Dynamic nutrition adjustment method and system based on metabolic adaptability

Abstract

The invention relates to a dynamic nutrition adjustment method and system based on metabolic adaptability, and the method comprises the steps: collecting historical metabolic rate data and real-time biosensor data, carrying out the preprocessing, and recognizing and outputting a structured metabolic data set containing a platform period marker; calculating a metabolic attenuation slope, a nutrient responsivity and an energy gap elastic coefficient, and generating a metabolic adaptability coefficient through weighted fusion; dynamically adjusting the macroscopic nutrient proportion and the total calorie value, and outputting a nutrition adjustment instruction; carrying out strengthening processing on the nutrition adjustment instruction; according to the nutrition enhancing instruction and a pre-configured user diet preference database, optimizing and calculating a specific food material combination, verifying a blood glucose fluctuation level, and outputting an executable meal replacement formula; and calculating the metabolic response rate and dynamically correcting the calculation weight of the metabolic adaptability coefficient based on the executed metabolic rate feedback data. According to the invention, the accuracy, timeliness and individual fitness of nutrition intervention are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent health management technology, and in particular to a method and system for dynamic nutritional adjustment based on metabolic adaptation. Background Technology

[0002] With the continuous improvement of people's living standards and the increasing incidence of chronic diseases, personalized nutrition management has become an important development direction in the field of health management. In recent years, with the popularization of wearable devices and mobile health monitoring systems, more and more data on human physiological status have been continuously collected and utilized, especially biosensor information such as basal metabolic rate, heart rate variability, skin temperature, and respiratory rate, which provide rich data support for achieving refined nutrition regulation.

[0003] Currently, traditional nutritional interventions largely rely on static models or empirical formulas for calorie allocation and macronutrient ratio distribution. For example, the Harris-Benedict equation is used to calculate the total daily energy expenditure and to develop a diet plan accordingly. However, these methods ignore the significant metabolic differences between individuals and the metabolic adaptive adjustments that occur over time, especially the "plateau" problem commonly encountered in long-term weight loss. A plateau refers to a period of time where weight loss ceases despite maintaining the original diet and exercise habits. This is usually considered a manifestation of the body's adaptive response to external interventions and is one of the main reasons for most weight loss failures.

[0004] In existing nutrition management systems, most solutions only focus on macro-level energy balance control, failing to delve into the specific impact pathways of each nutrient on different functional modules of the body. In particular, they lack the ability to accurately perceive the user's real-time physiological state, making it difficult to precisely locate the root cause of the problem and implement targeted intervention measures. Summary of the Invention

[0005] To address the aforementioned technical problems, this application provides a method and system for dynamic nutritional adjustment based on metabolic adaptation.

[0006] In a first aspect, this application provides a dynamic nutritional adjustment method based on metabolic adaptation, employing the following technical solution:

[0007] A dynamic nutrition adjustment method based on metabolic adaptation, the dynamic nutrition adjustment method comprising:

[0008] Collect users' historical metabolic rate data and real-time biosensor data and preprocess them, identify continuous data segments with metabolic rate changes below a preset change rate threshold as plateau phase markers, and output a structured metabolic dataset containing plateau phase markers.

[0009] Based on the structured metabolic dataset, the metabolic decay slope, nutrient responsiveness, and energy deficit elasticity coefficient are calculated, and a metabolic fitness coefficient is generated by weighted fusion.

[0010] Based on the numerical range of the metabolic adaptability coefficient, a predefined nutritional strategy is matched, the proportion of macronutrients and total calorie value are dynamically adjusted, and a nutritional adjustment instruction is output.

[0011] The nutrition adjustment instruction is enhanced based on the plateau phase marker, and an enhanced nutrition instruction is output.

[0012] Based on the enhanced nutrition instructions and the pre-configured user dietary preference database, the specific food combination is optimized and the blood sugar fluctuation level is verified, and an executable meal replacement formula is output.

[0013] Based on the metabolic rate feedback data after the execution of the fortified nutrition instructions and the executable meal replacement formula, the metabolic response rate is calculated and the calculation weight of the metabolic adaptability coefficient is dynamically adjusted.

[0014] By adopting the above technical solution, a closed-loop system has been achieved that intelligently identifies metabolic plateaus and quantifies metabolic status based on individual historical and real-time physiological data, and dynamically adjusts nutritional intake strategies accordingly. This technical solution adaptively optimizes the proportion of macronutrients and total calorie intake based on the user's current metabolic activity level. Combined with plateau-stage intensive intervention strategies (such as increasing nutrient density and periodically adjusting carbohydrate ratios), it generates personalized and actionable meal replacement formulas. Simultaneously, a feedback mechanism continuously corrects the weights of the metabolic assessment model, significantly improving the accuracy, timeliness, and individual suitability of nutritional interventions. This effectively addresses the weight loss bottleneck caused by metabolic adaptation and promotes the development of health management towards intelligence and dynamism.

[0015] Secondly, this application provides a dynamic nutritional adjustment system based on metabolic adaptation, employing the following technical solution:

[0016] A dynamic nutrition adjustment system based on metabolic adaptation, the dynamic nutrition adjustment system comprising:

[0017] The data acquisition and processing module is used to collect users' historical metabolic rate data and real-time biosensor data and preprocess them, identify continuous data segments with metabolic rate changes below a preset change rate threshold as plateau phase markers, and output a structured metabolic dataset containing plateau phase markers.

[0018] The metabolic adaptation analysis module is used to calculate the metabolic decay slope, nutrient responsiveness and energy deficit elasticity coefficient based on the structured metabolic dataset, and generate the metabolic adaptation coefficient through weighted fusion.

[0019] The nutrition strategy matching module is used to match a predefined nutrition strategy according to the numerical range of the metabolic adaptability coefficient, dynamically adjust the proportion of macronutrients and total calories, and output nutrition adjustment instructions.

[0020] The nutrition instruction enhancement module is used to enhance the nutrition adjustment instruction according to the plateau period marker and output the enhanced nutrition instruction;

[0021] The meal replacement formula optimization module is used to optimize and calculate specific ingredient combinations and verify blood sugar fluctuation levels based on the fortified nutrition instructions and a pre-configured user dietary preference database, and output an executable meal replacement formula.

[0022] The metabolic response feedback module is used to calculate the metabolic response rate and dynamically correct the calculation weight of the metabolic adaptability coefficient based on the metabolic rate feedback data after the execution of the fortified nutrition instruction and the executable meal replacement formula.

[0023] Thirdly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0024] A computer-readable storage medium storing a computer program that can be loaded by a processor and executed as in any of the methods in the first aspect.

[0025] In summary, this application includes at least one of the following beneficial technical effects: By monitoring the user's metabolic state in real time and identifying plateau characteristics, the metabolic adaptability coefficient can be accurately calculated, enabling intelligent matching and dynamic optimization of personalized nutrition strategies. The system employs a closed-loop feedback mechanism, continuously correcting the calculation model weights through metabolic response rate, thus improving the accuracy and timeliness of nutritional intervention. This effectively solves the technical problems of traditional nutrition programs lacking dynamic adaptability, such as difficulty in breaking through weight loss plateaus and poor individual response, achieving a technological leap from passive nutritional supplementation to active metabolic regulation. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the first process of a dynamic nutritional adjustment method based on metabolic adaptation, according to one embodiment of this application.

[0027] Figure 2 This is a schematic diagram of the second process of a dynamic nutritional adjustment method based on metabolic adaptation, according to one embodiment of this application.

[0028] Figure 3 This is a schematic diagram of the third process of a dynamic nutritional adjustment method based on metabolic adaptation, according to one embodiment of this application.

[0029] Figure 4 This is a schematic diagram of the fourth process of a dynamic nutritional adjustment method based on metabolic adaptation, according to one embodiment of this application.

[0030] Figure 5 This is a schematic diagram of the fifth process of a dynamic nutritional adjustment method based on metabolic adaptation, according to one embodiment of this application.

[0031] Figure 6 This is a schematic diagram of the sixth process of a dynamic nutritional adjustment method based on metabolic adaptation, according to one embodiment of this application.

[0032] Figure 7 This is a schematic diagram of the seventh process of a dynamic nutritional adjustment method based on metabolic adaptation, according to one embodiment of this application.

[0033] Figure 8 This is a schematic diagram of the eighth process of a dynamic nutrition adjustment method based on metabolic adaptation, according to one embodiment of this application. Detailed Implementation

[0034] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1-8 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0035] Currently, most existing nutrition management systems only address macro-level energy balance control, failing to delve into the specific pathways through which various nutrients affect different functional modules of the body. Examples include the correlation between carbohydrate intake and blood glucose fluctuations, the mechanism by which protein intake affects muscle protein synthesis rates, and the linkage between energy deficit size and weight loss efficiency. Without effective modeling and quantitative assessment of these key physiological responses, truly personalized nutrition recommendations are difficult to achieve. Furthermore, significant differences in genetic background, lifestyle, and gut microbiota composition among individuals mean that even the same external stimuli can lead to drastically different internal metabolic response patterns, further complicating the applicability of universal nutrition protocols.

[0036] Therefore, overcoming the problems of fixed templates, neglect of individual metabolic specificity, and inability to dynamically track feedback in traditional nutritional intervention methods has become a pressing technical challenge. Especially when facing the complex and ever-changing human metabolic system, there is an urgent need for an intelligent solution that can integrate diverse and heterogeneous physiological signals, possess adaptive learning capabilities, and flexibly adjust nutritional strategies based on the user's real-time metabolic status to improve the effectiveness and sustainability of nutritional interventions.

[0037] Based on this, this application discloses a method for dynamic nutritional adjustment based on metabolic adaptation.

[0038] Reference Figure 1A dynamic nutritional adjustment method based on metabolic adaptation, specifically including:

[0039] Step S101: Collect the user's historical metabolic rate data and real-time biosensor data and preprocess them, identify continuous data segments with metabolic rate change rates lower than a preset change rate threshold as plateau phase markers, and output a structured metabolic dataset containing plateau phase markers.

[0040] Specifically, historical metabolic rate data typically originates from past medical examination records or basal metabolic rate (BMR) metrics accumulated from previous use of smart wearable devices; while real-time biosensor data includes, but is not limited to, a set of variables reflecting the body's immediate state, such as heart rate variability, skin temperature, respiratory rate, exercise intensity, and sleep quality. This diverse and heterogeneous data undergoes standardized format conversion before entering the preprocessing stage. A key task is the identification and removal of outliers, such as sudden increases in heart rate readings due to improper wearing position or instantaneous fluctuations in blood glucose levels caused by sensor malfunctions. Furthermore, missing value imputation, noise smoothing, and time series alignment are performed to ensure the consistency and stability of subsequent calculations.

[0041] Subsequently, by statistically evaluating the trend of metabolic rate changes over a continuous period, time segments exhibiting a stable or even declining trend within a certain period are identified, known as "plateau periods." This criterion is generally set as a metabolic rate change of less than a certain threshold (e.g., 1%) for three consecutive days or more. Furthermore, the absolute value of the metabolic rate change per unit time is extracted as one of the key characterizing parameters of the plateau period, called the "metabolic decay slope," to quantify whether an individual is currently in a state of metabolic stagnation. After the above processing, the output is a structured metabolic dataset, which not only contains cleaned raw measurements but also includes label fields identifying different metabolic states, particularly clearly indicating the presence of plateau periods. This provides solid data support for the next step of establishing a metabolic adaptability evaluation system.

[0042] Step S102: Based on the structured metabolic dataset, calculate the metabolic decay slope, nutrient responsiveness, and energy deficit elasticity coefficient, and generate the metabolic fitness coefficient through weighted fusion.

[0043] The metabolic adaptability coefficient is a numerical indicator that comprehensively reflects the human body's ability to respond to external nutritional stimuli. Its role is to bridge the gap between objective physiological data and subjective nutritional regulation decisions. To construct such a representative composite factor, multiple sub-items need to be introduced for synergistic evaluation.

[0044] First, the slope of metabolic decline reflects the rate of natural metabolic deterioration in the absence of significant external disturbances, and can be considered an important indicator of metabolic activity. Second, it provides a quantitative characterization of the effects of the three macronutrients on specific functional modules of the human body, corresponding to: "carbohydrate sensitivity," which reflects the correlation between carbohydrate intake and its resulting blood glucose fluctuations; "protein responsiveness," derived from the linear regression relationship between protein intake and muscle protein synthesis rate; and "energy Deficit Elasticity Coefficient," which reflects the linkage between the size of the energy deficit and the rate of weight loss. These three parameters each carry different biological meanings and together constitute the underlying framework for comprehensively describing an individual's metabolic regulatory potential.

[0045] However, since these data come from different types of data sources and have inconsistent units, they must be unified to the same scale space using mathematical transformations before integration. For this purpose, a weighted fusion method was adopted, where the normalized components are superimposed according to pre-defined importance weights to obtain a comprehensive score value ranging from 0.6 to 1.4. This value is the so-called "metabolic fitness coefficient".

[0046] Understandably, this range was chosen instead of a simple [0,1] because some extreme conditions might lead to responses exceeding normal levels. Appropriately relaxing the upper limit helps to more accurately capture abnormal metabolic activity. This design fully embodies the principle of being data-driven and based on scientific theory, ensuring that the final metabolic fitness coefficient truly reflects the user's current metabolic status and its potential for change.

[0047] Step S103: Match a predefined nutritional strategy according to the numerical range of the metabolic adaptability coefficient, dynamically adjust the macronutrient ratio and total calorie value, and output a nutritional adjustment instruction.

[0048] One approach is to use a classification mapping method, dividing the continuously changing metabolic fitness coefficient into several discrete intervals, each corresponding to a specific set of nutritional intervention rules. For example, when the coefficient falls below a certain critical point (e.g., 0.8), it means that the individual may have a high tendency for insulin resistance or a low basal metabolic rate. In this case, a "metabolic compensation mode" should be activated. A typical approach is to moderately reduce the proportion of carbohydrates in the diet and correspondingly increase the proportion of healthy fats to promote ketone body production and thus stimulate the body's fat-burning mechanism.

[0049] Conversely, if the coefficient is high (e.g., greater than 1.2), it indicates that the person is in a more vigorous metabolic state. In this case, switching to "metabolic activation mode" can be considered, focusing on increasing the supply of high-quality protein and slightly increasing the daily total calorie intake to help maintain the material reserves needed for high-intensity training. Furthermore, the system will automatically derive corresponding safe calorie deficit settings based on different modes to precisely control the weight loss process and prevent malnutrition or other side effects. This strategy matching mechanism takes into account both individual differences and the concept of phased adjustments, making nutritional intervention more targeted and effective.

[0050] Step S104: Strengthen the nutrition adjustment instruction according to the plateau period marker and output the enhanced nutrition instruction;

[0051] Among these, the enhanced treatments include increasing nutrient density, triggering periodic carbohydrate ratio adjustment strategies, and increasing the proportion of branched-chain amino acids.

[0052] Specifically, a "plateau" refers to a period of time during which weight loss ceases despite maintaining the original dietary habits. This often indicates that the body has gradually adapted to the current energy supply method, and the original metabolic driving mechanism has begun to fail.

[0053] To avoid a prolonged stagnation, external disturbances are needed to disrupt the existing equilibrium and reawaken the dormant metabolic engine. Two main strategies are proposed: First, increase the overall nutritional density of food, packing as many essential nutrients as possible into a given volume of food, thus meeting higher-level functional needs without significantly increasing total calories. Second, employ a periodic carbohydrate ratio adjustment strategy, adjusting carbohydrate intake every few days to induce adaptive remodeling at the cellular level through frequent switching of energy substrate types. Third, increase the proportion of branched-chain amino acids to alleviate post-training fatigue and accelerate recovery.

[0054] It's important to note that when a plateau marker is absent, the nutritional adjustment instruction is directly output as a fortified nutritional instruction. This means that fortification is only triggered when the plateau marker is activated. If no plateau marker is detected, it indicates the user is in a period of active metabolic response. In this case, the system will directly output the original nutritional adjustment instruction as a fortified nutritional instruction, without performing disruptive interventions such as increasing nutrient density or periodically adjusting carbohydrate ratios. This is understandable because, in non-plateau phases, the body remains sensitive to basic nutritional strategies, and the desired effects can be maintained without additional fortification, thus avoiding the risk of metabolic disorders caused by excessive intervention.

[0055] Step S105: Based on the enhanced nutrition instructions and the pre-configured user dietary preference database, optimize the specific ingredient combination and verify the blood sugar fluctuation level, and output an executable meal replacement formula.

[0056] In this stage, it is necessary not only to deduce the appropriate weight share of each component based on the previously determined macronutrient allocation ratio, but also to fully consider multiple factors such as personal taste preferences, allergies and contraindications, and the impact on blood sugar fluctuations.

[0057] Specifically, a priority list of candidate foods that meet the target macronutrient ratio requirements is selected first. Then, a second layer of screening is conducted based on personalized dietary preference constraints provided by the user profile database. For example, if a user has lactose intolerance, all options containing dairy products will be excluded; or, to avoid drastic blood sugar fluctuations, low-GI ingredients should be prioritized, and if necessary, some refined carbohydrate sources can be replaced to achieve a stable release of glucose. After these multiple layers of filtering, the remaining options are the ideal dietary combinations best suited to the user's current situation.

[0058] It should be noted that throughout the process, it is necessary to continuously review and check whether the selected ingredient combination will bring unacceptable blood sugar fluctuation risks. Once an excess is found, adjustments must be made in a timely manner until the target is met. Only in this way can the newly formulated diet plan be truly guaranteed to achieve the predetermined fat loss and muscle gain goals while also taking into account the safety and comfort of the eating experience.

[0059] Step S106: Based on the metabolic rate feedback data after the execution of the fortified nutrition instruction and the executable meal replacement formula, calculate the metabolic response rate and dynamically adjust the calculation weight of the metabolic adaptability coefficient.

[0060] The metabolic adaptability coefficient is dynamically adjusted based on the information fed back from the actual execution results, enabling the system to gradually optimize its performance during operation.

[0061] Specifically, the metabolic response rate measures the ratio of the actual change in the body's metabolic level after each adjustment in nutritional structure to the change in the expected calorie difference. In other words, it observes whether a corresponding increase or decrease in the metabolic rate is observed after a certain percentage reduction in calorie intake. If the two are highly positively correlated, it indicates that the previous estimation model is relatively reliable; conversely, it indicates that some assumptions have deviated, and the relevant parameter settings need to be recalibrated.

[0062] Especially when extremely low or high response rates are repeatedly observed over several consecutive days, there is more reason to believe that certain specific factors are dominating the overall trend. In such cases, greater attention should be paid to the corresponding variables. For example, if multiple records show a strong correlation between carbohydrate intake and blood glucose peaks, the weight of carbohydrate sensitivity in the metabolic adaptability coefficient should be appropriately increased to give it a greater influence in similar future scenarios. Conversely, if it is found that protein supplementation significantly affects muscle growth rate, a higher value can be assigned to protein responsiveness in the next update of the weight matrix. Through repeated iterative evolution, the entire system will increasingly approximate real physiological laws, thereby continuously improving its predictive accuracy and service efficiency.

[0063] The above implementation achieves a closed-loop system that intelligently identifies metabolic plateaus and quantifies metabolic status based on individual historical and real-time physiological data, and dynamically adjusts nutritional intake strategies accordingly. This technical solution adaptively optimizes the proportion of macronutrients and total calorie intake based on the user's current metabolic activity level. Combined with plateau-stage intensive intervention strategies (such as increasing nutrient density and periodically adjusting carbohydrate ratios), it generates personalized and actionable meal replacement formulas. Simultaneously, through a feedback mechanism, it continuously corrects the weights of the metabolic assessment model, significantly improving the accuracy, timeliness, and individual suitability of nutritional interventions. This effectively addresses the weight loss bottleneck caused by metabolic adaptation and promotes the development of health management towards intelligence and dynamism.

[0064] Reference Figure 2 As one implementation of step S102, the step of calculating the metabolic decay slope, nutrient responsiveness, and energy deficit elasticity coefficient based on a structured metabolic dataset, and generating a metabolic fitness coefficient through weighted fusion includes:

[0065] Step S201: Receive a structured metabolic dataset containing plateau phase markers;

[0066] The system requires the collection and identification of a set of preprocessed time-series physiological and behavioral data. Plateau markers, as key time point identifiers, are used to define which time periods' metabolic performance should be included in subsequent analysis. The datasets involved generally include, but are not limited to, continuously monitored basal metabolic rate curves, daily nutrient intake logs, blood glucose fluctuation records, and biochemical indicators related to muscle protein synthesis. This information together constitutes a complete metabolic profile of the assessment subject, forming a basic material library.

[0067] Step S202: Based on the plateau metabolic rate sequence in the structured metabolic dataset, calculate the absolute value of the change in metabolic rate per unit time as the metabolic decay slope.

[0068] Specifically, the steps for calculating the metabolic decay slope include: extracting the continuous metabolic rate data sequence corresponding to the plateau phase marker; generating a linear regression model with time unit as the horizontal axis and metabolic rate value as the vertical axis; and extracting the absolute value of the slope of the model as the metabolic decay slope.

[0069] This step aims to capture the intensity of the gradual decline in metabolic levels over time during a plateau period. Since plateaus are often accompanied by the body developing resistance to external interventions (such as dietary control or exercise programs), the metabolic rate may exhibit a slow decline. To accurately measure this trend, a best-fitting straight line is fitted using statistical linear regression, and its slope is extracted and taken in absolute form to obtain the so-called "metabolic decay slope." This parameter essentially reflects an individual's ability to maintain efficient metabolic regulation after prolonged stress; a larger value indicates poor metabolic flexibility and difficulty in maintaining high energy expenditure efficiency; conversely, a smaller value indicates strong self-regulation potential.

[0070] Furthermore, by conducting cross-sectional comparisons of similar data across multiple periods, we can further explore the actual impact of different intervention strategies on improving basal metabolic status.

[0071] Step S203: Based on the nutrient intake records and corresponding biomarker change data in the structured metabolic dataset, quantify and generate carbohydrate sensitivity and protein response.

[0072] Specifically, calculating carbohydrate sensitivity includes performing Pearson correlation analysis on carbohydrate intake and blood glucose fluctuations, and outputting the correlation coefficient; calculating protein responsiveness includes performing linear regression on protein intake and changes in muscle synthesis biomarkers, and outputting the regression coefficient.

[0073] The core objective of this step is to deeply analyze the specific metabolic feedback characteristics of users to different types of macronutrients. Carbohydrate sensitivity mainly examines the degree and frequency of blood glucose concentration fluctuations after carbohydrate intake, thereby reflecting the overall efficiency of insulin secretion function and glucose transport system. Highly sensitive individuals often exhibit a rapid rise and fall in blood glucose after eating, suggesting a potential tendency towards glucose intolerance or that it has already developed into one of the early symptoms of prediabetes.

[0074] In contrast, protein responsiveness focuses more on whether dietary protein intake can effectively promote the activity of metabolic products, especially enzymes such as amino acid chain elongation factors, in skeletal muscle tissue, thereby indirectly evaluating protein utilization and muscle growth and repair capabilities. These two indicators together constitute important references for determining whether an individual is at risk of nutritional imbalance.

[0075] Step S204: Extract the diurnal fasting duration parameters from the structured metabolic dataset and calculate the energy deficit elasticity coefficient by combining them with the basal metabolic rate;

[0076] In this embodiment of the application, the step of calculating the energy gap elasticity coefficient specifically includes: obtaining the average day-night fasting duration of the user for 7 consecutive days; transforming the day-night fasting duration using the sigmoid function to obtain the weighting factor. Multiply the weighting factor by the basal metabolic rate to obtain the energy deficit elasticity coefficient; in the above formula, k is the adjustment factor.

[0077] The energy deficit elasticity coefficient describes the body's ability to flexibly switch to a more energy-efficient mode when subjected to prolonged periods of fasting, and to quickly return to a normal or even overcompensated state after resuming eating. This indicator can be used to predict how long a user can endure extreme hunger without developing severe functional impairment, and can also be used to optimize personalized dietary recommendations.

[0078] Therefore, this application proposes to use the Sigmoid function to map the measured average daily fasting duration to the range of [0,1] to form a weighting factor with certain biological rationality, and then multiply it by its corresponding basal metabolic rate value to obtain the final energy gap elasticity coefficient. This takes into account both the natural variation factors brought about by individual differences and the difference in baseline energy consumption between different genders and age groups.

[0079] Step S205: Normalize the metabolic decay slope, carbohydrate sensitivity, protein responsiveness, and energy deficit elasticity coefficient.

[0080] The normalization process employs differentiated strategies for various parameters: for example, the metabolic decay slope can be compressed using a hyperbolic tangent function to make its distribution range smoother and more controllable; while for carbohydrate sensitivity and protein responsiveness, a linear scaling method is used to rescale the proportions, ensuring they all fall under the same evaluation criteria; as for the energy deficit elasticity coefficient, since it already possesses good discriminative power, no further modifications are needed, and its original numerical range can be retained. This successfully achieves effective alignment of heterogeneous cross-domain data, laying a solid foundation for further constructing a comprehensive scoring system.

[0081] Step S206: The normalized parameters are fused according to preset weights, and the metabolic fitness coefficient within the preset range is output.

[0082] In this process, all normalized sub-indices are summed according to a pre-defined weighting rule to obtain a unique metabolic fitness coefficient (MAI). This weighting process draws heavily on the design principles of multiple regression models commonly used in clinical medicine, emphasizing the key elements considered most representative and best reflecting the robustness of the central regulatory network of basic human life activities.

[0083] In this embodiment, the configurable weighting scheme is as follows: metabolic decay slope accounts for 40%, carbohydrate sensitivity accounts for 25%, protein responsiveness accounts for 20%, and energy deficit elasticity coefficient accounts for 15%. The metabolic fitness coefficient is then calculated using a weighted sum formula. The entire weighting process is fully automated and requires no human intervention, minimizing bias caused by subjective judgment.

[0084] It should be noted that although the scores of each item may fluctuate, the final summary results are always strictly limited to a predetermined range (0.6~1.4) due to the use of reasonable normalization techniques and a scientific and rigorous weighting mechanism. This ensures that the results can reflect small differences sensitively while preventing extreme outliers from disrupting the overall stability.

[0085] The above implementation achieves precise characterization and quantitative expression of complex metabolic behavior in the human body, fills the gap in traditional health management tools that cannot fully reflect an individual's true metabolic potential, and provides technical support for more refined and personalized digital therapy products and services.

[0086] Reference Figure 3 As one implementation of step S103, the step of dynamically adjusting the proportion of macronutrients and total calorie value by matching a predefined nutritional strategy according to the numerical range of the metabolic adaptability coefficient and outputting a nutritional adjustment instruction includes:

[0087] Step S301: Receive metabolic fitness coefficient and user target parameters;

[0088] The metabolic adaptability coefficient is a key indicator reflecting the body's metabolic response during long-term dietary or exercise interventions. It comprehensively reflects an individual's basal metabolic efficiency, the thermic effect of food, and the degree of adaptation to external stimuli (such as dieting or muscle-building training). This coefficient is typically a dimensionless value derived from modeling and analyzing multidimensional data such as historical weight change trends, daily activity intensity, and dietary records. The user's target parameter represents their health management goals, such as fat loss, weight gain, maintaining current body shape, or improving body composition.

[0089] These two input variables form the core basis for all subsequent calculations. The metabolic adaptability coefficient determines the direction and intensity of nutritional adjustments, while the user target parameters are important reference factors that determine the adjustment range and priority.

[0090] Step S302: Compare the metabolic adaptability coefficient with the preset threshold range, and select the predefined nutrition adjustment mode based on the comparison results;

[0091] This step embodies the key classification mechanism in the entire algorithm. The preset threshold range essentially performs a functional division of the population under different physiological states, classifying the originally continuously distributed metabolic levels into three biologically significant state categories: low metabolic activity (<0.8), normal metabolic stability (0.8~1.2), and high metabolic reactivity (>1.2). This stratification not only facilitates the model's rapid location of an individual's metabolic stage but also makes subsequent operations more targeted and controllable.

[0092] Based on this, appropriate nutritional adjustment models are selected, employing differentiated interventions according to different metabolic types: compensatory interventions are used for those in a low metabolic state to avoid further suppression of basal metabolism; for those with normal metabolism, the existing structure is maintained but with minor adjustments to consolidate the results; and for those with high metabolic reactivity, the stimulation intensity can be increased to promote more active metabolic activity. This classification logic effectively solves the problem that traditional single nutritional programs cannot meet the needs of various body types.

[0093] Step S303: Based on the selected nutrition adjustment mode and user target parameters, dynamically calculate the macronutrient ratio adjustment amount and total calorie correction value;

[0094] Macronutrients mainly include three categories: carbohydrates, fats, and proteins. These are not only the primary source of energy but also play indispensable roles in various life activities, such as regulating endocrine function, maintaining tissue repair, and immune defense. Therefore, rationally allocating the intake ratio of these three nutrients under specific metabolic conditions is particularly important. For example, when it is determined that a "metabolic compensation mode" needs to be activated, it means that an individual may have experienced a decrease in basal metabolism due to long-term calorie restriction. In this case, the proportion of carbohydrates, which easily cause blood sugar fluctuations, should be appropriately reduced, while the content of fats, which can enhance satiety and contribute to hormone synthesis, should be increased. Conversely, if it is determined that a "metabolic activation mode" is activated, it indicates that the body is in a high-energy-consumption state, and it is necessary to increase protein supply to support muscle growth and recovery.

[0095] Total calorie correction refers to a re-estimation of the total daily calorie requirement. It is not a simple application of general standards (such as multiplying body weight by a fixed number of kilocalories), but a precise reassessment that fully considers an individual's intrinsic metabolic potential and recent behavioral feedback. For example, even if a user does not show obvious weight loss during high-intensity exercise, their actual energy consumption increases significantly, so the overall energy supply level still needs to be adjusted upwards to meet the dual needs of recovery and development.

[0096] Specifically, the total calorie correction value is calculated as follows: obtain the user's basal metabolic rate and daily activity consumption; calculate the safe calorie deficit base = basal metabolic rate × 0.2; dynamically adjust the calorie deficit = safe calorie deficit base × (0.9 + 0.1 × metabolic adaptability coefficient); total calorie correction value = basal metabolic rate + activity consumption - dynamically adjusted calorie deficit.

[0097] In some embodiments, the dynamic calculation step specifically includes: in metabolic compensation mode, the proportion of carbohydrates is reduced by 8-12%, the proportion of fat is increased by 6-10%, and the total calorie value is reduced by 4-6%; in metabolic activation mode, the proportion of protein is increased by 12-18%, and the total calorie value is increased by 6-10%.

[0098] Step S304: Combine the pre-acquired user basal metabolic rate and activity data to verify whether the total calorie correction value is within the safe range;

[0099] Specifically, the steps for verifying the safe range include: calculating the lower limit of total calories = (basal metabolic rate × 0.8) + activity expenditure; calculating the upper limit of total calories = (basal metabolic rate × 1.2) + activity expenditure; when the total calorie correction value is lower than the lower limit of total calories, it is forcibly set to the lower limit of total calories; when the total calorie correction value is higher than the upper limit of total calories, it is forcibly set to the upper limit of total calories.

[0100] Basal metabolic rate (BMR) is one of the standards for measuring the minimum energy expenditure required to maintain basic physiological functions in a person at rest. It is often estimated using empirical formulas based on factors such as age, gender, height, and weight, or it can be measured directly using indirect calorimetry to obtain more accurate results. Activity data describes the additional energy expenditure generated by physical labor or exercise during the day, in addition to BMR. The sum of these two data points constitutes the baseline of an individual's total daily energy requirement.

[0101] Understandably, the reason for performing a safety verification after completing the initial calorie planning is that, despite the highly customized design approach implemented in the preceding steps, there is still a risk that the recommended values ​​may deviate from the reasonable range under certain extreme conditions. Therefore, upper and lower thresholds are set as rigid constraints to ensure that even in the most unfavorable scenarios, severe malnutrition or energy surplus will not occur. This step reflects a high degree of attention to human health and also provides a guarantee for the robust operation of the automated decision-making system.

[0102] Step S305: Output a nutrition adjustment instruction containing the adjusted macronutrient ratios and total calorie values.

[0103] The nutrition adjustment instructions are a set of data packets that downstream application modules can parse and execute. These include optimal meal planning suggestions, refined through multiple layers of screening and optimization, covering the specific proportions of various major nutrients and corresponding food source guidelines. This information can be directly used to guide users' daily meal arrangements, or it can be further transformed into visual charts, shopping lists, or even automated ordering services for end consumers.

[0104] The above implementation method autonomously completes the entire process from individual metabolic characteristic identification to personalized nutritional prescription generation without relying on human intervention. By establishing a three-level metabolic zoning model and supplementing it with a two-dimensional (nutrient composition + total energy) synergistic regulation mechanism, it successfully overcomes the limitations of relying solely on experience and statistical data in the past. Furthermore, it emphasizes the importance of embedding safety assurance mechanisms throughout the entire operation chain, ensuring that the final output not only meets the user's actual needs but also strictly adheres to physiological limits, truly achieving an organic unity of intelligence, humanization, and professionalism.

[0105] Reference Figure 4 As one implementation of step S104, the step of enhancing the nutrient adjustment instruction based on the plateau phase marker and outputting the enhanced nutrient instruction includes:

[0106] Step S401: When a plateau phase marker exists, increase the nutrient density value in the nutrient adjustment instruction.

[0107] Understandably, the appearance of a plateau signifies that under sustained calorie control or a fixed dietary pattern, the body's energy metabolism system has reached a new homeostasis through a series of compensatory adaptations. One of its core characteristics is a passive increase in energy utilization efficiency, accompanied by a potential decrease in basal metabolic rate. At this point, continuing to use strategies that simply control total calories or macronutrient ratios will not only fail to break the weight plateau but may also exacerbate metabolic inhibition due to long-term insufficient nutrient intake, even leading to micronutrient deficiencies and affecting the normal functioning of physiological processes.

[0108] Nutrient density refers to the amount of essential nutrients contained in a unit of calories of food, and it is one of the important indicators for measuring dietary quality. During a plateau period, simply increasing total calorie intake may lead to the risk of fat accumulation; while simply reducing calories may not meet the basic metabolic needs. Therefore, increasing nutrient density is a compromise and a scientifically sound choice.

[0109] This approach is essentially part of a vertical fortification mechanism. It doesn't change the overall energy supply level, but rather maximizes the nutritional value of every calorie by concentrating and delivering various vitamins, minerals, high-quality protein, and other functional compounds. For example, the proportion of protein and fiber can be appropriately increased while reducing the proportion of empty-calorie carbohydrates, thereby improving the balance of the gut microbiota and stimulating muscle anabolic activity.

[0110] In some embodiments, the step of increasing the nutrient density value specifically includes: increasing the content of macronutrients per unit of calories by 15-25%; and increasing the concentration of micronutrients while keeping the total calorie value unchanged.

[0111] Step S402: Detect the user's glucose tolerance index data. When the glucose tolerance index data exceeds the preset threshold, trigger the periodic carbohydrate ratio adjustment strategy.

[0112] Glucose tolerance reflects the body's ability to clear glucose load and is an important parameter reflecting insulin sensitivity and overall glucose metabolism efficiency. Highly disruptive carbohydrate-ratio adjustment therapy should only be initiated when the subject is confirmed to have good glycemic control potential. This is because frequent and drastic switching between high and low carbohydrate patterns can put stress on the endocrine axis, posing certain safety risks, especially for individuals with prediabetes.

[0113] To this end, the system will pre-access the user's historical health records, extracting relevant physiological indicators such as oral glucose tolerance test results, fasting blood glucose concentration, and HbA1c levels, and comparing them with predetermined safety boundaries. Once the system determines that the conditions for use are met, it will proceed to the next stage of the operation. This strategy aims to disrupt the body's original metabolic homeostasis by altering the rhythm of exogenous nutrition, inducing an adaptive response similar to the starvation-refeeding cycle, thereby promoting a recovery in the efficiency of fat oxidation and decomposition.

[0114] In some embodiments, the steps for triggering a periodic carbohydrate ratio adjustment strategy specifically include: setting a cyclical scheme with a cycle of 3-5 days; and alternating between high-carb days and low-carb days within the cycle. Specifically, high-carb days increase the carbohydrate ratio to 55-65%, while low-carb days decrease the carbohydrate ratio to 25-35%; the ratio of high-carb days to low-carb days is 1:1 to 2:1.

[0115] Step S403: Increase the branched-chain amino acid ratio in the nutrition adjustment instructions;

[0116] Branched-chain amino acids (BCAAs) mainly include three essential amino acid isoforms: leucine, isoleucine, and valine. Their unique molecular structure allows them to bypass the first-pass effect in the liver and directly participate in skeletal muscle protein turnover, particularly excelling in resisting catabolistic stress. Studies have shown that appropriate BCAA supplementation not only helps alleviate post-training fatigue and accelerate recovery but also indirectly activates the mTOR signaling pathway, promoting autophagy and repair processes, which is especially important for individuals experiencing plateaus in their protein intake. Furthermore, since this increase is derived from portions originally allocated to conventional protein sources, it does not affect the overall balanced distribution of other amino acid profiles; instead, it achieves localized enrichment without additional burden on the kidneys.

[0117] In some embodiments, the step of increasing the proportion of branched-chain amino acids specifically includes: calculating the incremental amount of branched-chain amino acids based on the total calorie value: 0.04-0.06 grams of branched-chain amino acids per kilocalorie; and allocating a separate supplementary quota of branched-chain amino acids from the protein proportion.

[0118] Step S404: Integrate the nutrient density value increase, the periodic carbohydrate ratio adjustment strategy, and the branched-chain amino acid ratio increase, and output the fortified nutrition instruction.

[0119] In the embodiments of this application, the basic layer is a personalized nutritional adjustment instruction determined by the metabolic adaptability coefficient. It includes the initial macronutrient ratio and total calorie value, constituting the "basic layer" and "baseline" of nutritional intervention.

[0120] After the plateau phase is triggered, the three enhancement strategies mentioned above are applied to this baseline as dynamic "adjustment parameters" and "coverage rules." Specifically, the system converts the "nutrient density increase value" into a priority weight for food selection in the food library; for example, it assigns a higher selection probability to foods with high vitamin and mineral density. The "periodic carbohydrate ratio adjustment strategy" acts as a time function, dynamically covering the static carbohydrate ratio in the baseline instruction to generate a carbohydrate intake plan that fluctuates daily or periodically. The "branched-chain amino acid ratio increase value" serves as a detailed constraint on protein sources, requiring that, while meeting the total protein target, a specific proportion of protein must come from food categories rich in BCAAs.

[0121] The final "fortified nutrition instruction" is a comprehensive and executable plan that integrates static goals (total calories, fortified nutrient density requirements), dynamic planning (periodically changing macronutrient ratios), and component-level constraints (BCAA ratio). It retains personalized settings based on individual long-term metabolic characteristics (metabolic adaptability coefficient) while also incorporating powerful, multi-target interventions to address short-term metabolic adaptation difficulties (plateau periods). The output of this instruction marks the system's formal switch from an "adaptive nutrition maintenance" mode to an "active metabolic perturbation and breakthrough" mode, providing precise and enhanced input parameters for the subsequent generation of specific "executable meal replacement formulas" that simultaneously meet nutritional breakthrough goals and user preferences.

[0122] In the above embodiments, a dynamic nutrition management system was constructed, which uses plateau detection as the core trigger and integrates the synergistic effects of nutrient density optimization, carbohydrate cycle oscillation, and specific amino acid supplementation. This technical solution upgrades nutritional intervention from static "meal planning" to dynamic "metabolic regulation engineering," systematically addressing weight loss stagnation caused by metabolic adaptation. Through multi-target, periodic physiological perturbations, it effectively breaks the inertial homeostasis of energy metabolism, thus providing an intelligent, mechanism-driven solution for overcoming plateau bottlenecks in health management while ensuring safety and compliance.

[0123] Reference Figure 5 As one implementation of step S105, the steps of optimizing and calculating specific ingredient combinations and verifying blood sugar fluctuation levels based on fortified nutrition instructions and a pre-configured user dietary preference database, and outputting an executable meal replacement formula, include:

[0124] Step S501: Call the user's dietary preference database to obtain the user's allergen list, taste preferences and food taboo data, and obtain the user's dietary preference constraints.

[0125] This involves constructing a highly personalized dietary constraint framework to ensure that the subsequently generated meal replacement formulas not only meet nutritional requirements but also fully suit the user's physiological characteristics and subjective preferences.

[0126] Specifically, the user dietary preference database is a structured dataset. The allergen list records the user's history of adverse immune reactions to specific food components (such as allergic reactions to peanut protein or lactose). This information typically comes from medical records or user self-reporting, with the core purpose of avoiding triggering IgE-mediated immediate allergies or chronic food intolerances. Taste preference data captures an individual's preference for basic tastes such as sour, sweet, bitter, salty, and umami through quantitative scoring mechanisms (e.g., a 1-10 scale). This type of data is often obtained through interactive questionnaires or long-term dietary diary analysis. Its scientific basis lies in sensory differences caused by taste receptor gene polymorphisms; for example, a user carrying the TAS2R38 bitter taste receptor sensitivity gene may have an aversion to cruciferous vegetables. Food taboo data involves religious norms, ethical choices (such as vegetarianism), or disease management needs (such as potassium restriction for kidney disease patients). These constraints reflect the socio-cultural dimension of dietary behavior.

[0127] By integrating the aforementioned multidimensional data, the system generates a set of user dietary preference constraints. These constraints can be mathematically expressed as Boolean logic rules or weight vectors, which are used to either rigidly exclude risky ingredients or softly guide the recipe direction during subsequent optimization.

[0128] Step S502: Calculate the target gram amounts of protein, fat, and carbohydrates according to the fortified nutrition instructions;

[0129] Specifically, fortified nutrition instructions include macronutrient ratios (e.g., 20% protein, 30% fat, 50% carbohydrates) and total caloric values ​​(e.g., 1800 kcal) derived from metabolic adaptability coefficients. Calculating the target gram count relies on the principles of nutritional thermodynamics: each gram of protein and carbohydrate releases an average of 4 kcal of energy, while each gram of fat releases 9 kcal. The biological basis of this energy coefficient lies in the molecular oxidation pathways of nutrients. The complete oxidation of the carbon chains of proteins and carbohydrates produces approximately 4.1 kcal / gram, but this must be deducted for losses during digestion and absorption; fat, due to its higher density of carbon-hydrogen bonds, can release 9.3 kcal / gram.

[0130] In the specific calculation, the system first allocates the total calorie value to each nutrient proportionally. For example, the target protein weight in grams = (total calories × protein ratio) / 4, the fat weight in grams = (total calorie value × fat ratio) / 9, and the carbohydrate weight in grams = (total calorie value × carbohydrate ratio) / 4. This calculation ensures a strict correspondence between calorie distribution and the weight of the substance.

[0131] It should be noted that this process also implicitly includes a correction for the amino acid-glucose conversion effect: when protein intake exceeds physiological needs, some amino acids will be converted into glucose through gluconeogenesis. Therefore, in actual calculations, a bioavailability correction factor (such as 0.8-0.9) will be introduced to offset this metabolic spillover effect, making the formulation more consistent with the dynamic energy balance model.

[0132] Step S503: Based on the target weight and the user's dietary preference database, select candidate ingredient combinations that meet the user's dietary preference constraints from the ingredient library;

[0133] The ingredient database, as a structured database, must contain a complete nutritional profile (protein, fat, and carbohydrate content), glycemic index, price index, and flavor characteristic labels for each ingredient. The screening process first uses a constraint-satisfying algorithm to exclude all allergens and contraindicated ingredients (e.g., automatically filtering dairy products for lactose-intolerant individuals). Then, a utility maximization function is constructed based on taste preference data: for example, prioritizing ingredients with user ratings ≥8 points, controlling the proportion of high glycemic index ingredients to <15%, and using linear programming to solve for combinations of ingredients within a permissible fluctuation range (e.g., ±5%) for the target weight.

[0134] The scientific basis of this process lies in the theory of "sensory-specific satiety" in dietary behavior, which states that diverse and palatable meals can prolong the feeling of fullness and reduce the risk of overeating later. Technically, the system may use a greedy algorithm to initially generate basic combinations (such as selecting chicken breast, which has the highest protein density, to meet protein goals), and then fine-tune the proportions of complementary ingredients using a simulated annealing algorithm to improve palatability. Furthermore, the synergistic effects of bioactive components of ingredients (such as polyphenols and dietary fiber) are also taken into consideration; for example, pairing spinach, rich in tannins, with bell peppers, rich in vitamin C, to promote iron absorption. This cross-nutrient interaction optimization reflects a systems-level nutritional approach.

[0135] Step S504: Predict the blood sugar fluctuation level of the candidate ingredient combination. When the predicted value exceeds the preset blood sugar threshold, iterate and optimize again to output an executable meal replacement formula that meets the blood sugar fluctuation constraints and user preferences.

[0136] The principle behind this step is to prevent the formula from causing glucose metabolism disorders through a physiological response prediction model. The prediction of blood glucose fluctuation levels relies on a machine learning model (such as a gradient boosting decision tree). The training data for this model comes from large-scale population studies. Input features include the cumulative glycemic load (GL) of the food combination, the ratio of dietary fiber to carbohydrates, the content of organic acids (such as the delayed gastric emptying effect of acetic acid), and user-personalized parameters (such as insulin sensitivity coefficient and the standard deviation of previous blood glucose curves).

[0137] In this embodiment, when the predicted blood glucose peak exceeds a clinically safe threshold (such as 7.8 mmol / L, the diagnostic threshold for prediabetes), the system can initiate iterative optimization: for example, firstly, replacing high glycemic index ingredients (such as replacing white rice with brown rice), secondly, adjusting the timing of nutrition (such as increasing the pre-meal dietary fiber load), and if it still does not meet the target, introducing functional ingredients (such as adding cinnamon extract to inhibit α-glucosidase). This optimization follows the "minimum deviation principle," that is, making the smallest adjustment while ensuring the satisfaction of taste preferences. Its physiological basis lies in the gut-pancreatic axis feedback mechanism: rapidly digested carbohydrates trigger excessive insulin secretion, leading to reactive hypoglycemia and enhanced fat storage signals, while a low-GL diet can activate intestinal L cells to secrete GLP-1 through short-chain fatty acids (such as butyrate), naturally regulating blood glucose homeostasis. The final executable meal replacement formula not only indicates the specific ingredient weights but also includes cooking suggestions (such as cooling rice to increase resistant starch) to further smooth the blood glucose curve.

[0138] The above implementation constructs a closed-loop optimization system from metabolic characteristics to executable meals. By deeply integrating discrete user preference data with continuous physiological response predictions, a synergistic improvement in the accuracy, safety, and adherence of nutritional intervention programs is achieved. This technical solution avoids the "one-size-fits-all" drawbacks of traditional standardized recipes (such as eliminating safety risks through allergen filtering), overcomes the shortcomings of simple nutritional calculations that ignore metabolic dynamics (such as preventing hidden health damage through blood glucose prediction), and further enhances behavioral adherence through taste preference integration.

[0139] Reference Figure 6 As one implementation of step S106, the step of calculating the metabolic response rate and dynamically adjusting the calculation weights of the metabolic adaptability coefficient based on the metabolic rate feedback data after the execution of the fortified nutrition instruction and the executable meal replacement formula includes:

[0140] Step S601: Receive fortified nutrition instructions and continuous metabolic rate feedback data after the implementation of the executable meal replacement formula;

[0141] Wearable sensors or other portable physiological signal acquisition devices can be used to capture a user's resting metabolic rate or total energy expenditure level after implementing enhanced nutrition instructions and executable meal replacement formulas, ensuring that the sampling frequency is high enough to preserve subtle fluctuations. For example, collecting no fewer than five measurements per hour can effectively identify short-term energy expenditure trends and their potential disturbances.

[0142] Step S602: Based on continuous metabolic rate feedback data, extract the metabolic rate change and the corresponding calorie deficit change during the execution cycle of the executable meal replacement formula;

[0143] Among them, the change in metabolic rate is the difference in the actual metabolic rate of the user at different time nodes; the change in calorie deficit is the net deficit between the energy of the food they consume and their daily maintenance requirements. The former measures how the body functions change with the adjustment of the diet structure, while the latter reveals how much deficit there is in the current intake that needs to be supplemented or consumed in addition to supporting the basic life activity requirements. By pairing and comparing these two sets of time-synchronized values, a dataset of the mapping relationship between the energy supply-demand relationship and the induced metabolic response can be established, laying a foundation for further exploring the internal connection between the two.

[0144] Step S603: Calculate the metabolic response rate according to the ratio of the change in metabolic rate and the corresponding change in calorie deficit.

[0145] Among them, metabolic response rate = change in metabolic rate / change in calorie deficit.

[0146] Specifically, the metabolic response rate essentially describes the relative increase or decrease in the metabolic level caused by a unit change in calorie deficit, which reflects the ability of the human body to automatically adjust its own heat production efficiency in the case of insufficient or excessive energy intake.

[0147] It should be noted that due to large individual differences, even in the face of the same magnitude of food restriction measures, some people may show a significantly increased basal energy consumption rate, while others may have no obvious change or even a decrease. Therefore, such ratio-type indicators must be used to objectively evaluate the adaptability performance of different subjects. Further, considering the problem that short-term fluctuations may obscure long-term trends, it is preferred to use three days as a rolling observation window for averaging, making each estimation result more representative and more robust.

[0148] Step S604: Evaluate the stability level of the metabolic response rate, and adjust the calculation weight distribution of the metabolic adaptability coefficient according to the stability level.

[0149] Specifically, the steps for evaluating the stability level specifically include: calculating the coefficient of variation of the metabolic response rate as: ; in the above formula, σ R is the standard deviation of the response rate, and μ R is the mean value; set the stability level: when CV ≤ 15%, it is high stability; when 15% < CV ≤ 30%, it is medium stability; when CV > 30%, it is low stability.

[0150] This step introduces the statistical concept of the coefficient of variation to characterize the dispersion of a series of response rate samples around their mean, classifying them into three levels: high, medium, and low, representing good consistency, moderate controllability, and high uncertainty, respectively. Its significance lies in adopting a differentiated approach based on different response patterns, so as to rationally allocate the contribution proportions of each component affecting the metabolic fitness coefficient.

[0151] For example, when a user shows extremely high consistency, it indicates that they are more sensitive to carbohydrate intake. In this case, appropriately increasing the weight of related parameters can help better predict future possible changes. Conversely, if their response is drastic and unpredictable, more attention should be paid to the impact of protein intake on their basal metabolism, thus guiding the system to prioritize strengthening this parameter setting. Furthermore, a nonlinear adjustment function is set to control the specific magnitude of each fine-tuning, ensuring a smooth transition in the evolution path while also considering the need for rapid convergence under extreme conditions.

[0152] In some embodiments, the weighting adjustment rules include: when stability is high, increasing the carbohydrate sensitivity weight by 5% and decreasing the energy deficit elasticity coefficient weight by 3%; when stability is low, increasing the protein responsiveness weight by 8% and decreasing the metabolic decay slope weight by 5%; the weighting adjustment range is: k is the adjustment factor.

[0153] It should be noted that after obtaining the new weight allocation scheme, the previously fixed weighting factors have now been assigned new value ranges and combination structures. These optimized weight vectors will be sent to a functional unit specifically responsible for deriving the overall metabolic fitness coefficient to continue participating in the calculation. The new weights are uniformly loaded into the system at the beginning of the next nutritional cycle (72 hours), and the adjustment direction is monitored by an oscillation suppression algorithm. If a reverse adjustment occurs for three consecutive cycles, the parameter update is immediately frozen and a manual review process is triggered to prevent the system from entering a high-frequency oscillation state.

[0154] At the same time, to prevent certain parameters from exceeding reasonable limits and causing an uncontrollable situation due to repeated iterations, boundary constraints are added to limit their movement and ensure that any modifications fluctuate within acceptable limits. More importantly, to ensure that each component maintains its proper place in the overall evaluation system and does not conflict with or cancel each other out, it needs to be normalized and standardized to ensure that they always function synergistically within a closed space.

[0155] In the above embodiments, continuous metabolic rate data of users during the execution of fortified nutrition instructions and meal replacement formulas is collected in real time. The metabolic response rate is dynamically calculated by combining this with changes in the calorie deficit. Based on the stability level of this response rate, the calculation weight of the metabolic adaptability coefficient is adaptively adjusted, thereby achieving precise tracking and personalized regulation of individual metabolic status. This technical solution not only improves the scientific rigor and effectiveness of nutritional intervention strategies but also enhances the system's adaptability to different users' metabolic characteristics, ultimately achieving the technical effects of optimizing energy management and improving health levels.

[0156] Reference Figure 7 As a further implementation of the dynamic nutritional adjustment method for metabolic adaptation, after the step of dynamically correcting the calculation weights of the metabolic adaptation coefficient, the method further includes:

[0157] Step S701: Receive the dynamically corrected metabolic fitness coefficient and real-time metabolic rate data stream;

[0158] Specifically, the metabolic adaptability coefficient (MAC) is a dynamically corrected value generated by weighted fusion of metabolic decay slope, nutrient responsiveness, and energy deficit elasticity coefficient. Meanwhile, the real-time metabolic rate data stream originates from time-series data of resting metabolic rate (RMR) and active metabolic rate (AMR) continuously collected by wearable devices. Its high-frequency sampling (at least once per minute) ensures the temporal resolution and accuracy of the data, enabling the capture of instantaneous fluctuations in metabolic rate, such as excess post-exercise oxygen consumption or metabolic troughs during sleep.

[0159] Step S702: Extract the resting metabolic rate dataset within a continuous preset period from the real-time metabolic rate data stream, and calculate the standard deviation as a metabolic stability indicator.

[0160] The RMR data for a continuous preset period (default 14 days) constitutes a time series, and its standard deviation σRMR, as a statistical dispersion indicator, directly reflects the fluctuation range of metabolic rate around the mean. Biologically, this volatility is closely related to the regulatory functions of the hypothalamic-pituitary-adrenal axis and the autonomic nervous system: a healthy metabolic system will produce reasonable intra- and inter-diurnal variations due to sleep depth, stress events, or eating cycles. For example, a σRMR in the range of 4-5% indicates good metabolic flexibility, and the body can effectively respond to environmental changes; while a σRMR that is too low (e.g., below 3%) suggests metabolic rigidity, often stemming from neuroendocrine dulling caused by chronic energy restriction, such as decreased sensitivity of hypothalamic leptin signaling, causing the metabolic rate to flatten and lose elasticity. The design of this indicator is based on clinical evidence, such as the significantly higher σRMR in metabolically flexible individuals compared to metabolically impaired individuals, indicating that the standard deviation can not only identify early signs of metabolic failure but also distinguish between compensatory adaptation and pathological dysregulation.

[0161] Step S703: Analyze the diurnal rhythm fluctuation curve of the real-time metabolic rate data stream and generate the diurnal rhythm fluctuation amplitude;

[0162] Specifically, algorithms (such as Fourier transform or peak detection) are used to fit the fluctuation curve of 24-hour metabolic rate data and calculate its amplitude to assess the driving force of the biological clock on metabolism. The circadian rhythm is dominated by the suprachiasmatic nucleus (SCN), which affects the rhythm of mitochondrial oxidative phosphorylation and hormone secretion (such as the morning cortisol peak and the nighttime melatonin trough) by regulating the expression cycle of circadian clock genes (such as CLOCK and BMAL1).

[0163] Under normal physiological conditions, the RMR (Rhythmic Ratio) increases by 10-15% in the morning driven by cortisol and decreases at night. An amplitude (Acirc) greater than 8% indicates a healthy circadian rhythm system. Conversely, a decreased amplitude (e.g., below 8%) often suggests circadian rhythm disorder, possibly related to weakened SCN neuronal activity or peripheral tissue clock gene mutations, leading to decreased mitochondrial ATP synthesis efficiency. The core of this parameter lies in integrating chronobiological principles into metabolic assessment. For example, in animal studies, BMAL1 gene knockout resulted in a 40% decrease in amplitude, confirming the direct link between amplitude and energy metabolism.

[0164] Step S704: Calculate the metabolic elasticity recovery index based on metabolic stability indicators, diurnal rhythm fluctuation amplitude, and metabolic adaptability coefficient.

[0165] Among them, the Metabolic Elastic Recovery Index (MERI) is designed to integrate the elastic reserves of the metabolic system, rhythmic drive, and individual basic regulatory capacity.

[0166] Specifically, the formula for calculating MERI is MERI=(σRMR / Acirc)×MAC, where the numerator σRMR represents a metabolic stability index, quantifying the remaining amount of the system's adjustable space, i.e., elastic reserve. A higher σRMR indicates that the body retains its responsiveness to environmental disturbances; the denominator Acirc represents the amplitude of diurnal rhythm fluctuations, reflecting the intensity of metabolic dynamics driven by the biological clock. The larger the amplitude, the stronger the regulatory efficacy of the rhythm on metabolism; the coefficient MAC serves as a correction term, incorporating individual differences such as hereditary insulin sensitivity or baseline hormone levels to ensure the index is personalized.

[0167] Step S705: If the metabolic elasticity recovery index is lower than the preset index threshold, a metabolic repair enhancement signal is generated.

[0168] The preset threshold for the metabolic resilience recovery index (MERI) (e.g., ≤0.35 as critical) is based on large-scale cohort studies, corresponding to the mitochondrial functional compensation limit. When the activity of complex I falls below the baseline of 0.35, electron leakage leads to a burst of reactive oxygen species, causing irreversible damage. Therefore, MERI is not only a statistical indicator but also a predictor of cellular metabolic health. For example, when user A's MERI is 0.267, it indicates insufficient resilience, requiring external intervention.

[0169] Furthermore, after the metabolic repair enhancement signal is generated, the system initiates a secondary verification mechanism. For example, it monitors the slope of the RMR trend over the following 72 hours. If the slope is below -0.5 kcal / day, the trend of metabolic deterioration is confirmed, avoiding misjudgment due to short-term fluctuations (such as acute illness or data noise). This step reflects the logic of preventive medicine, transforming risk assessment into actionable instructions to ensure the timeliness and accuracy of intervention.

[0170] Step S706, in response to the metabolic repair enhancement signal, increases the proportion of electron transport chain cofactors in the micronutrient ratio of the executable meal replacement formula.

[0171] This approach translates metabolic repair signals into specific nutritional intervention strategies, directly optimizing mitochondrial energy metabolism by increasing the proportion of electron transport chain (ETC) cofactors. ETC is a protein complex (IV) system on the inner mitochondrial membrane, responsible for oxidative phosphorylation and ATP production. Cofactors, as non-protein components such as coenzyme Q10, R-lipoic acid, and L-carnitine, perform electron transport, antioxidant, and substrate transport functions, respectively. Increasing their proportion enhances the electron flow efficiency of complex I-IV, reduces reactive oxygen species production caused by electron leakage, and promotes fatty acid oxidation and ATP synthesis.

[0172] For example, coenzyme Q10, as an electron carrier in complexes I / II to III, can improve the continuity of electron transport by increasing the dosage from 20 mg / 100 kcal to 45 mg; R-lipoic acid protects complex IV from oxidative damage by regenerating glutathione; and L-carnitine accelerates fatty acid transport and supports β-oxidation. This intervention is based on the principles of cellular bioenergetics and targets the mitochondrial dysfunction indicated by MERI deficiency to achieve targeted enhancement of metabolic recovery.

[0173] It should be noted that electron transport chain cofactors such as coenzyme Q10, R-lipoic acid, and L-carnitine are all compliant food fortifiers and have been included in my country's "Standards for the Use of Food Fortifiers" (GB 14880-2024). They are easily obtained from natural sources or through synthetic routes, and through industrial technologies such as liposome encapsulation and microencapsulation, they can be compatible with existing meal replacement production lines, ensuring bioavailability and stability. The increase in cost per serving is controllable, making this step highly practical in large-scale health management.

[0174] In the above implementation, a three-dimensional assessment of metabolic stability, circadian rhythm driving force, and individual regulatory capacity is conducted to generate the MERI index, enabling early and accurate diagnosis of metabolic elasticity failure. When the threshold is triggered, the proportion of electron transport chain cofactors in the meal replacement is increased to directly optimize mitochondrial function, raising the success rate of traditional nutritional intervention from empirical to quantitative cellular level, and providing a feasible food engineering solution for chronic metabolic management.

[0175] Reference Figure 8 As one embodiment of step S706, the step of increasing the proportion of electron transport chain cofactors in the micronutrient ratio of the executable meal replacement formula includes:

[0176] Step S801: Obtain the dynamically corrected metabolic fitness coefficient and metabolic elasticity recovery index;

[0177] Step S802: Calculate the dynamic dose parameters of electron transport chain cofactors; where, coenzyme Q10 dose = basal dose + elasticity compensation term × (1 - metabolic elasticity recovery index), lipoic acid dose = response sensitivity coefficient × metabolic adaptability coefficient.

[0178] Specifically, for different cofactors, based on their specific mechanisms of action in the mitochondrial electron transport chain (ETC), different driving factors are associated with them for precise calculation.

[0179] In the calculation of coenzyme Q10 dosage, the basal dose in the formula is a preset constant (e.g., 50 mg / 100 kcal) to meet the daily mitochondrial function maintenance needs of healthy individuals, corresponding to the ubiquinone library capacity threshold of ETC complex I / II. The "elastic compensation term" is a preset adjustment range (e.g., 20 mg) used to counteract electron transport barriers. When the MERI decreases (e.g., 0.28), the 1-MERI value increases (0.72), and the compensation dose is correspondingly increased (20 × 0.72 = 14.4 mg), aiming to increase the carrier density of ubiquinone in the inner membrane, thereby facilitating electron flow, stabilizing membrane potential, and combating oxidative stress.

[0180] For the dosage calculation of lipoic acid (usually referring to the R-configuration), the response sensitivity coefficient in the formula is a preset biological conversion coefficient (e.g., 100 mg), quantifying the metabolic regulatory capacity of the metabolic adaptability coefficient (MAC) into the lipoic acid dosage. Lipoic acid mainly acts on the antioxidant protection of complex IV. Users with high MAC values ​​(e.g., 0.75) have better response efficiency to oxidative stress clearance, and their dosage should be linearly positively correlated with MAC.

[0181] Step S803: Lock the proportion of macronutrients in the executable meal replacement formula to remain unchanged;

[0182] Understandably, this step aims to ensure that micronutrient adjustments act precisely on predetermined cellular metabolic pathways without triggering uncontrollable changes to the entire dietary energy framework.

[0183] Specifically, the macronutrient ratios (i.e., the energy supply ratio of carbohydrates, fats, and proteins) in a feasible meal replacement formula have already been matched and generated in previous steps, determining the overall energy supply pattern and hormonal environment. Electron transport chain cofactors (such as coenzyme Q10 and alpha-lipoic acid) are micronutrients, and their target is the efficiency of biochemical reactions at the organelle (mitochondrial) level. If the macronutrient ratios are allowed to change automatically or in tandem when adjusting these micronutrients, it may interfere with the user's original dietary adaptation and complicate the attribution of metabolic improvements.

[0184] Therefore, clearly defining the predetermined macronutrient ratios essentially decouples the interventions in the two dimensions of "cellular function repair" and "macroeconomic energy regulation." This ensures the purity and precision of subsequent formula adjustments, allowing any observed metabolic improvements to be clearly attributed to the optimization of electron transport chain cofactors, rather than the confounding effects of changes in macronutrient structure.

[0185] Step S804: Update the micronutrient database of executable meal replacement formulas based on the dynamic dosage parameters of electron transport chain cofactors.

[0186] The micronutrient database for executable meal replacement formulas is a structured digital system where each nutrient has a corresponding field defining its content per unit of energy (e.g., per 100 kcal) in a meal replacement. Once the system calculates the precise dynamic dosage parameters for Coenzyme Q10 and Alpha-Lycic Acid, these milligram values ​​are immediately sent as key instructions and written into the corresponding user's digital file for "executable meal replacement formulas".

[0187] In the above embodiments, based on the biochemical mechanisms of different cofactors, a differentiated dynamic dosing algorithm is designed to convert physiological indices into specific supplementation doses for coenzyme Q10 and alpha-lipoic acid; by locking the proportion of macronutrients, the targeting of the intervention and the clarity of the effect attribution are ensured; finally, by updating the structured micronutrient database, a solid technical path is provided for realizing metabolic health management based on precision nutrition.

[0188] This application also discloses a dynamic nutrition adjustment system based on metabolic adaptation.

[0189] A dynamic nutritional adjustment system based on metabolic adaptation, specifically comprising:

[0190] The data acquisition and processing module is used to collect users' historical metabolic rate data and real-time biosensor data and preprocess them, identify continuous data segments with metabolic rate changes below a preset change rate threshold as plateau phase markers, and output a structured metabolic dataset containing plateau phase markers.

[0191] The metabolic adaptation analysis module is used to calculate the metabolic decay slope, nutrient responsiveness, and energy deficit elasticity coefficient based on a structured metabolic dataset, and generate the metabolic adaptation coefficient through weighted fusion.

[0192] The nutrition strategy matching module is used to match predefined nutrition strategies based on the numerical range of the metabolic adaptability coefficient, dynamically adjust the proportion of macronutrients and total calories, and output nutrition adjustment instructions.

[0193] The nutrition instruction enhancement module is used to enhance nutrition adjustment instructions based on the plateau period marker and output enhanced nutrition instructions.

[0194] The meal replacement formula optimization module is used to optimize and calculate specific ingredient combinations and verify blood sugar fluctuation levels based on fortified nutrition instructions and a pre-configured user dietary preference database, and output an executable meal replacement formula.

[0195] The metabolic response feedback module is used to calculate the metabolic response rate and dynamically adjust the calculation weight of the metabolic adaptability coefficient based on the metabolic rate feedback data after the execution of the fortified nutrition instructions and the executable meal replacement formula.

[0196] The dynamic nutrition adjustment system based on metabolic adaptation according to the present application embodiment can implement any of the above methods, and the specific working process of each module in the system can refer to the corresponding process in the above method embodiment.

[0197] In the several embodiments provided in this application, it should be understood that the provided methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for example, the division of a certain module is merely a logical functional division, and in actual implementation there may be other division methods, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0198] This application also discloses a computer-readable storage medium.

[0199] A computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described above in any of the methods of dynamic nutritional adjustment based on metabolic adaptation.

[0200] The computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device; the program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0201] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A dynamic nutritional adjustment method based on metabolic adaptation, characterized in that, The dynamic nutrition adjustment method includes: Collect users' historical metabolic rate data and real-time biosensor data and preprocess them, identify continuous data segments with metabolic rate changes below a preset change rate threshold as plateau phase markers, and output a structured metabolic dataset containing plateau phase markers. Based on the structured metabolic dataset, the metabolic decay slope, nutrient responsiveness, and energy deficit elasticity coefficient are calculated, and a metabolic fitness coefficient is generated by weighted fusion. Based on the numerical range of the metabolic adaptability coefficient, a predefined nutritional strategy is matched, the proportion of macronutrients and total calorie value are dynamically adjusted, and a nutritional adjustment instruction is output. The nutrition adjustment instruction is enhanced based on the plateau phase marker, and an enhanced nutrition instruction is output. Based on the enhanced nutrition instructions and the pre-configured user dietary preference database, the specific food combination is optimized and the blood sugar fluctuation level is verified, and an executable meal replacement formula is output. Based on the metabolic rate feedback data after the execution of the fortified nutrition instructions and the executable meal replacement formula, the metabolic response rate is calculated and the calculation weight of the metabolic adaptability coefficient is dynamically adjusted.

2. The dynamic nutritional adjustment method based on metabolic adaptation according to claim 1, characterized in that, Based on the structured metabolic dataset, the steps of calculating the metabolic decay slope, nutrient responsiveness, and energy deficit elasticity coefficient, and generating the metabolic fitness coefficient through weighted fusion include: Receive a structured metabolic dataset containing plateau phase markers; Based on the plateau metabolic rate sequence in the structured metabolic dataset, the absolute value of the change in metabolic rate per unit time is calculated as the metabolic decay slope. Based on the nutrient intake records and corresponding biomarker changes in the structured metabolic dataset, carbohydrate sensitivity and protein responsiveness are quantified. Extract the diurnal fasting duration parameter from the structured metabolic dataset and calculate the energy deficit elasticity coefficient by combining it with the basal metabolic rate; The metabolic decay slope, carbohydrate sensitivity, protein responsiveness, and energy deficit elasticity coefficient were normalized. The normalized parameters are fused according to preset weights, and the metabolic fitness coefficient within a preset range is output.

3. The dynamic nutritional adjustment method based on metabolic adaptation according to claim 2, characterized in that, The steps of dynamically adjusting the proportion of macronutrients and total calorie value based on the numerical range of the metabolic adaptability coefficient, and outputting nutritional adjustment instructions include: Receive metabolic fitness coefficients and user target parameters; The metabolic adaptability coefficient is compared with a preset threshold range, and a predefined nutritional adjustment mode is selected based on the comparison results. Based on the selected nutrition adjustment mode and user target parameters, dynamically calculate the adjustment amount of macronutrient ratio and the correction value of total calories. By combining pre-acquired user basal metabolic rate and activity level data, it is verified whether the total calorie correction value is within a safe range; The output includes nutritional adjustment instructions containing the adjusted macronutrient ratios and total calorie values.

4. The dynamic nutritional adjustment method based on metabolic adaptation according to claim 1, characterized in that, The steps of enhancing the nutritional adjustment instruction based on the plateau phase marker and outputting the enhanced nutritional instruction include: When a plateau phase marker is present, increase the nutrient density value in the nutrient adjustment instruction; The system monitors the user's glucose tolerance index data and triggers a periodic carbohydrate ratio adjustment strategy when the glucose tolerance index data exceeds a preset threshold. Increase the proportion of branched-chain amino acids in the nutrition adjustment instructions; It integrates the increase in nutrient density, the periodic adjustment strategy of carbohydrate ratio, and the increase in branched-chain amino acid ratio to output fortified nutrition instructions.

5. The dynamic nutritional adjustment method based on metabolic adaptation according to claim 4, characterized in that, Based on the enhanced nutrition instructions and a pre-configured user dietary preference database, the steps for optimizing specific ingredient combinations, verifying blood glucose fluctuation levels, and outputting an executable meal replacement formula include: Access the user's dietary preference database to obtain the user's allergen list, taste preferences, and food taboo data, and obtain the user's dietary preference constraints. Calculate the target gram amounts of protein, fat, and carbohydrates according to the fortified nutrition instructions; Based on the target weight and user dietary preference database, candidate ingredient combinations that meet the user dietary preference constraints are selected from the ingredient library; The system predicts the blood glucose fluctuation level of candidate ingredient combinations. When the predicted value exceeds the preset blood glucose threshold, it iterates and optimizes again, and outputs an executable meal replacement formula that meets the blood glucose fluctuation constraints and user preferences.

6. The method for dynamic nutritional adjustment based on metabolic adaptation according to claim 1, characterized in that, The steps of calculating the metabolic response rate and dynamically adjusting the calculation weights of the metabolic adaptability coefficient based on the metabolic rate feedback data after the execution of the fortified nutrition instructions and the executable meal replacement formula include: Receive the fortified nutrition instructions and continuous metabolic rate feedback data after the implementation of the executable meal replacement formula; Based on the continuous metabolic rate feedback data, extract the metabolic rate change and the corresponding calorie deficit change during the execution cycle of the executable meal replacement formula; The metabolic response rate is calculated based on the ratio of the change in metabolic rate to the corresponding change in calorie deficit. Assess the stability level of the metabolic response rate and adjust the calculation weight allocation of the metabolic fitness coefficient based on the stability level.

7. The dynamic nutritional adjustment method based on metabolic adaptation according to claim 6, characterized in that, Following the step of dynamically adjusting the calculation weights of the metabolic fitness coefficient, the method further includes: Receive dynamically corrected metabolic fitness coefficients and real-time metabolic rate data streams; Extract the resting metabolic rate dataset within a continuous preset period from the real-time metabolic rate data stream, and calculate the standard deviation as a metabolic stability indicator. The diurnal rhythm fluctuation curve of the real-time metabolic rate data stream is analyzed to generate the diurnal rhythm fluctuation amplitude; The metabolic elasticity recovery index is calculated based on the metabolic stability index, the diurnal rhythm fluctuation amplitude, and the metabolic adaptability coefficient. If the metabolic elasticity recovery index is lower than a preset index threshold, a metabolic repair enhancement signal is generated; In response to the metabolic repair enhancement signal, the proportion of electron transport chain cofactors is increased in the micronutrient ratio of the executable meal replacement formula.

8. The dynamic nutritional adjustment method based on metabolic adaptation according to claim 7, characterized in that, In the micronutrient ratio of the executable meal replacement formula, the step of increasing the content ratio of electron transport chain cofactors includes: Obtain the dynamically adjusted metabolic fitness coefficient and metabolic elasticity recovery index; Calculate the dynamic dose parameters of the electron transport chain cofactors; where, coenzyme Q10 dose = basal dose + elasticity compensation term × (1 - metabolic elasticity recovery index), lipoic acid dose = response sensitivity coefficient × metabolic adaptability coefficient; The proportion of macronutrients in the executable meal replacement formula remains unchanged. The micronutrient database of the executable meal replacement formula is updated based on the dynamic dosage parameters of the electron transport chain cofactor.

9. A dynamic nutritional adjustment system based on metabolic adaptation, characterized in that, The dynamic nutrition adjustment system includes: The data acquisition and processing module is used to collect users' historical metabolic rate data and real-time biosensor data and preprocess them, identify continuous data segments with metabolic rate changes below a preset change rate threshold as plateau phase markers, and output a structured metabolic dataset containing plateau phase markers. The metabolic adaptation analysis module is used to calculate the metabolic decay slope, nutrient responsiveness and energy deficit elasticity coefficient based on the structured metabolic dataset, and generate the metabolic adaptation coefficient through weighted fusion. The nutrition strategy matching module is used to match a predefined nutrition strategy according to the numerical range of the metabolic adaptability coefficient, dynamically adjust the proportion of macronutrients and total calories, and output nutrition adjustment instructions. The nutrition instruction enhancement module is used to enhance the nutrition adjustment instruction according to the plateau period marker and output the enhanced nutrition instruction; The meal replacement formula optimization module is used to optimize and calculate specific ingredient combinations and verify blood sugar fluctuation levels based on the fortified nutrition instructions and a pre-configured user dietary preference database, and output an executable meal replacement formula. The metabolic response feedback module is used to calculate the metabolic response rate and dynamically correct the calculation weight of the metabolic adaptability coefficient based on the metabolic rate feedback data after the execution of the fortified nutrition instruction and the executable meal replacement formula.

10. A computer-readable storage medium, characterized in that: The computer program is stored that can be loaded by a processor and executed as described in any one of claims 1 to 8.

Images