the patient's emotional perception state data;

[0080] In an embodiment of the present invention, the emotional state of the corresponding patient during the rehabilitation training process is further evaluated based on the fatigue perception level obtained by the previous quantitative calculation. The emotional evaluation is performed by monitoring physiological signals such as heart rate variability (HRV) and galvanic skin response (GSR). There is a certain correlation between fatigue and negative emotions. Therefore, the emotional state of the patient is reflected by the fluctuation degree of heart rate and the change of galvanic skin response. When the heart rate fluctuates greatly and the galvanic skin response increases, it indicates that the patient feels uncomfortable or is in a negative emotional state. Conversely, a stable heart rate and a lower galvanic skin response may indicate that the patient is in a more relaxed emotional state. In addition, the patient's subjective feedback data (such as analyzing the patient's tone and speech speed changes through voice recognition technology) is combined to further supplement and optimize the emotional evaluation results, thereby evaluating the patient's emotional perception state in real time, and finally obtaining the patient's emotional perception state data.

[0081] Step S15: Based on the real-time sports performance data, the patient's rehabilitation training sports ability evaluation and analysis are performed to obtain the patient's sports ability data.

[0082] In an embodiment of the present invention, the rehabilitation training motor ability of the corresponding patient is evaluated and calculated by combining the real-time motor performance data obtained by previous real-time monitoring (including the number of rehabilitation training sessions of the patient, the amount of rehabilitation training exercise of the patient, and the duration of each rehabilitation training session of the patient). This step relies on the motor data generated by the patient during the rehabilitation training process, including the number of exercises, the amount of exercise, the duration, and the intensity of exercise. Based on these data, an evaluation algorithm based on a sports biomechanical model is used to quantitatively evaluate the patient's motor ability. Specifically, the patient's performance in each training session will be evaluated by comparing with standard motor ability data. If the patient can maintain a higher amount of exercise and a longer exercise time in multiple training sessions, it indicates that his or her motor ability is better. On the contrary, if the patient's motor ability fails to meet the expected standard, corresponding rehabilitation adjustment suggestions will be provided, thereby comparing and calculating the patient's motor performance ability score during the training process, and finally obtaining the patient's motor ability data.

[0083] Further, step S13 includes the following steps:

[0084] Step S131: extracting the patient's resting heart rate at the start of training, the heart rate during training, and the heart rate at the end of training from the real-time physiological data, and performing an inter-frame change amplitude analysis of the patient's heart rate during rehabilitation training based on the resting heart rate at the start of training, the resting heart rate at the end of training, and the resting heart rate at the end of training, to obtain the patient's inter-frame increase amplitude before training and the patient's inter-frame decrease amplitude after training;

[0085] In an embodiment of the present invention, during the patient's rehabilitation training, the real-time monitoring device collects the patient's physiological heart rate change data through a heart rate monitoring instrument, and extracts the patient's resting heart rate recorded before the rehabilitation training begins, then continuously monitors the heart rate change during the rehabilitation training, and finally records the patient's resting heart rate again after the training ends. In a specific implementation, a heart rate sensor (such as an electrocardiogram sensor or a photoelectric volume pulse wave sensor) is used to obtain heart rate data, and the resting heart rate at the beginning and end of the rehabilitation training and the heart rate change during the training are calculated through a data analysis algorithm, so as to obtain the patient's resting heart rate change at the beginning of the rehabilitation training, the patient's heart rate change during the rehabilitation training, and the patient's resting heart rate change at the end of the rehabilitation training. At the same time, the resting heart rate at the beginning and end of the training is compared by time series analysis, and the heart rate change during the training is combined to analyze the change range of the patient's heart rate before and after the training, so as to obtain the heart rate increase change range before the patient's rehabilitation training and the heart rate decrease change range after the rehabilitation training, and finally obtain the inter-frame increase change range before the patient's rehabilitation training and the inter-frame decrease change range after the patient's rehabilitation training.

[0086] Step S132: calculating the heart rate recovery index of the patient based on the rehabilitation training process according to the increase variation range between frames before the rehabilitation training of the patient and the decrease variation range between frames after the rehabilitation training of the patient, so as to obtain the heart rate recovery index of the patient;

[0087] In an embodiment of the present invention, by combining the previously obtained heart rate variation amplitude data, a statistical analysis method is used to calculate the patient's heart rate recovery index, so as to quantitatively compare the heart rate increase amplitude before rehabilitation training with the heart rate decrease amplitude after the training. The index calculation formula is used to set a suitable weight coefficient, and the heart rate variation amplitude is converted into a heart rate recovery index, that is, the corresponding heart rate variation amplitude is multiplied by the respective weight coefficients and added. This index not only reflects the speed of the patient's heart rate recovery, but also can effectively characterize the recovery of the cardiovascular system, and finally the patient's heart rate recovery index is obtained.

[0088] Step S133: acquiring the patient's muscle activity during rehabilitation training according to the real-time physiological data, and performing muscle force contraction attenuation analysis according to the muscle activity to obtain the patient's muscle activity force contraction attenuation ratio during training; calculating the patient's muscle fatigue index based on the rehabilitation training process according to the muscle activity force contraction attenuation ratio to obtain the patient's muscle fatigue index of rehabilitation training;

[0089] In an embodiment of the present invention, the real-time muscle activity monitoring data of the patient is obtained from the real-time physiological data previously obtained by real-time monitoring, and an electromyography (EMG) sensor is used to capture the electrical activity signal of the muscle during training, and the muscle activity of each training stage is calculated using the electromyography data, so as to obtain the muscle activity of the patient during rehabilitation training. At the same time, by analyzing the changes in the muscle activity of the patient during rehabilitation training, especially focusing on the changes in the strength contraction stage, the attenuation ratio of muscle activity strength contraction during training is quantitatively calculated. Then, by comparing with the baseline muscle activity, the attenuation ratio is obtained and the patient's muscle fatigue index is calculated using a standardized formula. The index can reflect the patient's muscle fatigue degree during the rehabilitation training process, and finally the patient's muscle fatigue index of rehabilitation training is obtained.

[0090] Step S134: extracting the patient's joint range of motion and the duration of the motion according to the real-time physiological data; calculating the joint flexibility reduction index based on the rehabilitation training process according to the joint range of motion and the duration of the joint motion, to obtain the joint flexibility reduction index of the patient's rehabilitation training;

[0091] In an embodiment of the present invention, the range of motion (ROM) and duration of the patient's joints during rehabilitation training are extracted from the real-time physiological data previously obtained through real-time monitoring. Specifically, when the patient performs joint movements (such as flexion, extension, and rotation), the sensor captures the angle changes of each joint and generates data records. These data are sorted and analyzed to obtain the range of motion and duration of each joint during training. For example, for the flexion and extension of the knee joint, the maximum flexion angle recorded is 120 degrees, the extension angle is 0 degrees, and the range of motion is 120 degrees. The duration of the knee flexion and extension movement is recorded, thereby obtaining the patient's joint range of motion and duration of activity. At the same time, by calculating the data ratio of the corresponding range of motion of each joint to the duration of activity, the joint flexibility reduction index is calculated. This index can characterize the patient's joint flexibility and its changing trend during rehabilitation training, reflect the adaptability and rehabilitation effect of each joint, and finally obtain the joint flexibility reduction index of the patient's rehabilitation training.

[0092] Step S135: Perform statistical analysis on the training fatigue level based on the heart rate recovery index, the muscle fatigue index and the joint mobility flexibility reduction index to obtain the patient's fatigue level during rehabilitation training.

[0093] In an embodiment of the present invention, a statistical calculation of the training fatigue level is performed by combining the heart rate recovery index, muscle fatigue index and joint flexibility reduction index obtained by previous quantitative calculations. The specific operation is to integrate these three indicators into a multidimensional analysis model, and use statistical analysis software (such as SPSS or MATLAB) to perform correlation analysis and regression analysis on these data to find out the relationship between different indicators. In this way, the fatigue level felt by the patient during the rehabilitation training process can be quantitatively calculated, and finally the fatigue level of the patient's rehabilitation training can be obtained.

[0094] Further, the analysis of the amplitude of the inter-frame changes in the patient's heart rate during rehabilitation training before and after training based on the resting heart rate change at the start of the training, the resting heart rate change at the end of the training, and the resting heart rate change at the end of the patient's rehabilitation training described in step S131 includes the following steps:

[0095] Performing time coordinate system dimension synchronization processing based on the resting heart rate change at the start of training, the heart rate change during training, and the resting heart rate change at the end of training to obtain the resting heart rate change at the start of training, the heart rate change during training, and the resting heart rate change at the end of training in the same time series coordinate dimension;

[0096] In an embodiment of the present invention, before the patient's rehabilitation training begins, a heart rate monitoring device (such as an electrocardiograph or a portable heart rate monitor) is used to collect the patient's resting heart rate data. This data is recorded in a time series as the resting heart rate change at the beginning of the training. After the rehabilitation training begins, the patient monitors his or her heart rate changes in real time during the training process, and these data are recorded in the same time coordinate system. At the same time, after the training, the patient's resting heart rate is measured and recorded again. These data are synchronized to ensure that all heart rate data are compared in the same time series coordinate dimension to form a complete set of heart rate change time series, and finally the resting heart rate change at the beginning of the training, the heart rate change during the training, and the resting heart rate change at the end of the training in the same time series coordinate dimension are obtained.

[0097] Preferably, the resting heart rate change at the start of training and the heart rate change during training under the same time series coordinate dimension are divided into pre-training time frames to obtain the resting heart rate before training and the heart rate during training at different time frame points during the rehabilitation training process;

[0098] In an embodiment of the present invention, after obtaining the resting heart rate change at the beginning of training and the heart rate change during training, the two sets of data are divided into time frames. In the specific implementation process, the timestamp technology is used to divide the resting heart rate data before training and the heart rate data during training into several time frames (such as one time frame every minute or every 5 minutes). By setting a fixed time interval, the resting heart rate at the beginning of training and the heart rate during training in the corresponding time frame are matched one by one to form a structured data set, and finally the resting heart rate before training and the heart rate during training at different time frames during the rehabilitation training process are obtained.

[0099] Preferably, the pre-training inter-frame change amplitude analysis is performed based on the pre-training resting heart rate at different time frame points to obtain the pre-training inter-frame increase change amplitude of the patient;

[0100] In an embodiment of the present invention, the amplitude of the heart rate change during training at the corresponding time frame is analyzed based on the resting heart rate before training at different time frame points, that is, the difference between the heart rate during training and the resting heart rate before training in each time frame is calculated to obtain the heart rate change in each time frame. Then, the overall change trend of the resting heart rate before training and the heart rate during training is evaluated through statistical analysis methods (such as mean, standard deviation, etc.), so as to obtain the specific data of the patient's inter-frame increase in change before rehabilitation training, and finally obtain the patient's inter-frame increase in change before training.

[0101] Preferably, the heart rate change during training and the heart rate change at rest after training under the same time series coordinate dimension are divided into the time frame of the later stage of training, so as to obtain the heart rate during training and the heart rate at rest after training corresponding to different time frame points during the rehabilitation training process;

[0102] In an embodiment of the present invention, similarly, by dividing the changing heart rate during training and the changing heart rate at rest at the end of training into later time frames under the same time coordinate dimension, and by using the same timestamp technology, the heart rate data during training and the resting heart rate data after the end of training are divided into multiple time frames in chronological order, ensuring that the data of each time frame can be clearly corresponding. In this process, the integrity and accuracy of the data are maintained, and analysis deviations caused by inconsistent time frames are avoided. Finally, the heart rate during training and the resting heart rate after training corresponding to different time frame points in the rehabilitation training process are obtained.

[0103] Preferably, the post-training inter-frame change amplitude analysis is performed based on the post-training resting heart rate at different time frame points to obtain the post-training inter-frame decline change amplitude of the patient.

[0104] In an embodiment of the present invention, the heart rate during training at the corresponding time frame is analyzed by analyzing the resting heart rate after training at different time frames. During the implementation process, the difference between the resting heart rate after training and the heart rate during training is first calculated, and a standard value (such as the average value of the resting heart rate) is set for comparison to obtain the heart rate change in each time frame. Statistical analysis methods such as linear regression are used to analyze the decline in the range of changes between time frames after training, so as to quantitatively evaluate the heart rate recovery of the patient after rehabilitation training, and finally obtain the decline in the range of changes between frames after training.

[0105] Further, step S133 includes the following steps:

[0106] Extracting the patient's muscle activity frequency and muscle activity change duration during training from the real-time physiological data, and performing muscle activity measurement calculation based on the muscle activity change duration and the muscle activity frequency to obtain the patient's muscle activity during rehabilitation training;

[0107] In an embodiment of the present invention, during the patient's rehabilitation training, the muscle activity frequency and the duration of muscle activity change during the patient's training are extracted from the real-time physiological data. The real-time physiological data monitoring system collects the patient's muscle activity signal through a sensor. The system can use an electromyography (EMG) sensor attached to the relevant muscle part of the patient. These sensors record the electrical activity of the muscle in real time, generate time series data, and perform spectrum analysis on these signals to obtain the frequency of the patient's muscle activity. Signal processing techniques such as fast Fourier transform (FFT) are usually used. This process also requires setting a threshold to identify the duration of muscle activity change, that is, the period during which the patient's muscle activity is higher than the threshold during training, so as to obtain the patient's muscle activity frequency and the duration of muscle activity change during training. At the same time, by combining the patient's muscle activity frequency and the duration of muscle activity change during training, the corresponding muscle activity is calculated, and the muscle activity degree = muscle activity frequency / muscle activity change duration is used as a key indicator to measure the effectiveness of the patient's rehabilitation training, ensuring that the muscle activity during the training process is quantified and analyzed, and finally obtaining the patient's muscle activity during rehabilitation training.

[0108] Preferably, based on the muscle activity, a muscle force contraction statistical analysis is performed on each muscle activity contraction during the rehabilitation training process to obtain an estimated muscle activity contraction force corresponding to each contraction process;

[0109] In an embodiment of the present invention, a statistical analysis of the contraction force of each muscle activity contraction during the rehabilitation training is performed by combining the muscle activity obtained by previous quantitative calculation, so as to construct a database to record the relevant data of each muscle activity contraction, including parameters such as contraction time, force intensity and frequency, and use a biomechanical model to calculate the estimated force of muscle contraction. The model comprehensively considers the physiological characteristics of the muscle, the intensity and frequency of training, and through correlation analysis with the muscle activity, the estimated force value of the muscle activity contraction during the training period corresponding to each contraction can be obtained. The calculation of the estimated force can use Newton's second law, and the force value required in the contraction process is determined through dynamic mechanical analysis, and finally the estimated force of the muscle activity contraction corresponding to each contraction process is obtained.

[0110] Preferably, a muscle force contraction decay analysis is performed based on the estimated muscle activity contraction force to obtain a muscle activity force contraction decay ratio during the patient's training;

[0111] In an embodiment of the present invention, the contraction attenuation of muscle activity force is quantitatively calculated by using the estimated muscle activity contraction force during training corresponding to each contraction process obtained from previous evaluation and analysis, so as to record the initial force of each contraction and the force measurement values ​​of subsequent contractions by establishing a time series model, and calculate the ratio of the force measurement value of each subsequent contraction to the estimated force value corresponding to the initial contraction to obtain the attenuation ratio. The specific calculation process includes subtracting the measured value of the current contraction force from the initial force value, and then dividing it by the initial force value, so as to obtain the percentage of the corresponding attenuation ratio at each subsequent contraction time, and finally obtain the contraction attenuation ratio of the muscle activity force of the patient during training.

[0112] Preferably, based on the estimated muscle activity contraction force, the contraction fatigue cumulative effect evaluation and analysis is performed on each muscle activity contraction during the rehabilitation training to obtain a contraction fatigue cumulative effect factor;

[0113] In an embodiment of the present invention, the fatigue cumulative effect of each muscle activity contraction during the rehabilitation training process is evaluated and analyzed by combining the estimated force of muscle activity contraction during the training corresponding to each contraction process collected previously, and a statistical analysis method, such as analysis of variance (ANOVA), is used to evaluate the influence of fatigue effect on force output in different training stages. By successively comparing the force output of each training contraction and the corresponding time interval, the cumulative effect factor of fatigue can be calculated. This process requires accurate recording of the force output data of each stage during the training process, and finally the contraction fatigue cumulative effect factor is obtained.

[0114] Preferably, the muscle fatigue index is calculated based on the muscle activity force contraction attenuation ratio and the contraction fatigue cumulative effect factor using a muscle contraction fatigue index calculation formula to obtain the patient's rehabilitation training muscle fatigue index.

[0115] In an embodiment of the present invention, a suitable muscle contraction fatigue index calculation formula is formed by combining the time variable parameters during the rehabilitation training process, the muscle activity force contraction attenuation ratio, the contraction fatigue cumulative effect factor, the external load of muscle activity, the muscle activity recovery ability, the muscle force contraction attenuation constant and related parameters to calculate the muscle fatigue index of the corresponding rehabilitation training process, so as to quantitatively calculate the fatigue index corresponding to different training stages and different contraction types, and finally obtain the patient's rehabilitation training muscle fatigue index.

[0116] Furthermore, the muscle contraction fatigue index calculation formula is specifically as follows:

[0117] ;

[0118] In the formula, The muscle fatigue index for patients' rehabilitation training, is the total time of the rehabilitation training process, For time, For time The muscle activity force contraction attenuation ratio at For time The cumulative effect factor of contraction fatigue at For time External load on muscle activity at For time The muscle activity recovery ability of is the muscle force contraction attenuation constant, It is the correction factor of muscle fatigue index.

[0119] The present invention obtains a muscle contraction fatigue index calculation formula by using a specific mathematical model and after verification, which is used to calculate the muscle fatigue index of the corresponding rehabilitation training process. The muscle contraction fatigue index calculation formula contains multiple variables (such as muscle activity force contraction attenuation ratio, contraction fatigue cumulative effect factor, external load and recovery ability), which enables MFI to comprehensively evaluate the performance of muscles under different conditions. This comprehensive analysis takes into account different influencing factors. MFI can more accurately reflect the actual fatigue state of the muscle, not just a single factor. According to the performance of different patients, a personalized training plan is formulated to improve the pertinence and effectiveness of the training. The time variable and related parameter factors in the calculation formula allow dynamic monitoring throughout the rehabilitation process, and can evaluate the fatigue changes of patients during the training process in real time, and adjust the training intensity and content in time to avoid excessive fatigue or injury. In addition, the correction coefficient in the formula allows the results of MFI to be fine-tuned to adapt to individual differences and specific situations. Through the correction coefficient, it can increase the credibility of the evaluation according to the special needs and reactions of different patients, adapt to different types of training and rehabilitation methods, and ensure the wide applicability of the formula. In summary, the formula fully considers the muscle fatigue index of patient rehabilitation training. , the total time of rehabilitation training process ,time ,time The muscle activity force contraction decay ratio ,time Cumulative effect factor of contraction fatigue at ,time External load on muscle activity ,time Muscle activity recovery ability , muscle force contraction decay constant , correction factor of muscle fatigue index , according to the patient's rehabilitation training muscle fatigue index The correlation between the above parameters constitutes a functional relationship This formula can realize the calculation process of muscle fatigue index of the corresponding rehabilitation training process. At the same time, through the correction coefficient of muscle fatigue index The introduction of can be adjusted according to the errors that occur in the calculation process, thereby improving the accuracy and applicability of the calculation formula for muscle contraction fatigue index.

[0120] Furthermore, the calculation of the joint flexibility reduction index based on the joint range of motion and the joint activity duration during the rehabilitation training process includes the following steps:

[0121] Performing joint motion variation analysis on the joint motion range to obtain the patient's joint motion variation range;

[0122] In an embodiment of the present invention, by using a joint movement measurement tool, such as an electronic joint goniometer or a motion capture system, the patient's joint movement range is accurately measured to determine the starting position of the joint. For example, in a sitting or standing position, the initial angle of the joint is recorded, and the patient is guided to perform specific joint movements, such as flexion and extension, abduction, adduction, etc. The tool is used to record the changes in joint angles in real time. After a certain period of training, the maximum movement angle of the joint under the same action is re-measured, and the amplitude of the change in joint movement is calculated by comparing the data before and after training, and finally the amplitude of the change in the patient's joint movement is obtained.

[0123] Preferably, the joint movement rate is quantitatively calculated based on the joint movement duration and the joint movement variation range to obtain the joint movement rate of the patient during rehabilitation training;

[0124] In an embodiment of the present invention, after obtaining the amplitude of change in the patient's joint movement, the next step is to monitor and record the duration of the patient's joint movement during rehabilitation training, so as to track the time data of the patient's joint movement in real time by using a motion capture system or a gait analyzer. The specific operation is that when the patient performs actions such as knee flexion and extension, the start and end time of each action is recorded, and the rate of joint movement is calculated by counting the time of each action and combining the amplitude of change in joint movement obtained in the previous step. The calculation formula for the joint movement rate is: rate = amplitude of change / duration. This rate can be used to evaluate the effectiveness of rehabilitation training, reflecting the flexibility of the patient's joint movement during training, and finally obtaining the joint movement rate of the patient during rehabilitation training.

[0125] Preferably, the joint flexibility reduction index is calculated based on the joint motion range and the joint motion rate to obtain the joint flexibility reduction index for the patient's rehabilitation training.

[0126] In the embodiment of the present invention, the joint flexibility reduction index is quantitatively calculated for the corresponding rehabilitation training process by combining the joint range of motion and the joint movement rate obtained by the previous analysis, so as to calculate the index value based on the combination of the joint range of motion and the joint movement rate of the patient during the rehabilitation training and using the calculation formula of the flexibility reduction index. The formula can be set as: flexibility reduction index = (joint range of motion) Joint movement rate) / duration, through the obtained flexibility reduction index, the degree of joint flexibility reduction and rehabilitation effect of the patient can be evaluated, and finally the joint movement flexibility reduction index of the patient's rehabilitation training can be obtained.

[0127] Further, step S2 includes the following steps:

[0128] Step S22: performing feature engineering preprocessing on the emotional state data and the motor ability data to obtain the emotional state characteristics and motor ability characteristics of the patient's rehabilitation training; performing feature time series correlation mining analysis on the emotional state characteristics and the motor ability characteristics to obtain the time series correlation relationship between the emotional state and the motor ability;

[0129] Step S23: designing rehabilitation time sequence effect conditions according to the time sequence association relationship combined with the emotional feeling state data and the motor ability data, and generating effect conditions of the current rehabilitation training strategy under different time sequence conditions;

[0130] Step S24: performing rehabilitation target prediction analysis based on the effect condition and the current rehabilitation training strategy to obtain a predicted rehabilitation training target for the patient;

[0131] Step S25: performing a target feedback gap comparison analysis based on the expected target of the patient's rehabilitation training and the predicted target, and obtaining a target gap comparison feedback result corresponding to the current rehabilitation training strategy.

[0132] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S2 in FIG. 1 , in this embodiment, step S2 includes the following steps:

[0133] Step S22: performing feature engineering preprocessing on the emotional state data and the motor ability data to obtain the emotional state characteristics and motor ability characteristics of the patient's rehabilitation training; performing feature time series correlation mining analysis on the emotional state characteristics and the motor ability characteristics to obtain the time series correlation relationship between the emotional state and the motor ability;

[0134] In an embodiment of the present invention, data cleaning is performed on the emotional feeling state data and motor ability data obtained by previous statistical analysis to remove invalid data and outliers, and standardization and normalization techniques are used to process the emotional feeling state data (such as emotional indicators such as anxiety, depression, optimism, etc.) and motor ability data (such as strength and endurance indicators) to ensure data consistency. At the same time, representative feature data is extracted from the emotional feeling state data and motor ability data through feature extraction algorithms, such as principal component analysis (PCA) and autoencoders, including emotional feeling state change trends, gait, muscle strength, endurance, etc., so as to obtain the emotional state characteristics and motor ability characteristics of the patient's rehabilitation training. At the same time, the patient's emotional state characteristics and motor ability characteristics are aligned according to the training time series in order to observe the pattern of feature changes at each time point. Subsequently, time series analysis is performed using algorithms such as dynamic time warping (DTW) to extract the temporal correlation between emotional state and motor ability. Statistical analysis methods, such as correlation coefficient and covariance matrix, are used to evaluate the correlation between emotional state and motor ability characteristics, thereby forming a set of temporal correlation models between emotional state and motor ability, and finally obtaining the temporal correlation between emotional state and motor ability.

[0135] Step S23: designing rehabilitation time sequence effect conditions according to the time sequence association relationship combined with the emotional feeling state data and the motor ability data, and generating effect conditions of the current rehabilitation training strategy under different time sequence conditions;

[0136] In an embodiment of the present invention, the rehabilitation effect conditions are designed for the emotional feeling states and motor abilities corresponding to the corresponding rehabilitation training time stages by combining the temporal correlation relationship obtained by previous analysis, so as to determine the key time nodes, such as before, in the middle and after the training, which correspond to different training strategies and intensities respectively. At these time nodes, targeted training plans are formulated. For example, at the beginning of training, the goal is to stimulate positive emotions and set interesting activities; in the middle, focus on improving abilities and set higher-intensity exercises; after the training, evaluate the effects, adjust the emotional states, and maintain positive feedback. By designing different training timing condition points, the effects of the rehabilitation training strategies under the conditions of each time stage can be clarified, that is, the corresponding emotional feeling states and motor abilities under each time stage, and finally the effect conditions of the current rehabilitation training strategies under different timing conditions are generated.

[0137] Step S24: performing rehabilitation target prediction analysis based on the effect condition and the current rehabilitation training strategy to obtain a predicted rehabilitation training target for the patient;

[0138] In an embodiment of the present invention, a predictive analysis is performed on the rehabilitation training goals corresponding to the strategy effects of the currently adopted rehabilitation training strategy in the corresponding training timing stage by combining the effect conditions determined by the previous analysis, so as to use a machine learning model (such as a random forest or a support vector machine) to train the strategy effect data previously collected in the corresponding training timing stage to achieve the prediction of the patient's rehabilitation training goals. The input of the model includes emotional state characteristics, motor ability characteristics and corresponding training conditions. The prediction accuracy of the model is evaluated through cross-validation and other methods, thereby generating a prediction report, indicating the rehabilitation goals that each patient may achieve under different training conditions, ensuring the quantifiability and evaluability of the goals, and finally obtaining the patient's predicted rehabilitation training goals.

[0139] Step S25: performing a target feedback gap comparison analysis based on the expected target of the patient's rehabilitation training and the predicted target, and obtaining a target gap comparison feedback result corresponding to the current rehabilitation training strategy.

[0140] In an embodiment of the present invention, a comparative analysis is performed on the corresponding predicted goals of patient rehabilitation training according to the expected goals of the patient's rehabilitation training. The specific method includes adopting a target reward and punishment analysis method to calculate the comparative differences in training parameters between the expected goals and the predicted goals, including the functional recovery rate, pain relief efficiency, and activity improvement rate corresponding to the comparative differences, to quantify the target gap and analyze the reasons behind it, to further understand the relationship between the patient's emotions and motor skills during the rehabilitation training process, and to adjust and optimize the rehabilitation training strategy based on the analysis results to ensure that the patient's actual rehabilitation effect is as close to its expected goal as possible, and finally obtain the target gap comparison feedback result corresponding to the current rehabilitation training strategy.

[0141] Further, step S25 includes the following steps:

[0142] Step S251: constructing a target evaluation index system according to the expected target and the predicted target of the patient's rehabilitation training to generate a target evaluation index system for the patient's rehabilitation training, wherein the target evaluation index system includes the functional recovery rate, pain relief efficiency and activity ability improvement rate of the rehabilitation training;

[0143] Step S252: performing target reward and punishment gap comparison calculation on the expected target and the predicted target based on the target evaluation index system to obtain reward and punishment gap comparison data;

[0144] Step S253: performing gap cause feedback analysis on the reward and punishment gap comparison data to obtain a target gap comparison feedback result corresponding to the current rehabilitation training strategy.

[0145] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 Detailed step flow diagram of step S25 in FIG. 1 , in this embodiment, step S25 includes the following steps:

[0146] Step S251: constructing a target evaluation index system according to the expected target and the predicted target of the patient's rehabilitation training to generate a target evaluation index system for the patient's rehabilitation training, wherein the target evaluation index system includes the functional recovery rate, pain relief efficiency and activity ability improvement rate of the rehabilitation training;

[0147] In an embodiment of the present invention, by analyzing and constructing a target evaluation index system for the predicted target of patient rehabilitation training obtained by prediction analysis according to the expected target of patient rehabilitation training, basic data related to patient rehabilitation training needs to be collected, including the patient's past medical history, current physical condition and preliminary expected target of rehabilitation training. These data can be obtained through the patient's electronic health record system, and a set of specific evaluation indicators are formulated according to the predicted target of patient rehabilitation training at different rehabilitation training time stages. These indicators include rehabilitation training function recovery rate, pain relief efficiency and activity ability improvement rate, so as to determine the relationship between these indicators and the effect of patient rehabilitation training. For example, the rehabilitation training function recovery rate can be determined by measuring the improvement of the patient's performance in a specific functional evaluation test, the pain relief efficiency can be quantitatively analyzed by the Visual Analog Scale (VAS), recording the changes in the patient's pain perception before and after training, and the activity ability improvement rate can be evaluated by standardized tests such as the Functional Independence Measure (FIM). Once these indicators are determined, they will be managed and recorded by constructing a database to form a preliminary framework of the patient rehabilitation training target evaluation index system, and finally construct a target evaluation index system for patient rehabilitation training.

[0148] Step S252: performing target reward and punishment gap comparison calculation on the expected target and the predicted target based on the target evaluation index system to obtain reward and punishment gap comparison data;

[0149] In an embodiment of the present invention, a quantitative calculation of the reward and punishment gap comparison value between the expected target and the predicted target is performed by combining the target evaluation index system obtained by previous analysis and construction, so as to define a corresponding calculation formula for measuring the reward and punishment gap by using statistical software tools, such as SPSS or R language, and input the evaluation index data previously collected according to the rehabilitation target analysis to calculate the gap between the actual rehabilitation effect (i.e., the predicted target) and the set rehabilitation expected target, thereby quantifying the reward and punishment gap between the two. For example, the specific calculation formula is:

[0150] ;

[0151] In the formula, is the contrast value of the training target reward and penalty gap between the expected target and the predicted target, is the expected functional recovery rate corresponding to the expected target, is the predicted function recovery rate corresponding to the predicted target, The expected pain relief efficiency corresponding to the desired goal, The predicted pain relief efficiency corresponding to the predicted target, is the expected activity ability improvement rate corresponding to the expected goal, is the improvement rate of the predicted activity ability corresponding to the predicted target, , and They are all corresponding weight coefficients, and each evaluation indicator can be weighted, and different indicators can be given different importance weights to ensure that the final data can truly reflect the overall effect of rehabilitation training and finally obtain reward and punishment gap comparison data.

[0152] Step S253: performing gap cause feedback analysis on the reward and punishment gap comparison data to obtain a target gap comparison feedback result corresponding to the current rehabilitation training strategy.

[0153] In an embodiment of the present invention, after completing the reward and punishment gap comparison calculation, a feedback analysis of the reasons for the gap is performed on the reward and punishment gap comparison data between the corresponding expected target and the predicted target to find out the reasons for the gap between the expected target and the predicted target. With the help of data visualization tools, such as Tableau or Excel, the performance of each indicator is analyzed, and horizontal and vertical comparative analysis is performed. By comparing the gap data of different patients, common points and specific differences are found. For example, the interview method is used to collect the patient's subjective feelings during the rehabilitation training process, especially the adaptability of the training content, pain management, and perception of training intensity. This analysis will form a detailed feedback report, including the specific reasons for the gap of each indicator, such as insufficient design of the training program, low patient participation, etc., and finally obtain the target gap comparison feedback result corresponding to the current rehabilitation training strategy.

[0154] Furthermore, the present invention also provides an optimization system based on a rehabilitation training strategy, which is used to execute the above-mentioned optimization method based on a rehabilitation training strategy. The optimization system based on a rehabilitation training strategy includes:

[0155] The rehabilitation training process evaluation and analysis module is used to monitor the patient's physiology and training performance in real time during the rehabilitation training process through wearable devices to obtain the patient's real-time physiological data and real-time sports performance data; based on the real-time physiological data and the real-time sports performance data, the patient's emotional state and sports ability evaluation and analysis are performed to obtain the patient's emotional state data and sports ability data;

[0156] A rehabilitation training target feedback comparison and analysis module is used to perform rehabilitation target prediction analysis based on the emotional feeling state data and the motor ability data based on the current rehabilitation training strategy to obtain the predicted target of the patient's rehabilitation training; and to perform target feedback gap comparison analysis between the predicted target and the expected target to obtain the target gap feedback result;

[0157] A rehabilitation training strategy optimization suggestion module is used to perform strategy optimization analysis on the current rehabilitation training strategy according to the target gap feedback result, so as to adopt a decision tree or an optimization algorithm to provide corresponding rehabilitation training strategy optimization suggestions for different target gap situations of the target gap feedback result, thereby generating a rehabilitation training strategy optimization plan;

[0158] The training strategy dynamic optimization and adjustment module is used to dynamically optimize and adjust the current rehabilitation training strategy according to the strategy optimization scheme, so as to obtain an optimized rehabilitation training strategy. The specific operations of the strategy dynamic optimization and adjustment include redesigning the training course and adjusting the parameter settings of the training process.

[0159] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0160] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An optimization method based on rehabilitation training strategy, characterized in that: The following steps are involved: Step S1: monitoring the patient's physiology and training performance in real time during rehabilitation training through a wearable device to obtain the patient's real-time physiological data and real-time sports performance data; Based on the real-time physiological data and the real-time sports performance data, the patient's emotional state and sports ability are evaluated and analyzed to obtain the patient's emotional state data and sports ability data; Step S2: performing rehabilitation target prediction analysis based on the emotional state data and the motor ability data and the current rehabilitation training strategy to obtain a predicted target for the patient's rehabilitation training; Performing a target feedback gap comparison analysis on the predicted target and the expected target to obtain a target gap feedback result; wherein step S2 includes the following steps: Step S22: performing feature engineering preprocessing on the emotional state data and the motor ability data to obtain the emotional state characteristics and motor ability characteristics of the patient's rehabilitation training; performing feature time series correlation mining analysis on the emotional state characteristics and the motor ability characteristics to obtain the time series correlation relationship between the emotional state and the motor ability; Step S23: designing rehabilitation time sequence effect conditions according to the time sequence association relationship combined with the emotional feeling state data and the motor ability data, and generating effect conditions of the current rehabilitation training strategy under different time sequence conditions; Step S24: performing rehabilitation target prediction analysis based on the effect condition and the current rehabilitation training strategy to obtain a predicted rehabilitation training target for the patient; Step S25: performing a target feedback gap comparison analysis based on the patient's expected target of rehabilitation training and the predicted target to obtain a target gap comparison feedback result corresponding to the current rehabilitation training strategy; wherein step S25 includes the following steps: Step S251: constructing a target evaluation index system according to the expected target and the predicted target of the patient's rehabilitation training to generate a target evaluation index system for the patient's rehabilitation training, wherein the target evaluation index system includes the functional recovery rate, pain relief efficiency and activity ability improvement rate of the rehabilitation training; Step S252: Based on the target evaluation index system, target reward and punishment gap comparison calculation is performed on the expected target and the predicted target to obtain reward and punishment gap comparison data; wherein the target reward and punishment gap comparison calculation is calculated by a calculation formula for reward and punishment gap measurement, and the calculation formula is specifically: ； In the formula, is the contrast value of the training target reward and penalty gap between the expected target and the predicted target, is the expected functional recovery rate corresponding to the expected target, is the predicted function recovery rate corresponding to the predicted target, The expected pain relief efficiency corresponding to the desired goal, The predicted pain relief efficiency corresponding to the predicted target, is the expected activity ability improvement rate corresponding to the expected goal, is the improvement rate of the predicted activity ability corresponding to the predicted target, , and are the corresponding weight coefficients; Step S253: performing gap cause feedback analysis on the reward and punishment gap comparison data to obtain a target gap comparison feedback result corresponding to the current rehabilitation training strategy; Step S3: performing strategy optimization analysis on the current rehabilitation training strategy according to the target gap feedback result, so as to provide corresponding rehabilitation training strategy optimization suggestions for different target gap situations of the target gap feedback result by using a decision tree or optimization algorithm, and generate a rehabilitation training strategy optimization plan; Step S4: dynamically optimizing and adjusting the current rehabilitation training strategy according to the rehabilitation training strategy optimization scheme to obtain an optimized rehabilitation training strategy. The specific operations of the dynamic optimization and adjustment of the strategy include redesigning the training course and adjusting the parameter settings of the training process.

2. The optimization method based on rehabilitation training strategy according to claim 1, characterized in that: The step of evaluating and analyzing the patient's emotional state and athletic ability based on the real-time physiological data and the real-time athletic performance data to obtain the patient's emotional state data and athletic ability data includes: Step S13: performing statistical analysis on the patient's training fatigue level based on the real-time physiological data to obtain the patient's fatigue level; Step S14: evaluating and analyzing the patient's training emotional state according to the fatigue perception level to obtain the patient's emotional perception state data; Step S15: Based on the real-time sports performance data, the patient's rehabilitation training sports ability evaluation and analysis are performed to obtain the patient's sports ability data.

3. The optimization method based on rehabilitation training strategy according to claim 2, characterized in that: Step S13 includes the following steps: Step S131: extracting the patient's resting heart rate at the start of training, the heart rate during training, and the heart rate at the end of training from the real-time physiological data, and performing an inter-frame change amplitude analysis of the patient's heart rate during rehabilitation training based on the resting heart rate at the start of training, the resting heart rate at the end of training, and the resting heart rate at the end of training, to obtain the patient's inter-frame increase amplitude before training and the patient's inter-frame decrease amplitude after training; Step S132: calculating the heart rate recovery index of the patient based on the rehabilitation training process according to the increase variation range between frames before the rehabilitation training of the patient and the decrease variation range between frames after the rehabilitation training of the patient, so as to obtain the heart rate recovery index of the patient; Step S133: acquiring the patient's muscle activity during rehabilitation training according to the real-time physiological data, and performing muscle force contraction attenuation analysis according to the muscle activity to obtain the patient's muscle activity force contraction attenuation ratio during training; calculating the patient's muscle fatigue index based on the rehabilitation training process according to the muscle activity force contraction attenuation ratio to obtain the patient's muscle fatigue index of rehabilitation training; Step S134: extracting the patient's joint range of motion and the duration of the motion according to the real-time physiological data; calculating the joint flexibility reduction index based on the rehabilitation training process according to the joint range of motion and the duration of the joint motion, to obtain the joint flexibility reduction index of the patient's rehabilitation training; Step S135: Perform statistical analysis on the training fatigue level based on the heart rate recovery index, the muscle fatigue index and the joint mobility flexibility reduction index to obtain the patient's fatigue level during rehabilitation training.

4. The optimization method based on rehabilitation training strategy according to claim 3, characterized in that: The analysis of the variation amplitude between frames before and after training of the patient's varying heart rate during rehabilitation training based on the varying resting heart rate at the start of training, the varying resting heart rate at the end of training, and the varying resting heart rate at the end of the patient's rehabilitation training described in step S131 includes the following steps: Performing time coordinate system dimension synchronization processing based on the resting heart rate change at the start of training, the heart rate change during training, and the resting heart rate change at the end of training to obtain the resting heart rate change at the start of training, the heart rate change during training, and the resting heart rate change at the end of training in the same time series coordinate dimension; Divide the resting heart rate change at the beginning of training and the heart rate change during training in the same time series coordinate dimension into the pre-training time frame, and obtain the resting heart rate before training and the heart rate during training at different time frame points during the rehabilitation training; Based on the pre-training resting heart rate at different time frame points, the pre-training time frame change amplitude analysis is performed to obtain the pre-training frame increase change amplitude of the patient; The heart rate change during training and the resting heart rate change after training in the same time series coordinate dimension are divided into the post-training time frame to obtain the heart rate during training and the resting heart rate after training corresponding to different time frame points during the rehabilitation training process; The post-training inter-frame change amplitude analysis is performed based on the post-training resting heart rate at different time frame points to obtain the post-training inter-frame decline change amplitude of the patient.

5. The optimization method based on rehabilitation training strategy according to claim 3, characterized in that: Step S133 includes the following steps: Extracting the patient's muscle activity frequency and muscle activity change duration during training from the real-time physiological data, and performing muscle activity measurement calculation based on the muscle activity change duration and the muscle activity frequency to obtain the patient's muscle activity during rehabilitation training; Performing muscle force contraction statistical analysis on each muscle activity contraction during the rehabilitation training based on the muscle activity, and obtaining an estimated muscle activity contraction force corresponding to each contraction process; Performing muscle force contraction attenuation analysis based on the estimated muscle activity contraction force to obtain the muscle activity force contraction attenuation ratio during the patient's training; Based on the estimated muscle activity contraction force, the contraction fatigue cumulative effect is evaluated and analyzed for each muscle activity contraction during the rehabilitation training to obtain a contraction fatigue cumulative effect factor; The muscle fatigue index is calculated based on the muscle activity force contraction attenuation ratio and the contraction fatigue cumulative effect factor using the muscle contraction fatigue index calculation formula to obtain the patient's rehabilitation training muscle fatigue index.

6. The optimization method based on rehabilitation training strategy according to claim 5, characterized in that: The muscle contraction fatigue index calculation formula is specifically: ； In the formula, Muscle fatigue index for patients' rehabilitation training, is the total time of the rehabilitation training process, For time, For time The muscle activity force contraction decay ratio at For time The cumulative effect factor of contraction fatigue at For time External load on muscle activity at For time The muscle activity recovery ability of is the muscle force contraction attenuation constant, It is the correction factor of muscle fatigue index.

7. The optimization method based on rehabilitation training strategy according to claim 3, characterized in that: The calculation of the joint flexibility reduction index based on the joint range of motion and the joint activity duration in the rehabilitation training process comprises the following steps: Performing joint motion variation analysis on the joint motion range to obtain the patient's joint motion variation; Quantitatively calculate the joint movement rate based on the joint movement duration and the joint movement change amplitude to obtain the joint movement rate of the patient during rehabilitation training; The joint flexibility reduction index is calculated according to the joint motion range and the joint motion rate to obtain the joint flexibility reduction index of the patient's rehabilitation training.

8. An optimization system based on rehabilitation training strategy, characterized in that: For executing the optimization method based on rehabilitation training strategy as claimed in claim 1, the optimization system based on rehabilitation training strategy comprises: The rehabilitation training process evaluation and analysis module is used to monitor the patient's physiology and training performance in real time during the rehabilitation training process through wearable devices to obtain the patient's real-time physiological data and real-time sports performance data; based on the real-time physiological data and the real-time sports performance data, the patient's emotional state and sports ability evaluation and analysis are performed to obtain the patient's emotional state data and sports ability data; A rehabilitation training target feedback comparison and analysis module is used to perform rehabilitation target prediction analysis based on the emotional feeling state data and the motor ability data based on the current rehabilitation training strategy to obtain the predicted target of the patient's rehabilitation training; and to perform target feedback gap comparison analysis between the predicted target and the expected target to obtain the target gap feedback result; A rehabilitation training strategy optimization suggestion module is used to perform strategy optimization analysis on the current rehabilitation training strategy according to the target gap feedback result, so as to adopt a decision tree or an optimization algorithm to provide corresponding rehabilitation training strategy optimization suggestions for different target gap situations of the target gap feedback result, thereby generating a rehabilitation training strategy optimization plan; The training strategy dynamic optimization and adjustment module is used to dynamically optimize and adjust the current rehabilitation training strategy according to the strategy optimization scheme, so as to obtain an optimized rehabilitation training strategy. The specific operations of the strategy dynamic optimization and adjustment include redesigning the training course and adjusting the parameter settings of the training process.

Images