A method, system, and storage medium for assessing metabolic capacity

Abstract

Embodiments of the present application relate to the technical field of healthcare informatics, and in particular to a metabolic capacity evaluation method, system and storage medium. The method can include: acquiring time series data of interstitial fluid lactate values of an athlete before, during and after exercise; extracting feature parameters from the time series data; for each of a plurality of dimensions representing different metabolic capacities, determining a dimension score of the athlete in the dimension according to the feature parameters; and generating an evaluation result about the metabolic capacity of the athlete according to the plurality of dimension scores. The technical solution of the embodiments of the present application can accurately evaluate the metabolic capacity of the athlete.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of healthcare informatics technology, and in particular to a method, system and storage medium for assessing metabolic capacity. Background Technology

[0002] With the rapid development of wearable biosensor technology, it has become possible to monitor athletes' physiological and biochemical indicators in real time and non-invasively during training and competition, and these indicators can be used to assess athletes' metabolic capacity.

[0003] Lactic acid, as a key molecule reflecting anaerobic metabolic intensity, aerobic metabolic efficiency, and the body's fatigue resistance and recovery capabilities, contains rich information in its dynamic change curve for assessing athletes' metabolic quality. How to extract physiologically significant characteristics from the complex lactate response curve that can comprehensively and fairly assess athletes' overall metabolic capacity, and transform them into intuitive and operable assessment results, is a core challenge and cutting-edge direction in the fields of athletic performance analysis, scientific talent selection, and personalized training program development.

[0004] Current lactate collection mainly involves intermittently collecting blood from athletes' earlobes or fingertips. The number of collection points is limited, which cannot cover the entire exercise cycle, resulting in low efficiency and high cost. The relevant programs for assessing athletes' metabolic capacity mainly focus on the following aspects: (1) using a single indicator assessment method, which only focuses on a single characteristic point of the lactate response curve; (2) using simple composite indicators, attempting to combine 2-3 indicators, but the relationship between the indicators is vague, and it is impossible to form a three-dimensional portrait of the athlete's metabolic characteristics; (3) lacking standardization and visualization, the assessment results given by the relevant programs are mostly numerical or simple charts (such as lactate-time curves), lacking a unified and standardized scoring system that can be compared with different athletes or sports. This makes it difficult for coaches and athletes to intuitively and quickly understand the assessment results, and even more difficult to formulate targeted training programs for weak links based on this.

[0005] Essentially, the main problem lies in how to accurately assess an athlete's metabolic capacity. Summary of the Invention

[0006] This invention provides a method, system, and storage medium for assessing metabolic capacity, solving the problem of the inability to accurately assess the metabolic capacity of athletes.

[0007] According to one aspect of the present invention, a method for assessing metabolic capacity is provided, which may include:

[0008] Obtain time-series data on interstitial lactate levels in athletes during and before exercise;

[0009] Extract feature parameters from time series data;

[0010] For each of the multiple dimensions characterizing different metabolic capabilities, the athlete's dimensional score is determined based on the feature parameters.

[0011] Based on scores from multiple dimensions, an assessment of the athlete's metabolic capacity is generated.

[0012] According to another aspect of the present invention, a metabolic capacity assessment system is provided, which may include: a sensor, an athlete terminal, and a server; wherein the sensor is worn by the athlete; wherein,

[0013] The athlete terminal is used to acquire time-series data collected by sensors and send the time-series data to the server. The time-series data is the time-series data of interstitial lactate values ​​of athletes during and before exercise.

[0014] The server is used to extract feature parameters from time-series data sent from athlete terminals, and determine the athlete's dimensional score in each dimension based on the feature parameters for multiple dimensions that characterize different metabolic capabilities. Based on the scores of multiple dimensions, the server generates an assessment result on the athlete's metabolic capabilities.

[0015] According to another aspect of the present invention, a metabolic capacity assessment device is provided, which may include:

[0016] The time-series data acquisition module can be used to acquire time-series data of interstitial lactate levels in athletes during and before exercise.

[0017] The feature parameter extraction module is used to extract feature parameters from time series data;

[0018] The dimensional score determination module is used to determine the athlete's dimensional score for each of the multiple dimensions that characterize different metabolic capabilities, based on the feature parameters.

[0019] The assessment results generation module is used to generate assessment results about the athlete's metabolic capacity based on scores from multiple dimensions.

[0020] According to another aspect of the present invention, a server is provided, which may include:

[0021] At least one processor; and

[0022] A memory that is communicatively connected to at least one processor; wherein,

[0023] The memory stores a computer program that can be executed by at least one processor to implement the metabolic capacity assessment method provided in any embodiment of the present invention when executed by at least one processor.

[0024] According to another aspect of the present invention, a computer-readable storage medium is provided having computer instructions stored thereon for causing a processor to execute and implement the metabolic capacity assessment method provided in any embodiment of the present invention.

[0025] According to another aspect of the present invention, a computer program product is provided, on which a computer program is stored, which, when executed by a processor, implements the metabolic capacity assessment method provided in any embodiment of the present invention.

[0026] The technical solution of this invention acquires time-series data of interstitial lactate levels in athletes during and before exercise; extracts feature parameters from the time-series data; and determines a dimension score for each of multiple dimensions characterizing different metabolic capacities based on the feature parameters. Then, based on the scores across multiple dimensions, an assessment result of the athlete's metabolic capacity is generated. Compared to related schemes that use single or simple composite indicators for metabolic capacity assessment, the above technical solution, by acquiring time-series data of interstitial lactate levels and extracting feature parameters, and then comprehensively assessing the results based on scores across multiple dimensions, helps to form a multidimensional description of metabolic characteristics, achieving an accurate assessment of the athlete's metabolic capacity. Moreover, it relies solely on readily available interstitial lactate levels, resulting in lower costs, thus making it widely applicable in routine training, outdoor sports, and mass fitness scenarios. Furthermore, its standardized scoring system facilitates comparisons with different athletes or different sports, allowing coaches and athletes to intuitively and quickly understand the assessment results and develop targeted training programs for weaknesses.

[0027] It should be understood that the description in this section is not intended to identify key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a flowchart of a metabolic capacity assessment method provided by an embodiment of the present invention;

[0030] Figure 2a This is a schematic diagram of the rising segment of the lactic acid response curve provided in an embodiment of the present invention;

[0031] Figure 2bThis is a schematic diagram of an approximately linearly increasing segment in the rising segment provided by an embodiment of the present invention;

[0032] Figure 2c This is a schematic diagram of lactic acid levels before and after an anaerobic power test according to an embodiment of the present invention;

[0033] Figure 2d This is a schematic diagram of the descending segment of the lactic acid response curve provided in an embodiment of the present invention;

[0034] Figure 2e This is a schematic diagram of an approximately linear descending segment in a descending segment provided according to an embodiment of the present invention;

[0035] Figure 2f This is a schematic diagram of the correlation analysis of the area under the lactate curve within different target time periods provided by an embodiment of the present invention;

[0036] Figure 2g This is a schematic diagram illustrating the relationship between the peak increment (i.e., the first net increment) and the relative maximum power according to an embodiment of the present invention;

[0037] Figure 3 This is a flowchart of another metabolic capacity assessment method provided by an embodiment of the present invention;

[0038] Figure 4 This is a schematic diagram of a radar chart regarding dimensional scoring provided in an embodiment of the present invention;

[0039] Figure 5 This is a structural block diagram of a metabolic capacity assessment system provided according to an embodiment of the present invention;

[0040] Figure 6 This is a schematic diagram of the component composition of a server provided according to an embodiment of the present invention;

[0041] Figure 7 This is a schematic diagram of another radar chart for dimensional scoring provided according to an embodiment of the present invention;

[0042] Figure 8 This is a structural block diagram of a metabolic capacity assessment device provided according to an embodiment of the present invention;

[0043] Figure 9 This is a schematic diagram of the structure of a server that implements the metabolic capacity assessment method of this invention. Detailed Implementation

[0044] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0045] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. The same applies to "target," "original," etc., and will not be repeated here. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0046] It should be noted that the collection, gathering, updating, analysis, processing, use, transmission, and storage of user personal information involved in the technical solution of this invention all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to maintain user personal information security and network security.

[0047] Figure 1 This is a flowchart of a metabolic capacity assessment method provided in an embodiment of the present invention. This embodiment is applicable to assessing the metabolic capacity of athletes. The method can be executed by the metabolic capacity assessment device provided in this embodiment of the present invention, which can be implemented in software and / or hardware and can be integrated on a server.

[0048] See Figure 1 The method of this invention specifically includes the following steps:

[0049] S110. Obtain time-series data of interstitial lactate levels in athletes during and before exercise.

[0050] The exercise process includes the time segment from the start to the end of the exercise; the pre-exercise segment includes the resting time segment before the start of the exercise (i.e., the time segment during which the athlete is in a resting state); and the post-exercise segment includes the time segment from the end of the exercise until the interstitial fluid lactate value falls below a set lactate value threshold. In this embodiment of the invention, optionally, the set lactate value threshold can be set according to different exercise programs. For example, in an anaerobic power test (such as wingate), the set lactate value threshold can be the average value of the interstitial fluid lactate value within the resting time segment.

[0051] Interstitial fluid lactate levels can be understood as the numerical value of lactate concentration in the interstitial fluid of athletes. Time-series data can be understood as a sequence of interstitial fluid lactate levels collected chronologically during and before / after exercise.

[0052] Acquiring time-series data. Compared to methods that involve intermittently collecting blood from an athlete's earlobe or fingertip and then using related equipment to measure interstitial fluid lactate levels to obtain time-series data, this embodiment of the invention can collect time-series data based on wearable biosensor technology. This allows for continuous collection of interstitial fluid lactate levels to cover the entire exercise cycle, and has the advantages of high efficiency, low cost, and avoiding pain for the athlete.

[0053] In this step, by acquiring time-series data that fully covers the metabolic stress and recovery process, a reliable foundation can be provided for subsequent feature parameter extraction, avoiding misleading single-point values.

[0054] S120. Extract feature parameters from time series data.

[0055] Among them, the feature parameters can be understood as quantitative indicators reflecting the dynamic law of lactate extracted from time series data. Based on this, combined with the application scenarios that may be involved in the embodiments of the present invention, the feature parameters may optionally include one or more of the following: resting lactate value, response lactate value, lactate rise half width, early metabolic sensitivity, lactate rise slope, lactate peak value, lactate half peak value, lactate clearance half width, lactate clearance rate, and area under the lactate curve, etc. Therefore, the feature parameters can be considered as multi-dimensional feature parameters.

[0056] In this step, feature parameters are extracted from time-series data. These feature parameters encapsulate the dynamic information of the original data, enabling quantitative comparison of the metabolic responses of different athletes and supporting multi-dimensional analysis.

[0057] S130. For each of the multiple dimensions that characterize different metabolic capabilities, determine the athlete's dimension score under each dimension based on the feature parameters.

[0058] Metabolic capacity can be understood as the overall physiological level of an athlete in utilizing energy substrates and producing and clearing lactic acid. Different dimensions are preset for different metabolic capacities. Based on this, and considering the application scenarios that may be involved in the embodiments of this invention, optionally, the above-mentioned multiple dimensions may include multiple of the following: explosive power dimension reflecting the ability to rapidly mobilize energy, maximal capacity dimension reflecting the anaerobic capacity limit, blood return capacity dimension reflecting the lactic acid clearance rate, basic endurance dimension reflecting aerobic metabolic efficiency, metabolic efficiency dimension reflecting metabolic economy, and metabolic sensitivity dimension reflecting the awakening speed of the metabolic system. Of course, other dimensions that can reflect metabolic capacity can also be used, without specific limitations here.

[0059] It should be noted that the aforementioned dimensions can be considered as deconstructing lactate kinetics information into six orthogonal dimensions with clear physiological significance: "explosive power, maximal volume, blood return capacity, basic endurance, metabolic efficiency, and metabolic sensitivity." These six dimensions cover the entire process of the metabolic system from "start-up," "output," and "endurance" to "recovery," "economy," and "agility," thus achieving a panoramic and structured assessment of an athlete's metabolic capacity based on interstitial lactate levels. In particular, it introduces two key dimensions that have been neglected in traditional assessments: "metabolic sensitivity" (system start-up delay) and "metabolic efficiency" (the ratio of output to cost).

[0060] Based on the characteristic parameters, the athlete's dimensional scores are determined for each dimension. In this step, multi-dimensional scoring reveals the specific strengths and weaknesses of metabolic capacity, avoiding one-sided evaluation based on a single indicator and facilitating targeted training.

[0061] S140. Based on scores from multiple dimensions, generate an assessment of the athlete's metabolic capacity.

[0062] In this invention, after obtaining the dimensional scores corresponding to multiple dimensions, an evaluation result can be generated based on these scores. This evaluation result can be understood as a conclusive output that comprehensively judges the athlete's metabolic capacity level. In this embodiment of the invention, optionally, the evaluation result can be represented by one or more methods such as total score, level, and radar chart, which can be set according to actual needs and is not specifically limited here.

[0063] For example, the scores for each dimension are weighted and summed to obtain a total metabolic capacity score, which is then categorized into levels based on thresholds. Another example is inputting all dimension scores into a rule-based system, which then outputs a qualitative assessment result. Of course, assessment results can also be generated using other methods, which are not specifically limited here.

[0064] In this step, an intuitive and interpretable assessment result is formed by integrating multi-dimensional scores, which can directly serve the analysis of athletic performance, talent selection, and training program development.

[0065] The technical solution of this invention acquires time-series data of interstitial lactate levels in athletes during and before exercise; extracts feature parameters from the time-series data; and determines a dimension score for each of multiple dimensions characterizing different metabolic capacities based on the feature parameters. Then, based on the scores across multiple dimensions, an assessment result of the athlete's metabolic capacity is generated. Compared to related schemes that use single or simple composite indicators for metabolic capacity assessment, the above technical solution, by acquiring time-series data of interstitial lactate levels and extracting feature parameters, and then comprehensively assessing the results based on scores across multiple dimensions, helps to form a multidimensional description of metabolic characteristics, achieving an accurate assessment of the athlete's metabolic capacity. Moreover, it relies solely on readily available interstitial lactate levels, resulting in lower costs, thus making it widely applicable in routine training, outdoor sports, and mass fitness scenarios. Furthermore, its standardized scoring system facilitates comparisons with different athletes or different sports, allowing coaches and athletes to intuitively and quickly understand the assessment results and develop targeted training programs for weaknesses.

[0066] An optional technical solution for determining an athlete's dimensional score in a dimension based on a feature parameter may include: in response to the dimension being the explosive power dimension and the feature parameter being the lactate rise slope, determining the athlete's dimensional score in the explosive power dimension based on the lactate rise slope.

[0067] Among them, the explosive power dimension can reflect the ability to rapidly mobilize energy.

[0068] The lactate rise slope can be understood as the rate at which the interstitial fluid lactate level increases over time. It characterizes the speed at which the athlete's body produces and accumulates lactate after the onset of exercise. For example, for a lactate response curve plotted based on time-series data, the lactate rise slope... This can be understood as the slope of the rising segment of the lactic acid response curve (e.g., Figure 2a As shown), it can be further understood as the slope of the approximately linearly increasing segment in the ascending segment (e.g. Figure 2b (As shown). In this technical solution, optionally, the approximately linearly increasing segment can be defined as the segment from the response lactate value to 90% of the lactate peak, such as... Figure 2b As shown, after fitting Alternatively, this approximately linearly increasing segment can also be defined as the segment from the response lactate value to lactate minus 0.5 mM.

[0069] The athlete's score in the explosive power dimension is determined based on the lactate rise slope. An example is the score in the explosive power dimension. The calculation formula is as follows:

[0070] ;

[0071] in, The lactate rise slope was measured based on an athlete's lactate response curve. , It is the benchmark lactate rise slope against which the athlete's athletic test is compared, such as in the wingate test. The best performance value for the sport test and / or the athlete's historical best value can be taken.

[0072] The above technical solution uses the lactate rise slope to directly quantify the energy mobilization speed, avoiding the loss of the rapid rise segment during intermittent blood sampling, thereby providing a standardized score for explosive power.

[0073] Another optional technical solution is to determine the athlete's dimensional score in the dimension based on the feature parameter, including: in response to the dimension being the limit capacity dimension and the feature parameter being the lactate peak, obtaining the first net increment corresponding to the lactate peak, and determining the athlete's dimensional score in the limit capacity dimension based on the first net increment.

[0074] Among them, the limiting capacity dimension can reflect the anaerobic capacity limit.

[0075] lactate peak This can be understood as the peak point in the lactic acid response curve, for example... Figure 2c The value shown is 5.57 mM. First net increment. This can be understood as the net increase in lactate peak value relative to resting lactate value, i.e., the difference between the lactate peak value and the resting lactate value. In this technical solution, optionally, the resting lactate value... Take the mean or median value of interstitial lactate within the resting time period.

[0076] Building upon this, and combining it with the lactate peak value, let's further illustrate the lactate half-peak value to better understand its use in determining dimension scores later in the text. The lactate half-peak value can be understood as half the lactate peak value. Since the actual interstitial fluid lactate value is a discrete value, the rising lactate half-peak value (i.e., the lactate half-peak value in the rising segment) and the falling lactate half-peak value (i.e., the lactate half-peak value in the falling segment) can be taken as the interstitial fluid lactate value closest to the calculated lactate half-peak value. For example... Figure 2c As shown, the lactate peak value is 5.57 mM, and the corresponding calculated lactate half-peak value is 2.79 mM. The interstitial fluid lactate value closest to it in the rising segment is 2.88 mM, so 2.88 mM is taken as the rising half-peak value of lactate. The interstitial fluid lactate value closest to it in the falling segment is 2.78 mM, so 2.78 mM is taken as the falling half-peak value of lactate.

[0077] Based on the first net increment, determine the athlete's dimensional score in the limit capacity dimension. For example, the dimensional score in the limit capacity dimension. The calculation formula is as follows:

[0078] ;

[0079] ;

[0080] in, The first net increment was measured based on an athlete's lactate response curve. ; The net increment of the baseline lactate peak value can be, optionally, taken as the better level value of the corresponding sports test and / or the athlete's historical best value in this technical solution.

[0081] The above-mentioned technical solution uses the first net increment to assess the anaerobic capacity limit, overcoming the defect that the single lactate peak is easily affected by individual baseline differences, and is more accurate than a single lactate peak.

[0082] Another alternative technical solution, which determines the athlete's dimensional score in a dimension based on feature parameters, may include: in response to the dimension being the blood return capacity dimension and the feature parameters being lactate clearance rate and lactate clearance half-width, determining the athlete's dimensional score in the blood return capacity dimension based on the lactate clearance rate and lactate clearance half-width.

[0083] Among them, the blood return capacity dimension reflects the lactate clearance rate. Lactic acid clearance rate This can be understood as the slope of the descending segment of the lactic acid response curve (e.g., Figure 2d As shown), it can be further understood as the slope of the approximately linearly decreasing segment within the decreasing segment (e.g., Figure 2e As shown in the figure, in this technical solution, optionally, the approximately linear decreasing segment is defined as the segment from 95% of the lactate peak to the half-peak of lactate decrease, and the fitted... (like Figure 2e (As shown). Lactic acid scavenging half-width. This can be understood as the time interval between the time point corresponding to the half-peak of lactate decrease in the lactate response curve and the time point corresponding to the peak of lactate in the lactate response curve. To distinguish this from other time intervals, this time interval is referred to as the second time interval. For example, see [link to example]. Figure 2c , ,in, This is the time point corresponding to the half-peak value of lactate decrease in the lactate response curve. It is the time point corresponding to the lactate peak in the lactate response curve.

[0084] Based on lactate clearance rate and lactate clearance half-width, the athlete's dimensional score in the blood return capacity dimension can be determined. An example is the dimensional score in the blood return capacity dimension. The calculation formula is as follows:

[0085] ;

[0086] in, The baseline lactate clearance half-width, For single-sensor lactate clearance half-width ; Lactic acid clearance rate for a single sensor The absolute value, The baseline lactate clearance rate; The indicator weight is an empirical threshold, for example... Take 60.

[0087] The above technical solution combines lactate clearance rate and lactate half-peak width to assess blood return ability. This is more effective than lactate clearance rate alone in characterizing the speed and persistence of the clearance process, thus avoiding one-sided conclusions.

[0088] Another optional technical solution is to determine the athlete's dimensional score under the dimensional dimension based on the feature parameter, including: in response to the dimensional dimension being the baseline endurance dimensional dimension and the feature parameter being the steady-state lactate value, obtaining the second net increment corresponding to the steady-state lactate value, and determining the athlete's dimensional score under the baseline endurance dimensional dimension based on the second net increment.

[0089] Among them, the basic endurance dimension can reflect the efficiency of aerobic metabolism.

[0090] Steady-state lactate value This can be understood as the interstitial fluid lactate level measured when the athlete is in a steady state during or after exercise. Here, steady state can be understood as a physiological state in which the interstitial fluid lactate level is relatively stable with minimal fluctuations. In this technical solution, optionally, in endurance testing... It can be defined as the baseline value at steady state, and can be taken as the median value of lactate in each interstitial fluid within a set time period (e.g., 10 minutes) before the end of endurance exercise, to focus on assessing the athlete's endurance. Alternatively, in explosive power tests, It can be defined as the baseline value at the point of recovery to steady state after exercise. It can be the median lactate value of each interstitial fluid within a set time period (e.g., 30 minutes) after recovery to the target lactate level, to focus on assessing the athlete's fatigue index. Second Net Increment It can be understood as the net increase in steady-state lactate value relative to resting lactate value, that is, the difference between steady-state lactate value and resting lactate value.

[0091] Furthermore, the athlete's dimensional score in the baseline endurance dimension is determined based on the second net increment. For example, the dimensional score in the baseline endurance dimension... The calculation formula is as follows:

[0092] ;

[0093] ;

[0094] in, This is the resting lactate value. This represents the net increase corresponding to the baseline steady-state lactate value. The second net increment corresponding to the steady-state lactate value of a single sensor (i.e., the athlete). .

[0095] The above technical solution uses the net increase in steady-state lactate value to reflect aerobic metabolic efficiency, avoiding the limitations of traditional aerobic / anaerobic threshold sampling points and reliance on external equipment, making it suitable for routine training.

[0096] Based on this, optionally, obtaining the second net increment corresponding to the steady-state lactate value may include: obtaining the first difference between the steady-state lactate value and the resting lactate value, and weighting the first difference based on the first net increment to obtain the second net increment corresponding to the steady-state lactate value.

[0097] Among them, the net increase of lactate peak (i.e., the first net increase) is taken into account. )right The impact, usually The larger the value, the longer it takes for the baseline to stabilize; therefore, it can be... As a weighting metric, accordingly, The calculation formula is as follows:

[0098] ;

[0099] Among them, the sports tests conducted on athletes This represents the average of the athletes' first net increments in this sport test. For example, using... Taking 4mM as an example, calculate the results in both unweighted and weighted cases. The calculation results are shown in Table 1. By considering... right Weighted adjustments can be made to allow those below a certain threshold to... of Weight > 1, thus improving To adjust appropriately This compensates for its advantage of rapid recovery; while higher than of Weight < 1, thus reducing To adjust appropriately This compensates for its slow recovery.

[0100] Table 1 Comparison of calculation results

[0101]

[0102] The above technical solution introduces the first net increment as a weight, so that the steady-state lactate value not only reflects the current steady-state level, but also takes into account the individual's anaerobic capacity limit, thereby improving the individualized accuracy of basic endurance assessment.

[0103] Another alternative technical solution, which determines the athlete's dimensional score under a dimension based on the feature parameter, may include: in response to the dimension being the metabolic efficiency dimension and the feature parameter being the area under the lactate curve, obtaining the metabolic efficiency based on the area under the lactate curve, and determining the athlete's dimensional score under the metabolic efficiency dimension based on the metabolic efficiency and the subjective score.

[0104] Among them, metabolic efficiency can reflect metabolic economy.

[0105] For the interstitial lactate values ​​within the target time period in the lactate response curve, the area under the lactate curve (AUC_net) can be understood as the sum of the differences (i.e., the second difference) between each interstitial lactate value and the response lactate value. This sum can also be called the net area increment under the curve. For example, Figure 2c The AUC_net shown is to The net area under the curve increases within this target time period. For example, because the lactic acid response curve tails after the half-peak, the contribution value of the net area under the curve increase is relatively low, so we can take... to The net increase in area under the curve during this target time period. For example, Table 2 and... Figure 2f As shown, the difference in the net area increment under the curves of AUC_net(t1-t5) and AUC_net(t1-t4) ranges from 1.33% to 11.3%, with a relatively small overall difference. The relationship between the two is approximately linear, and the fitted R-squared value is [value missing]. 2 The value is 0.99, and the area under the lactate curve (AUC_net) is acceptable. to The net area under the curve is the increase in lactate levels. Here, the area under the lactate curve is defined as the sum of the differences between interstitial lactate values ​​and response lactate values ​​(i.e., the second difference), thereby eliminating the influence of individual baseline differences on the total amount of lactate accumulation and making the scores of the metabolic efficiency dimension more comparable.

[0106] Table 2 Area under the lactate curve

[0107]

[0108] Subjective rating This can be understood as the fatigue perception score recorded by athletes after exercise, i.e. Subjective fatigue perception is used to measure the consistency between "mental fatigue" and "physiological metabolism." For example, athletes can record a subjective score (0-10) after completing training. Optionally, the subjective score levels can be: 0 points represent no effort at all; 1-3 points represent easy; 4-6 points represent moderate; 7-9 points represent difficult; and 10 points represent the limit, complete exhaustion.

[0109] Furthermore, metabolic efficiency is obtained from the area under the lactate curve, and then the athlete's dimensional score in the metabolic efficiency dimension can be determined based on metabolic efficiency and subjective rating. For example, the formula for calculating the dimensional score in the metabolic efficiency dimension is as follows:

[0110] ;

[0111] in, The metabolic efficiency corresponding to each sensor. This is the baseline metabolic efficiency.

[0112] The above technical solution combines objective lactate burden and subjective fatigue perception to comprehensively evaluate metabolic economy, making up for the shortcomings of the single lactate curve area under the curve that ignores subjective feelings.

[0113] Optionally, metabolic efficiency can be obtained based on the area under the lactate curve, including: obtaining metabolic efficiency based on the power output of the sports equipment used by the athlete and the area under the lactate curve, or obtaining metabolic efficiency based on the first net increment and the area under the lactate curve.

[0114] For example, the power output of the sports equipment used by athletes during sports testing. In the availability In this case, The calculation formula is as follows:

[0115] ;

[0116] in, It can be the average relative power or the maximum relative power.

[0117] For another example, when it is impossible to obtain In this case, the first net increment can be used It represents the magnitude of work done. For example... Figure 2g As shown, here is Taking relative maximum power as an example, and There is a positive correlation between them, therefore when it is not possible to obtain When, can be used to replace ,but The calculation formula is as follows:

[0118] ;

[0119] in, This represents the feature weight coefficient, determined by empirical values. Because... relatively The difference is small, and direct division has little distinguishing effect; it can be set... To expand The weighting of these weights improves the ability to differentiate athletes of different levels and in different events, and more accurately reflects training effectiveness. For example, the comparison results for n=1, 2, and 3 are shown in Table 3. According to Table 3, When the value is 1, the feature discrimination is not significant; as... The improvement in differentiation is more obvious. In this example, we take... =3 indicates a more significant differentiation in the calculation results.

[0120] Table 3 Differences Values Calculation results

[0121]

[0122] The above technical solution provides two optional methods for calculating metabolic efficiency, which can be flexibly selected according to actual equipment conditions. Method 1 is suitable for professional scenarios with power meters, directly linking the output of exercise equipment with metabolic burden; Method 2 relies solely on lactate data, eliminating dependence on expensive external equipment, and has the advantages of low cost and easy popularization, enabling metabolic efficiency assessment to be extended to regular training and outdoor scenarios.

[0123] Another optional technical solution, which determines the athlete's dimensional score under a dimension based on the feature parameters, may include: in response to the dimension being the metabolic sensitivity dimension and the feature parameters being early metabolic sensitivity or a first time interval, obtaining the metabolic sensitivity based on the early metabolic sensitivity or the first time interval, and determining the athlete's dimensional score under the metabolic sensitivity dimension based on the metabolic sensitivity.

[0124] Among them, the metabolic sensitivity dimension can reflect the awakening speed of the metabolic system.

[0125] Early metabolic sensitivity characterizes the time required to increase one unit of interstitial lactate level. For example, for a lactate response curve plotted based on time-series data, the half-width at half-maximum (WHM), half-peak value at half-maximum (HHM), and resting lactate level are extracted from the lactate response curve. Then, early metabolic sensitivity is obtained based on the extraction results (i.e., the extracted WHM, HHM, and resting lactate levels).

[0126] Among them, the half-maximum width of lactic acid rises This can be understood as the third time interval between the time point corresponding to the lactate value on the lactate response curve and the time point corresponding to the half-peak value of lactate on the lactate response curve. For example, see... Figure 2c The half-peak width of lactic acid increases .

[0127] Based on this, optionally, in order to eliminate the interference of baseline fluctuation error, the interstitial lactate value after the first first-order difference value after the start of the motion is greater than a set threshold can be selected as the response lactate value. For example, a threshold of 0.1 mM is set, and the specific data is shown in Table 4. After the start of exercise, when the first-order difference value is greater than 0.1 mM, the interstitial fluid lactate value is 1.64 mM, which is the response lactate value. =1.64mM.

[0128] Table 4 Response Lactic Acid Value

[0129]

[0130] Furthermore, as explained above, early metabolic sensitivity... This can characterize the time required to increase the liquid lactate value by one unit (i.e., 1 mM), and the calculation formula is as follows:

[0131] ;

[0132] in, The half-peak value of lactic acid rise. This is the resting lactate value.

[0133] Furthermore, metabolic sensitivity can be derived from early metabolic sensitivity, for example, by directly using early metabolic sensitivity as the metabolic sensitivity. For instance, Table 5 shows data on how, in some cases, the time required for resting baseline +0.5 mM, the time required for resting baseline +1 mM, and early metabolic sensitivity can characterize the metabolic sensitivity of different athletes. As shown in Table 5, the time required for resting baseline +0.5 mM has little discriminatory power, while the time required for resting baseline +1 mM and early metabolic sensitivity can be well distinguished among different athletes. Early metabolic sensitivity considers the factor of lactate increase increment, and can better distinguish the impact of different lactate increments on metabolic sensitivity in athletes 6 and 10. Here, the half-width at half-maximum (WHM) and half-peak value of lactate increase are used to accurately quantify the awakening speed, avoiding noise interference from relying solely on a single-point threshold, which helps improve the robustness of metabolic sensitivity assessment.

[0134] Table 5. Metabolic sensitivity of different sensors (i.e., athletes)

[0135]

[0136] The first time interval can be understood as the time interval between the point when the interstitial fluid lactate level rises to the set lactate level and the point when exercise begins. In other words, this time interval is the time interval between the rise of the resting lactate level to the set lactate level at the start of exercise. Optionally, the set lactate level can be an empirical threshold, such as 0.5 mM or 1 mM. The calculation formula is as follows:

[0137] ;

[0138] in, To reach the set lactate level at the set time point, This refers to the point in time when the movement begins.

[0139] In this technical solution, metabolic sensitivity can be obtained based on the first time interval. Generally, the shorter the first time interval, the higher the metabolic sensitivity, which can be mapped to a score via a function.

[0140] Furthermore, after obtaining metabolic sensitivity based on early metabolic sensitivity or the first time interval, the athlete's dimensional score in the metabolic sensitivity dimension is determined based on the metabolic sensitivity. For example:

[0141] ;

[0142] in, As a baseline metabolic sensitivity, Metabolic sensitivity characterized for each sensor.

[0143] The above technical solution quantifies the awakening speed by early metabolic sensitivity or the first time interval, capturing the initial reaction stage that is easily missed during intermittent blood sampling, thus making the assessment more complete.

[0144] Figure 3 This is a flowchart of another metabolic capacity assessment method provided by an embodiment of the present invention. This embodiment is an optimization based on the above-described technical solutions. Optionally, in this embodiment, generating an assessment result of an athlete's metabolic capacity based on multiple dimension scores may include: determining the type of exercise performed by the athlete and obtaining a weight combination set for the exercise type, wherein the weight combination includes weights corresponding to each of the multiple dimensions; and weighting the multiple dimension scores according to the weight combination to generate an assessment result of the athlete's metabolic capacity. Explanations of terms that are the same as or corresponding to those in the above embodiments are not repeated here.

[0145] See Figure 3 The method in this embodiment may specifically include the following steps:

[0146] S210. Obtain time-series data of interstitial lactate levels in athletes during and before exercise.

[0147] S220. Extract feature parameters from time series data.

[0148] S230. For each of the multiple dimensions that characterize different metabolic capabilities, determine the athlete's dimension score under each dimension based on the feature parameters.

[0149] S240. Determine the type of sport the athlete is performing and obtain the weight combination set for the sport type, wherein the weight combination includes weights corresponding to multiple dimensions respectively.

[0150] The type of exercise can be understood as the specific type of exercise performed by the athlete. In combination with the application scenarios that may be involved in the embodiments of the present invention, the type may be explosive exercise, endurance exercise or high-intensity interval exercise, etc., which is related to the actual situation and is not specifically limited here.

[0151] The weight combination can be understood as a set of numerical values, corresponding to the multiple dimensions described above. Each dimension is assigned a weight, reflecting the importance of that dimension to the current motion type.

[0152] The system retrieves weight combinations set for specific sports types. For example, the system may have built-in weight combinations for different sports types, allowing direct access to the corresponding weight combination after obtaining the sports type input or identified by the athlete. Alternatively, coaches or athletes may be allowed to customize sports types and weight combinations within the system, or optimize weight combinations through machine learning using historical data. This allows the system to retrieve the corresponding weight combination from the database after determining the sports type. And so on, without further specific limitations.

[0153] This step aligns the assessment results with exercise needs, preventing generic scoring from masking key metabolic capabilities specific to a particular exercise, thereby enhancing the relevance and practical value of the assessment results.

[0154] Building upon this foundation, and to better understand this step, an example as shown in Table 6 is provided. The scores for each of the six dimensions are weighted according to the type of exercise. This weighting is not an arbitrary empirical combination, but strictly corresponds to the differences in the dependence of different exercise types on the phosphagen system, glycolysis system, and aerobic oxidation system. For example, the weight range for explosive power exercise, endurance exercise, and high-intensity interval training is set to [0, 1.5], as shown in Table 6.

[0155] Table 6. Weight combinations for different types of exercise

[0156]

[0157] The weighting combination for explosive power exercises is set as (Sq: [1.5, 1.5, 1.5, 0.2, 1, 1.2]). Explosive power performance directly depends on the muscles' ability to generate high power (S1: lactate rise slope) and maintain high energy output levels (S2: initial net increment) in a very short time, requiring a relatively high weight of 1.5. Although a single competition session is short, athletes need to complete multiple sets of lifts or sprints during training and competition. The recovery speed between sets or repetitions directly determines the ability to maintain subsequent performance; therefore, (S3: blood return) is as important as output ability and also requires a relatively high weight of 1.5. Reaction speed, starting speed, and explosive start all depend on the metabolic system's "wake-up speed" from rest to maximum output, and (S6: metabolic sensitivity) determines whether the athlete can enter the optimal state the instant the starting gun fires; therefore, it also requires a relatively high weight of 1.2. In single-attack bursts of maximum output, metabolic economy is not the primary consideration ("generating power at all costs"), but it still has value in long-term training and body composition management (S5: metabolic efficiency), hence it is given a moderate weight of 1. Explosive power sports are primarily powered by the anaerobic system, with minimal contribution from the aerobic system; therefore, the extremely low weight of (S4: baseline endurance) reflects the low predictive value of this dimension for specific performance. However, the recovery baseline for explosive power sports can determine the athlete's fatigue index, and a relatively low weight of 0.2 can be assigned.

[0158] The weighting for endurance sports is set to (Sq: [0, 0, 0, 1.5, 0, 0]). The essence of endurance sports is to maximize aerobic metabolic efficiency and minimize lactate accumulation. Lower steady-state lactate levels correspond to a second net increment (S4: basal endurance), meaning athletes can exercise at higher intensity without fatigue, which is a decisive physiological factor in determining long-distance event performance. In typical sustained endurance sports (such as marathons), athletes are always at submaximal intensity and do not trigger significant anaerobic glycolysis and large amounts of lactate accumulation. Therefore, the indicators characterizing anaerobic burst (S1, S2), rapid clearance (S3), and rapid start (S6) have very weak correlations with endurance sports performance. Setting the weight to 0 allows the evaluation to focus absolutely on aerobic endurance.

[0159] The weighting for high-intensity interval training (HIIT) is set as (Sq: [1.5, 1.5, 1.0, 0.2, 0.1, 1.2]). Every sprint, jump, and contact requires significant anaerobic power output; therefore, the weights for (S1: Explosive Power) and (S2: Maximum Capacity) are relatively high, set at 1.5. The transitions between offense and defense and the initiation of movements during competition require extremely fast metabolic response; therefore, (S6: Metabolic Sensitivity) is also crucial, with a weight of 1.0. (S3: Recovery) is also important but slightly less so than explosive power. Recovery during interval training is incomplete, but faster clearance means a better state at the start of the next interval cycle; its weight can be slightly lower than pure explosive power training, reflecting its slightly less importance than single-output capacity, set at 1. (S5: Metabolic Efficiency) and (S4: Baseline Endurance) are non-dominant factors in HIIT, with lower weights, set at 0.1 and 0.2 respectively.

[0160] S250. Based on the weight combination, the scores of multiple dimensions are weighted to generate an assessment result on the athlete's metabolic capacity.

[0161] The evaluation results are generated by multiplying the scores of each dimension by their corresponding weights.

[0162] For example, the formula for calculating the final overall metabolic capacity assessment result is as follows:

[0163] ;

[0164] in, For comprehensive scoring, - These are the weights in the weighted combination.

[0165] The dimensional scores (i.e., baseline scores) for each dimension can be represented by radar charts to assess the athlete's metabolic capacity in each component. For example, the dimensional scores and corresponding weights for the six dimensions calculated based on the feature parameters extracted from the lactate response curve are shown in Table 7, and the corresponding radar charts are shown below. Figure 4 As shown:

[0166] Table 7. Dimension Scores and Corresponding Weights for the Six Dimensions

[0167]

[0168] Therefore, the comprehensive score is calculated using the following formula. It is 87.58:

[0169] .

[0170] In this step, by weighting and integrating the scores from various dimensions, a comprehensive evaluation result closely related to the type of sport is generated, which can provide an intuitive and comparable data basis for sports performance analysis, talent selection, and the development of personalized training programs.

[0171] The technical solution of this invention introduces an adaptive mechanism based on exercise type, assigning weights to each metabolic dimension according to the characteristics of different sports, and then generating a comprehensive evaluation result through weighted processing. This solves the problems of lack of standardization and visualization in existing technologies, and the difficulty in comparing evaluation results across sports. It makes the evaluation results both holistic (overall score) and targeted (weights reflect the needs of the sport), making it easier for coaches and athletes to quickly understand the significance of their strengths and weaknesses in metabolic capacity relative to their sport, thereby developing more scientific training plans.

[0172] An optional technical solution for obtaining a weight combination set for a sport type may include: determining the tactical role an athlete assumes during a sport; and obtaining a weight combination set for the sport type and the tactical role.

[0173] Tactical roles can represent the functions that athletes undertake during the sport. In this technical solution, it can be a forward, midfielder or defender in football, a defender or center in basketball, or a defensive core or offensive initiator in team sports. This is related to the actual situation and is not specifically limited here.

[0174] For example, after a coach or athlete selects a sport type in the system interface, they can choose the athlete's tactical role from a pop-up role list, and the system records this selection. As another example, tactical roles can be automatically identified or recommended by analyzing the athlete's historical competition data (such as running distance, number of sprints, and position heatmaps), and then used after manual confirmation. Introducing tactical roles on top of sport types allows for further refinement of the evaluation granularity, ensuring that weight combinations not only match the sport type but also the differences in metabolic needs among different tactical roles within the same sport type, thereby improving the level of precision.

[0175] Furthermore, the system obtains weight combinations based on sport type and tactical role. For example, the system maintains a two-dimensional mapping table: the first dimension is sport type, and the second dimension is tactical role; each cell can store a set of weight combinations. Once both are determined, the weights are retrieved directly from the table. Another example is to first obtain the basic weight combination based on the sport type, and then apply adjustment coefficients based on the tactical role (e.g., increasing the explosive power weight coefficient by 1.2 for "forward," while correspondingly reducing the weights of other dimensions) to obtain the final weight combination. This allows the evaluation results to distinguish the core ability requirements of different tactical roles within the same sport type; for example, a football midfielder needs higher basic endurance and metabolic efficiency, while a forward needs higher explosive power and maximum capacity, thus providing more precise training guidance.

[0176] Based on this, specific examples are given below to better understand this technical solution.

[0177] For the same sport, weight combinations need to be set according to the assigned tactical role and the required metabolic characteristics. For example, in explosive sports, the activity patterns of football players are highly position-specific. The following weight combinations are given based on tactical roles and their physiological characteristics, as shown in Table 8:

[0178] Table 8 Weight Combinations for Tactical Roles

[0179]

[0180] Based on this, the optional weight combination for a forward / winger in football is set to (Sq: [1.5, 1.3, 1.2, 0.5, 0.8, 1.5]). Their abilities emphasize rapid attacks, requiring extremely fast starting speed (S6: metabolic sensitivity) and the highest sprint speed over short distances (S1: explosive power) to complete breakthroughs and poaching, hence the relatively high weight of 1.5. They also need a certain anaerobic capacity to support multiple sprints in a single match; rapid offensive and defensive transitions require them to clear lactic acid quickly after the next sprint, therefore (S2: maximum capacity) and (S3: recovery ability) have relatively high weights of 1.3 and 1.2, respectively. During numerous anaerobic sprints, good metabolic efficiency helps delay fatigue, hence (S5: metabolic efficiency) is set to 0.8. They also need a certain aerobic base to support all-field activities, but this is not the primary determining factor, hence (S4: basic endurance) is set to 0.5.

[0181] Optionally, the weighting combination for the central midfielder / defensive midfielder in football can be set to (Sq: [1.0, 1.0, 1.5, 1.2, 1.0, 1.0]). Their abilities emphasize all-around performance. They have a large range of movement and need to alternate between numerous high-intensity and low-speed runs. They require high recovery ability after each high-intensity run, therefore (S3: Recovery Ability) needs a relatively high weight of 1.5. Excellent aerobic endurance is also fundamental to ensuring sustained high-efficiency output for 90 minutes, therefore (S4: Basic Endurance) needs a relatively high weight of 1.2. Other dimensions are also relatively important, but not as prominent, so they are all set to 1.

[0182] Alternatively, the weighted combination for a center-back in football can be set to (Sq: [1.2, 1.4, 1.0, 0.8, 0.5, 1.3]). Their abilities are focused on both offense and defense. In defense, they often need to engage in continuous, high-intensity confrontations and tracking back, requiring a strong anaerobic system capacity to cope with this sustained load. Therefore, (S2: Limit Capacity) is set to a high weight of 1.4. They also need quick reaction and starting ability to cope with the sudden changes of direction and acceleration of forwards. Therefore, (S6: Metabolic Sensitivity) and (S1: Explosiveness) are set to relatively high weights of 1.3 and 1.2, respectively. However, the requirements for these two metabolic dimensions are not as high as those for forwards or wingers. They need a certain amount of endurance, but usually less than that of midfielders. Therefore, (S4: Basic Endurance) is set to 0.8. Compared to attacking players, the requirements for their economy in repeated sprints on the offensive end are lower. Therefore, (S5: Metabolic Efficiency) is set to 0.5.

[0183] The aforementioned technical solution, based on sport type, further introduces the dimension of tactical role. That is, after determining the sport type, it is also necessary to determine the specific tactical role undertaken by the athlete, and obtain a weighted combination under these dual conditions. This solves the problem that the "one-size-fits-all" assessment model in related solutions cannot adapt to the different metabolic needs of different tactical roles in team sports. Through this two-tiered subdivision of sport type and tactical role, the assessment results accurately reflect the metabolic capacity matching degree of athletes in their specific functions. This provides a scientific basis for coaches to make position adjustments, design tactics, and conduct targeted role-strengthening training, significantly enhancing the application value of the assessment results in team sports scenarios.

[0184] To further verify the effectiveness of the proposed metabolic capacity assessment method, the characteristic parameters extracted from the lactate response curves of 14 athletes tested with wingate are shown in Table 9:

[0185] Table 9. Characteristic parameters extracted from lactic acid response curves

[0186]

[0187] Based on the extracted feature parameters, the scores for the six dimensions were calculated, and the weight combination was set as (Sq: [1.5,1.5, 1.5, 0.2, 1, 1.2]). The comprehensive score obtained based on this is shown in Table 10.

[0188] Table 10 Overall Score

[0189]

[0190] Furthermore, the actual ranking of the wingate test is obtained based on indicators such as peak power, relative peak power, average power, time to reach peak power, and peak blood lactate, calculated by the equipment and instruments.

[0191] As shown in Table 10, the overall score of the proposed method in the explosive power test (i.e., the wingate test) is consistent with the athlete's actual ranking, further verifying the effectiveness of the method.

[0192] Figure 5 This is a structural block diagram of a metabolic capacity assessment system provided in an embodiment of the present invention. This embodiment is applicable to assessing the metabolic capacity of athletes.

[0193] See Figure 5 The metabolic capacity assessment system described in this embodiment of the invention may include: a sensor 1, an athlete terminal 2, and a server 3; wherein, the sensor 1 is worn by the athlete; wherein,

[0194] Athlete terminal 2 is used to acquire time-series data collected by sensor 1 and send the time-series data to server 3. The time-series data is the time-series data of interstitial lactate value of the athlete during and before and after exercise.

[0195] Server 3 is used to extract feature parameters from the time-series data sent by athlete terminal 2, and determine the athlete's dimensional score in each dimension based on the feature parameters for multiple dimensions that characterize different metabolic capabilities, and generate an assessment result on the athlete's metabolic capabilities based on the multiple dimensional scores.

[0196] In this embodiment of the invention, sensor 1 can also be called a continuous lactate interstitial fluid sensor, athlete terminal 2 can also be called an athlete mobile terminal, and server 3 can also be called a cloud system. Optionally, additional components may be included. Figure 5 The instructor terminal 4 shown can also be called the instructor cockpit.

[0197] Based on this, for example, sensor 1 is communicatively connected to athlete terminal 2, athlete terminal 2 is communicatively connected to server 3, and server 3 is communicatively connected to coach terminal 4. Server 3 can be used to execute any of the aforementioned metabolic capacity assessment methods, the details of which have been described above and will not be repeated here.

[0198] Based on this, optionally, see [link / reference]. Figure 6 Server 3 may include data access component 3-1, core computing component 3-2, intelligent parsing and generation component 3-3, and application interaction component 3-4.

[0199] The data access component 3-1 can be used to receive time-series data, exercise tags (such as start / end tags), exercise type, subjective scores, exercise program descriptions (such as a 30-second Wingate test), and optional auxiliary data (such as power meter readings and heart rate readings) from the athlete terminal 2. The data access component 3-1 provides a standardized interface, supporting data exchange with different types of athlete terminals 2, dedicated lactate sensor readers, and third-party sports monitoring platforms; it supports multiple data transmission protocols such as Bluetooth, wireless, and cellular networks.

[0200] The core computing component 3-2 encapsulates a program for performing metabolic capacity assessment methods. It can perform metabolic capacity assessment based on the data transmitted by the data access component 3-1, and package information such as the six-dimensional scores, comprehensive scores, and the weight combinations used into a structured assessment result for downstream components to call.

[0201] The intelligent analysis and generation component 3-3 can be used to generate personalized reports containing natural language interpretation and targeted training suggestions based on six-dimensional scores, comprehensive scores, athlete profiles, and training goals.

[0202] Application interaction component 3-4 is used to transform targeted training suggestions into an executable training task sequence and push it to athlete terminal 2. Application interaction component 3-4 includes a gateway and management backend, and interfaces with athlete terminal 2. This gateway and management backend provide management functions such as system configuration, user management, access control, and data transmission.

[0203] The technical solution of this invention utilizes sensors to collect time-series data of interstitial lactate levels. This time-series data is uploaded to a server via an athlete's terminal. The server then extracts feature parameters from this data and comprehensively evaluates it based on multiple dimensions. This helps to form a multidimensional description of metabolic characteristics and achieves an accurate assessment of the athlete's metabolic capacity.

[0204] In an optional technical solution, the aforementioned server is also used for:

[0205] Obtain athletes' training goals and historical evaluation results, and generate context based on the evaluation results, historical evaluation results, and training goals;

[0206] For the type of sport the athlete is engaged in, the system retrieves prompt word templates that match the sport type and training objectives from the prompt word template library, and retrieves sports science knowledge that matches the sport type and training objectives from the sports science knowledge base;

[0207] The context and sports science knowledge are combined into the prompt word template to obtain the target prompt word, and the large language model is called based on the target prompt word to generate training suggestions.

[0208] The training objective can be understood as the desired direction or specific indicator of metabolic capacity improvement for the athlete (such as increasing lactate clearance rate or reducing resting lactate levels). Historical assessment results can be understood as the athlete's past assessments of metabolic capacity; multiple historical assessments reflect trends in metabolic capacity changes. Context can be understood as a structured set of information formed by integrating current assessment results, historical assessment results, and training objectives, used for subsequent prompt word construction. Using the above example, the assessment context builder in the intelligent parsing and generation component 3-3 is used to integrate the content and construct a rich text context containing "current state - historical comparison - training objective." This associates static assessment results with dynamic trends and training objectives, providing a sufficient information foundation for generating personalized training suggestions.

[0209] The prompt word template library stores prompt word templates for different sports types and training goals. The prompt word templates in this technical solution can be understood as those selected from these templates that match the current sports type and training goal. Similarly, the sports science knowledge base can be understood as a structured database or graph that stores principles of training physiology, a library of classic training methods (such as different types of interval training and endurance training programs), nutritional recovery recommendations, and guidelines for preventing common sports injuries. The sports science knowledge in this technical solution is selected from this library that matches the sports type and training goal, thereby ensuring that the training recommendations generated by the large language model conform to sports science consensus. Using the above example, the above steps can be implemented through the large model interface and prompt engineering manager in the intelligent parsing and generation component 3-3. Here, prompt word template matching and sports science knowledge retrieval ensure that the final generated training recommendations have both a standardized output format and scientific evidence support.

[0210] Contextual information and sports science knowledge are injected into the prompt word template to obtain the target prompt word. Based on the target prompt word, a large language model is invoked to generate training suggestions. The application of the target prompt word improves the professionalism and accuracy of the large language model's answers and provides a traceable scientific basis for the output training suggestions.

[0211] The above technical solution, by further incorporating training objectives, historical assessment results, a prompt word template library, a sports science knowledge base, and a large language model, achieves a closed loop from "assessment" to "recommendation." This solves the problem of the disconnect between assessment and training in related solutions, enabling coaches and athletes to not only know their metabolic capacity but also how to train next, significantly improving the efficiency of converting assessment results into actual training guidance.

[0212] Based on this, optionally, the aforementioned metabolic capacity assessment system may further include: a coaching terminal; wherein,

[0213] The server is also used to send evaluation results and training suggestions to the coach terminal;

[0214] The coach terminal is used to display the received evaluation results and training suggestions, and in response to the issued instructions, return the target training suggestions to the server. The target training suggestions are either training suggestions or training suggestions adjusted based on the evaluation results.

[0215] The server is also used to generate training tasks based on the received target training suggestions and send the training tasks to the athlete's terminal.

[0216] The athlete terminal is also used to display the received training tasks.

[0217] The "issuing instruction" can be understood as the submission action made by the coach after confirming or modifying training suggestions through the coach terminal interface. The target training suggestion can be understood as the final training suggestion issued to the athlete, which may be the original training suggestion or a version adjusted by the coach based on the evaluation results. For example, the coach terminal displays the evaluation results and the original training suggestion; the coach directly clicks "Confirm Issuance" to return the original training suggestion as the target training suggestion to the server. As another example, the coach edits and modifies the training suggestion on the coach terminal and clicks "Confirm Issuance" to return the modified training suggestion as the target training suggestion to the server. This retains the coach's professional judgment and intervention capabilities, allowing the final training to combine the advantages of artificial intelligence and human experience.

[0218] Furthermore, training tasks can be understood as structured training plan content, such as executable instructions including at least one of the following: training program, training duration, training intensity, training frequency, and precautions. For example, a workflow generator on the server can be used to parse the target training suggestions, identify key action items (such as performing four sets of 400-meter runs with two minutes of rest between sets or adding a 10-minute cool-down cycling session after training), and automatically convert them into structured training calendar events or to-do lists. This transforms training suggestions into executable and trackable training tasks, ensuring athletes can clearly understand and execute them.

[0219] Based on this, in order to better understand the athlete terminal and coach terminal described in the above technical solution, the following is an exemplary explanation with specific examples.

[0220] For example, an athlete's terminal mainly includes a personal data portal unit, an intelligent training assistant unit, and a training execution and feedback unit. The personal data portal unit receives interstitial lactate levels and uploads them to the server, then receives and visualizes the athlete's latest hexagonal assessment results, overall score, and historical comparisons from the server. The intelligent training assistant unit receives and displays daily / weekly training tasks approved by the coach or intelligently generated by the system, presented in a clear task card format. The training execution and feedback unit provides training timing and check-in functions, and allows for convenient recording of subjective scores after each training session. It also sends back sensor data and recorded feedback data for optimizing subsequent calculations, evaluations, and model iterations.

[0221] The coaching terminal includes both web and desktop versions, primarily comprising a visual dashboard, a comprehensive management view, an intelligent report review and editing interface, and a long-term trend analysis unit. The visual dashboard uses a hexagonal radar chart to visually display the metabolic capacity of individual athletes or groups, overlaid with a professional baseline. The comprehensive management view displays the overall scores and rankings of all athletes in a list, supporting filtering and sorting by dimension. The intelligent report review and editing interface displays personalized reports and training suggestions generated by a large language model, which coaches can review, modify, and annotate, and approve for one-click distribution to athlete terminals. The long-term trend analysis unit uses charts to display the changing trends of athletes' scores across various dimensions and overall scores over time.

[0222] The aforementioned technical solution introduces a coach terminal and constructs a three-way interactive closed loop between the server, coach terminal, and athlete terminal. The server sends the assessment results and training suggestions to the coach terminal. The coach can confirm or adjust the suggestions and generate target training recommendations, which are then returned to the server. Based on this, the server forms structured training tasks and distributes them to the athlete terminal for display. This achieves full-process digital management of assessment → suggestion → approval → task → execution, retaining the automatic analysis and suggestion capabilities of artificial intelligence while incorporating the coach's professional judgment and intervention authority. Ultimately, this ensures that athletes receive clear and actionable training task guidance, thereby significantly improving the completeness and efficiency from metabolic capacity assessment to actual training implementation.

[0223] To demonstrate the effectiveness of the aforementioned metabolic capacity assessment system, a detailed example is provided here, which assesses an athlete's metabolic capacity after a power exercise test (such as a 30-second wingate test) and intelligently generates personalized training tasks based on the assessment results.

[0224] See Figure 5 and Figure 6The athlete enters athlete terminal 2, inputs personal information, and wears sensor 1 for continuous monitoring of interstitial fluid lactate levels. After sensor 1 has warmed up and stabilized, the athlete performs a 30-second wingate sprint test (power bike equipped with a power meter). The power bike records information such as maximum relative power and average relative power. After the test, the athlete continues to rest, and sensor 1 continues to monitor the recovery of interstitial fluid lactate until the interstitial fluid lactate level drops to near resting level (i.e., resting lactate level). During this period, the athlete records their subjective score (9 points, difficult) for the test through athlete terminal 2. The time-series data of interstitial fluid lactate levels, exercise tags, external power (850W), and subjective scores throughout the entire test process are transmitted to data access component 3-1 in server 3 via athlete terminal 2.

[0225] Data access component 3-1 sends the received data to core computing component 3-2, at which point core computing component 3-2 can generate the final metabolic capacity assessment result based on this data. For example, Table 11 shows the feature parameters and their values ​​extracted by core computing component 3-2, and Table 12 and... Figure 7 The core computing component 3-2 is shown to generate a six-dimensional score based on this.

[0226] Table 11 Extracted feature names and feature values

[0227]

[0228] Table 12 Six-Dimensional Scoring

[0229]

[0230] Furthermore, taking the six-dimensional weight combination of explosive power movement [1.5, 1.5, 1.5, 0.2, 1, 1.2], the final comprehensive score is calculated as follows:

[0231] .

[0232] Then, the intelligent parsing and generation component 3-3 constructs the context, integrating the athlete's six-dimensional scores, comprehensive score, personal profile (professional basketball guard, recent training goal is to improve sprint endurance), and historical evaluation results. The above context is combined with the preset "basketball player - sprint endurance" prompt template, and based on this, the large language model is invoked, instructing the large language model to focus on analyzing explosive power, blood recovery ability, metabolic sensitivity, and metabolic efficiency. On this basis, the large language model, combined with the local sports science knowledge base, generates the following personalized report: "Your anaerobic explosive power (100), maximum capacity (100), and metabolic sensitivity (100) all meet the professional benchmark, which is highly consistent with the requirements of the guard position for quick start and single sprint ability. Your lactate clearance ability (100) is excellent, which helps to recover quickly between high-intensity rounds. The main weakness is metabolic efficiency (21.8), combined with your subjective score of 9 points, indicating that when you produce the same power, your physiological consumption (lactate accumulation) and mental fatigue are significantly higher, which may lead to a decrease in power in the second half of the game due to the accumulation of metabolic waste."

[0233] Furthermore, targeted training recommendations are generated: "You need to improve metabolic efficiency and delay fatigue. Option a: Strengthen your aerobic base: Add two 30-minute sessions of low-intensity steady-state aerobic training per week (maintaining heart rate at 60-70% of maximum heart rate). Purpose: To improve mitochondrial density and function, enhance lactate clearance and aerobic metabolism, and provide more efficient support for anaerobic work. Option b: Techno-economical training: Incorporate 'rhythm control' exercises for explosive movements into strength training (such as rapid eccentric and concentric control in box squats). Purpose: To improve neuromuscular coordination, producing the same power with more economical energy expenditure."

[0234] Then, the coach logs into Coach Terminal 4 and sees the radar chart of the athlete's various scores and the overall score of 88.09 in the comprehensive management view unit. The coach views the radar chart and notices a significant dip in the "metabolic efficiency dimension." The coach reviews the personalized report and personalized training suggestions generated by the large language model in the intelligent report review and editing interface. He considers the training suggestions reasonable, but slightly adjusts the frequency of "aerobic base strengthening" from twice to once to accommodate the intensive tactical training schedule this week, adding the annotation: "Pay attention to monitoring morning pulse to prevent over-fatigue." The coach clicks "Confirm and Send," and the personalized training suggestion (i.e., the target training suggestion) is sent back to Server 3. The workflow generator on Server 3 parses it into specific training calendar events for the next two weeks and sends them to Athlete Terminal 2, such as: "Tuesday afternoon: 30 minutes of low-intensity aerobic cycling."

[0235] At this point, the athlete receives the training task approved by the coach in the intelligent training assistant unit of athlete terminal 2, and then records the subjective score of this training session as 8 points during the next explosive power exercise test. All execution data and lactate data generated in the new training session will be automatically transmitted to server 3 to update the athlete's performance ranking and personal profile, and to provide historical comparison data for the next evaluation.

[0236] The above example demonstrates how intelligent metabolic dimension analysis and training suggestions can be provided. Coaches can then make professional fine-tunings based on the training suggestions given by artificial intelligence and supervise their implementation. Athletes can then execute the suggestions and provide feedback, significantly improving the scientific nature and personalization of training.

[0237] Figure 8 This is a structural block diagram of a metabolic capacity assessment device provided in an embodiment of the present invention. This device is used to execute the metabolic capacity assessment method provided in any of the above embodiments. This device and the metabolic capacity assessment methods of the above embodiments belong to the same inventive concept. Details not described in detail in the embodiments of the metabolic capacity assessment device can be found in the embodiments of the above metabolic capacity assessment methods. See also... Figure 8 The device may specifically include: a time-series data acquisition module 410, a feature parameter extraction module 420, a dimension scoring determination module 430, and an evaluation result generation module 440.

[0238] The time-series data acquisition module 410 can be used to acquire time-series data of interstitial lactate values ​​of athletes during and before exercise.

[0239] The feature parameter extraction module 420 can be used to extract feature parameters from time series data;

[0240] The dimension scoring determination module 430 can be used to determine the athlete's dimension score for each of the multiple dimensions that characterize different metabolic capabilities, based on the feature parameters.

[0241] The assessment results generation module 440 can be used to generate assessment results about an athlete's metabolic capacity based on scores across multiple dimensions.

[0242] Optionally, the dimension scoring determination module 430 may include at least one of the following units:

[0243] The first determining unit is used to determine the athlete's dimension score under the explosive power dimension in response to the dimension being explosive power dimension and the feature parameter being lactate rise slope, based on the lactate rise slope.

[0244] The second determining unit is used to obtain the first net increment corresponding to the lactate peak in response to the dimension being the limit capacity dimension and the feature parameter being the lactate peak, and to determine the athlete's dimension score in the limit capacity dimension based on the first net increment.

[0245] The third determining unit is used to determine the athlete's dimension score under the blood return ability dimension in response to the dimension being the blood return ability dimension and the feature parameters being lactate clearance rate and lactate clearance half-width.

[0246] The fourth determining unit is used to respond to the condition that the dimension is the basic endurance dimension and the feature parameter is the steady-state lactate value, to obtain the second net increment corresponding to the steady-state lactate value, and to determine the athlete's dimension score under the basic endurance dimension based on the second net increment.

[0247] The fifth determining unit is used to respond to a situation where the dimension is metabolic efficiency and the feature parameter is the area under the lactate curve. It obtains the metabolic efficiency based on the area under the lactate curve and determines the athlete's dimension score under the metabolic efficiency dimension based on the metabolic efficiency and subjective score.

[0248] The sixth determining unit is used to respond to a situation where the dimension is the metabolic sensitivity dimension and the feature parameter is the early metabolic sensitivity or the first time interval, to obtain the metabolic sensitivity based on the early metabolic sensitivity or the first time interval, and to determine the athlete's dimension score under the metabolic sensitivity dimension based on the metabolic sensitivity.

[0249] Based on this, an optional fourth determining unit may include:

[0250] The second net increment sub-unit can be used to obtain the first difference between the steady-state lactate value and the resting lactate value, and to perform weighted processing on the first difference based on the first net increment to obtain the second net increment corresponding to the steady-state lactate value; and / or,

[0251] The fifth determining unit may include:

[0252] The metabolic efficiency sub-unit is used to obtain metabolic efficiency based on the power output of the sports equipment used by the athlete and the area under the lactate curve, or based on the first net increment and the area under the lactate curve.

[0253] Alternatively, the feature parameter extraction module 420 may include at least one of the following units:

[0254] The early metabolic sensitivity unit is used to respond to the characteristic parameter of early metabolic sensitivity. For the lactate response curve plotted based on time-series data, the lactate half-peak width, lactate half-peak value and resting lactate value are extracted from the lactate response curve, and the early metabolic sensitivity is obtained based on the extraction results.

[0255] The lactate clearance rate unit is used to extract the slope of the descending segment of the lactate response curve from the lactate response curve in response to the characteristic parameter being the lactate clearance rate, and the slope is used as the lactate clearance rate.

[0256] The lactate clearance half-width is obtained as a unit. In response to the characteristic parameter, the lactate clearance half-width is obtained. For the lactate decrease half-peak and lactate peak in the lactate response curve, the second time interval between the time point corresponding to the lactate decrease half-peak in the lactate response curve and the time point corresponding to the lactate peak in the lactate response curve is obtained, and the second time interval is used as the lactate clearance half-width.

[0257] The area under the lactate curve is used to obtain the unit. The characteristic parameter is the area under the lactate curve. For the interstitial lactate value in the target time period in the lactate response curve, the second difference between each interstitial lactate value and the response lactate value is determined, and the sum of each second difference is used as the area under the lactate curve.

[0258] Optionally, the evaluation result generation module 440 may include:

[0259] The weight combination acquisition submodule is used to determine the type of sport the athlete is performing and to acquire the weight combination set for the sport type. The weight combination includes the weights corresponding to multiple dimensions.

[0260] The evaluation results generation submodule is used to weight the scores of multiple dimensions according to the weight combination to generate an evaluation result on the athlete's metabolic capacity.

[0261] Based on this, the optional weight combination acquisition submodule may include:

[0262] The tactical role determination unit is used to determine the tactical role that an athlete assumes during the sport.

[0263] The weight combination acquisition unit is used to acquire weight combinations set for sports type and tactical role.

[0264] The metabolic capacity assessment device provided in this invention acquires time-series data of interstitial lactate levels in athletes during and before exercise through a time-series data acquisition module. A feature parameter extraction module and a dimension scoring module work together to extract feature parameters from the time-series data. For each of the multiple dimensions representing different metabolic capacities, a dimension score for the athlete is determined based on the feature parameters. Then, an assessment result generation module generates an assessment result of the athlete's metabolic capacity based on the multiple dimension scores. Compared to devices that use single or simple composite indicators for metabolic capacity assessment, this device, by acquiring time-series data of interstitial lactate levels and extracting feature parameters, and then comprehensively assessing the data by scoring multiple dimensions, helps to form a multidimensional description of metabolic characteristics, achieving accurate assessment of the athlete's metabolic capacity. Moreover, it relies only on readily available interstitial lactate levels, resulting in lower costs and making it suitable for use in routine training, outdoor sports, and mass fitness activities. Furthermore, its standardized scoring system facilitates comparisons with different athletes or sports, allowing coaches and athletes to intuitively and quickly understand the assessment results and develop targeted training programs for weaknesses.

[0265] The metabolic capacity assessment device provided in the embodiments of the present invention can execute the metabolic capacity assessment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0266] It is worth noting that in the embodiments of the above-mentioned metabolic capacity assessment device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0267] Figure 9 A schematic diagram of a server 3, which can be used to implement embodiments of the present invention, is shown. The server is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The server can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0268] like Figure 9As shown, server 3 includes at least one processor 11 and memory, such as read-only memory (ROM) 12 and random access memory (RAM) 13, communicatively connected to at least one processor 11. The memory stores computer programs executable by at least one processor. Processor 11 can perform various appropriate actions and processes based on the computer program stored in ROM 12 or loaded into RAM 13 from storage unit 18. RAM 13 can also store various programs and data required for the operation of server 3. Processor 11, ROM 12, and RAM 13 are interconnected via bus 14. Input / output (I / O) interface 15 is also connected to bus 14.

[0269] Multiple components in server 3 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows server 3 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0270] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as metabolic capacity assessment methods.

[0271] In some embodiments, the metabolic capacity assessment method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on server 3 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the metabolic capacity assessment method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the metabolic capacity assessment method by any other suitable means (e.g., by means of firmware).

[0272] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips or system-on-a-chips (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0273] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0274] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0275] To provide interaction with the user, the systems and techniques described herein can be implemented on a server having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the server. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including voice input, speech input, or tactile input).

[0276] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0277] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0278] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0279] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0280] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for assessing metabolic capacity, characterized in that, include: Obtain time-series data on interstitial lactate levels in athletes during and before exercise; Feature parameters are extracted from the time-series data; For each of the multiple dimensions characterizing different metabolic capabilities, the athlete's dimension score in that dimension is determined based on the feature parameters. The scores of the multiple dimensions are weighted to generate an assessment of the athlete's metabolic capacity; Determining the athlete's dimensional score in the given dimension based on the feature parameters includes: In response to the fact that the dimension is the explosive power dimension and the feature parameter is the lactate rise slope, the athlete's dimension score in the explosive power dimension is determined based on the lactate rise slope. In response to the fact that the dimension is a limit capacity dimension and the feature parameter is the lactate peak, a first net increment corresponding to the lactate peak is obtained, and the athlete's dimension score under the limit capacity dimension is determined based on the first net increment. In response to the fact that the dimension is the blood return capacity dimension and the feature parameters are lactate clearance rate and lactate clearance half-width, the athlete's dimension score in the blood return capacity dimension is determined based on the lactate clearance rate and lactate clearance half-width. In response to the fact that the dimension is the basic endurance dimension and the feature parameter is the steady-state lactate value, a second net increment corresponding to the steady-state lactate value is obtained, and the athlete's dimension score under the basic endurance dimension is determined based on the second net increment. In response to the fact that the dimension is the metabolic efficiency dimension and the feature parameter is the area under the lactate curve, the metabolic efficiency is obtained based on the area under the lactate curve, and the athlete's dimension score under the metabolic efficiency dimension is determined based on the metabolic efficiency and the subjective score. In response to the fact that the dimension is a metabolic sensitivity dimension and the feature parameter is an early metabolic sensitivity or a first time interval, the metabolic sensitivity is obtained based on the early metabolic sensitivity or the first time interval, and the athlete's dimension score under the metabolic sensitivity dimension is determined based on the metabolic sensitivity. Extracting feature parameters from the time-series data includes at least one of the following steps: In response to the characteristic parameter being the early metabolic sensitivity, for the lactate response curve plotted based on the time-series data, the lactate half-width, lactate half-peak value, and resting lactate value are extracted from the lactate response curve, and the early metabolic sensitivity is obtained based on the extraction results. In response to the characteristic parameter being the lactate clearance rate, the slope of the descending segment of the lactate response curve is extracted from the lactate response curve, and the slope is used as the lactate clearance rate; In response to the characteristic parameter being the lactate clearance half-width, for the lactate decrease half-peak and lactate peak in the lactate response curve, a second time interval is obtained between the time point corresponding to the lactate decrease half-peak in the lactate response curve and the time point corresponding to the lactate peak in the lactate response curve, and the second time interval is used as the lactate clearance half-width. In response to the characteristic parameter being the area under the lactate curve, for the interstitial lactate value within the target time period in the lactate response curve, a second difference between each interstitial lactate value and the response lactate value is determined, and the sum of each second difference is taken as the area under the lactate curve.

2. The metabolic capacity assessment method according to claim 1, characterized in that, The process of obtaining the second net increment corresponding to the steady-state lactate value includes: The first difference between the steady-state lactate value and the resting lactate value is obtained, and the first difference is weighted based on the first net increment to obtain the second net increment corresponding to the steady-state lactate value. And / or, the step of obtaining metabolic efficiency based on the area under the lactate curve includes: The metabolic efficiency can be obtained based on the power output of the sports equipment used by the athlete and the area under the lactate curve, or based on the first net increment and the area under the lactate curve.

3. The metabolic capacity assessment method according to claim 1, characterized in that, The weighted processing of the scores across multiple dimensions to generate an assessment of the athlete's metabolic capacity includes: The type of sport performed by the athlete is determined, and a weight combination set for the type of sport is obtained, wherein the weight combination includes weights corresponding to multiple dimensions respectively; The scores of the multiple dimensions are weighted according to the weight combination to generate an assessment of the athlete's metabolic capacity.

4. The metabolic capacity assessment method according to claim 3, characterized in that, The step of obtaining the weight combination set for the sports type includes: Determine the tactical role played by the athlete during the sport; Obtain the weight combination set for the sports type and the tactical role.

5. A metabolic capacity assessment system, characterized in that, include: Sensors, athlete terminals, and servers; wherein the sensors are worn by the athlete; wherein, The athlete terminal is used to acquire time-series data collected by the sensor and send the time-series data to the server, wherein the time-series data is the time-series data of the athlete's interstitial lactate value during and before and after exercise. The server is used to implement the metabolic capacity assessment method as described in any one of claims 1-4.

6. The metabolic capacity assessment system according to claim 5, characterized in that, The server is also used for: Obtain the athlete's training goals and historical evaluation results, and generate a context based on the evaluation results, the historical evaluation results, and the training goals; For the type of sport performed by the athlete, a prompt word template matching the type of sport and the training objective is obtained from the prompt word template library, and sports science knowledge matching the type of sport and the training objective is obtained from the sports science knowledge base; The context and the sports science knowledge are combined into the prompt word template to obtain the target prompt word, and the large language model is invoked based on the target prompt word to generate training suggestions.

7. The metabolic capacity assessment system according to claim 6, characterized in that, Also includes: Coach terminal; among which, The server is also used to send the evaluation results and the training suggestions to the coach terminal; The coach terminal is used to display the received evaluation results and training suggestions, and in response to issuing instructions, return the target training suggestions to the server, wherein the target training suggestions are the training suggestions or are obtained by adjusting the training suggestions based on the evaluation results; The server is also configured to generate a training task based on the received target training suggestion, and send the training task to the athlete terminal; The athlete terminal is also used to display the received training tasks.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the metabolic capacity assessment method as described in any one of claims 1-4.

Images