Muscle satellite cell regulation-based skeletal muscle repair method and system

Abstract

The application discloses a skeletal muscle repair method and system based on muscle satellite cell regulation, and performs proliferation differentiation correlation analysis on satellite cell steady state data and aerobic exercise intensity data to establish a proliferation regulation map; a synergistic repair time window is determined according to the map, a difference response deviation correction parameter is extracted to form an activity correction factor, repair intensity correction is performed on the synergistic repair time window to generate a self-adaptive repair window; the self-adaptive repair window is subjected to exercise prescription adaptation and satellite cell activation regulation pathways are identified, an activation delay time is obtained through activation efficiency mapping, a response level is generated according to the activation delay time to form a layered repair configuration; a preferred activation mode is determined through activation delay evaluation on the layered repair configuration, dynamic activation characteristics are formed by extracting data of the best activation time window, skeletal muscle repair execution instructions are output in combination with an exercise prescription parameter table, and satellite cell repair state monitoring and dynamic synergistic adaptation of training scheme parameters are realized.

Description

Technical Field

[0001] This invention relates to the field of sports medicine information processing technology, and in particular to a method and system for skeletal muscle repair based on muscle satellite cell regulation. Background Technology

[0002] In rehabilitation training following skeletal muscle injury, aerobic exercise intervention can promote muscle function recovery by improving the microenvironment of the injured area. However, there are significant differences among individuals in terms of the degree of injury, the stage of repair, and exercise tolerance. Existing rehabilitation training programs mostly rely on empirically defined general intensity ranges and fixed training time windows, lacking dynamic perception of the individual's muscle repair status. This makes it difficult to accurately match the timing and intensity of exercise intervention to the current repair rhythm, resulting in insufficient individualization of training programs.

[0003] On the other hand, continuous and intermittent exercise modes have different effects on promoting muscle repair. Existing methods lack a quantitative comparison mechanism for the differences in cellular responses between the two modes, making it impossible to dynamically adjust the intensity boundaries of the training window. Similarly, at the level of activation pathway assessment and training timing planning, existing methods lack the ability to integrate the spatial distribution characteristics of the injury area, activation response delay, and cumulative training load into a unified decision-making framework, making it difficult to output executable, individualized training instructions. Summary of the Invention

[0004] This invention discloses a skeletal muscle repair method and system based on muscle satellite cell regulation. By collecting satellite cell homeostasis data and aerobic exercise intensity data, a proliferation regulation map is established. Based on the map, a collaborative repair time window is determined and an adaptive repair window is generated by combining exercise mode response deviation. On this basis, satellite cell activation regulation pathways are identified, activation delays are assessed, and response levels are defined to generate a hierarchical repair configuration. Finally, based on the exercise prescription parameter table and intervention execution sequence, executable skeletal muscle repair instructions are output, realizing individualized collaborative planning of repair window, exercise intensity, and intervention timing.

[0005] The first aspect of this invention proposes a skeletal muscle repair method based on myosatellite cell regulation, comprising the following steps:

[0006] Satellite cell homeostasis data and aerobic exercise intensity data were collected from the damaged skeletal muscle region. Based on the satellite cell homeostasis data and the aerobic exercise intensity data, a proliferation regulation map was established by performing a proliferation and differentiation correlation analysis.

[0007] Based on the proliferation regulation map, a synergistic repair time window is determined. Differential response deviation correction parameters are extracted from the satellite cell homeostasis data and the aerobic exercise intensity data to form an activity correction factor. The activity correction factor is used to correct the repair intensity of the synergistic repair time window to generate an adaptive repair window.

[0008] The adaptive repair window is adapted to the exercise prescription to form an exercise prescription parameter table. Satellite cell activation regulation pathways are identified according to the exercise prescription parameter table. The activation delay time is obtained by mapping the muscle satellite cell activation efficiency of the satellite cell activation regulation pathways. The response level is determined according to the activation delay time to generate a layered repair configuration.

[0009] The activation delay of the layered repair configuration is evaluated to determine the preferred activation method. The optimal activation time window data of the preferred activation method is detected. Based on the optimal activation time window data, the dynamic activation characteristics of muscle satellite cells are extracted, the activation priority is adjusted, and an intervention execution sequence is formed. Based on the exercise prescription parameter table and the intervention execution sequence, the skeletal muscle repair execution command is output.

[0010] A second aspect of this invention proposes a skeletal muscle repair system based on myosatellite cell regulation, comprising:

[0011] The data acquisition module is used to collect satellite cell homeostasis data and aerobic exercise intensity data in the damaged skeletal muscle region, and to establish a proliferation regulation map based on the proliferation and differentiation correlation analysis of the satellite cell homeostasis data and the aerobic exercise intensity data.

[0012] The window correction module is used to determine the synergistic repair time window based on the proliferation regulation map, extract differential response deviation correction parameters from the satellite cell homeostasis data and the aerobic exercise intensity data to form an activity correction factor, and use the activity correction factor to perform repair intensity correction on the synergistic repair time window to generate an adaptive repair window;

[0013] The prescription adaptation module is used to adapt the adaptive repair window to the exercise prescription to form an exercise prescription parameter table, identify the satellite cell activation regulation pathway according to the exercise prescription parameter table, perform muscle satellite cell activation efficiency mapping on the satellite cell activation regulation pathway to obtain the activation delay time, and determine the response level and generate a layered repair configuration based on the activation delay time.

[0014] The instruction generation module is used to evaluate the activation delay of the layered repair configuration to determine the preferred activation method, detect the optimal activation time window data of the preferred activation method, extract the dynamic activation characteristics of muscle satellite cells based on the optimal activation time window data, adjust the activation priority to form an intervention execution sequence, and output skeletal muscle repair execution instructions based on the exercise prescription parameter table and the intervention execution sequence.

[0015] The beneficial effects of this invention are reflected in the following aspects: First, by collecting satellite cell homeostasis data and aerobic exercise intensity data, a proliferation regulation map is established through proliferation and differentiation correlation analysis. Differential response deviation correction parameters are extracted to form activity correction factors, which are then used to correct the repair intensity within the synergistic repair time window. This establishes a quantitative mapping link from satellite cell repair status to exercise prescription parameters, improving the accuracy of the repair time window's adaptation to individual exercise response differences. Second, after adapting the adaptive repair window to an exercise prescription, satellite cell activation regulation pathways are identified, and activation efficiency mapping is performed to obtain activation delay time. Based on the activation delay time, response levels are defined, and repair weights are assigned to generate a tiered repair configuration. This achieves a direct correlation between activation efficiency assessment and training sequence planning, improving the ability of the tiered repair configuration to express response differences at different repair stages. Finally, by evaluating the activation delay of the tiered repair configuration to determine the preferred activation method and extracting dynamic activation characteristics based on the optimal activation time window data to form an intervention execution sequence, the dynamic activation characteristics of satellite cells are transformed into executable training parameters, enabling skeletal muscle repair execution commands to have individualized adjustment capabilities at the activation response characteristic level.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The accompanying drawings illustrate specific examples of the technical solutions described in this invention and, together with the detailed embodiments, form part of the specification, serving to explain the technical solutions, principles, and effects of this invention.

[0018] Figure 1 This is a flowchart of the skeletal muscle repair method based on muscle satellite cell regulation according to the present invention.

[0019] Figure 2 This is a structural block diagram of the skeletal muscle repair system based on muscle satellite cell regulation, as described in this invention. Detailed Implementation

[0020] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0021] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0022] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0023] The technical solutions of the embodiments of this application will be described below.

[0024] like Figure 1 As shown, this embodiment of the invention provides a skeletal muscle repair method based on myosatellite cell regulation, including the following steps S110-S140:

[0025] Step S110: Collect satellite cell homeostasis data and aerobic exercise intensity data in the damaged skeletal muscle region, and establish a proliferation regulation map based on the proliferation and differentiation correlation analysis of satellite cell homeostasis data and aerobic exercise intensity data.

[0026] Specifically, satellite cell homeostasis data and aerobic exercise intensity data were collected from the damaged skeletal muscle region. Fluorescent immunohistochemistry was used to sequentially label biopsy sections of the damaged area with four antibodies: Pax7, Ki67, MyoD, and Myogenin. The count density, co-expression ratio, and fluorescence intensity of each labeled positive cell were recorded in the satellite cell homeostasis data. Spatial sampling of the satellite cell homeostasis data covered three levels: the core of the injury, the edge of the injury, and the surrounding normal area. Three non-overlapping fields of view (field area not less than 0.2 mm²) were taken from each level. The Pax7 positive density (cells / mm²), percentage of activated cells (%), MyoD expression intensity (fluorescence integral gray value), and Myogenin co-expression ratio (%) of each field of view were independently recorded and labeled with location. Satellite cell homeostasis data were collected within 24 hours after the end of exercise intervention on days 3, 7, and 14 post-skeletal muscle injury. The three collection time points were aligned with the exercise intervention time window, covering the three repair phases: acute inflammation, peak proliferation, and remodeling. Aerobic exercise intensity data were collected simultaneously by a heart rate monitor and a portable metabolic analyzer. Fields included heart rate (bpm), oxygen uptake (mL / kg / min), and duration of a single exercise session (min), with a temporal resolution of recording every 30 seconds. The exercise intervention began on day 2 after skeletal muscle injury. Aerobic exercise intensity data were continuously recorded from the start of each warm-up phase until the end of the recovery period, fully covering the metabolic change curves throughout aerobic exercises such as running, stationary cycling, or swimming. Aerobic exercise intensity data were collected at each session during the entire exercise intervention. The pairing rule for satellite cell homeostasis data and aerobic exercise intensity data was as follows: satellite cell homeostasis data on days 3, 7, and 14 were aligned with the aerobic exercise intensity data from the most recent exercise intervention at the same time point. The two types of data formed a point-by-point pairing association at these three time points. Data with a pairing interval exceeding 48 hours were discarded and not included in subsequent feature extraction.

[0027] In some embodiments, the step of establishing a proliferation regulation map based on the proliferation and differentiation correlation analysis of the satellite cell homeostasis data and the aerobic exercise intensity data includes: performing multidimensional feature extraction on the satellite cell homeostasis data and the aerobic exercise intensity data to obtain a set of cell feature parameters; performing damage degree grading identification based on the set of cell feature parameters to obtain damage grading identifiers; performing proliferation and differentiation potential correlation analysis on the damage grading identifiers and the set of cell feature parameters to form potential correlation parameters; and constructing a proliferation regulation map through the potential correlation parameters.

[0028] Multidimensional feature extraction was performed on satellite cell homeostasis data and aerobic exercise intensity data to obtain a set of cell feature parameters. First, spatial hierarchical normalization was performed on the satellite cell homeostasis data. The mean of each measurement item in the surrounding normal area was used as the baseline, and the absolute values ​​of the damaged core area and the edge area were converted into the change ratio relative to the baseline. The transformed satellite cell homeostasis data extracted two features in the morphological dimension: Pax7 density change ratio and activated state ratio; two features in the proliferation kinetic dimension: Ki67 marker proliferation index and MyoD expression intensity change rate; one feature in the spatial gradient dimension: Pax7 density difference between the core area and the edge area; and one feature in the differentiation process dimension: the co-expression ratio of MyoD and Myogenin. A total of six satellite cell homeostasis data features were obtained from the four dimensions. Aerobic exercise intensity data was analyzed using two features: percentage of maximum oxygen uptake and heart rate (bpm) corresponding to lactate threshold, extracted from the metabolic dimension; two features: duration of peak intensity (min) and slope of intensity change (%VO2max / min), extracted from the temporal dimension; and one feature: total energy consumption per session (kcal), extracted from the cumulative load dimension. This yielded five aerobic exercise intensity data features across three dimensions. After the satellite cellular homeostasis data and aerobic exercise intensity data were extracted at each time point, the two sets of features at the same time point were concatenated into a feature vector of length 11. The feature vectors from the three time points were arranged chronologically to form a cellular feature parameter set. The cellular feature parameter set has a dimension of 3×11, with rows corresponding to time points and columns corresponding to feature items. Missing values ​​in the cellular feature parameter set were filled using linear interpolation. When the completeness rate was below 85%, the cellular feature parameter set was marked as low-quality. After marking low-quality states, max-min normalization was performed on each column of the cellular feature parameter set, mapping the values ​​of each feature item to the [0,1] interval.

[0029] Damage severity grading is performed based on a set of cellular feature parameters to obtain damage grading labels. Before being input into the classifier, the cellular feature parameter set undergoes feature importance screening, removing redundant features with a variance below 0.05, retaining 7 to 9 effective features. Damage severity grading is performed using a support vector machine classifier. The classifier takes the effective features from the screened cellular feature parameter set as input and outputs three damage level labels: mild, moderate, and severe. The classifier's training samples are derived from 500 historical skeletal muscle repair observation data points with manually labeled damage severity. When the Pax7 density change ratio in the morphological dimension of the cellular feature parameter set is below 0.5 and the Ki67 proliferation index in the proliferation kinetic dimension is above 0.6, the classifier initially classifies the sample at that time point as a severe damage category. The spatial gradient features of the cellular feature parameter set are used to distinguish between localized and diffuse damage. A Pax7 density difference greater than 0.4 between the core and peripheral areas of the damage is classified as localized, and less than or equal to 0.4 as diffuse. The range type is added as an auxiliary field to the damage grading label. When the cell feature parameter set carries low-quality state labels, the classification confidence score output by the classifier is automatically reduced by 0.15 to reflect the impact of insufficient input data quality on classification reliability. The core fields of the damage classification label include three items: damage level label, damage range type, and classification confidence score for each time point. Time points with a confidence score below 0.7 in the damage classification label are marked as classification uncertain states. The soft label records the probability distribution of this point belonging to each level, which is used for probability-weighted processing in the subsequent potential association parameter generation step.

[0030] A correlation analysis of proliferation and differentiation potential was performed between damage grading labels and cell characteristic parameter sets to form potential correlation parameters. The three damage grading labels—mild, moderate, and severe—each correspond to a set of pre-defined proliferation potential curves. These curves were derived from historical observation data from in vitro satellite cell damage intensity gradient experiments. The proliferation and differentiation potential correlation analysis mapped the damage grading label at each time point to the corresponding pre-defined curve to obtain the expected proliferation value at that time point. For diffuse damage, the expected proliferation value at the time point was taken as the upper quartile of historical repair-achieving samples of the same grade; for localized damage, the median value was taken. The difference between the measured Ki67-labeled proliferation index and the expected proliferation value in the cell characteristic parameter set was defined as the proliferation deviation. The percentage of activated states in the cell characteristic parameter set was used as an auxiliary verification item. A positive proliferation deviation indicated that the measured proliferation level was higher than expected, while a negative value indicated that it was lower than expected. The proliferation deviation values ​​at each time point were written into the first field of the potential correlation parameters. Differentiation state categories are determined by the co-expression ratio of MyoD and Myogenin in the cell characteristic parameter set. A co-expression ratio exceeding 40% is labeled as a differentiation-dominant state, below 20% as a proliferation and expansion state, and between 20% and 40% as a proliferation-differentiation transition state. For uncertain time points with a confidence level below 0.7 in the damage grading identifier, the differentiation state category is determined by weighting the soft-label probability distribution. The differentiation state category at each time point is written into the second field of the potential association parameter. The differentiation direction confidence score is based on the grading confidence score of the damage grading identifier. It is increased by 0.05 when the co-expression ratio in the cell characteristic parameter set is above 60% or below 10%, and decreased by 0.05 in the 20% to 40% transition range, truncated to the [0.4, 0.95] interval. The differentiation direction confidence score at each time point is written into the third field of the potential association parameter. The potential association parameter includes three fields at each of the three time points: proliferation deviation value (%), differentiation state category, and differentiation direction confidence score.

[0031] A proliferation regulation map was constructed using potential correlation parameters. The proliferation deviation values ​​at three time points in the potential correlation parameters were projected onto the vertical axis of a two-dimensional coordinate system, while the values ​​at days 3, 7, and 14 post-injury were projected onto the horizontal axis. These three coordinate points were connected using cubic spline interpolation to form the proliferation trajectory curve of the proliferation regulation map. A positive slope indicates repair progress, while a negative slope suggests suppressed proliferation. The differentiation state category field of the potential correlation parameters determined the naming of the three functional zones of the proliferation regulation map. The coordinate space was sequentially divided into a proliferation-dominant zone, a proliferation-differentiation transition zone, and a differentiation-dominant zone. The numerical coordinates of the boundaries of each zone were determined by the mean ± 1 standard deviation of the proliferation deviation distribution under the corresponding differentiation state category in historical repair-achieving samples. Each functional zone of the proliferation regulation map is labeled with a recommended range of aerobic exercise intensity. The upper and lower limits of the recommended range are determined by the quartile intervals of aerobic exercise intensity data from 14-day rehabilitated samples within the zone. The proliferation-dominant zone corresponds to low-to-moderate intensity at 40% to 60% of maximum oxygen uptake, the transition zone corresponds to moderate intensity at 60% to 70%, and the differentiation-dominant zone corresponds to high intensity at 70% to 80%. The differentiation direction confidence field of the potential-related parameter adjusts the ambiguity of the boundaries of each zone in the proliferation regulation map. When the confidence level is higher than 0.8, the zone boundaries are hard-defined; when the confidence level is between 0.6 and 0.8, a 5% ambiguity overlap area is allowed; and when the confidence level is lower than 0.6, a 10% ambiguity overlap area is allowed. The recommended exercise intensity value for the overlapping area is the weighted average of the recommended ranges of adjacent zones. The proliferation regulation map is stored in the form of a structure, and the structure fields include four items: proliferation trajectory curve data points, functional zone boundary coordinates, recommended range of aerobic exercise intensity for each zone, and zone confidence weight.

[0032] Step S120: Determine the synergistic repair time window based on the proliferation regulation map, extract differential response deviation correction parameters from satellite cell homeostasis data and aerobic exercise intensity data to form an activity correction factor, and use the activity correction factor to perform repair intensity correction on the synergistic repair time window to generate an adaptive repair window.

[0033] Specifically, the synergistic repair time window is determined based on the proliferation regulation map. After the proliferation trajectory curve data points of the proliferation regulation map are interpolated using cubic splines to generate a continuous curve, the earliest moment when the slope of the proliferation deviation on the curve changes from negative to positive is defined as the initial boundary of the synergistic repair time window. A positive slope indicates that the satellite cell proliferation level has begun to exceed the damage inhibition effect, and skeletal muscle has entered a repair active period suitable for aerobic exercise intervention. The functional zone boundary coordinates of the proliferation regulation map are used to verify the zone where the initial boundary is located. When the initial boundary falls into the proliferation-dominant zone, the initial boundary of the synergistic repair time window is advanced by 0.5 days; when it falls into the transition zone, the original judgment value is maintained; when it falls into the differentiation-dominant zone, the synergistic repair time window is delayed by 1 day to allow the differentiation process to fully initiate. The recommended range of aerobic exercise intensity for each zone in the proliferation regulation map is mapped to the intensity range of the synergistic repair time window. The upper limit of the recommended range for the zone where the initial boundary is located is used as the initial upper bound of the intensity range, and the lower limit is used as the initial lower bound. For example, when the initial boundary falls into the proliferation-dominant zone, the intensity range is set to 40%-60% of maximum oxygen uptake. The termination boundary of the synergistic repair time window is defined as the moment when the proliferation deviation on the spline interpolation curve of the proliferation regulation map exceeds the peak and then continues to decrease, with the absolute value of the slope exceeding 0.02 for three consecutive days. If the above-mentioned continuous decrease characteristic does not appear within the sample data coverage area, the termination boundary is set by default to day 14 post-injury. When the confidence weight of the partition of the proliferation regulation map is less than 0.6, the start and termination boundaries of the synergistic repair time window are each extended by ±0.5 days to cover the uncertainty assessment; when the confidence weight is greater than 0.8, the boundary is hard-divided and not extended. The synergistic repair time window is calibrated by the start and termination boundary times, and the intensity interval within the window is described by the percentage interval of maximum oxygen uptake. Both the start and termination boundaries are in units of days post-injury.

[0034] In some embodiments, the step of extracting differential response deviation correction parameters from the satellite cell homeostasis data and the aerobic exercise intensity data to form an active correction factor includes: identifying exercise type in the satellite cell homeostasis data and the aerobic exercise intensity data to obtain exercise mode labels; extracting continuous exercise response deviation and intermittent exercise response deviation using the exercise mode labels; differentially integrating the continuous exercise response deviation and the intermittent exercise response deviation to form differential response deviation correction parameters; and generating an active correction factor based on the differential response deviation correction parameters.

[0035] Exercise mode labels are obtained by identifying exercise types from satellite cell homeostasis data and aerobic exercise intensity data. After converting the aerobic exercise intensity data rate to heart rate reserve percentage (Heart Rate Reserve Percentage = (Real-time Heart Rate - Resting Heart Rate) / (Maximum Heart Rate - Resting Heart Rate) × 100%, where resting heart rate is the average of the previous 5 minutes of rest, and maximum heart rate is estimated by subtracting age from 220), exercise segments with a heart rate reserve percentage maintained continuously in the 50%-70% range for more than 15 minutes and with amplitude fluctuations not exceeding 10% are identified as continuous exercise modes. Aerobic exercise intensity data periods meeting these criteria are labeled as continuous in the exercise mode label. Exercise segments with a heart rate reserve percentage sequence of aerobic exercise intensity data showing more than two peak-to-trough alternations within 15 minutes and a peak-to-trough difference of not less than 20% are identified as intermittent exercise modes. The intermittent identification result is simultaneously written into the intermittent category field of the exercise mode label. When the mean difference of the Ki67 proliferation index in satellite cell homeostasis data between the corresponding time points of continuous and intermittent modes exceeds 15%, it serves as a valid criterion for validating the exercise pattern label classification, and the confidence level remains unchanged. A difference of less than 5% indicates that the two types of exercise do not clearly distinguish the satellite cell responses, and the confidence level of the exercise pattern label classification decreases. Exercise pattern labels are generated only at time points where both satellite cell homeostasis data and aerobic exercise intensity data are completely paired; no exercise pattern label is generated for any missing time point. Exercise pattern labels are stored in the form of time point sequences, with each exercise intervention time point accompanied by a continuous or intermittent category label. For example, a subject might be labeled as having a continuous exercise pattern on day 3 and an intermittent exercise pattern on day 7. In aerobic exercise intensity data, if the duration of a continuous mode exceeds 60% in a certain exercise segment, continuous mode is used as the overall exercise pattern label; if the duration of an intermittent mode exceeds 60%, intermittent mode is used as the overall exercise pattern label; if the duration of both continuous and intermittent modes does not exceed 60%, they are uniformly labeled as a mixed mode, and bias extraction is skipped, covering all duration proportions.

[0036] For example, the step of extracting continuous exercise response deviation and intermittent exercise response deviation using the exercise pattern label includes: obtaining key nodes of exercise intensity in the exercise pattern label; detecting cardiopulmonary metabolic response fluctuation features at the key nodes of exercise intensity to generate response tracking parameters; using the response tracking parameters to perform deviation correlation localization to generate a deviation candidate set; and generating continuous exercise response deviation and intermittent exercise response deviation based on the deviation candidate set and the response tracking parameters.

[0037] Retrieve key intensity nodes from exercise pattern tags. Moments where the heart rate variability exceeds 5 bpm / min for two consecutive minutes within the corresponding time period of the exercise pattern tag are marked as candidate intensity inflection points. Adjacent candidate points with an interval of less than 3 minutes are merged into a single key intensity node. Key intensity nodes for continuous exercise pattern segments within exercise pattern tags typically appear 5-10 minutes after exercise initiation, corresponding to the physiological inflection point where oxygen uptake transitions from a rapid increase to a steady state. Each intervention in a continuous exercise segment usually generates 2-4 key intensity nodes. For intermittent exercise pattern segments within exercise pattern tags, each set of high-intensity sprints generates 2 key intensity nodes, corresponding to the start of the intensity increase and the end of the intensity decrease, respectively. The heart rate decline during the recovery phase between sets is already included in the preceding changes at the start of the increase and does not generate additional independent nodes. An intermittent intervention with 6 sets of sprints typically generates 12 key intensity nodes. Key intensity nodes are stored as a timestamp sequence, with each node including two attributes: the type of exercise pattern tag it belongs to and the direction of the intensity inflection (increase or decrease). In motion mode labels, key motion intensity nodes are not extracted for mixed mode time points, as bias extraction is skipped in the motion mode label generation step. If the number of key motion intensity nodes is less than 2, the motion intensity change at that time point is considered insignificant, and the response tracking parameter generation step skips that time point.

[0038] Response tracking parameters are generated by detecting the fluctuation characteristics of cardiopulmonary metabolic response at key nodes of exercise intensity. For each key node, a 60-second data segment is extracted before and after it. The peak-to-trough difference in oxygen uptake (mL / kg / min) within the data segment is defined as the fluctuation amplitude component of the response tracking parameter. This component is calculated for all node types to ensure a consistent vector dimension for the response tracking parameter. When the key node of exercise intensity is ascending, the rate of heart rate rise (bpm / s) within the 60-second window is used as the dynamic response component of the response tracking parameter, while the recovery response component is set to 0. For descending nodes, the rate of oxygen uptake fall (mL / kg / min / s) within the 60-second window is used as the recovery response component, while the dynamic response component is set to 0. Both types of nodes maintain a three-dimensional vector structure of fluctuation amplitude, dynamic response, and recovery response. The three-dimensional vectors of the response tracking parameters are arranged chronologically to form a response tracking parameter sequence. The vector dimension of the response tracking parameters across multiple nodes is consistent, supporting direct comparison across node types. When data is missing within the 60-second window corresponding to a key node of exercise intensity, the missing components of the response tracking parameter are filled in using the mean value of nodes of the same type within the same exercise segment. When the standard deviation of the amplitude component of the response tracking parameter sequence exceeds 0.3, it indicates that the motion intensity fluctuates violently, and the representativeness of the overall response tracking parameters has decreased.

[0039] Deviation candidate sets are generated using response tracking parameters for deviation correlation localization. Nodes in the response tracking parameter sequence whose fluctuation amplitude component exceeds 1.5 times the average oxygen uptake during the entire exercise are marked as high-response candidate points, and their response tracking parameter vectors are included in the deviation candidate set. Nodes with a dynamic response component exceeding 0.2 bpm / s and a recovery response component below 0.05 mL / kg / min / s are simultaneously included in the deviation candidate set; this feature combination corresponds to the fatigue accumulation phenomenon of rapid heart rate increase but slow oxygen uptake decline. Each candidate point in the deviation candidate set records two pieces of information: the corresponding response tracking parameter vector and the node's exercise mode label type. Nodes whose response tracking parameters simultaneously meet both fluctuation amplitude and dynamic / recovery response thresholds are assigned dual candidate labels. The weight coefficient for dual candidate points in the deviation candidate set is set to 1.5 (derived from the correlation regression analysis between dual threshold features and satellite cell activation efficiency in historical samples), while the weight coefficient for single-threshold candidate points is 1.0. When the number of candidate points in the deviation candidate set exceeds 10, the top 10 are retained in descending order of fluctuation amplitude component; this number limitation prevents a decrease in deviation identification accuracy due to an excessive number of candidate points. When the candidate set of deviations is empty, it is marked as a state with no significant deviation. The next step is to return the continuous motion response deviation and the intermittent motion response deviation as zero vectors based on this state.

[0040] Based on the deviation candidate set and response tracking parameters, persistent motion response deviations and intermittent motion response deviations are generated. The motion mode label type field of each candidate point in the deviation candidate set assigns the candidate point to the persistent or intermittent category. The fluctuation amplitude component in the response tracking parameter vector of the persistent category candidate points is normalized and used as a weighting coefficient. The weighted mean of the weighting coefficients forms the basic value of the fluctuation amplitude of the persistent motion response deviation. The difference between the baseline value of the fluctuation amplitude of the response tracking parameters and the mean value of the fluctuation amplitude of the response tracking parameters in the continuous exercise mode of historical repair samples with the same degree of damage is used as the active state proportion deviation component of the continuous exercise response bias. The larger the fluctuation amplitude, the stronger the satellite cell active state proportion response. The difference between the weighted mean of the dynamic response component of the response tracking parameters and the historical baseline dynamic response mean is used as the Ki67 bias component. The faster the heart rate rise rate, the more significant the Ki67 proliferation index response. The difference between the weighted mean of the recovery response component of the response tracking parameters and the historical baseline recovery response mean is used as the MyoD bias component. The slower the oxygen uptake decline rate, the more sufficient the MyoD differentiation and expression. The three components together constitute the three-dimensional vector of the continuous exercise response bias (active state proportion bias, Ki67 bias, MyoD bias). Intermittent movement response bias is generated using the same logic. Intermittent category candidate points in the bias candidate set are independently normalized and weighted. The historical baseline is the mean of samples with the same level of injury in the intermittent movement pattern. For example, if the mean of the fluctuation amplitude component of the intermittent movement response tracking parameter for a subject's current intervention is 0.45, higher than the historical baseline of 0.32, the activation state proportion bias component is recorded as +0.13. When the bias candidate set is labeled as having no significant bias, both continuous movement response bias and intermittent movement response bias return zero vectors, indicating that no significant response fluctuation was detected in this intervention. The three-dimensional vectors of continuous and intermittent movement response bias each include two auxiliary fields: sample size and confidence score. When the sample size is less than 2, the confidence score for the corresponding type of response bias automatically decreases to below 0.5.

[0041] Differential response bias and intermittent motion response bias are integrated to form differential response bias correction parameters. When the absolute value of the difference in vector magnitude between the persistent and intermittent motion response biases exceeds 0.1, a significant differential satellite cell response is identified between the two modes, and this difference is incorporated into the principal component integration of the differential response bias correction parameters. The corresponding components of the persistent and intermittent motion response biases (activation state percentage bias, Ki67 bias, and MyoD bias) are subtracted from each other. Each of the three differences is then standardized by dividing by the historical sample standard deviation of the corresponding component to ensure comparability of components with different dimensions. The standardized three differences constitute a three-dimensional vector of the differential response bias correction parameters. The direction of each component is determined by subtracting the persistent from the intermittent; positive values ​​indicate a stronger intermittent motion response. After standardizing the three-dimensional vector of the differential response bias correction parameter and taking its magnitude, the maximum difference in magnitude between the standardized response biases of the two motion modes in the historical samples is used as the normalization benchmark. The magnitude is mapped to the interval of 0 to 0.3. A positive value is taken when the magnitude of the intermittent vector is greater than that of the persistent vector, and a negative value is taken otherwise. The final scalar range is -0.3 to +0.3. When the difference in sample size between the persistent and intermittent motion response biases exceeds two time points, a sample imbalance label is added to the differential response bias correction parameter. The confidence score is reduced by 0.1 in the imbalanced state. The confidence level of the differential response bias correction parameter is determined by taking the lower of the mean confidence levels of the persistent and intermittent motion response biases. When the lower value is below 0.7, the differential response bias correction parameter is labeled as having low confidence.

[0042] An activity correction factor is generated based on the differential response bias correction parameter. A positive scalar value of the differential response bias correction parameter indicates that the intermittent movement pattern is more effective in activating satellite cells in the current repair phase than the continuous movement pattern, while a negative value indicates that the continuous movement pattern is superior. The goal of generating the activity correction factor is to quantify this difference as a coefficient of increase or decrease in repair intensity. Positive differential response bias correction parameters are linearly mapped piecewise to generate an activity correction factor greater than 1. When the differential response bias correction parameter is in the range of 0 to 0.1, the difference between the two movement patterns has no practical adjustment significance, and the activity correction factor is set to 1.0. In the range of 0.1 to 0.2, it is linearly mapped to 1.0 to 1.2, with a mapping slope of 2.0 / unit scalar value, reflecting the linear amplification effect of moderate difference on repair intensity. In the range of 0.2 to 0.3, it is mapped to 1.2 to 1.3, with the slope decreasing to 1.0 / unit scalar value. The decreasing slope prevents extreme differences from causing the activity correction factor to be too large. The negative value range is mirrored to the 0.7 to 1.0 range with zero as the axis of symmetry. The mapping rule is completely symmetrical with that of the positive values, and the overall range of the activity correction factor is constrained to 0.7 to 1.3. When the differential response bias correction parameter carries a sample imbalance label, the mapping result of the activity correction factor is shrunk by 10% towards the neutral value of 1.0 according to the formula f_adj=1.0+(f-1.0)×0.9. For example, if the original mapping result is 1.2, it will be 1.18 after shrinkage. The shrinkage operation avoids excessive deviation of the activity correction factor from the neutral value caused by sample bias. When the confidence level of the differential response bias correction parameter is lower than 0.5, the activity correction factor is forced to take the neutral value of 1.0. The neutral value indicates that the current data quality is insufficient to support the application of correction to the repair intensity. The confidence field of the activity correction factor inherits the confidence value and low confidence label of the differential response bias correction parameter. When the confidence level is lower than 0.6, it is recommended to increase the frequency of satellite cell steady-state data acquisition and then re-extract the differential response bias correction parameter.

[0043] An adaptive repair window is generated by correcting the repair intensity of the synergistic repair time window using an activity correction factor. The starting boundary time of the synergistic repair time window is corrected by the activity correction factor, with the correction formula being T_start*=T_start-(f-1.0)×k, where T_start* is the number of days of the corrected starting boundary, T_start is the original number of days of the starting boundary, f is the activity correction factor, and k is the adjustment ratio coefficient (determined by historical sample regression, defaulting to 2 days). When the activity correction factor is greater than 1.0, the correction result causes the window to start earlier; when it is less than 1.0, the start is delayed, with an adjustment range not exceeding ±1 day. The activity correction factor is applied to correct the upper and lower bounds of the intensity interval of the synergistic repair time window. The upper bound of the intensity interval is multiplied by the activity correction factor to obtain the corrected upper bound of the adaptive repair window intensity, and the lower bound of the intensity interval is multiplied by the activity correction factor to the power of 0.8 (the coefficient of the power of 0.8 comes from the regression fitting of the compression amplitude of the lower bound of historical samples with the repair effect) to obtain the corrected lower bound of the intensity. A reduction coefficient is introduced into the lower bound to prevent the low-intensity interval from being over-compressed. When the upper bound of the adaptive repair window's correction intensity exceeds 85% of maximum oxygen uptake, it is forcibly truncated to 85% to prevent the exercise load from exceeding the current capacity of skeletal muscle. For example, performing aerobic exercise at an intensity exceeding 85% on the third day after a severe injury can inhibit satellite cell proliferation. The termination boundary of the co-repair time window is not affected by the activity correction factor; the termination boundary retains the original judgment value as the termination time of the adaptive repair window. When the confidence level of the activity correction factor is below 0.6, the adaptive repair window is marked as a low-confidence state, and the correction start time and correction intensity range are synchronously reverted to the original start boundary and intensity range of the co-repair time window to ensure the internal consistency of the window parameters in the low-confidence state. The adaptive repair window uses the correction start time and termination time to define the effective intervention range, and the correction intensity range is described as a percentage range of maximum oxygen uptake. The low-confidence state label is output along with the window parameters for reference in subsequent adaptation steps.

[0044] Step S130: Adapt the adaptive repair window to the exercise prescription to form an exercise prescription parameter table. Identify the satellite cell activation regulation pathway based on the exercise prescription parameter table. Map the muscle satellite cell activation efficiency of the satellite cell activation regulation pathway to obtain the activation delay time. Determine the response level based on the activation delay time to generate a layered repair configuration.

[0045] Specifically, the adaptive repair window is adapted to form an exercise prescription parameter table. The time span from the start to the end of the adaptive repair window is divided into three equal parts. The boundaries of the three time segments are calculated sequentially from the start of the correction and written into the prescription phase time window field of the exercise prescription parameter table. The three phases correspond to the early activation phase, the peak proliferation phase, and the functional remodeling phase of skeletal muscle repair, respectively. For example, when the adaptive repair window correction start time is day 2 after injury and the total duration is 12 days, the three phases are day 2-5, day 6-9, and day 10-13, respectively. The upper and lower limits of the intensity range of the adaptive repair window are written into the intensity prescription range field of the exercise prescription parameter table. For example, when the intensity range is 50%-65% of maximum oxygen uptake, the intensity prescription range is recorded as 50%-65% with a heart rate reference conversion value (calculated by subtracting age from 220 to estimate maximum heart rate and then converting). The single exercise duration field in the exercise prescription parameter table is assigned a value based on the confidence level of the adaptive repair window. When the confidence level is normal, the single exercise duration is set to 30-45 minutes; when the confidence level is low, it is conservatively set to 20-30 minutes to reduce the risk of over-intervention. The total duration of the adaptive repair window determines the weekly exercise frequency field in the exercise prescription parameter table. When the total duration exceeds 10 days, the repair response has entered a stable phase, and excessively high frequency can easily lead to cumulative fatigue; the frequency is set to 3 times per week. For 5-10 days, it is set to 4 times per week; when less than 5 days, the window is concentrated in the rapid activation phase, and the frequency is set to 5 times per week to fully utilize the limited intervention period. After the exercise prescription parameter table is generated, its rationality is verified. If the intensity prescription range exceeds 85% of the maximum oxygen uptake, it is automatically truncated to 85%. If the product of the single exercise duration and the weekly exercise frequency exceeds 180 minutes / week, the single exercise duration is recalculated according to the formula T_single=180 / weekly exercise frequency, where T_single is the single exercise duration in minutes, to ensure that the total weekly exercise duration does not exceed 180 minutes, preventing excessive total load in the early repair stage from inhibiting satellite cell proliferation.

[0046] Satellite cell activation regulatory pathways were identified based on exercise prescription parameters. When the intensity prescription range of the exercise prescription parameters fell within 40%-60% of VO2 max, the AMPK-PGC1α pathway was preferentially activated. When it fell within 60%-75%, the IGF-1 / Akt / mTOR pathway was identified as the main satellite cell activation regulatory pathway. When it exceeded 75%, the IGF-1 / Akt / mTOR pathway and the downstream S6K1-4EBP1 axis of mTORC1 were simultaneously incorporated into the satellite cell activation regulatory pathway. During the early activation period of the prescription phase, when the exercise frequency was greater than or equal to 4 times per week and the lower limit of the intensity prescription range was not lower than 45% of VO2 max, the HGF-MET signaling axis was additionally incorporated into the satellite cell activation regulatory pathway. High frequency and sufficient intensity together maintained the HGF paracrine concentration to trigger the satellite cell proliferation program. The pathway activation sequence field of satellite cell activation regulation pathways records the initial activation delay of each pathway and the corresponding spatial location of the damaged area. A delay of 0.5-2 hours for the AMPK pathway corresponds to the peripheral region, a delay of 2-6 hours for IGF-1 / Akt / mTOR corresponds to the diffusion front of the peripheral region, and a delay of 6-12 hours for HGF-MET corresponds to the density peak in the core region. The damage area coverage field of satellite cell activation regulation pathways is jointly determined by the intensity prescription interval and prescription stage time window of the exercise prescription parameter table. When the upper limit of the intensity prescription interval is higher than 60% of the maximum oxygen uptake, the coverage extends to the damaged core and peripheral regions; when it is lower than 60%, the coverage is limited to the peripheral region and the surrounding normal area. The Pax7 positive cell density at each level is recorded in the coverage field as the typical density value of the historical sample with the same degree of damage corresponding to the repair stage of the exercise prescription parameter table. The signal intensity coefficient of the satellite cell activation regulation pathway was determined by normalizing the product of the single exercise duration and weekly exercise frequency in the exercise prescription parameter table to the [0,1] interval based on the maximum product value of historical samples. When the signal intensity coefficient is lower than 0.3, the corresponding pathway has a very low weight contribution in the weighted average of activation delay time, and the influence of this pathway is naturally compressed in the efficiency correction mapping.

[0047] In some embodiments, the step of mapping the muscle satellite cell activation efficiency of the satellite cell activation regulation pathway to obtain the activation delay time includes: performing spatial distribution analysis of the damaged area of ​​the satellite cell activation regulation pathway to obtain regional distribution parameters; identifying the satellite cell co-activation density distribution based on the regional distribution parameters to obtain density grading identifiers; performing paracrine signal intensity analysis on the density grading identifiers to form co-activation correction coefficients; and generating the activation delay time by correcting and mapping the execution efficiency of the satellite cell activation regulation pathway according to the co-activation correction coefficients.

[0048] Spatial distribution analysis of the damaged area was performed on satellite cell activation regulation pathways to obtain regional distribution parameters. In the damaged area coverage field of the satellite cell activation regulation pathway, Pax7-positive cell density data for each of the three spatial levels—damaged core, damaged edge, and surrounding normal area—were read layer by layer. Density at each layer was recorded in cells / mm², with the core density denoted as ρ_core, the edge density as ρ_edge, and the normal density as ρ_norm. In the pathway activation sequence field of the satellite cell activation regulation pathway, the activation time of each pathway was correlated with its corresponding spatial location. The initial activation time of the HGF-MET pathway corresponded to the peak cell density in the core area, and the activation time of the IGF-1 / Akt pathway corresponded to the density diffusion front in the edge area. The spatial-temporal correlation between these two values ​​depicted the activation wave dynamics of the damaged area. The spatial gradient of the regional distribution parameters is obtained by the formula grad=(ρ_core-ρ_edge) / d, where d is the distance between the anatomical center points of the core and edge regions (the straight-line distance between the geometric centers of the two regions marked by the spatial coordinates of the biopsy slice, in mm), and grad is in cells / mm³. A larger spatial gradient value indicates a more uneven distribution of cells in the damaged area; the gradient value of large-area diffuse damage is usually lower than that of localized damage. The signal intensity coefficient of satellite cell activation regulatory pathways is positively correlated with the density of each layer of the regional distribution parameters; pathways with high signal intensity coefficients correspond to regions with higher Pax7 density. The measurement quality control information of the regional distribution parameters records the number of fields of view in each layer. Layers with fewer than 3 fields of view are marked with a confidence level below 0.6. When quality control is insufficient, the grading results of the regional distribution parameters are for reference only.

[0049] Density grading is achieved by identifying the co-activation density distribution of satellite cells based on regional distribution parameters. The ratio of the core density ρ_core to the normal density ρ_norm is defined as the density activation index IAD = ρ_core / ρ_norm. An IAD greater than 2.0 is considered high-density activation, 1.0-2.0 is considered medium-density activation, and less than 1.0 is considered low-density activation. For example, in the acute phase of severe muscle tears, the IAD usually exceeds 3.0, while in chronic overuse injuries, the IAD is mostly maintained between 1.2 and 1.8. The density activation level is independent of the S110 injury severity grading. The injury severity reflects the extent of tissue damage, while the density activation level reflects the current satellite cell recruitment status. The two can be inconsistent; for example, in moderate injury with rich local blood supply, the IAD can reach high-density activation. The ratio of edge density ρ_edge to core density ρ_core in the regional distribution parameter is defined as the diffusion ratio R_diff = ρ_edge / ρ_core. An R_diff greater than 0.7 indicates high proliferation and diffusion efficiency. When R_diff is less than 0.3, a diffusion-impeded marker is added to the density grading label. Diffusion-impeded conditions are often seen in cases where fibrosis or hematoma compression exists around the lesion area. When the spatial gradient value of the regional distribution parameter exceeds 200 cells / mm³, a high-gradient marker is added to the density grading label. The high-gradient marker indicates significant density heterogeneity in the lesion area. For layers with fewer than three fields of view in the regional distribution parameter measurement quality control information, the corresponding grading confidence field for the density grading label is marked as less than 0.6. In paracrine signal analysis, this confidence level is adjusted using a discount factor to correct the co-activation correction coefficient. The auxiliary fields of the density grading label include the diffusion ratio value, diffusion-impeded marker, high-gradient marker, and grading confidence level. Each auxiliary field is referenced in the paracrine signal analysis steps.

[0050] Paracrine signal intensity analysis was performed on density grading markers to generate co-activation correction coefficients. The base value for the co-activation correction coefficient was set to 1.3 for high-density activation, 1.0 for medium-density activation, and 0.7 for low-density activation. These base values ​​were derived from regression analysis of paracrine signal intensity and activation rate in in vitro satellite cell density gradient culture experiments. In high-density conditions, positive feedback from satellite cell paracrine signals significantly accelerates activation. The diffusion ratio field of the density grading markers corrected the co-activation correction coefficients. A +0.1 was added to the base value when R_diff was greater than 0.7, and a -0.1 was added when R_diff was less than 0.3. For example, a subject with an IAD of 2.3 was considered to have high-density activation, and an R_diff of 0.8 had a co-activation correction coefficient of 1.4. When the density grading markers carried a high gradient label, a spatial heterogeneity penalty of -0.05 was added to the co-activation correction coefficient. This reflects how uneven density distribution leads to decreased paracrine co-activation efficiency. For example, when local hematoma causes high density in the core area but impaired diffusion at the periphery, the gradient penalty prevents overestimation of the overall co-activation effect. When the confidence level of the density grading identifier is below 0.6, each correction increment is multiplied by that confidence level before execution (e.g., when the confidence level is 0.5, the increment of +0.1 is reduced to +0.05) to avoid excessive bias caused by low-quality grading results. The cumulative total of all increments of the co-activation correction coefficient is truncated to the range of [0.6, 1.4], with an upper limit of 1.4 to prevent excessive compression of the activation delay time. When the density grading identifier carries a diffusion obstruction marker, the co-activation correction coefficient is forcibly set to the lower limit of 0.6, and a paracrine deficiency warning marker is simultaneously added. The paracrine deficiency warning marker indicates that the signal diffusion range is limited and the co-activation efficiency in the skeletal muscle repair area is significantly reduced.

[0051] The activation delay time is generated by mapping the efficiency correction of satellite cell activation regulation pathways based on the co-activation correction coefficient. The baseline delay value of each pathway in the pathway activation sequence field of the satellite cell activation regulation pathway (the median of the historical delay range for the corresponding pathway: AMPK 1.25 hours, IGF-1 / Akt / mTOR 4 hours, HGF-MET 9 hours) is divided by the co-activation correction coefficient. The quotient is the estimated activation delay time of a single pathway after efficiency correction. When the co-activation correction coefficient is 1.4, the baseline delay of a certain pathway is corrected from 8 hours to approximately 5.7 hours, reflecting the accelerated signal transduction effect under high-density satellite cell aggregation. When the satellite cell activation regulation pathway contains multiple pathways, the estimated delay after efficiency correction for each pathway is a weighted average based on the signal intensity coefficient of the satellite cell activation regulation pathway, using the formula T_delay=Σ(w_i×t_i) / Σw_i, where T_delay is the activation delay time, w_i is the signal intensity coefficient of the i-th pathway normalized to [0,1], and t_i is the delay after efficiency correction for the i-th pathway. When the co-activation correction coefficient carries a paracrine deficiency warning marker, the activation delay time is extended by 20% based on the weighted mean. For example, for a subject with lower limb muscle injury, the weighted mean is 8 hours and a paracrine deficiency warning marker is carried, the final activation delay time is 9.6 hours. The effective range of activation delay time is constrained to 3-24 hours. After efficiency correction, if it exceeds the upper limit, it is truncated to 24 hours and an activation blockage status marker is added. If it is less than 3 hours, it is truncated to 3 hours. The stratified repair configuration generation step forces the repair weight of the corresponding stage to the lowest level of 0.2 based on the activation blockage status marker and simultaneously triggers a low response warning.

[0052] In some embodiments, the step of defining response levels and generating hierarchical repair configurations based on the activation delay time includes: performing delay time distribution analysis on the activation delay time to obtain a delay time distribution sequence; performing dynamic hierarchical classification of repair phases based on the delay time distribution sequence to obtain phase response levels; performing level mapping on the phase response levels to form response levels; and allocating repair weights based on the response levels to generate hierarchical repair configurations.

[0053] Delay time distribution analysis is performed on the activation delay time to obtain a delay time distribution sequence. The activation delay time is updated in real time after each exercise intervention according to the S130 efficiency correction mapping process. For interventions between three fixed time points, the activation delay time is estimated by linear interpolation of the efficiency correction mapping results from the two interventions before and after, ensuring the activation delay time sequence covers all interventions. The activation delay time values ​​after three or more consecutive exercise interventions are arranged in the order of intervention to form the original time series input for the delay time distribution sequence. The time series length equals the number of effective interventions. If the number of effective interventions is less than three, the trend slope in the delay time distribution sequence does not participate in the subsequent stage response level adjustment. The difference between two adjacent values ​​in the activation delay time value sequence constitutes the delay change sequence. A negative delay change indicates an accelerated activation speed, while a positive value indicates a slowed activation speed. For example, if a subject's activation delay time is 9 hours for the third intervention and 7.5 hours for the fourth, a change of -1.5 hours indicates a positive recovery process. The trend slope k of the delayed time distribution sequence is determined by linear regression of the activation delayed time sequence. When there are fewer than 5 data points, the slope is not used to determine the upward adjustment of the stage response level. A negative slope indicates that the activation speed continues to increase with the number of interventions, while a positive slope indicates that the repair process is blocked. Activation delayed time values ​​carrying the activation blocked status are separately marked in the delayed time distribution sequence. When the number of outliers exceeds 30% of the total number of times, the delayed time distribution sequence is marked as a high anomaly rate state. In the high anomaly rate state, the representativeness of the trend slope decreases. The statistical characteristics of the delayed time distribution sequence are described by the mean and standard deviation of each activation delayed time. A standard deviation of less than 1 hour indicates a stable activation response, while a standard deviation of more than 3 hours indicates large fluctuations in individual response. When the fluctuations are too large, it is recommended to review whether the intensity prescription range of the exercise prescription parameter table is suitable for the current repair stage.

[0054] The response level of each repair phase is obtained by dynamically grading the delayed time distribution sequence. The delayed time distribution sequence is divided into three phases based on the number of interventions: early activation phase (interventions 1-5), peak proliferation phase (interventions 6-10), and functional remodeling phase (intervention 11 and beyond). For phases with fewer than 5 interventions, the mean is calculated using available data. The mean activation delay time for each intervention within each phase represents the typical response speed for that repair phase. Phases with mean values ​​below 6 hours are classified as high response levels, 6-12 hours as medium response levels, and over 12 hours as low response levels. These three levels are applied independently to the three repair phases. For example, a subject with a mean of 8 hours in the early activation phase is classified as a medium response level, while a mean value decreasing to 4.5 hours in the peak proliferation phase elevates to a high response level, reflecting the gradual emergence of the cumulative effect of the intervention. When the trend slope k of the delayed time distribution sequence is negative and its absolute value exceeds 0.5 hours / intervention, the response level for each phase is adjusted upwards by one level from the static determination. If already at a high response level, the high response level is maintained without further upward adjustment. When a high anomaly rate is triggered in a delayed time distribution sequence, the response level of the corresponding repair phase is lowered by one level, and a high density of anomalies indicates that the repair rhythm of that phase is unstable. For repair phases where the standard deviation of the delayed time distribution sequence exceeds 3 hours, a volatility flag is added to the response level, and the volatility flag is incorporated into the stability assessment during the level mapping step.

[0055] A level mapping is implemented to form response levels for each stage of the response hierarchy. The three segments of the stage response hierarchy are numerically coded (high response level = 2, medium response level = 1, low response level = 0) and substituted into the weighted formula Score = 0.2 × L_early + 0.5 × L_peak + 0.3 × L_remodel, where L_early, L_peak, and L_remodel are the hierarchical coding values ​​for the early activation segment, the peak proliferation segment, and the functional remodeling segment, respectively. The weight allocation reflects the dominant role of the peak proliferation segment in skeletal muscle repair. A Score greater than or equal to 1.6 is classified as excellent; greater than or equal to 1.0 and less than 1.6 is classified as good; greater than or equal to 0.5 and less than 1.0 is classified as medium; and less than 0.5 is classified as poor. Boundary values ​​are assigned to low levels if they are greater than or equal to the lower limit of the low level and less than the lower limit of the high level, eliminating boundary overlap. For example, if all three segments are high response levels, a Score of 2.0 is considered excellent; if the peak proliferation segment has other high responses, a Score of 1.5 is considered good. The volatility marker field of the stage response hierarchy is included in the stability assessment of the response level. A stability rating is "moderate" when one stage carries a volatility marker, and "unstable" when two or more stages carry a volatility marker. When the functional remodeling stage encoding value in the stage response hierarchy array is better than the early activation stage encoding value, a positive progression marker is added to the response level. The positive progression marker indicates that the repair response continues to improve with intervention. The response level is stored as an enumeration of values ​​(excellent / good / moderate / poor), with two auxiliary fields: a stability marker and a positive progression marker. A poor level triggers a clinical review prompt simultaneously.

[0056] A tiered repair configuration is generated based on the repair weights assigned according to the response level. For an excellent response level, the repair weight during high-intensity exercise is set to 0.6; for a good response level, it's 0.5; for a moderate response level, it's 0.35; and for a poor response level, it's 0.2. These four weights correspond to a gradient of repair resource input from strong to weak satellite cell activation response. For example, standard intervention procedures for acute injuries in professional athletes typically present a good to excellent response, with weights of 0.5-0.6 supporting an aggressive, high-load repair strategy. When the response level is marked as unstable, the tiered repair configuration is adjusted downwards by 0.05 as a safety margin to avoid applying excessive repair load during unstable response phases. When the response level enumeration value is excellent or good, the tiered repair configuration assigns independent weights to the injury core and peripheral areas. For moderate and poor responses, the core area weight is uniformly set to 0.7 times the peripheral area weight (this 0.7 factor is derived from a correlation analysis of core area overload and repair delay during low response phases in historical samples), to avoid prematurely applying high loads to the core area during low response phases. When the response level carries a positive progress marker, the stratified repair configuration adds a progress bonus coefficient of 0.05 to the current level weight. After the addition, the upper limit of the repair weight is truncated to 0.65. For example, when the level is good and carries a positive progress marker, the repair weight increases from 0.5 to 0.55, and when it is excellent, it increases from 0.6 to 0.65. When the level is poor and the stability is marked as unstable, the stratified repair configuration simultaneously triggers a low response warning, prompting clinicians to assess whether the current exercise prescription parameter table needs to be refitted.

[0057] Step S140: Activation delay assessment is performed on the layered repair configuration to determine the preferred activation method. The optimal activation time window data of the preferred activation method is detected. Based on the optimal activation time window data, the dynamic activation characteristics of muscle satellite cells are extracted, the activation priority is adjusted, and an intervention execution sequence is formed. Based on the exercise prescription parameter table and the intervention execution sequence, the skeletal muscle repair execution instruction is output.

[0058] In some embodiments, the step of performing activation delay evaluation on the hierarchical repair configuration to determine the preferred activation method includes: extracting delay time differences from the hierarchical repair configuration to obtain a delay gradient sequence; performing cumulative fatigue correction evaluation based on the delay gradient sequence to obtain a fatigue correction coefficient; performing anomaly detection on the fatigue correction coefficient to identify activation coordination deficiency sites; and reconfiguring the delay gradient sequence using the activation coordination deficiency sites to determine the preferred activation method.

[0059] Delay gradient sequences are obtained by extracting delay time differences from the hierarchical repair configuration. The repair weights of each repair stage in the hierarchical repair configuration array are aligned by stage index. The average activation delay time for each stage is taken as the typical average delay of the corresponding stage in historical samples of the same response level. The difference between the average activation delay times of adjacent stages forms a single-step delay difference. All single-step delay differences of adjacent stages are arranged in chronological order to form a delay gradient sequence. The total number of repair stages in the hierarchical repair configuration determines the length of the delay gradient sequence; when there are N repair stages, the length of the delay gradient sequence is N-1. In the delay gradient sequence, a negative difference indicates an accelerated activation speed in adjacent stages, while a positive difference indicates a decelerated activation speed. A difference with an absolute value exceeding 2 hours is marked as a significant gradient point. For example, when transitioning from the early activation stage to the peak proliferation stage, the activation delay time decreases from 10 hours to 6 hours; a difference of -4 hours is a significant gradient point, indicating a significant activation acceleration at the stage transition. The spatial hierarchy labeling field of the hierarchical repair configuration is used to distinguish the core and edge components in the delay gradient sequence. The core and edge delay gradient sequences are extracted independently, providing spatial resolution for fatigue correction.

[0060] Fatigue correction coefficients are obtained through cumulative fatigue correction assessment based on delayed gradient sequences. The cumulative exercise load corresponding to each stage of the delayed gradient sequence is determined by accumulating the product of the single exercise duration and the median of the intensity prescription interval from the exercise prescription parameter table over the number of interventions. The accumulated result is defined as the cumulative load index CL = Σ(n_i × HR_i), where n_i is the single exercise duration (min) of the i-th intervention, HR_i is the percentage of heart rate reserve (%) corresponding to the median of the intensity prescription interval, and CL is in min·%, reflecting the total cumulative exercise stimulation. After extracting the cumulative load index of the stage containing the significant gradient point in the delayed gradient sequence, it is compared with the expected load index of normal repair for that stage. A ratio exceeding 1.3 indicates a risk of cumulative fatigue in that stage, while a ratio below 0.7 indicates insufficient exercise stimulation. The fatigue correction coefficient is determined by a piecewise function based on the ratio. When the ratio is within the normal range of 0.7-1.3, the fatigue correction coefficient is 1.0. When the ratio exceeds 1.3, the fatigue correction coefficient decreases linearly according to the formula f = 1.0 - 0.3 × (ratio - 1.3), where ratio is the ratio value, and the lower limit of f is 0.5. When the ratio is below 0.7, the fatigue correction coefficient increases linearly according to f = 1.0 + 0.2 × (0.7 - ratio) to reflect the decrease in activation efficiency under understimulation. The fatigue correction coefficient is evaluated independently for each repair stage, and the output is a coefficient array of the same length as the delayed gradient sequence, with each element corresponding to the fatigue correction coefficient value for one stage interval.

[0061] Anomaly detection was performed on the fatigue correction coefficients to identify sites of insufficient activation synergy. Positions in the fatigue correction coefficient array where two consecutive adjacent elements are below 0.7 were marked as deep fatigue segments. These segments indicated that the cumulative load on the skeletal muscle within that consecutive phase interval significantly exceeded its repair capacity, resulting in persistently low activation synergy efficiency. Positions in the fatigue correction coefficient array where the element value dropped by more than 0.2 relative to the previous element were marked as acute fatigue jump points. Acute fatigue jump points typically correspond to a sudden increase in fatigue after a high-intensity exercise intervention, such as when a subject unexpectedly performed training exceeding the prescribed intensity range, leading to a sharp drop in the fatigue correction coefficient during the repair phase. Positions in the fatigue correction coefficient array where two consecutive adjacent elements are above 1.2 were marked as insufficient stimulation segments. These insufficient stimulation segments, deep fatigue segments, and acute fatigue jump points together constituted the set of sites of insufficient activation synergy. Each site recorded two attributes: its phase index and its fatigue correction coefficient value. An empty set of sites of insufficient activation synergy indicated that no significant abnormalities in cumulative fatigue occurred during the skeletal muscle repair process under the current intervention protocol, and the activation synergy status at each phase was good. In the reconfiguration step, the delayed gradient sequence maintained its original value without correction. When the number of insufficient activation sites exceeds 40% of the length of the delayed gradient sequence, the overall repair scheme is marked as a high fatigue risk state. Under the high fatigue risk state, the preferred activation method will be tightened towards low intensity and low frequency.

[0062] The preferred activation method is determined by reconfiguring the delayed gradient sequence after activating co-deficient sites. The delayed gradient sequence element corresponding to the stage index of the activated co-deficient site is multiplied by the fatigue correction coefficient of that site; the product is the corrected delayed gradient value after reconfiguration. The correction operation appropriately narrows the gradient amplitude at the fatigue site according to the degree of fatigue. The reconfigured delayed gradient sequence is formed after correction by activating co-deficient sites. The mean and standard deviation of the reconfigured delayed gradient sequence characterize the overall gradient distribution after reconfiguration; a negative mean indicates that the overall activation rate is still accelerating, while a small standard deviation indicates that the activation rate changes smoothly between stages. The difference between the core and edge discriminants of the reconfigured delayed gradient sequence is taken as the mean of absolute values. If the mean difference is greater than 1.5 hours, it is judged as spatial activation imbalance, and the preferred activation mode is determined to be edge-leading. If the mean difference is less than 0.5 hours, it is judged as spatial activation synchronization, and the preferred activation mode is determined to be co-synchronous. If the difference is between the two, it is judged as progressive diffusion. Under high fatigue risk, the preferred activation mode is superimposed with a reduction label on the original judgment result. The reduction label requires that the exercise intensity of the corresponding number of interventions in the skeletal muscle repair execution instruction be reduced to the lower limit of the intensity prescription interval. The preferred activation mode is stored as an enumerated value, and the reduction label is recorded as an auxiliary field.

[0063] The optimal activation time window data for the preferred activation mode is determined by the type of preferred activation mode. For edge-leading preferred activation modes, the detection start point is set 2 hours after each exercise intervention, corresponding to satellite cells in the edge region typically completing the early activation process first. For synergistic preferred activation modes, the detection start point is set 1 hour after exercise, corresponding to faster synchronous activation of satellite cells across the entire region. For progressive diffusion preferred activation modes, the detection start point is set 3 hours after exercise, allowing paracrine signals from the core region to fully diffuse to the edge region before assessing the activation window. Starting from the detection start point, the percentage of activated satellite cells is continuously collected at 30-minute intervals using the same rapid fluorescence immunohistochemistry detection protocol as S110. The first moment when the percentage of activated satellite cells increases by more than 10 percentage points relative to the detection start point is defined as the initial boundary of the optimal activation time window. The period after the initial boundary when the percentage of activated satellite cells remains above 80% of the peak level is defined as the effective interval of the optimal activation time window. The effective interval is typically 2-5 hours long; for example, the effective interval for subjects with superior response levels can reach 4-5 hours, while the effective interval for subjects with poor response levels is typically no more than 2 hours. The optimal activation time window data records two values: the start boundary time and the effective interval duration. If the effective interval duration of the optimal activation time window data is less than 1 hour, it is marked as a "window too narrow" state, which triggers the re-evaluation process of the preferred activation method.

[0064] In some embodiments, the step of extracting dynamic activation characteristics of muscle satellite cells based on the optimal activation time window data, adjusting the activation priority, and forming an intervention execution sequence includes: obtaining the activation frequency distribution characteristics of the optimal activation time window data; separating fast-response subpopulation characteristics and slow-response subpopulation characteristics based on the activation frequency distribution characteristics to obtain subpopulation activation rate coefficients; performing threshold determination on the subpopulation activation rate coefficients to form an activation effectiveness determination result; and adjusting the activation priority based on the activation effectiveness determination result to form an intervention execution sequence.

[0065] The activation frequency distribution characteristics of the optimal activation time window data are obtained. Within the effective interval of the optimal activation time window data, the percentage of satellite cells in the activated state is collected every 30 minutes. The collected values ​​at each time point are arranged chronologically to form an activation state time-series vector. The length of the time-series vector is equal to the effective interval length divided by 0.5 hours. For example, when the effective interval is 3 hours, the activation state time-series vector contains 6 sampling points. Before performing a Discrete Fourier Transform (DFT), the mean of the entire sequence is subtracted from the activation state time-series vector to eliminate the DC component. The mean-free time-series vector is then subjected to a DFT to output complex spectral coefficients, with the amplitude at each frequency point taken as the complex modulus. The spectrum is arranged from low to high frequency. Components with a period greater than 2 hours are classified as low-frequency, components with a period between 1 and 2 hours as mid-frequency, and components with a period less than 1 hour as high-frequency. The low-frequency segment reflects the overall upward or downward trend of the satellite cell activation process, while the high-frequency segment reflects short-term activation fluctuations and rapid alternation responses between subpopulations. The energy proportion of each frequency band is determined by dividing the sum of the squares of the amplitudes at each frequency point within that band by the sum of the squares of the amplitudes of the entire spectrum. The sum of the low-frequency energy proportion and the high-frequency energy proportion is not equal to 1 because the mid-frequency energy is not included at either end. The activation frequency distribution characteristics are described in the form of a spectrum amplitude array, the length of which is equal to half the length of the activation state time vector. The energy proportions of the low-frequency and high-frequency components in the array quantify the overall trend intensity and short-term fluctuation intensity of the activation process, respectively.

[0066] Based on activation frequency distribution characteristics, the characteristics of fast-response and slow-response subpopulations were separated to obtain subpopulation activation rate coefficients. The high-frequency energy component of the activation frequency distribution characteristics, after normalization, served as a quantitative indicator of the fast-response subpopulation characteristics. The fast-response subpopulation corresponds to the MyoD-highly-expressing satellite cell population in skeletal muscle, which enters a division-ready state within 0.5-1 hour after exercise stimulation. The low-frequency energy component of the activation frequency distribution characteristics, after normalization, served as a quantitative indicator of the slow-response subpopulation characteristics. The slow-response subpopulation corresponds to the Pax7-highly-expressing satellite cell population in a deep resting state, which typically requires multiple cumulative exercise stimulations before entering an activated state. The quantitative indicator of the fast-response subpopulation characteristics, divided by the effective interval duration, yields the fast subpopulation activation rate coefficient k_fast, and the quantitative indicator of the slow-response subpopulation characteristics, divided by the effective interval duration, yields the slow subpopulation activation rate coefficient k_slow. The denominator for both coefficients is the effective interval duration. The units for k_fast and k_slow are both 1 / hour to ensure dimensional consistency in subsequent L2 norm and ratio calculations. The ratio of the subpopulation activation rate coefficients k_fast to k_slow reflects the relative activation dominance of the fast and slow subpopulations. When the ratio is greater than 2.0, the fast subpopulation dominates the current repair phase and is marked as fast subpopulation-preferred. When the ratio is less than 0.5, the slow subpopulation dominates and is marked as slow subpopulation-preferred. Between these two values ​​is a state of equilibrium between the two subpopulations. For example, the peak proliferation period from day 5 to 8 post-injury usually shows a fast subpopulation-preferred characteristic. When the optimal activation time window data is too narrow, the subpopulation activation rate coefficients are multiplied by a discount factor of 0.8, reflecting the overall inhibition of the subpopulation response due to insufficient activation window.

[0067] For example, the step of thresholding the activation rate coefficient of the subgroup to form an activation validity determination result includes: performing feature intensity quantization on the activation rate coefficient of the subgroup to obtain an activation intensity value; determining the stage-adapted activation level by performing dynamic threshold division of the repair stage based on the activation intensity value; performing temporal stability analysis on the stage-adapted activation level to form an activation stability feature; and combining the activation stability feature with the activation intensity value to perform a validity confidence assessment to form an activation validity determination result.

[0068] The activation rate coefficients of the subgroups are quantified using feature intensity quantification to obtain activation intensity values. The L2 norm of the subgroup activation rate coefficients k_fast and k_slow is used as a comprehensive activation intensity quantification index, with the formula A = sqrt(k_fast² + k_slow²), where A is the activation intensity value, and the L2 norm comprehensively reflects the overall activation level of both fast and slow subgroups. The ratio of the subgroup activation rate coefficients k_fast / k_slow is supplemented with a directional modulation factor R_dir. When R_dir is greater than 2.0, a fast subgroup bias is added; when R_dir is less than 0.5, a slow subgroup bias is added. These two bias labels are used for stage level correction and intervention sequence adjustment steps. The range of activation intensity values ​​is determined by historical samples. 95% of historical samples show activation intensity values ​​between 0.05 and 0.35. Activation intensity values ​​below 0.05 are marked as extremely low activation, and values ​​exceeding 0.35 are truncated to 0.35 to prevent sensor misreading or abnormal subject conditions leading to artificially high activation intensity values.

[0069] The activation level is determined by dynamically dividing the repair phase based on the activation intensity value. The effective threshold for activation intensity is set at 0.10 for the early activation phase, 0.15 for the peak proliferation phase, and 0.12 for the functional remodeling phase. The difference in thresholds among these three phases reflects the biological principle that the peak proliferation phase requires the highest activation intensity. When the activation intensity value exceeds the corresponding repair phase's effective threshold by 1.5 times, the phase-adapted activation level is determined as strong activation; exceeding the threshold but less than 1.5 times is determined as medium activation; and falling below the threshold is determined as weak activation. The phase-adapted activation level is bound to the repair phase. Threshold changes across phases mean that the same activation intensity value may correspond to different levels in different repair phases. For example, an activation intensity value of 0.18 might be determined as strong activation in the early activation phase but only as medium activation in the peak proliferation phase. When the directional modulation factor R_dir of the activation intensity value deviates from the equilibrium range (0.5-2.0), the phase-adapted activation level is reduced by half a level to balance the reduction in overall activation effect caused by subpopulation imbalance. When determining the weak activation level, the activation intensity value is simultaneously checked to see if it carries a label indicating an extremely low activation state. If both appear at the same time, the stage-adapted activation level triggers the clinical review process.

[0070] Temporal stability analysis of stage-adapted activation levels is used to form activation stability features. Stage-adapted activation levels from three or more consecutive interventions are arranged in the order of intervention to form a tiered temporal sequence. The absolute value of the coding difference (strong=2, medium=1, weak=0) between two adjacent stage-adapted activation levels in the tiered temporal sequence constitutes a fluctuation sequence. An activation stability feature is considered high-stability when the mean of the fluctuation sequence is below 0.5, medium-stability when it is between 0.5 and 1.0, and low-stability when it exceeds 1.0. When the stage-adapted activation level is strong for three consecutive times in the tiered temporal sequence, a sustained strong activation marker is added to the activation stability feature. This sustained strong activation marker indicates a high match between the intensity prescription range of the current exercise prescription parameter table and the individual's repair rhythm, thus upgrading the stability assessment result of the activation stability feature by one level. The temporal position where the stage-adapted activation level abruptly drops from strong to weak activation is marked as an activation collapse point. The activation collapse point corresponds to the subject experiencing additional interference from non-exercise factors such as insufficient sleep or nutritional intake. When the activation stability feature carries the collapse point marker, its stability level is forcibly reduced to low stability. The final stability assessment is formed by three sources: the mean fluctuation of the overall activation stability feature time series, the sustained strong activation markers, and the location of the collapse point. Low stability of the activation stability feature triggers clinical re-examination, and it is recommended to combine the subject's recent life records to rule out the influence of non-motor factors.

[0071] The effectiveness confidence assessment is performed by combining activation stability features and activation intensity values ​​to form the activation effectiveness judgment result. When the activation intensity value exceeds the dynamic threshold of the corresponding repair stage and the activation stability feature is high stability, the base confidence of the activation effectiveness judgment result is set to 0.9. This combination indicates that the current satellite cell activation state is reliable and the expected effect of motion intervention is stable. When the activation intensity value exceeds the threshold but the activation stability feature is low stability, the base confidence drops to 0.6. The unstable activation state reduces the representativeness of a single effective judgment. When the activation stability feature carries a continuous strong activation marker, the confidence is increased by +0.05 on the base value; when the activation stability feature carries a collapse point marker, the confidence is increased by -0.1. The collapse point indicates that the activation state has undergone a sudden change, and the stability of the current judgment result is questionable. The final confidence is truncated to the range of [0.4, 0.95]. When the activation intensity value exceeds the threshold and the final confidence is higher than 0.7, the activation effectiveness judgment result is marked as effective; when the final confidence is between 0.5 and 0.7, it is marked as pending confirmation; and when the activation intensity value is lower than the threshold, it is marked as invalid. When the activation validity assessment result is invalid and the activation stability feature is low stability, a simultaneous review of the exercise prescription parameter table fit is triggered. It is recommended to reassess whether the current intensity prescription range matches the subject's recovery phase. The activation validity assessment result includes the stability level of the activation stability feature as an auxiliary field for reference in subsequent activation priority adjustment steps.

[0072] The activation priority is adjusted based on the activation effectiveness assessment results to form the intervention execution sequence. When the activation effectiveness assessment result is effective and the accompanying stability level is high stability, the activation priority is set to high. When the activation effectiveness assessment result is effective but the stability level is medium stability or the activation effectiveness assessment result is pending confirmation, the activation priority is set to medium. When the activation effectiveness assessment result is ineffective, the activation priority is set to low. These three priority levels correspond to the degree of advance intervention. High priority corresponds to intervention within 30 minutes after the initial boundary of the optimal activation time window data; medium priority corresponds to intervention within 30-60 minutes after the initial boundary; and low priority corresponds to intervention within 60-90 minutes after the initial boundary, delaying intervention to wait for the activation conditions to improve. When the activation effectiveness assessment result carries a fast subpopulation preference marker, the exercise intensity of the corresponding number of times in the intervention execution sequence is increased to the upper limit of the intensity prescription interval to fully stimulate the proliferative potential of the fast-response subpopulation; when it carries a slow subpopulation preference marker, the exercise intensity is decreased to the lower limit of the interval to continuously accumulate the stimulation threshold of the slow subpopulation. The intervention execution sequences are grouped and arranged according to the repair phase. Sequence elements include the suggested execution time, activation priority, and the direction of intensity correction for each intervention. For example, if a subject's third intervention during their peak proliferative phase is deemed effective and highly stable, the activation priority is high, the execution time is specified as 25 minutes after the start of the window, and the intensity is set to the upper limit of the interval. Interventions with an activation effectiveness confidence level below 0.6 have their activation priority forcibly reduced to low priority in the intervention execution sequence.

[0073] Based on the exercise prescription parameter table and intervention execution sequence, skeletal muscle repair execution instructions are output. The intensity prescription ranges in the exercise prescription parameter table are matched one-to-one with the activation priority markings in the intervention execution sequence. The matching rule is that intervention times with high activation priority correspond to the upper limit of the intensity prescription range, and intervention times with low activation priority correspond to the lower limit of the intensity prescription range. For example, if an intervention has a high activation priority and an intensity prescription range of 50%-65%, the skeletal muscle repair execution instruction specifies the exercise intensity for that intervention as 62%-65%. The suggested execution time of the intervention execution sequence is cross-checked with the prescription stage time window in the exercise prescription parameter table. If the execution time falls within the functional remodeling period, the upper limit of intensity can be increased by 5 percentage points based on the intensity prescription range; if it falls within the early activation period, the upper limit of intensity can be decreased by 5 percentage points to protect the still unstable repair area. The single exercise duration field of the exercise prescription parameter table records the duration of each exercise session in the skeletal muscle repair execution instruction. The duration is fine-tuned according to the current exercise intensity correction direction of the intervention execution sequence: if the intensity fluctuates upwards, the single session duration is shortened by 5 minutes to concentrate on utilizing the high-response interval at the beginning of the window; if the intensity fluctuates downwards, the single session duration is extended by 5 minutes to fully accumulate activation stimulation of the slow-moving subgroups; if the correction direction is to maintain the original value, the duration remains the original value in the exercise prescription parameter table. The skeletal muscle repair execution instruction integrates four core parameters: exercise intensity, exercise duration, execution time, and phased time window, outputting them in the form of a structured execution order. Each execution order corresponds to one exercise intervention, and the execution order includes the effective interval duration of the optimal activation time window data as a reference, prompting the operator to complete the intervention within the effective interval. When the preferred activation method carries a reduction label, the exercise intensity of the corresponding number of interventions in the skeletal muscle repair execution instruction is lowered to the lower limit of the intensity prescription interval. The reduction label ensures that the exercise load under high fatigue risk conditions does not exceed the current capacity of the skeletal muscle. The skeletal muscle repair execution command includes an additional operation prompt for the number of interventions that trigger a low response warning in the layered repair configuration. It is recommended that the operator apply a mild heat compress or electrical stimulation to the damaged area 30 minutes before the intervention to improve the quality of the window.

[0074] To implement the skeletal muscle repair method based on muscle satellite cell regulation corresponding to the above method embodiments, and to achieve the corresponding functional and technical effects. See also Figure 2 , Figure 2 A structural block diagram of a skeletal muscle repair system 200 based on muscle satellite cell regulation provided in this application embodiment is shown. For ease of explanation, only the parts relevant to this embodiment are shown. The skeletal muscle repair system 200 based on muscle satellite cell regulation provided in this application embodiment includes:

[0075] Data acquisition module 201 is used to collect satellite cell homeostasis data and aerobic exercise intensity data in the damaged skeletal muscle region, and to establish a proliferation regulation map based on the proliferation and differentiation correlation analysis of the satellite cell homeostasis data and the aerobic exercise intensity data.

[0076] The window correction module 202 is used to determine the synergistic repair time window based on the proliferation regulation map, extract the differential response deviation correction parameter from the satellite cell homeostasis data and the aerobic exercise intensity data to form an activity correction factor, and use the activity correction factor to perform repair intensity correction on the synergistic repair time window to generate an adaptive repair window.

[0077] The prescription adaptation module 203 is used to adapt the adaptive repair window to the exercise prescription to form an exercise prescription parameter table, identify satellite cell activation regulation pathways according to the exercise prescription parameter table, perform muscle satellite cell activation efficiency mapping on the satellite cell activation regulation pathways to obtain activation delay time, and determine the response level and generate a layered repair configuration based on the activation delay time.

[0078] The instruction generation module 204 is used to evaluate the activation delay of the layered repair configuration to determine the preferred activation method, detect the optimal activation time window data of the preferred activation method, extract the dynamic activation characteristics of muscle satellite cells based on the optimal activation time window data, adjust the activation priority to form an intervention execution sequence, and output skeletal muscle repair execution instructions based on the exercise prescription parameter table and the intervention execution sequence.

[0079] The aforementioned skeletal muscle repair system 200 based on muscle satellite cell regulation can implement the skeletal muscle repair method based on muscle satellite cell regulation described in the above method embodiments. The options in the above method embodiments are also applicable to this embodiment and will not be detailed here. The remaining content of this application's embodiments can be referred to the content of the above method embodiments, and will not be repeated in this embodiment.

[0080] The above embodiments are not an exhaustive list based on the present invention, and there may be many other embodiments not listed. Any substitutions and improvements made without departing from the concept of the present invention are within the protection scope of the present invention.

Claims

1. A skeletal muscle repair method based on muscle satellite cell regulation, characterized in that, include: Satellite cell homeostasis data and aerobic exercise intensity data were collected from the damaged skeletal muscle region. Based on the satellite cell homeostasis data and the aerobic exercise intensity data, a proliferation regulation map was established by performing a proliferation and differentiation correlation analysis. Based on the proliferation regulation map, a synergistic repair time window is determined. Differential response deviation correction parameters are extracted from the satellite cell homeostasis data and the aerobic exercise intensity data to form an activity correction factor. The activity correction factor is used to correct the repair intensity of the synergistic repair time window to generate an adaptive repair window. The adaptive repair window is adapted to the exercise prescription to form an exercise prescription parameter table. Satellite cell activation regulation pathways are identified according to the exercise prescription parameter table. The activation delay time is obtained by mapping the muscle satellite cell activation efficiency of the satellite cell activation regulation pathways. The response level is determined according to the activation delay time to generate a layered repair configuration. The activation delay of the layered repair configuration is evaluated to determine the preferred activation method. The optimal activation time window data of the preferred activation method is detected. Based on the optimal activation time window data, the dynamic activation characteristics of muscle satellite cells are extracted, the activation priority is adjusted, and an intervention execution sequence is formed. Based on the exercise prescription parameter table and the intervention execution sequence, the skeletal muscle repair execution command is output.

2. The method according to claim 1, characterized in that, The establishment of a proliferation regulation map based on the correlation analysis of proliferation and differentiation using the satellite cell homeostasis data and the aerobic exercise intensity data includes: Multidimensional feature extraction is performed on the satellite cell homeostasis data and the aerobic exercise intensity data to obtain a set of cell feature parameters; Based on the cell feature parameter set, damage severity classification identification is performed to obtain damage classification identifiers; A potential correlation parameter is formed by performing a correlation analysis between the damage grading identifier and the set of cell characteristic parameters to determine the proliferation and differentiation potential. A proliferation regulation map was constructed using the potential correlation parameters.

3. The method according to claim 1, characterized in that, The step of extracting differential response bias correction parameters from the satellite cell homeostasis data and the aerobic exercise intensity data to form an activity correction factor includes: Exercise type identification is performed on the satellite cell homeostasis data and the aerobic exercise intensity data to obtain exercise mode labels; The continuous motion response bias and intermittent motion response bias are extracted using the motion pattern labels. The persistent motion response deviation and the intermittent motion response deviation are differentiated and integrated to form a differential response deviation correction parameter; An active correction factor is generated based on the difference response deviation correction parameters.

4. The method according to claim 1, characterized in that, The step of mapping the muscle satellite cell activation efficiency of the satellite cell activation regulation pathway to obtain the activation delay time includes: Spatial distribution analysis of the damaged regions was performed on the satellite cell activation and regulation pathways to obtain regional distribution parameters; Based on the regional distribution parameters, the density grading identifier is obtained by identifying the satellite cell co-activation density distribution. Paracrine signal intensity analysis was performed on the density grading markers to generate co-activation correction coefficients; The activation delay time is generated by correcting the execution efficiency of the satellite cell activation regulation pathway based on the co-activation correction coefficient.

5. The method according to claim 1, characterized in that, The step of generating a tiered repair configuration based on the activation delay time to determine the response level includes: Perform delay time distribution analysis on the activation delay time to obtain a delay time distribution sequence; Based on the aforementioned delay time distribution sequence, the dynamic hierarchical acquisition of the phase response level is performed during the repair phase. The stage response levels are mapped to form response levels; Based on the response level, repair weights are assigned to generate a tiered repair configuration.

6. The method according to claim 1, characterized in that, The step of determining the preferred activation method by evaluating the activation delay of the layered repair configuration includes: Delay gradient sequences are obtained by extracting delay time differences from the layered repair configuration. The fatigue correction coefficient is obtained by performing a cumulative fatigue correction evaluation based on the delay gradient sequence; Anomaly detection is performed on the fatigue correction coefficients to identify and activate insufficient collaborative sites; The preferred activation mode is determined by reconfiguring the delayed gradient sequence using the activated co-existing insufficient sites.

7. The method according to claim 1, characterized in that, The step of extracting dynamic activation characteristics of muscle satellite cells based on the optimal activation time window data, adjusting activation priority, and forming an intervention execution sequence includes: Obtain the activation frequency distribution characteristics of the optimal activation time window data; Based on the activation frequency distribution characteristics, the characteristics of fast-response subgroups and slow-response subgroups are separated to obtain the subgroup activation rate coefficients. The activation rate coefficients of the subgroups are thresholded to determine the activation effectiveness. Based on the activation effectiveness determination results, the activation priority is adjusted to form an intervention execution sequence.

8. The method according to claim 3, characterized in that, The extraction of continuous motion response bias and intermittent motion response bias using the motion pattern labels includes: Obtain the key nodes of motion intensity from the motion mode labels; At key nodes of exercise intensity, cardiopulmonary metabolic response fluctuation characteristics are detected to generate response tracking parameters. The aforementioned response tracking parameters are used to perform deviation correlation localization and generate a deviation candidate set; Based on the candidate set of deviations and the response tracking parameters, continuous motion response deviations and intermittent motion response deviations are generated.

9. The method according to claim 7, characterized in that, The step of thresholding the activation rate coefficients of the subgroups to form an activation effectiveness determination result includes: The activation rate coefficients of the subgroups are subjected to feature intensity quantization to obtain activation intensity values; Based on the activation intensity value, the dynamic threshold division of the repair phase is used to determine the phase-adaptive activation level. Temporal stability analysis is performed on the activation levels adapted to the aforementioned stages to form activation stability characteristics; The activation stability characteristics and activation intensity values ​​are combined to perform an effectiveness confidence assessment to form an activation effectiveness determination result.

10. A skeletal muscle repair system based on muscle satellite cell regulation, characterized in that, include: The data acquisition module is used to collect satellite cell homeostasis data and aerobic exercise intensity data in the damaged skeletal muscle region, and to establish a proliferation regulation map based on the proliferation and differentiation correlation analysis of the satellite cell homeostasis data and the aerobic exercise intensity data. The window correction module is used to determine the synergistic repair time window based on the proliferation regulation map, extract differential response deviation correction parameters from the satellite cell homeostasis data and the aerobic exercise intensity data to form an activity correction factor, and use the activity correction factor to perform repair intensity correction on the synergistic repair time window to generate an adaptive repair window; The prescription adaptation module is used to adapt the adaptive repair window to the exercise prescription to form an exercise prescription parameter table, identify the satellite cell activation regulation pathway according to the exercise prescription parameter table, perform muscle satellite cell activation efficiency mapping on the satellite cell activation regulation pathway to obtain the activation delay time, and determine the response level and generate a layered repair configuration based on the activation delay time. The instruction generation module is used to evaluate the activation delay of the layered repair configuration to determine the preferred activation method, detect the optimal activation time window data of the preferred activation method, extract the dynamic activation characteristics of muscle satellite cells based on the optimal activation time window data, adjust the activation priority to form an intervention execution sequence, and output skeletal muscle repair execution instructions based on the exercise prescription parameter table and the intervention execution sequence.

Images