Insulin sensitivity enhancement training method and system

Abstract

The invention relates to the field of biomedicine, and discloses an insulin sensitivity enhancement training method and system.The insulin sensitivity enhancement training method comprises the steps that continuous blood sugar monitoring values of a training object under a sugar load experiment are collected to construct a blood sugar time sequence curve; recognizing the metabolic state of the training object, and determining the effective physical activity intensity of the training object; measuring the body composition and the energy consumption rate of the training object, and extracting the personalized metabolism characteristics of the training object; creating an adaptability training plan of the training object, and setting a training feedback unit of the training object; calculating an instant effect score of the adaptability training plan, and setting an adaptive scheme optimization mechanism of the adaptability training plan in combination with a training feedback unit; and executing insulin sensitivity enhancement training of the training object by using the suitability training plan, the instant effect score and the adaptive scheme optimization mechanism. According to the invention, individual differentiation training requirements can be effectively met, and the insulin sensitivity enhancement effect is improved.

Description

Technical Field

[0001] The invention relates to an insulin sensitivity enhancement training method and system, and belongs to the field of biomedicine. Background Art

[0002] Insulin is a hormone secreted by the pancreas. Its main function is to break down glucose and carbohydrates in other foods in the human body. Insulin sensitivity can be used to describe the degree of insulin resistance. The lower the insulin sensitivity, the worse the effect of a unit of insulin, and the worse its effect on breaking down sugars. The latest research shows that decreased insulin sensitivity has gradually become the main reason for the increase in the prevalence of diabetes, and the primary manifestation of decreased insulin sensitivity is hyperinsulinemia, which is accompanied by cardiovascular damage, decreased quality of life, and the further occurrence and development of diabetes. Therefore, it is particularly important to conduct insulin sensitivity enhancement training.

[0003] However, existing technologies mostly use standardized programs for insulin sensitivity enhancement training, that is, by formulating a unified diet and exercise plan to enhance individual insulin sensitivity. However, during use, this program does not fully consider the differences between individuals, such as different exercise endurance and metabolic status between individuals, resulting in a mismatch between training plans and individual characteristics, thereby affecting the enhancement effect of insulin sensitivity.

[0004] Therefore, there is an urgent need for a solution that can effectively meet the differentiated training needs of individuals and improve the enhancement effect of insulin sensitivity. Summary of the Invention

[0005] The present invention provides an insulin sensitivity enhancement training method and system, the main purpose of which is to effectively meet the differentiated training needs of individuals and improve the enhancement effect of insulin sensitivity.

[0006] To achieve the above objectives, the present invention provides a method for enhancing insulin sensitivity training, comprising: Obtaining continuous blood glucose monitoring values ​​collected from the training subject during a glucose load experiment to construct a blood glucose time series curve of the training subject, and testing the fasting insulin and glycosylated hemoglobin of the training subject to obtain fasting insulin content and glycosylated hemoglobin level; identifying the metabolic state of the training subject according to the blood glucose time series curve, the fasting insulin content, and the glycosylated hemoglobin level, and determining the effective physical activity intensity of the training subject based on the metabolic state; measuring the body composition and energy expenditure rate of the training subject, identifying the energy expenditure characteristics of the training subject based on the body composition and the energy expenditure rate, and extracting the personalized metabolic characteristics of the training subject based on the body composition and the energy expenditure characteristics; creating an adaptive training plan for the training subject according to the effective physical activity intensity and the personalized metabolic characteristics, and setting a training feedback unit for the training subject based on the adaptive training plan; Calculating an immediate effect score of the adaptive training program based on the fasting insulin and blood glucose time series curves, and setting an adaptive program optimization mechanism of the adaptive training program according to the immediate effect score and the training feedback unit; In combination with the adaptive training plan, the immediate effect score and the adaptive program optimization mechanism, the insulin sensitivity enhancement training of the training subject is performed to obtain an insulin sensitivity enhancement training result.

[0007] Optionally, identifying the metabolic state of the training subject according to the blood glucose time series curve, the fasting insulin content, and the glycosylated hemoglobin level includes: identifying a fasting blood glucose value and a blood glucose peak value in the blood glucose time series curve; Based on the fasting blood glucose value and the blood glucose peak value, performing stage quantization processing on the blood glucose time series curve to obtain a staged blood glucose curve; extracting metabolic evaluation indicators of the staged blood glucose curves; identifying the metabolic phenotype of the training subject by combining the metabolic evaluation index, the fasting insulin content, and the glycosylated hemoglobin level; calculating a metabolic score of the training subject within the metabolic phenotype; Based on the metabolic score and the metabolic phenotype, a metabolic state of the training subject is identified.

[0008] Optionally, determining the effective physical activity intensity of the training subject based on the metabolic state includes: Based on the metabolic state, identifying the metabolite level, gene expression and protein activity of the training subject; Analyzing the metabolic regulation mechanism of the training subject and identifying the metabolic pathway of the training subject based on the metabolite level, the gene expression and the protein activity; identifying the metabolic energy requirement of the training subject based on the metabolic regulation mechanism and the metabolic pathway; analyzing the metabolic responses of the training subjects at different physical activity intensities; The effective physical activity intensity of the training subject is determined by combining the metabolic energy demand and the metabolic response.

[0009] Optionally, identifying the energy expenditure characteristics of the training subject based on the body composition and the energy expenditure rate includes: calculating the muscle-to-fat ratio of the training subject based on the body composition; collecting subcutaneous fat thickness measurement data of the training subject, and identifying the fat distribution type of the training subject using the subcutaneous fat thickness measurement data; collecting motion data of the training subject, and identifying the motion pattern of the training subject based on the motion data; Based on the movement pattern, using wavelet transform method to analyze the short-term fluctuation and long-term trend of the energy consumption rate; identifying a fluctuation range of the energy expenditure rate of the training subject based on the short-term fluctuation and the long-term trend; The energy consumption characteristics of the training subject are identified by combining the muscle-to-fat ratio, the fat distribution type, and the energy consumption rate fluctuation amplitude.

[0010] Optionally, extracting the personalized metabolic characteristics of the training subject based on the body composition and the energy expenditure characteristics includes: collecting body composition data and energy consumption characteristic data of the training subject according to the body composition and the energy consumption characteristic; calculating a correlation coefficient between the body composition and the energy expenditure characteristic; Based on the correlation coefficient, a graph neural network is used to construct a correlation map between the body composition data and the energy consumption characteristic data; identifying, based on the association map, a potential relationship between the body composition and the energy expenditure characteristic; Based on the potential relationship, performing dimensionality reduction processing on the body composition data and the energy consumption characteristic data to obtain first dimensionality reduction data and second dimensionality reduction data; The personalized metabolic features of the training subject are extracted from the first dimensionality reduction data and the second dimensionality reduction data.

[0011] Optionally, creating an adaptive training plan for the training subject according to the effective physical activity intensity and the personalized metabolic characteristics includes: identifying the metabolic tendency type of the training subject based on the personalized metabolic signature; extracting a metabolic evaluation index of the training subject according to the metabolic tendency type and the effective physical activity intensity; constructing a metabolic assessment matrix for the training subject based on the metabolic evaluation index; Setting the metabolic typing of the training subject according to the metabolic assessment matrix; setting an adaptive exercise type for the training subject based on the metabolic typing and the effective physical activity intensity; Identifying the fatigue index and metabolic flexibility of the training subject during training; setting an adaptive training opportunity for the training subject according to the fatigue index and the metabolic flexibility; An adaptive training plan for the training subject is created by combining the metabolic typing, the adaptive exercise type and the adaptive training opportunity.

[0012] Optionally, the step of setting a training feedback unit for the training subject based on the adaptive training plan includes: Based on the adaptive training plan, setting a plan completion threshold for the training subject; Acquiring the training completion status of the training subject in real time, and configuring a compliance monitor for the training subject based on the plan completion threshold and the training completion status; collecting compliance training data of the training subject according to the compliance monitor; identifying an execution deviation of the training subject based on the compliance training data; Setting an abnormality reminder module for the adaptive training plan according to the execution deviation and the plan completion threshold; Analyzing the deviation risk level of the training subject based on the execution deviation degree, and constructing a progressive intervention mechanism of the adaptive training program according to the deviation risk level; In combination with the progressive intervention mechanism, the abnormality reminder unit and the compliance supervision module, a training feedback unit for the training subject is set.

[0013] Optionally, the calculating of the immediate effect score of the adaptive training program based on the fasting insulin and the blood glucose time series curves includes: obtaining the highest blood glucose value in the blood glucose time series curve, and extracting the blood glucose fluctuation characteristics of the training subject based on the blood glucose time series curve; determining the insulin sensitivity index of the training subject according to the maximum blood glucose value and the fasting insulin; identifying the blood glucose-insulin response pattern of the training subject based on the blood glucose fluctuation characteristics and the insulin sensitivity index; setting differentiated evaluation indicators for the adaptive training program according to the blood glucose-insulin response pattern; Determining a training goal for the training subject based on the adaptive training plan, and assigning weights to the differentiated evaluation indicators according to the training goals to obtain indicator weights; Calculate the immediate effect score of the adaptive training program based on the differentiated scoring index and the index weight.

[0014] Optionally, setting a self-adaptive scheme optimization mechanism for the adaptive training plan according to the immediate effect score and the training feedback unit includes: Performing spatiotemporal alignment processing on the instant effect score and the original data of the training feedback unit to obtain difference data; Based on the difference data, identifying conflicting signals between the immediate effect score and the training feedback unit; Setting a dual-effect verification method of the adaptive training program according to the conflicting signal; Constructing a blood glucose-insulin knowledge graph for the training object; Generating personalized training advice for the training subject using the blood glucose-insulin knowledge graph according to the immediate effect score and the training feedback unit; Creating a training parameter optimizer for the adaptive training plan based on the personalized training advice; In combination with the dual effect verification method and the training parameter optimizer, an adaptive scheme optimization mechanism of the adaptive training plan is set.

[0015] In order to solve the above problems, the present invention also provides an insulin sensitivity enhancement training system, which includes: A blood glucose analysis module is used to obtain continuous blood glucose monitoring values ​​collected by the training subject during the glucose load experiment to construct a blood glucose time series curve of the training subject, and to detect the fasting insulin and glycosylated hemoglobin of the training subject to obtain the fasting insulin content and glycosylated hemoglobin level; a metabolic state identification module, configured to identify the metabolic state of the training subject based on the blood glucose time series curve, the fasting insulin content, and the glycosylated hemoglobin level, and determine the effective physical activity intensity of the training subject based on the metabolic state; an energy consumption analysis module, configured to measure the body composition and energy consumption rate of the training subject, identify the energy consumption characteristics of the training subject based on the body composition and the energy consumption rate, and extract the personalized metabolic characteristics of the training subject based on the body composition and the energy consumption characteristics; a plan generating module, configured to create an adaptive training plan for the training subject according to the effective physical activity intensity and the personalized metabolic characteristics, and to set a training feedback unit for the training subject based on the adaptive training plan; a program optimization module, configured to calculate an immediate effect score of the adaptive training program based on the fasting insulin and the blood glucose time series curve, and to set an adaptive program optimization mechanism of the adaptive training program according to the immediate effect score and the training feedback unit; The final training module is used to combine the adaptive training plan, the immediate effect score and the adaptive program optimization mechanism to perform insulin sensitivity enhancement training for the training subject and obtain insulin sensitivity enhancement training results.

[0016] Compared with the problems described in the background art, the embodiments of the present invention obtain continuous blood glucose monitoring values ​​collected by the training subject under the glucose load experiment to construct the blood glucose time series curve of the training subject, thereby accurately assessing the insulin sensitivity of the training subject and tailoring a personalized insulin sensitivity enhancement training program for the training subject; further, the embodiments of the present invention identify the metabolic state of the training subject based on the blood glucose time series curve, the fasting insulin content and the glycated hemoglobin level, determine the effective physical activity intensity of the training subject, and stimulate the pancreatic beta cells to secrete insulin and increase the amount of insulin secretion; the embodiments of the present invention identify the energy consumption characteristics of the training subject based on the body composition and the energy consumption rate, and can predict the changing trend of insulin sensitivity in advance and adjust the training program in time; further, the embodiments of the present invention extract the personalized metabolic characteristics of the training subject based on the body composition and the energy consumption characteristics, which can help the training subject achieve better training results within a limited time; the embodiments of the present invention create an adaptive training plan for the training subject based on the effective physical activity intensity and the personalized metabolic characteristics, which can better stimulate the body's metabolic response, promote fat metabolism, increase muscle mass, and thereby improve Insulin sensitivity; further, the embodiment of the present invention provides the training subject with a training feedback unit based on the adaptive training plan, which can provide the training subject with periodic summaries and suggestions, helping them to better understand their physical condition and training progress, and at the same time avoid injuries and fatigue caused by overtraining; the embodiment of the present invention calculates the immediate effect score of the adaptive training plan based on the fasting insulin and the blood glucose time series curve, which helps to improve the individual's training compliance, enable them to more actively participate in training, and thus better achieve long-term improvement in insulin sensitivity; further, the embodiment of the present invention provides an adaptive program optimization mechanism for the adaptive training plan based on the immediate effect score and the training feedback unit, which can accurately adjust the intensity and method of insulin sensitivity enhancement training and improve the efficiency of insulin sensitivity improvement; finally, the embodiment of the present invention combines the adaptive training plan, the immediate effect score and the adaptive program optimization mechanism to perform insulin sensitivity enhancement training for the training subject, obtain insulin sensitivity enhancement training results, and significantly improve the pertinence and effectiveness of insulin sensitivity enhancement training, effectively meet the differentiated training needs of individuals, improve the individual's blood glucose regulation ability and reduce the risk of metabolic syndrome. Therefore, the insulin sensitivity enhancement training method and system provided by the embodiments of the present invention can effectively meet the differentiated training needs of individuals and improve the enhancement effect of insulin sensitivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1A schematic diagram of a flow chart of an insulin sensitivity enhancement training method provided in one embodiment of the present invention; Figure 2 This is a schematic diagram of modules for implementing the insulin sensitivity enhancement training method provided in one embodiment of the present invention.

[0018] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0019] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] The present application provides an insulin sensitivity enhancement training method. The execution entity of the insulin sensitivity enhancement training method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the present application. In other words, the insulin sensitivity enhancement training method can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0021] Example 1 Reference Figure 1 FIG. 1 is a flow chart of a method for enhancing insulin sensitivity training according to an embodiment of the present invention. In this embodiment, the method for enhancing insulin sensitivity training includes: S1. Obtain continuous blood glucose monitoring values ​​collected from a training subject during a glucose load experiment to construct a blood glucose time series curve of the training subject, and test the fasting insulin and glycosylated hemoglobin of the training subject to obtain the fasting insulin content and glycosylated hemoglobin level.

[0022] The embodiments of the present invention obtain continuous blood glucose monitoring values ​​collected by training subjects during a glucose load test to construct a blood glucose time series curve for the training subjects, thereby accurately assessing the training subjects' insulin sensitivity and tailoring a personalized insulin sensitivity enhancement training program for the training subjects. The training subjects refer to individuals participating in insulin sensitivity enhancement training, and can be healthy people or people with insulin resistance-related problems (such as obesity, prediabetes, etc.). The glucose load test refers to a test method for assessing the human body's ability to metabolize carbohydrates. The continuous blood glucose monitoring values ​​refer to data obtained by real-time, continuous monitoring of the training subjects' blood glucose using a continuous blood glucose monitoring system. The blood glucose time series curve refers to a curve drawn with time as the horizontal axis and the continuous blood glucose monitoring values ​​as the vertical axis. Through this curve, the rise in blood glucose after ingestion of a glucose load, the time and value of the peak, the subsequent decline process, and the recovery to normal levels can be clearly seen.

[0023] Exemplarily, continuous blood glucose monitoring values ​​collected from the training subjects under a glucose load experiment are obtained. For example, the fasting blood glucose value of the training subjects is recorded at 8:00 in the morning as the initial data. The training subjects are then asked to orally take 300 ml of a solution containing 75 grams of anhydrous glucose within 5 minutes. The continuous blood glucose monitoring device is set to automatically collect the blood glucose value of the training subjects every 2 minutes. The data is collected continuously for 180 minutes to obtain 90 sets of data to form a continuous blood glucose monitoring value.

[0024] Optionally, the blood glucose time series curve of the training subject can be constructed using a drawing function in R language.

[0025] Furthermore, embodiments of the present invention can help determine the enhanced insulin sensitivity and long-term improvement in blood sugar control of the training subject by testing the training subject's fasting insulin and glycated hemoglobin to obtain fasting insulin content and glycated hemoglobin levels. The fasting insulin content refers to the concentration of insulin in the blood when the human body is fasting. Insulin is a protein hormone secreted by pancreatic beta cells in the pancreas and is used to regulate blood sugar levels. The glycated hemoglobin level refers to the percentage of glycated hemoglobin in the blood to the total hemoglobin. Glycated hemoglobin is a stable compound formed by the non-enzymatic combination of hemoglobin and glucose in the blood. Since the lifespan of red blood cells is approximately 120 days, the glycated hemoglobin level reflects the average blood sugar level over the past 2-3 months.

[0026] Optionally, the fasting insulin content of the training subject can be detected by radioimmunoassay, and the glycated hemoglobin level of the training subject can be detected by high performance liquid chromatography.

[0027] S2. Identify the metabolic state of the training subject according to the blood glucose time series curve, the fasting insulin content, and the glycosylated hemoglobin level, and determine the effective physical activity intensity of the training subject based on the metabolic state.

[0028] The embodiment of the present invention can help assess diabetes risk by identifying the metabolic state of the training subject based on the blood glucose time series curve, the fasting insulin content, and the glycated hemoglobin level. Insulin sensitivity refers to the sensitivity and responsiveness of the body's tissue cells to the effects of insulin. High insulin sensitivity means that tissue cells respond well to insulin. A small amount of insulin can prompt cells to effectively absorb and utilize glucose, keeping blood glucose within a normal range. Conversely, decreased insulin sensitivity indicates a weakened cell response to insulin. Even if there are normal or even high levels of insulin in the body, the cell's ability to absorb and utilize glucose will decrease, leading to increased blood glucose.

[0029] As an embodiment of the present invention, identifying the metabolic state of the training subject based on the blood glucose time series curve, the fasting insulin content, and the glycosylated hemoglobin level includes: identifying a fasting blood glucose value and a blood glucose peak value in the blood glucose time series curve; Based on the fasting blood glucose value and the blood glucose peak value, performing stage quantization processing on the blood glucose time series curve to obtain a staged blood glucose curve; extracting metabolic evaluation indicators of the staged blood glucose curves; identifying the metabolic phenotype of the training subject by combining the metabolic evaluation index, the fasting insulin content, and the glycosylated hemoglobin level; calculating a metabolic score of the training subject within the metabolic phenotype; Based on the metabolic score and the metabolic phenotype, a metabolic state of the training subject is identified.

[0030] Among them, the fasting blood glucose value refers to the blood glucose concentration measured by venous plasma or a calibrated continuous blood glucose monitoring device after the training subject has not consumed calories for at least 8 hours. The blood glucose peak refers to the highest blood glucose value that appears in the blood glucose time series curve after the start of eating, which generally occurs 0.5-2 hours after eating, for example, the maximum blood glucose concentration value that appears within 120 minutes after the start of eating. The stage quantification processing refers to the process of dividing the blood glucose time series curve into different stages according to characteristics such as fasting blood glucose value and blood glucose peak, for example, it can be divided into fasting period, rising period, peak plateau period, falling period, etc. The metabolic evaluation index refers to the index extracted from the staged blood glucose curve that can reflect the characteristics of blood glucose metabolism. Quantitative indicators include but are not limited to the difference between fasting blood glucose value and peak blood glucose value, blood glucose rising rate, blood glucose fluctuation amplitude during the peak plateau period, blood glucose decline half-life, area under the curve of each stage, etc. The metabolic phenotype refers to the different types obtained by comprehensively classifying the metabolic characteristics of the training subjects based on multi-dimensional data such as metabolic evaluation indicators, fasting insulin content and glycated hemoglobin level. For example, it can be divided into insulin sensitive type, insulin resistant type, unstable blood glucose fluctuation type, delayed blood glucose regulation type, etc. The metabolic score refers to a value calculated by a weighted formula or a machine learning model based on the performance of the training subjects in various metabolic evaluation indicators, combined with fasting insulin content and glycated hemoglobin level.

[0031] Optionally, the stage quantification processing of the blood glucose time series curve based on the fasting blood glucose value and the blood glucose peak value can be achieved through a non-fixed time window division method. For example, the size and boundary of the time window are dynamically determined according to the inherent characteristics of the blood glucose time series curve, such as the changing trend of the blood glucose value, the slope change, the extreme point, etc., so as to achieve the stage division and quantification processing of the curve. The metabolic evaluation index of the staged blood glucose curve can be extracted using feature engineering.

[0032] Furthermore, the embodiments of the present invention can stimulate pancreatic beta cells to secrete insulin and increase the amount of insulin secretion by determining the effective physical activity intensity of the training subject based on the metabolic state. The effective physical activity intensity refers to the activity intensity range that can produce positive physiological and metabolic effects on the body during physical activity to achieve specific training goals (such as enhancing insulin sensitivity).

[0033] As an embodiment of the present invention, determining the effective physical activity intensity of the training subject based on the metabolic state includes: Based on the metabolic state, identifying the metabolite level, gene expression and protein activity of the training subject; Analyzing the metabolic regulation mechanism of the training subject and identifying the metabolic pathway of the training subject based on the metabolite level, the gene expression and the protein activity; identifying the metabolic energy requirement of the training subject based on the metabolic regulation mechanism and the metabolic pathway; analyzing the metabolic responses of the training subjects at different physical activity intensities; The effective physical activity intensity of the training subject is determined by combining the metabolic energy demand and the metabolic response.

[0034] The metabolite level refers to the intermediate or final product of metabolism, including the content, concentration or change of sugars, lipids, amino acids, nucleotides and their derivatives in the organism, for example, the glucose concentration in the blood, the fatty acid content, the creatinine level in the urine, etc. The gene expression refers to the mRNA expression of core genes related to energy metabolism detected by RNA sequencing (RNA-seq) or qPCR, and the protein activity level refers to the expression of mRNA of core genes related to energy metabolism detected by Western blotting. Phosphorylated protein or enzyme activity detected by blot or ELISA, the metabolic regulation mechanism refers to the feedback network formed by the interaction of metabolites, genes and proteins to ensure the balance, stability and adaptation of the metabolic process to environmental changes. For example, when blood glucose levels rise, insulin secretion increases, activating a series of enzymes and transporters through the insulin signaling pathway to promote the uptake and utilization of glucose by cells, while inhibiting gluconeogenesis and glycogenolysis to lower blood glucose levels. The metabolic pathway refers to a series of highly ordered and interrelated chemical reaction sequences catalyzed by enzymes in cells. The metabolic energy demand refers to the energy required for an organism to maintain normal life activities and physiological functions, including basal metabolism, physical activity, food digestion and absorption, growth and development, tissue repair and other processes. The metabolic reaction refers to the chemical reaction that occurs in the body of a training subject under a specific physical activity intensity. For example, during exercise, the body will increase the catabolic reaction of carbohydrates and fats to provide more energy.

[0035] Optionally, the metabolite level of the training subject can be identified by blood or urine testing, and based on the metabolite level, the gene expression status and the protein activity level, the metabolic regulation mechanism of the training subject can be analyzed by liquid chromatography-mass spectrometry (LC-MS) technology, and the metabolic pathway of the training subject can be identified using the KEGG pathway database. Based on the metabolic regulation mechanism and the metabolic pathway, the metabolic energy requirement of the training subject can be identified by the doubly labeled water method (DLW). In combination with the metabolic energy requirement and the metabolic reaction, the effective physical activity intensity of the training subject can be determined using the heart rate reserve method, where heart rate reserve (HRR) = maximum heart rate (HRmax) - resting heart rate (HRrest). Then, according to different training goals, the target heart rate range is determined. For example, for training aimed at improving aerobic endurance, a target heart rate of 60%-70% of HRR is generally recommended; when the goal is to enhance cardiopulmonary function, the target heart rate can be set to 70%-85% of HRR.

[0036] S3. Measure the body composition and energy expenditure rate of the training subject, identify the energy expenditure characteristics of the training subject based on the body composition and the energy expenditure rate, and extract the personalized metabolic characteristics of the training subject according to the body composition and the energy expenditure characteristics.

[0037] The embodiment of the present invention can intuitively reflect the improvement of body composition caused by training by measuring the body composition and energy consumption rate of the training subject, providing an important reference for the formulation of training plans. The body composition refers to the various components that make up the human body, mainly including fat, muscle, bone, water, minerals, etc., which can be obtained through a body composition analyzer. The energy consumption rate refers to the ratio of the energy consumed per unit time when the human body performs various activities to the basic energy demand or total energy intake.

[0038] Optionally, the training subject's energy expenditure rate may be determined using indirect calorimetry.

[0039] Furthermore, the embodiments of the present invention can predict the changing trend of insulin sensitivity in advance and adjust the training plan in a timely manner by identifying the energy consumption characteristics of the training subject based on the body composition and the energy consumption rate. The energy consumption characteristics refer to the characteristics and patterns exhibited by the training subject in terms of energy consumption. For example, people with a higher body fat percentage will consume more fat for energy in the early stages of aerobic exercise, but as the exercise intensity increases, their exercise performance and energy supply may be limited.

[0040] As an embodiment of the present invention, identifying the energy expenditure characteristics of the training subject based on the body composition and the energy expenditure rate includes: calculating the muscle-to-fat ratio of the training subject based on the body composition; collecting subcutaneous fat thickness measurement data of the training subject, and identifying the fat distribution type of the training subject using the subcutaneous fat thickness measurement data; collecting motion data of the training subject, and identifying the motion pattern of the training subject based on the motion data; Based on the movement pattern, using wavelet transform method to analyze the short-term fluctuation and long-term trend of the energy consumption rate; identifying a fluctuation range of the energy expenditure rate of the training subject based on the short-term fluctuation and the long-term trend; The energy consumption characteristics of the training subject are identified by combining the muscle-to-fat ratio, the fat distribution type, and the energy consumption rate fluctuation amplitude.

[0041] Among them, the muscle-to-fat ratio refers to the ratio of muscle tissue mass to fat tissue mass in the training subject's body; the subcutaneous fat thickness measurement data refers to the subcutaneous fat layer thickness value measured on the training subject's abdomen and limbs using a skinfold thickness meter; the fat distribution type refers to the distribution pattern of fat in the body, including central type (visceral fat type), peripheral type (subcutaneous fat type) and balanced type. For example, a large accumulation of visceral fat and a large waist-to-hip ratio are manifestations of central fat distribution; and the exercise data refers to relevant information of the training subject during exercise collected by various sensor devices. Including but not limited to exercise time, exercise distance, exercise speed, exercise acceleration, heart rate, oxygen uptake, etc., the exercise mode refers to the result of classifying the exercise behavior of the training object based on exercise data using pattern recognition algorithms (such as decision trees, support vector machines, etc.), including aerobic exercise mode, anaerobic exercise mode and mixed exercise mode, such as strength training and sprinting as anaerobic exercise modes. The wavelet transformation method refers to a mathematical signal processing method used to perform multi-scale analysis on energy consumption rate data. The short-term fluctuation refers to the change information within a shorter time scale (such as minutes and hours) extracted from the energy consumption rate data by the wavelet transform method. The long-term trend refers to the overall change direction within a longer time scale (such as weeks, months, and quarters) obtained from the energy consumption rate data by the wavelet transform method. The energy consumption rate fluctuation amplitude refers to the difference between the maximum and minimum values ​​of the energy consumption rate obtained by combining the analysis period of short-term fluctuations and long-term trends.

[0042] Optionally, the identification of the fat distribution type of the training subject using the subcutaneous fat thickness measurement data can be achieved through a cluster analysis algorithm. In combination with the muscle-to-fat ratio, the fat distribution type and the energy consumption rate fluctuation amplitude, the energy consumption characteristics of the training subject can be identified using a multi-parameter model trained by machine learning, such as a random forest model.

[0043] In an optional embodiment of the present invention, the following formula is used to identify the fluctuation amplitude of the energy consumption rate of the training subject based on the short-term fluctuation and the long-term trend: ; Where D represents the fluctuation range of the energy consumption rate of the training subject, Indicates the maximum value of energy consumption rate in short-term fluctuations and long-term trends. It represents the minimum value of energy consumption rate in short-term fluctuation and long-term trend, A represents the energy consumption rate corresponding to short-term fluctuation and long-term trend, k represents the adjustment coefficient, It represents the slope of the long-term trend, b represents the slope, and L represents the long-term trend.

[0044] It should be noted that, in this application, by introducing the long-term trend slope, the fluctuation of energy consumption rate can be more comprehensively reflected. In particular, it should be noted that when the slope of the long-term trend When it is larger, it means that the energy consumption rate is on an upward or downward trend as a whole, e.g. When the absolute value of is greater than 1, the energy consumption rate will have a more obvious upward or downward trend. At this time, the fluctuation amplitude depends not only on the difference between the maximum and minimum values, but also on the degree of change of the trend.

[0045] The embodiments of the present invention can help the training subject achieve better training results within a limited time by extracting the personalized metabolic characteristics of the training subject based on the body composition and the energy expenditure characteristics. The personalized metabolic characteristics refer to the specific energy metabolism characteristics exhibited by each training subject due to factors such as their unique body composition, physiological function, and lifestyle. For example, individuals with low energy consumption have relatively stable energy metabolism, and their bodies can better adapt to different physiological states, such as eating and exercise. However, individuals with high energy consumption may have an imperfect energy metabolism regulation mechanism, which leads to large fluctuations in blood sugar and affects insulin sensitivity.

[0046] As an embodiment of the present invention, extracting the personalized metabolic characteristics of the training subject based on the body composition and the energy expenditure characteristics includes: collecting body composition data and energy consumption characteristic data of the training subject according to the body composition and the energy consumption characteristic; calculating a correlation coefficient between the body composition and the energy expenditure characteristic; Based on the correlation coefficient, a graph neural network is used to construct a correlation map between the body composition data and the energy consumption characteristic data; identifying, based on the association map, a potential relationship between the body composition and the energy expenditure characteristic; Based on the potential relationship, performing dimensionality reduction processing on the body composition data and the energy consumption characteristic data to obtain first dimensionality reduction data and second dimensionality reduction data; The personalized metabolic features of the training subject are extracted from the first dimensionality reduction data and the second dimensionality reduction data.

[0047] Among them, the body composition data refers to the quantitative data of the body composition of the training subject obtained by the bioelectrical impedance analysis (BIA) method, including but not limited to muscle mass, fat mass, body fat percentage, water content, bone density, visceral fat area, etc. The energy consumption characteristic data refers to the energy metabolism-related data of the training subject in different states collected by indirect calorimetry, heart rate monitoring combined with algorithms, accelerometers and other technologies, including resting energy consumption fluctuation data and exercise energy consumption curves. The correlation coefficient refers to a quantitative indicator of the degree of linear correlation between body composition data and energy consumption characteristic data, which is obtained using the Pearson correlation coefficient. The association map refers to a topological structure constructed based on a graph neural network (GNN), with various indicators of body composition data (such as muscle mass, fat mass, etc.) and various parameters of energy consumption characteristic data (such as basal metabolic rate, exercise energy consumption peak, etc.) as nodes, and the correlation coefficient as the weight of the edge. The potential relationship refers to the relationship between the body composition data and the energy consumption characteristic data obtained by the association map. The spectral analysis reveals the non-intuitive and nonlinear causal relationship between body composition data and energy consumption characteristic data, including but not limited to the impact path of specific body composition combinations on energy consumption efficiency, and the feedback regulation mechanism of changes in energy consumption patterns on dynamic changes in body composition. The first dimensionality reduction data refers to the feature vector obtained by mapping high-dimensional body composition data to a low-dimensional space using the linear discriminant analysis (LDA) algorithm for body composition data while retaining core information. The second dimensionality reduction data refers to the low-dimensional feature representation generated after removing redundant information from the energy consumption characteristic data using a deep learning dimensionality reduction method based on the attention mechanism. The personalized metabolic feature refers to a feature set extracted from the first dimensionality reduction data and the second dimensionality reduction data, which can uniquely identify the individual energy metabolic characteristics of the training subject, including but not limited to metabolic rate type (high / low basal metabolic type), energy consumption preference pattern (aerobic metabolism-dominant type / anaerobic metabolism-dominant type), and body composition-energy consumption response characteristics.

[0048] S4. Creating an adaptive training plan for the training subject according to the effective physical activity intensity and the personalized metabolic characteristics, and setting a training feedback unit for the training subject based on the adaptive training plan.

[0049] The embodiment of the present invention creates an adaptive training plan for the training subject based on the effective physical activity intensity and the personalized metabolic characteristics, which can better stimulate the body's metabolic response, promote fat metabolism, increase muscle mass, and thus improve insulin sensitivity. The adaptive training plan refers to a targeted, scientific, and reasonable training program tailored to individual differences such as the training subject's effective physical activity intensity and personalized metabolic characteristics.

[0050] As an embodiment of the present invention, creating an adaptive training plan for the training subject based on the effective physical activity intensity and the personalized metabolic characteristics includes: identifying the metabolic tendency type of the training subject based on the personalized metabolic signature; extracting a metabolic evaluation index of the training subject according to the metabolic tendency type and the effective physical activity intensity; constructing a metabolic assessment matrix for the training subject based on the metabolic evaluation index; Setting the metabolic typing of the training subject according to the metabolic assessment matrix; setting an adaptive exercise type for the training subject based on the metabolic typing and the effective physical activity intensity; Identifying the fatigue index and metabolic flexibility of the training subject during training; setting an adaptive training opportunity for the training subject according to the fatigue index and the metabolic flexibility; An adaptive training plan for the training subject is created by combining the metabolic typing, the adaptive exercise type and the adaptive training opportunity.

[0051] Among them, the metabolic tendency type refers to the specific preference or trend that an individual shows in energy metabolism, such as some people prefer to use fat for energy metabolism when resting or exercising, while others rely more on carbohydrates for energy metabolism. The metabolic evaluation index refers to a quantitative index used to measure the metabolic state of an individual, such as common metabolic evaluation indicators include blood glucose, blood lactate, insulin level, fat oxidation rate, heart rate variability, etc. The metabolic assessment matrix refers to a multidimensional assessment system formed by the comprehensive integration of multiple metabolic evaluation indicators. The metabolic typing refers to the classification of training subjects according to the comprehensive metabolic characteristics reflected by the metabolic assessment matrix, including fat metabolism dominant type, carbohydrate metabolism balanced type, and metabolic flexibility disorder type. The adaptive exercise type refers to the suitable exercise method recommended for the training subject based on the individual's metabolic typing and effective physical activity intensity. For example, for people with fat metabolism dominant type, Long-term aerobic exercise such as jogging and swimming may be more helpful in further improving fat burning efficiency. The fatigue index refers to a quantitative indicator used to measure the degree of physical fatigue of the training subject during training. The metabolic flexibility refers to the ability of an individual to quickly and effectively switch between different energy metabolism pathways. For example, when switching from a resting state to an exercise state, it can quickly switch from fat metabolism to carbohydrate metabolism to provide the body with sufficient energy. The adaptive training timing refers to the optimal time point for training dynamically determined according to the real-time fatigue index and metabolic flexibility of the training subject. When the fatigue index is low, it means that the body has recovered well and has sufficient energy and physical strength for the next training; when the metabolic flexibility is high, it means that the body can use energy more effectively at this moment and adapt to different types and intensities of exercise. Training at this time may achieve better results.

[0052] Optionally, according to the metabolic assessment matrix, the metabolic typing of the training subject can be set by a threshold-based method. For example, when the fat oxidation rate is higher than a certain threshold and the blood glucose and insulin levels are within a specific range, the training subject is classified as a fat metabolism dominant type; if the blood lactate rises rapidly after exercise and recovers slowly, and other relevant indicators meet certain conditions, it can be classified as a metabolic flexibility disorder type, etc. The metabolic flexibility of the training subject during training can be identified by monitoring the training subject's blood glucose, blood lactate, respiratory quotient and other physiological indicators. Based on the metabolic evaluation indicators, the metabolic evaluation matrix of the training subject can be constructed using a convolutional neural network. For example, the metabolic evaluation index data of the training subject is input into a trained CNN model, and the output of the model is the metabolic evaluation matrix of the training subject. The fatigue index of the training subject during training can be identified using a perceived fatigue scale, such as the CR10 scale.

[0053] Furthermore, the embodiment of the present invention provides the training subjects with periodic summaries and suggestions by setting up a training feedback unit based on the adaptive training plan, helping them to better understand their physical condition and training progress, while avoiding injuries and fatigue caused by overtraining. The training feedback unit refers to a system or mechanism for collecting and analyzing training-related information and adjusting and optimizing the training plan based on this information.

[0054] As an embodiment of the present invention, the setting of the training feedback unit for the training subject based on the adaptive training plan includes: Based on the adaptive training plan, setting a plan completion threshold for the training subject; Acquiring the training completion status of the training subject in real time, and configuring a compliance monitor for the training subject based on the plan completion threshold and the training completion status; collecting compliance training data of the training subject according to the compliance monitor; identifying an execution deviation of the training subject based on the compliance training data; Setting an abnormality reminder module for the adaptive training plan according to the execution deviation and the plan completion threshold; Analyzing the deviation risk level of the training subject based on the execution deviation degree, and constructing a progressive intervention mechanism of the adaptive training program according to the deviation risk level; In combination with the progressive intervention mechanism, the abnormality reminder unit and the compliance supervision module, a training feedback unit for the training subject is set.

[0055] The plan completion threshold refers to the minimum qualification standard required to complete the adaptive training plan, such as the required intensity load 10%, the training completion status refers to the training execution data obtained in real time during the training process through multi-source data collection devices (such as smart bracelets, diet record APPs). The compliance monitor refers to an intelligent monitoring device that compares, analyzes, and evaluates the training completion status in real time based on a planned completion threshold, such as a sports bracelet. The compliance training data refers to the data set continuously collected and stored by the compliance monitoring module during the training process for evaluating the quality of training execution, such as the start and end times of each training, the exercise intensity curve, and the details of diet records. The execution deviation refers to the difference between the actual behavior of the training object and the planned completion rule identified by analyzing the compliance training data. The deviation risk level refers to the risk level obtained by quantitatively grading the possible adverse consequences (such as sports injuries, metabolic disorders) that the training object may face through a risk assessment model according to the degree of behavior deviation. For example, when the execution deviation R ≤ 0.2, the level is judged as general; when 0.2 < R ≤ 0.5, the level is judged as acceptable; when R > 0.5, the level is judged as high risk. The progressive intervention mechanism refers to an intelligent response system that automatically triggers different-intensity intervention measures according to the risk level.

[0056] Optionally, based on the adaptable training plan, the planned completion threshold of the training object can be set through the K-Means clustering algorithm. For example, among groups of the same age and similar training bases, if most people can complete 80% of the planned duration in endurance training, the endurance training duration completion threshold of this training object can be initially set to 80%. Based on the planned completion threshold and the training completion status, the compliance monitor of the training object can be configured using a wearable device. According to the execution deviation and the planned completion threshold, the abnormal reminder module of the adaptable training plan can be set through a rule engine. For example, define that "when the execution deviation is greater than 20% and the planned completion threshold is less than 80%, trigger the abnormal reminder rule. The rule engine will match and judge according to the input real-time data to decide whether to issue an abnormal reminder. According to the deviation risk level, the progressive intervention mechanism of the adaptable training plan can be constructed using a fuzzy control algorithm.

[0057] In an optional embodiment of the present invention, based on the compliance training data, the execution deviation of the training object is identified using the following formula: ; where R represents the execution deviation of the training object, m represents the number of samples in the compliance training data, j represents the sample index, represents the measured value of the jth compliance data, represents the standard value corresponding to the compliance training data.

[0058] S5. Calculate the immediate effect score of the adaptive training program based on the fasting insulin and blood glucose time series curves, and set a self-adaptive program optimization mechanism for the adaptive training program according to the immediate effect score and the training feedback unit.

[0059] The embodiment of the present invention calculates the immediate effect score of the adaptive training program based on the fasting insulin and blood glucose time series curves, which helps to improve the individual's training compliance and enable them to participate in training more actively, thereby better achieving long-term improvement in insulin sensitivity. The immediate effect score refers to a quantitative indicator used to measure the effect of the adaptive training program on the training subject at the moment.

[0060] As an embodiment of the present invention, the calculating of the immediate effect score of the adaptive training program based on the fasting insulin and the blood glucose time series curves includes: obtaining the highest blood glucose value in the blood glucose time series curve, and extracting the blood glucose fluctuation characteristics of the training subject based on the blood glucose time series curve; determining the insulin sensitivity index of the training subject according to the maximum blood glucose value and the fasting insulin; identifying the blood glucose-insulin response pattern of the training subject based on the blood glucose fluctuation characteristics and the insulin sensitivity index; setting differentiated evaluation indicators for the adaptive training program according to the blood glucose-insulin response pattern; Determining a training goal for the training subject based on the adaptive training plan, and assigning weights to the differentiated evaluation indicators according to the training goals to obtain indicator weights; Calculate the immediate effect score of the adaptive training program based on the differentiated scoring index and the index weight.

[0061] Among them, the maximum blood glucose value refers to the maximum value of the blood glucose concentration recorded by the blood glucose time series curve; the blood glucose fluctuation characteristics refer to a series of parameters extracted from the blood glucose time series curve that can describe the law and characteristics of blood glucose changes, including blood glucose fluctuation amplitude, fluctuation frequency, duration of blood glucose changes, etc.; the insulin sensitivity index refers to an indicator used to quantify the body's sensitivity to insulin; the blood glucose-insulin response pattern refers to the typical pattern of dynamic interaction between blood glucose level and insulin secretion when the human body ingests glucose or engages in physical activity. For example, the resistance pattern is manifested as blood glucose: rising to 9.5mmol / L in 60 minutes, still higher than 7.0mmol / L at 120 minutes, and insulin : Secretion is delayed and remains at a high level, but blood sugar drops slowly. The differentiated evaluation index refers to a series of specific indicators specially set according to different blood sugar-insulin response modes for evaluating the effectiveness of the training plan. For example, for the rapid response mode, attention is paid to indicators such as blood sugar recovery rate and insulin consumption efficiency; for the slow response mode, more attention is paid to indicators such as the stability of blood sugar fluctuations and the continuity of insulin secretion. The training goal refers to the specific training direction and expected goals formulated for the training subject based on factors such as the physical condition, health needs and expected health effects of the training subject. The indicator weight refers to the relative importance of each differentiated evaluation indicator using the entropy weight method when calculating the immediate effect score of the adaptive training plan.

[0062] Optionally, based on the maximum blood glucose value and the fasting insulin, the insulin sensitivity index of the training subject can be determined using the Matsuda index formula, and based on the blood glucose fluctuation characteristics and the insulin sensitivity index, the blood glucose-insulin response pattern of the training subject can be identified by a decision tree model.

[0063] Furthermore, the embodiment of the present invention sets an adaptive program optimization mechanism for the adaptive training plan based on the immediate effect score and the training feedback unit, thereby accurately adjusting the intensity and method of insulin sensitivity enhancement training and improving the efficiency of insulin sensitivity improvement. The adaptive program optimization mechanism refers to a training management system that can automatically adjust the training plan based on the immediate effect score and feedback of the training subject.

[0064] As an embodiment of the present invention, the self-adaptive scheme optimization mechanism of the adaptive training plan is set according to the immediate effect score and the training feedback unit, including: Performing spatiotemporal alignment processing on the instant effect score and the original data of the training feedback unit to obtain difference data; Based on the difference data, identifying conflicting signals between the immediate effect score and the training feedback unit; Setting a dual-effect verification method of the adaptive training program according to the conflicting signal; Constructing a blood glucose-insulin knowledge graph for the training object; Generating personalized training advice for the training subject using the blood glucose-insulin knowledge graph according to the immediate effect score and the training feedback unit; Creating a training parameter optimizer for the adaptive training plan based on the personalized training advice; In combination with the dual effect verification method and the training parameter optimizer, an adaptive scheme optimization mechanism of the adaptive training plan is set.

[0065] Among them, the difference data refers to the deviation data between the immediate effect score obtained by processing the spatiotemporal alignment algorithm and the original data of the training feedback unit. The contradictory signal refers to a signal that there is a conflict or inconsistency between the immediate effect score and the situation reflected by the training feedback unit. For example, the immediate effect score shows that the training effect is good and various indicators have improved, but the training feedback unit shows that the training subject is physically tired, has discomfort symptoms, or certain physiological indicators have abnormal changes. This contradictory situation is regarded as a contradictory signal. The dual effect verification method refers to a method of verifying the effect of the training plan using two different evaluation methods or from two different angles. For example, on the one hand, objective physiological indicators (such as changes in blood sugar and insulin levels) are used to evaluate the impact of training on body metabolism; on the other hand, the subjective feelings of the training subject (such as fatigue, self-assessment of exercise ability, etc.) are used to comprehensively judge the training effect. The blood glucose-insulin knowledge graph refers to a model that structuredly represents knowledge related to blood glucose and insulin. It integrates a large amount of knowledge about the physiological mechanisms, influencing factors, interrelationships of blood sugar and insulin, and their associations with lifestyles such as training and diet. The personalized training advice refers to training suggestions tailored for the training subjects based on immediate effect scores, training feedback units, and blood sugar-insulin knowledge graphs. The training parameter optimizer refers to a module that adjusts and optimizes various parameters of the adaptive training plan based on personalized training advice. Training parameters include exercise intensity, frequency, duration, nutritional ratios and intake of dietary nutrients, and rest time.

[0066] Optionally, the contradictory signal between the immediate effect score based on the difference data and the training feedback unit can be judged by setting a threshold. For example, the judgment threshold must simultaneously meet the following requirements: the difference degree is greater than 1.5, and the contradictory state lasts for ≥2 consecutive detection cycles. The blood glucose-insulin knowledge graph of the training object can be constructed using the Neo4j tool. The training parameter optimizer of the adaptive training plan based on the personalized training opinions can be created by the gradient descent method.

[0067] S6. In combination with the adaptive training plan, the immediate effect score and the adaptive program optimization mechanism, perform insulin sensitivity enhancement training on the training subject to obtain an insulin sensitivity enhancement training result.

[0068] The embodiment of the present invention combines the adaptive training plan, the immediate effect score and the adaptive scheme optimization mechanism to perform insulin sensitivity enhancement training for the training subject and obtain insulin sensitivity enhancement training results, which can significantly improve the pertinence and effectiveness of insulin sensitivity enhancement training, effectively meet the differentiated training needs of individuals, improve the individual's blood sugar regulation ability and reduce the risk of metabolic syndrome. The insulin sensitivity enhancement training refers to the process of targetedly improving the body's physiological response to insulin through a scientifically designed exercise intervention plan combined with real-time metabolic monitoring and dynamic optimization technology. The insulin sensitivity enhancement training result refers to the comprehensive evaluation result of the training subject's insulin sensitivity and related metabolic indicators after systematic training intervention, for example, the skeletal muscle glucose uptake rate is increased by ≥25% and the liver insulin resistance index is decreased by ≥20%.

[0069] Compared with the problems described in the background art, the embodiments of the present invention obtain continuous blood glucose monitoring values ​​collected by the training subject under the glucose load experiment to construct the blood glucose time series curve of the training subject, thereby accurately assessing the insulin sensitivity of the training subject and tailoring a personalized insulin sensitivity enhancement training program for the training subject; further, the embodiments of the present invention identify the metabolic state of the training subject based on the blood glucose time series curve, the fasting insulin content and the glycated hemoglobin level, determine the effective physical activity intensity of the training subject, and stimulate the pancreatic beta cells to secrete insulin and increase the amount of insulin secretion; the embodiments of the present invention identify the energy consumption characteristics of the training subject based on the body composition and the energy consumption rate, and can predict the changing trend of insulin sensitivity in advance and adjust the training program in time; further, the embodiments of the present invention extract the personalized metabolic characteristics of the training subject based on the body composition and the energy consumption characteristics, which can help the training subject achieve better training results within a limited time; the embodiments of the present invention create an adaptive training plan for the training subject based on the effective physical activity intensity and the personalized metabolic characteristics, which can better stimulate the body's metabolic response, promote fat metabolism, increase muscle mass, and thereby improve Insulin sensitivity; further, the embodiment of the present invention provides the training subject with a training feedback unit based on the adaptive training plan, which can provide the training subject with periodic summaries and suggestions, helping them to better understand their physical condition and training progress, and at the same time avoid injuries and fatigue caused by overtraining; the embodiment of the present invention calculates the immediate effect score of the adaptive training plan based on the fasting insulin and the blood glucose time series curve, which helps to improve the individual's training compliance, enable them to more actively participate in training, and thus better achieve long-term improvement in insulin sensitivity; further, the embodiment of the present invention provides an adaptive program optimization mechanism for the adaptive training plan based on the immediate effect score and the training feedback unit, which can accurately adjust the intensity and method of insulin sensitivity enhancement training and improve the efficiency of insulin sensitivity improvement; finally, the embodiment of the present invention combines the adaptive training plan, the immediate effect score and the adaptive program optimization mechanism to perform insulin sensitivity enhancement training for the training subject, obtain insulin sensitivity enhancement training results, and significantly improve the pertinence and effectiveness of insulin sensitivity enhancement training, effectively meet the differentiated training needs of individuals, improve the individual's blood glucose regulation ability and reduce the risk of metabolic syndrome. Therefore, the insulin sensitivity enhancement training method and system provided by the embodiments of the present invention can effectively meet the differentiated training needs of individuals and improve the enhancement effect of insulin sensitivity.

[0070] Example 2 like Figure 2The figure shows a functional module diagram of the insulin sensitivity enhancement training system of the present invention.

[0071] The insulin sensitivity enhancement training system 200 described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the insulin sensitivity enhancement training system may include a blood glucose analysis module 201, a metabolic state identification module 202, an energy consumption analysis module 203, a plan generation module 204, a program optimization module 205, and a final training module 206. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function. These modules are stored in the electronic device's memory.

[0072] In the embodiment of the present invention, the functions of each module / unit are as follows: The blood glucose analysis module 201 is used to obtain continuous blood glucose monitoring values ​​collected by the training subject during the glucose load experiment to construct a blood glucose time series curve of the training subject, and to detect the fasting insulin and glycosylated hemoglobin of the training subject to obtain the fasting insulin content and glycosylated hemoglobin level; The metabolic state identification module 202 is configured to identify the metabolic state of the training subject based on the blood glucose time series curve, the fasting insulin content, and the glycosylated hemoglobin level, and determine the effective physical activity intensity of the training subject based on the metabolic state; The consumption analysis module 203 is used to measure the body composition and energy consumption rate of the training subject, identify the energy consumption characteristics of the training subject based on the body composition and the energy consumption rate, and extract the personalized metabolic characteristics of the training subject based on the body composition and the energy consumption characteristics; The plan generating module 204 is configured to create an adaptive training plan for the training subject according to the effective physical activity intensity and the personalized metabolic characteristics, and to set a training feedback unit for the training subject based on the adaptive training plan; The program optimization module 205 is used to calculate the immediate effect score of the adaptive training program based on the fasting insulin and the blood glucose time series curve, and set an adaptive program optimization mechanism of the adaptive training program according to the immediate effect score and the training feedback unit; The final training module 206 is used to combine the adaptive training plan, the immediate effect score and the adaptive program optimization mechanism to perform insulin sensitivity enhancement training on the training subject and obtain insulin sensitivity enhancement training results.

[0073] In detail, each module in the insulin sensitivity enhancement training system 200 of the embodiment of the present invention is used in the same manner as above. Figure 1The technical means are the same as the insulin sensitivity enhancement training method described in, and can produce the same technical effects, so I will not go into details here.

[0074] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for enhancing insulin sensitivity training, characterized in that: The method comprises: Obtaining continuous blood glucose monitoring values ​​collected from the training subject during a glucose load experiment to construct a blood glucose time series curve of the training subject, and testing the fasting insulin and glycosylated hemoglobin of the training subject to obtain fasting insulin content and glycosylated hemoglobin level; identifying the metabolic state of the training subject according to the blood glucose time series curve, the fasting insulin content, and the glycosylated hemoglobin level, and determining the effective physical activity intensity of the training subject based on the metabolic state; measuring the body composition and energy expenditure rate of the training subject, identifying the energy expenditure characteristics of the training subject based on the body composition and the energy expenditure rate, and extracting the personalized metabolic characteristics of the training subject based on the body composition and the energy expenditure characteristics; creating an adaptive training plan for the training subject according to the effective physical activity intensity and the personalized metabolic characteristics, and setting a training feedback unit for the training subject based on the adaptive training plan; Calculating an immediate effect score of the adaptive training program based on the fasting insulin and blood glucose time series curves, and setting an adaptive program optimization mechanism of the adaptive training program according to the immediate effect score and the training feedback unit; In combination with the adaptive training plan, the immediate effect score and the adaptive program optimization mechanism, the insulin sensitivity enhancement training of the training subject is performed to obtain an insulin sensitivity enhancement training result.

2. The insulin sensitivity enhancement training method according to claim 1, wherein: The identifying the metabolic state of the training subject according to the blood glucose time series curve, the fasting insulin content and the glycosylated hemoglobin level includes: identifying a fasting blood glucose value and a blood glucose peak value in the blood glucose time series curve; Based on the fasting blood glucose value and the blood glucose peak value, performing stage quantization processing on the blood glucose time series curve to obtain a staged blood glucose curve; extracting metabolic evaluation indicators of the staged blood glucose curves; identifying the metabolic phenotype of the training subject by combining the metabolic evaluation index, the fasting insulin content, and the glycosylated hemoglobin level; calculating a metabolic score of the training subject within the metabolic phenotype; Based on the metabolic score and the metabolic phenotype, a metabolic state of the training subject is identified.

3. The insulin sensitivity enhancement training method according to claim 1, wherein: Determining the effective physical activity intensity of the training subject based on the metabolic state includes: Based on the metabolic state, identifying the metabolite level, gene expression and protein activity of the training subject; Analyzing the metabolic regulation mechanism of the training subject and identifying the metabolic pathway of the training subject based on the metabolite level, the gene expression and the protein activity; identifying the metabolic energy requirement of the training subject based on the metabolic regulation mechanism and the metabolic pathway; analyzing the metabolic responses of the training subjects at different physical activity intensities; The effective physical activity intensity of the training subject is determined by combining the metabolic energy demand and the metabolic response.

4. The insulin sensitivity enhancement training method according to claim 1, wherein: Identifying an energy expenditure characteristic of the training subject based on the body composition and the energy expenditure rate includes: calculating the muscle-to-fat ratio of the training subject based on the body composition; collecting subcutaneous fat thickness measurement data of the training subject, and identifying the fat distribution type of the training subject using the subcutaneous fat thickness measurement data; collecting motion data of the training subject, and identifying the motion pattern of the training subject based on the motion data; Based on the movement pattern, using wavelet transform method to analyze the short-term fluctuation and long-term trend of the energy consumption rate; identifying a fluctuation range of the energy expenditure rate of the training subject based on the short-term fluctuation and the long-term trend; The energy consumption characteristics of the training subject are identified by combining the muscle-to-fat ratio, the fat distribution type, and the energy consumption rate fluctuation amplitude.

5. The insulin sensitivity enhancement training method according to claim 1, wherein: The extracting the personalized metabolic characteristics of the training subject according to the body composition and the energy expenditure characteristics includes: collecting body composition data and energy consumption characteristic data of the training subject according to the body composition and the energy consumption characteristic; calculating a correlation coefficient between the body composition and the energy expenditure characteristic; Based on the correlation coefficient, a graph neural network is used to construct a correlation map between the body composition data and the energy consumption characteristic data; identifying, based on the association map, a potential relationship between the body composition and the energy expenditure characteristic; Based on the potential relationship, performing dimensionality reduction processing on the body composition data and the energy consumption characteristic data to obtain first dimensionality reduction data and second dimensionality reduction data; The personalized metabolic features of the training subject are extracted from the first dimensionality reduction data and the second dimensionality reduction data.

6. The insulin sensitivity enhancement training method according to claim 1, wherein: The step of creating an adaptive training plan for the training subject based on the effective physical activity intensity and the personalized metabolic characteristics includes: identifying the metabolic tendency type of the training subject based on the personalized metabolic signature; extracting a metabolic evaluation index of the training subject according to the metabolic tendency type and the effective physical activity intensity; constructing a metabolic assessment matrix for the training subject based on the metabolic evaluation index; Setting the metabolic typing of the training subject according to the metabolic assessment matrix; setting an adaptive exercise type for the training subject based on the metabolic typing and the effective physical activity intensity; Identifying the fatigue index and metabolic flexibility of the training subject during training; setting an adaptive training opportunity for the training subject according to the fatigue index and the metabolic flexibility; An adaptive training plan for the training subject is created by combining the metabolic typing, the adaptive exercise type and the adaptive training opportunity.

7. The insulin sensitivity enhancement training method according to claim 1, wherein: The step of setting a training feedback unit for the training subject based on the adaptive training plan includes: Based on the adaptive training plan, setting a plan completion threshold for the training subject; Acquiring the training completion status of the training subject in real time, and configuring a compliance monitor for the training subject based on the plan completion threshold and the training completion status; collecting compliance training data of the training subject according to the compliance monitor; identifying an execution deviation of the training subject based on the compliance training data; Setting an abnormality reminder module for the adaptive training plan according to the execution deviation and the plan completion threshold; Analyzing the deviation risk level of the training subject based on the execution deviation degree, and constructing a progressive intervention mechanism of the adaptive training program according to the deviation risk level; In combination with the progressive intervention mechanism, the abnormality reminder unit and the compliance supervision module, a training feedback unit for the training subject is set.

8. The insulin sensitivity enhancement training method according to claim 1, wherein: The calculating the immediate effect score of the adaptive training program based on the fasting insulin and the blood glucose time series curve comprises: obtaining the highest blood glucose value in the blood glucose time series curve, and extracting the blood glucose fluctuation characteristics of the training subject based on the blood glucose time series curve; determining the insulin sensitivity index of the training subject according to the maximum blood glucose value and the fasting insulin; identifying the blood glucose-insulin response pattern of the training subject based on the blood glucose fluctuation characteristics and the insulin sensitivity index; setting differentiated evaluation indicators for the adaptive training program according to the blood glucose-insulin response pattern; Determining a training goal for the training subject based on the adaptive training plan, and assigning weights to the differentiated evaluation indicators according to the training goals to obtain indicator weights; Calculate the immediate effect score of the adaptive training program based on the differentiated scoring index and the index weight.

9. The insulin sensitivity enhancement training method according to claim 1, wherein: The step of setting the adaptive scheme optimization mechanism of the adaptive training plan according to the immediate effect score and the training feedback unit includes: Performing spatiotemporal alignment processing on the instant effect score and the original data of the training feedback unit to obtain difference data; Based on the difference data, identifying conflicting signals between the immediate effect score and the training feedback unit; Setting a dual-effect verification method of the adaptive training program according to the conflicting signal; Constructing a blood glucose-insulin knowledge graph for the training object; Generating personalized training advice for the training subject using the blood glucose-insulin knowledge graph according to the immediate effect score and the training feedback unit; Creating a training parameter optimizer for the adaptive training plan based on the personalized training advice; In combination with the dual effect verification method and the training parameter optimizer, an adaptive scheme optimization mechanism of the adaptive training plan is set.

10. An insulin sensitivity enhancement training system, characterized in that: The system comprises: A blood glucose analysis module is used to obtain continuous blood glucose monitoring values ​​collected by the training subject during the glucose load experiment to construct a blood glucose time series curve of the training subject, and to detect the fasting insulin and glycosylated hemoglobin of the training subject to obtain the fasting insulin content and glycosylated hemoglobin level; a metabolic state identification module, configured to identify the metabolic state of the training subject based on the blood glucose time series curve, the fasting insulin content, and the glycosylated hemoglobin level, and determine the effective physical activity intensity of the training subject based on the metabolic state; an energy consumption analysis module, configured to measure the body composition and energy consumption rate of the training subject, identify the energy consumption characteristics of the training subject based on the body composition and the energy consumption rate, and extract the personalized metabolic characteristics of the training subject based on the body composition and the energy consumption characteristics; a plan generating module, configured to create an adaptive training plan for the training subject according to the effective physical activity intensity and the personalized metabolic characteristics, and to set a training feedback unit for the training subject based on the adaptive training plan; a program optimization module, configured to calculate an immediate effect score of the adaptive training program based on the fasting insulin and the blood glucose time series curve, and to set an adaptive program optimization mechanism of the adaptive training program according to the immediate effect score and the training feedback unit; The final training module is used to combine the adaptive training plan, the immediate effect score and the adaptive program optimization mechanism to perform insulin sensitivity enhancement training for the training subject and obtain insulin sensitivity enhancement training results.

Images