A system, method, electronic device, and storage medium for metabolic assessment

Abstract

The application provides a system, method, electronic device and storage medium for metabolic evaluation, comprising: a static data acquisition module for acquiring static physiological parameters, a dynamic data acquisition module for acquiring dynamic monitoring data and blood glucose recovery data, and a data processing module for correlating and calculating the static physiological parameters, dynamic monitoring data and blood glucose recovery data to obtain a metabolic evaluation result. By incorporating the static physiological parameters, dynamic monitoring data and blood glucose recovery data into a unified correlation calculation framework, metabolic characteristics are extracted from three dimensions of fasting homeostasis, daily dynamic behavior and blood glucose recovery response, which can more comprehensively and accurately reflect the metabolic regulation capacity and dynamic change trend of the subject, and provide reliable data support for metabolic health management.

Description

Technical Field

[0001] This application relates to the field of metabolic assessment technology, and more specifically, to a system, method, electronic device, and storage medium for metabolic assessment. Background Technology

[0002] In existing metabolic assessment techniques, static behavioral data typically reflect basal metabolic characteristics at a specific time by collecting individual physiological parameters such as fasting blood glucose and triglycerides. This type of data is widely used in assessing risk states such as insulin resistance, abnormal glucose and lipid metabolism, and metabolic syndrome, and is one of the most commonly used basic indicators in metabolic health monitoring.

[0003] However, existing methods for assessing static behavioral data can only reflect metabolic status at a single point in time, making it difficult to capture the changing trends and recovery characteristics of an individual's metabolic status during daily dynamic behaviors. Due to the lack of systematic analysis of the relationship between static behavioral data and dynamic metabolic processes, existing technologies cannot effectively assess the interaction between fasting homeostasis indicators and daily behavioral fluctuations, thus limiting a comprehensive assessment of metabolic regulatory capacity and its dynamic trends. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a system, method, electronic device and storage medium for metabolic assessment to overcome the problems in the prior art.

[0005] In a first aspect, embodiments of this application provide a system for metabolic assessment, comprising: A static data acquisition module is used to acquire static physiological parameters; wherein, the static physiological parameters characterize the basal metabolic features at the first acquisition time under fasting conditions; A dynamic data acquisition module is used to acquire dynamic monitoring data and blood glucose recovery data; wherein, the dynamic monitoring data represents the dynamic behavioral characteristics of a second consecutive acquisition time series during a dynamic behavior process; The data processing module is used to perform correlation calculations on the static physiological parameters, the dynamic monitoring data, and the blood glucose recovery data to obtain metabolic assessment results.

[0006] In some technical solutions of this application, the aforementioned dynamic monitoring data includes dynamic physiological characteristics and behavioral event characteristics; the data processing module is used to perform correlation calculations on the static physiological parameters, the dynamic monitoring data, and the blood glucose recovery data to obtain metabolic assessment results, including: The dynamic metabolic state is determined based on the static physiological parameters and the dynamic physiological characteristics. Based on the blood glucose recovery data, determine the blood glucose recovery status; The multimodal trend deviation parameter is determined based on multiple sets of dynamic feature values ​​and their corresponding historical baseline values. Based on the characteristics of the behavioral events, determine the behavioral impact parameters; The metabolic assessment results are generated based on the dynamic metabolic state, the blood glucose recovery state, the multimodal trend deviation parameter, and the behavioral influence parameter.

[0007] In some technical solutions of this application, determining the dynamic metabolic state based on the static physiological parameters and the dynamic physiological characteristics includes: Calculate the triglyceride-glucose index based on the aforementioned static physiological parameters; Determine the consistency score between the dynamic physiological characteristics and the triglyceride-glucose index; The dynamic metabolic state is determined based on the triglyceride-glucose index and the consistency score.

[0008] In some technical solutions of this application, determining the blood glucose recovery status based on the blood glucose recovery data includes: Recovery kinetic parameters are extracted from the dynamic physiological characteristics and the blood glucose recovery data; The blood glucose recovery status is determined based on the blood glucose recovery data, the dynamic physiological characteristics, and the recovery kinetic parameters.

[0009] In some technical solutions of this application, the determination of multimodal trend deviation parameters based on multiple sets of dynamic feature values ​​and their corresponding historical baseline values ​​includes: Based on the dynamic physiological characteristics and the behavioral event characteristics, multiple sets of dynamic feature values ​​are extracted; The multiple sets of dynamic feature values ​​are compared with their respective historical baseline values ​​to determine the degree of deviation of each dynamic feature value. The multimodal trend deviation parameter is determined based on the degree of deviation of each dynamic feature value and its corresponding weight.

[0010] In some technical solutions of this application, the above-mentioned determination of behavioral influence parameters based on the characteristics of the behavioral event includes: Based on the characteristics of each behavioral event, sub-influence parameters for each behavioral event are determined; wherein, the sub-influence parameters characterize the direction and degree of influence of the behavioral event on the metabolic trend. The sub-influence parameters of each behavioral event are fused together to obtain the behavioral influence parameters.

[0011] In some technical solutions of this application, the above system also includes: The impact analysis module is used to perform behavioral impact analysis based on the metabolic assessment results and output the correlation between behavior and metabolic trends.

[0012] Secondly, embodiments of this application provide a method for metabolic assessment, the method comprising: Static physiological parameters are collected through a static data acquisition module; wherein, the static physiological parameters characterize the basal metabolic features at the first acquisition time under fasting conditions. Dynamic monitoring data and blood glucose recovery data are collected through a dynamic data acquisition module; wherein, the dynamic monitoring data represents the dynamic behavioral characteristics of a second consecutive acquisition time series during the dynamic behavior process; The data processing module performs correlation calculations on the static physiological parameters, the dynamic monitoring data, and the blood glucose recovery data to obtain metabolic assessment results.

[0013] Thirdly, embodiments of this application provide an electronic device, a processor, a memory, and a bus. The memory stores machine instructions executed by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine instructions are executed by the processor, the steps of the metabolic assessment method described above are performed.

[0014] Fourthly, embodiments of this application provide a computer storage medium storing a computer program, which, when run by a processor, executes the steps of the metabolic assessment method described above.

[0015] The technical solutions provided by the embodiments of this application may include the following beneficial effects: This application provides a metabolic assessment system, comprising: a static data acquisition module for acquiring static physiological parameters, wherein the static physiological parameters characterize the basal metabolic characteristics at a first acquisition time in a fasting state; a dynamic data acquisition module for acquiring dynamic monitoring data and blood glucose recovery data, wherein the dynamic monitoring data characterizes the dynamic behavioral characteristics of a second consecutive acquisition time series during dynamic behavior; and a data processing module for performing correlation calculations on the static physiological parameters, the dynamic monitoring data, and the blood glucose recovery data to obtain metabolic assessment results.

[0016] This application integrates static physiological parameters, dynamic monitoring data, and blood glucose recovery data into a unified correlation calculation framework by setting up static data acquisition modules, dynamic data acquisition modules, and data processing modules, thereby achieving a comprehensive assessment of an individual's metabolic state. Compared with existing assessment methods that rely solely on a single fasting indicator or a single dynamic signal, this application can jointly extract metabolic features from three dimensions: fasting homeostasis, daily dynamic behavior, and blood glucose recovery response. Through correlation calculation, it reveals the intrinsic relationships between different data dimensions, thus more comprehensively and accurately reflecting the subject's metabolic regulation capacity and providing more reliable data support for metabolic health management.

[0017] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This illustration shows a schematic diagram of a metabolic assessment system provided by an embodiment of this application; Figure 2 A flowchart illustrating a metabolic assessment method provided in an embodiment of this application is shown. Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0021] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0023] In existing metabolic assessment techniques, static behavioral data typically reflect basal metabolic characteristics at a specific time by collecting individual physiological parameters such as fasting blood glucose and triglycerides. This type of data is widely used in assessing risk states such as insulin resistance, abnormal glucose and lipid metabolism, and metabolic syndrome, and is one of the most commonly used basic indicators in metabolic health monitoring.

[0024] However, existing methods for assessing static behavioral data can only reflect metabolic status at a single point in time, making it difficult to capture the changing trends and recovery characteristics of an individual's metabolic status during daily dynamic behaviors. Due to the lack of systematic analysis of the relationship between static behavioral data and dynamic metabolic processes, existing technologies cannot effectively assess the interaction between fasting homeostasis indicators and daily behavioral fluctuations, thus limiting a comprehensive assessment of metabolic regulatory capacity and its dynamic trends.

[0025] Based on this, embodiments of this application provide a system, method, electronic device, and storage medium for metabolic assessment, which are described below through embodiments. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0026] Figure 1 This application illustrates a metabolic assessment system provided by an embodiment of the present application. The system includes a static data acquisition module, a dynamic data acquisition module, and a data processing module. The static data acquisition module is used to collect static physiological parameters of the subject at a specific time when the subject is in a fasting state. These static physiological parameters are a quantitative representation of the subject's fasting basal metabolic level and can reflect the subject's glucose and lipid metabolism characteristics in a basal state without interference from external behaviors such as eating or exercise.

[0027] Specifically, the static data acquisition module can be implemented through in vitro testing devices such as blood glucose meters and blood lipid analyzers, or through hardware such as biochemical sensors integrated into wearable devices. After the subject has fasted for at least 8 hours, blood or tissue fluid samples are collected from the subject at a preset first collection time. Physiological parameters related to basal metabolism are obtained by performing biochemical analysis on the samples.

[0028] Furthermore, the static physiological parameters may include fasting plasma glucose (FPG) and fasting triglyceride (TG). Fasting plasma glucose is used to assess the body's regulation of glucose in a fasting state, and fasting triglyceride is used to assess the lipid metabolism status of a subject in a fasting state. Both can be obtained by finger-prick blood sampling combined with blood glucose test strips and by venous blood sampling combined with enzymatic analysis, respectively, or by simultaneous detection using an integrated multi-parameter biochemical sensor.

[0029] The static physiological parameters acquired by the static data acquisition module are transmitted to the data processing module as one of the basic input data for subsequent dynamic metabolic status assessment. These static physiological parameters characterize the homeostatic level of the subject's basal metabolism in a fasting state, complementing the dynamic monitoring data and blood glucose recovery data acquired by the dynamic data acquisition module, and together constitute the basic data source of the metabolic assessment system of this application.

[0030] The dynamic data acquisition module is used to collect dynamic monitoring data and blood glucose recovery data of subjects during their daily activities. This dynamic monitoring data characterizes the dynamic behavioral characteristics of subjects during a continuous second time series of acquisitions, reflecting the impact of subjects' daily activities, physiological state changes, and behavioral events on metabolism. Dynamic monitoring data includes dynamic physiological characteristics and behavioral event characteristics. Dynamic physiological characteristics consist of continuously acquired physiological signal sequences, including continuous blood glucose monitoring data, PPG data, and activity data. Continuous blood glucose monitoring data is continuously acquired by a CGM sensor worn by the subject, recording a blood glucose value at preset time intervals to form a continuous blood glucose time series, reflecting the continuous changes in the subject's blood glucose level over time. PPG data is acquired by a photoplethysmography (PPG) sensor worn by the subject, including continuous time series of heart rate, blood oxygen saturation, and HRV signals, used to characterize the subject's autonomic nervous system activity and cardiovascular response characteristics. Activity data is acquired by sensors such as accelerometers or gyroscopes in wearable devices, including parameters such as daily steps, activity duration, activity intensity, and ambient light, used to characterize the intensity and regularity of the subject's daily activities. Behavioral event characteristics consist of records of discrete behavioral events, including exercise events, eating events, and medication intervention events. Exercise event data was obtained by subjects through fitness trackers or mobile applications, including exercise type, duration, intensity, and environment. Eating event data was obtained by subjects through mobile applications or smart devices, including the start time and duration of eating. Medication intervention event data was obtained by subjects according to medical advice or automatically collected by the medication management system, including disease type, duration of medication use, and start time of medication administration. The dynamic physiological characteristics and behavioral event characteristics in the dynamic monitoring data reflect the behavioral changes and physiological fluctuations of subjects within the preset collection period from different perspectives, providing a raw data foundation for subsequent determination of dynamic metabolic status, multimodal trend deviation parameters, and behavioral impact parameters.

[0031] In specific implementation, continuous blood glucose monitoring data, PPG data, sleep data, activity data, exercise event data, eating event data, and medication intervention data for at least 14 consecutive days are acquired, along with fasting plasma glucose (FPG) and fasting triglyceride (TG) data corresponding to the continuous blood glucose monitoring period. The continuous monitoring period is divided into daily analysis windows according to natural days, and a trend assessment window is formed by seven consecutive daily analysis windows. Adjacent trend assessment windows slide in 1-day increments. For example, the first trend assessment window is from day 1 to day 7, the second trend assessment window is from day 2 to day 8, and so on. In other optional implementations, the trend assessment window can be set to 3 to 30 days, and the sliding step can be set to 1 to 7 days, with specific parameters determined according to the length of the monitoring data and application requirements.

[0032] Furthermore, blood glucose recovery data characterizes blood glucose recovery events and their associated recovery characteristic parameters identified from continuous blood glucose monitoring data. Blood glucose recovery events are identified by analyzing local peaks in the continuous blood glucose curve and their subsequent trends. The identification rule can be that when a local peak appears in the continuous blood glucose curve and the rate of change of blood glucose after the peak changes from positive to negative or from an increasing trend to a decreasing trend, and continues to decrease or approach the individual blood glucose baseline range within a preset time window, it is determined to be a blood glucose recovery event. Blood glucose recovery events include different types such as postprandial blood glucose recovery events, post-exercise blood glucose recovery events, blood glucose recovery events during sleep, recovery events after long-term blood glucose fluctuations, and blood glucose recovery events after drug intervention. Different types of blood glucose recovery events correspond to blood glucose responses and recovery processes triggered by different external behavioral events. Blood glucose recovery data is used to subsequently determine the blood glucose recovery status and recovery kinetic parameters, and together with dynamic monitoring data, constitutes two parallel data inputs collected by the dynamic data acquisition module. The dynamic data acquisition module continuously collects the aforementioned dynamic monitoring data and blood glucose recovery data within a preset acquisition period through various sensors and recording interfaces in wearable or portable monitoring devices. The acquired data is then transmitted to the data processing module via wireless or wired communication as the basic data input for subsequent correlation calculations.

[0033] The data processing module is used to perform correlation calculations on static physiological parameters, dynamic monitoring data, and blood glucose recovery data to obtain metabolic assessment results. This module can be implemented using hardware such as a microprocessor, digital signal processor, application-specific integrated circuit (ASIC), or a computing unit deployed on a cloud server. It receives various types of data transmitted from the static and dynamic data acquisition modules via wired or wireless communication, and comprehensively processes this data according to preset calculation logic to obtain the metabolic assessment results. The metabolic assessment results indicate the direction of the subject's current overall metabolic trend and the degree of influence of various external behavioral factors on this trend, providing comprehensive data support for metabolic health management.

[0034] In an optional implementation, the data processing module performs correlation calculations on static physiological parameters, dynamic monitoring data, and blood glucose recovery data to generate metabolic assessment results. Specifically, the data processing module first determines the dynamic metabolic state based on static physiological parameters and dynamic physiological characteristics. This dynamic metabolic state characterizes the overall level of the subject's metabolic regulation ability during daily dynamic behaviors, reflecting the degree of matching between static basal metabolic characteristics and dynamic blood glucose behavior. The dynamic metabolic state can be used to determine whether the subject is currently in different states such as early dynamic abnormality, dynamic fluctuation, stable metabolism, or compensatory metabolism, thereby providing a dynamic dimension of reference for assessing the subject's metabolic regulation ability.

[0035] The data processing module then determines the blood glucose recovery status based on the blood glucose recovery data. This blood glucose recovery status is used to characterize the quality of the subject's blood glucose recovery ability and the characteristics of the recovery process. The blood glucose recovery status reflects the recovery behavior characteristics of the subject, such as the speed, stability, and completeness of the recovery to the baseline level after blood glucose fluctuations. By analyzing the blood glucose recovery status, it can be determined whether the subject belongs to the type of rapid recovery, delayed recovery, oscillating recovery, incomplete recovery, or compensatory recovery, thereby providing a reference for assessing the subject's recovery ability and recovery stress.

[0036] The data processing module also determines multimodal trend deviation parameters based on dynamic physiological characteristics and behavioral event characteristics. These parameters characterize the degree of deviation of the subject's multimodal physiological and behavioral state from their historical baseline. They comprehensively measure the difference between the current state and the historical baseline from multiple dimensions, including PPG trend, HRV trend, sleep trend, activity trend, motor behavior trend, and rhythm trend. The multimodal trend deviation parameters can help determine whether the subject's physiological state has deviated significantly and to what extent, thus providing a basis for identifying metabolic abnormality trends.

[0037] The data processing module also determines behavioral impact parameters based on the characteristics of behavioral events. These behavioral impact parameters are used to characterize the direction and degree of influence of external behavioral factors on the metabolic trends of subjects. These external behavioral factors include sleep behavior, exercise behavior, eating behavior, stress behavior, and drug intervention behavior. By analyzing the sub-impact parameters of each behavioral event, it is possible to determine which behaviors have a positive, negative, or neutral impact on metabolic trends, thereby providing a reference for behavioral intervention.

[0038] The data processing module ultimately generates metabolic assessment results based on dynamic metabolic status, blood glucose recovery status, multimodal trend deviation parameters, and behavioral influence parameters. These metabolic assessment results integrate information from four dimensions: metabolic status, recovery capacity, physiological deviation, and behavioral influence. They can comprehensively reflect the direction of the subject's current overall metabolic trend and the degree of influence of various external behavioral factors on this trend, providing comprehensive data support for metabolic health management.

[0039] In an optional implementation, the data processing module determines the dynamic metabolic state based on static physiological parameters and dynamic physiological characteristics. Specifically, the data processing module first calculates the triglyceride-glucose index based on static physiological parameters, including fasting blood glucose and fasting triglyceride levels. The triglyceride-glucose index is obtained by taking the natural logarithm of half the product of the triglyceride and fasting blood glucose levels, and this index is used to reflect the level of basal metabolic risk of the subject in a fasting state.

[0040] In practical implementation, when determining the dynamic metabolic state, the static physiological parameters used are FPG and TG. Therefore, the TyG index is:

[0041] The data processing module also determines a consistency score between dynamic physiological characteristics and the triglyceride-glucose index based on dynamic physiological characteristics. This consistency score is used to measure the degree of matching between dynamic blood glucose behavior represented by dynamic physiological characteristics and static metabolic risk represented by the triglyceride-glucose index. When dynamic blood glucose behavior matches static metabolic risk, the consistency score is high, and vice versa.

[0042] The data processing module determines the dynamic metabolic state based on the triglyceride-glucose index and the consistency score. In specific implementation:

[0043] in: Dynamic metabolic state; TyG risk level; TyG consistency score. Dynamic metabolic status is used to characterize the overall level of a subject's metabolic regulation ability during daily dynamic behaviors. It reflects the coupling relationship between static basal metabolic characteristics and dynamic blood glucose behavior. Dynamic metabolic status can specifically include early dynamic abnormality, mild dynamic fluctuation, stable metabolic status, dynamic-static mismatch, intermediate metabolic status, consistent moderate metabolic abnormality pattern, compensatory metabolic status, partially metabolically consistent status, and typical insulin resistance status. Among them, early dynamic abnormality indicates that dynamic blood glucose fluctuations have become abnormal but static metabolic indicators have not yet increased significantly. Stable metabolic status indicates that both dynamic blood glucose behavior and static metabolic risk are within the normal range and have high consistency. Dynamic-static mismatch indicates that there is a significant mismatch between dynamic blood glucose behavior and static metabolic risk. Compensatory metabolic status indicates that static metabolic risk is high but dynamic blood glucose behavior can still maintain relative stability. Through the above multiple status types, the subject's metabolic regulation ability and its dynamic change trend can be characterized from multiple perspectives, providing basic information on the dynamic dimension for subsequent overall metabolic assessment.

[0044] Furthermore, in specific implementations, the aforementioned dynamic metabolic states can be converted into dynamic state risk values ​​Is(d) according to the degree of abnormality. The dynamic metabolic state risk value increases with the degree of dynamic metabolic abnormality. For example, an exemplary assignment method is as follows: stable metabolic state is assigned a value of 0; mild dynamic fluctuation state is assigned a value of 1; early dynamic abnormal state is assigned a value of 2; dynamic-static mismatch state is assigned a value of 3; intermediate metabolic state is assigned a value of 4; partially metabolically consistent state is assigned a value of 5; consistent moderate metabolic abnormality pattern is assigned a value of 6; compensatory metabolic state is assigned a value of 7; and typical insulin resistance state is assigned a value of 8. These assignments are used to characterize the degree of dynamic metabolic abnormality and are not used for clinical disease diagnosis. In other embodiments, corresponding risk values ​​can also be configured for different dynamic metabolic states based on sample statistical results, expert-defined rules, or trained risk mapping models.

[0045] For the k-th trend assessment window, calculate the mean dynamic state risk:

[0046] Where N is the number of daily analysis windows included in the trend assessment window. Further, a linear fit is performed with the time position of each daily analysis window as the independent variable and the corresponding dynamic metabolic state risk value as the dependent variable, and the slope of the dynamic metabolic risk change corresponding to the k-th trend assessment window is determined according to the following formula:

[0047] Here, Ksk>0 indicates an increase in the degree of dynamic metabolic abnormality, while Ksk<0 indicates an improvement in the dynamic metabolic state. The above dynamic state risk assignment and trend analysis provide quantitative input for the dynamic metabolic dimension of the subsequent calculation of the total metabolic trend index.

[0048] In an optional implementation, the data processing module determines the blood glucose recovery status based on the blood glucose recovery data. Specifically, the data processing module first extracts recovery kinetic parameters from dynamic physiological characteristics and blood glucose recovery data. These recovery kinetic parameters are used to quantify various response characteristics of the subject during the blood glucose recovery process, including recovery half-life, recovery completion time, recovery area parameter, recovery phase oscillation frequency, steady-state fluctuation parameter, rhythm recovery parameter, recovery slope parameter, baseline deviation, and recovery completion rate. Among these, the recovery half-life represents the time required for blood glucose to recover from the peak to the target proportion; the recovery completion time represents the time required for blood glucose to recover to the baseline range; the recovery area parameter represents the area of ​​blood glucose exceeding the baseline during the recovery phase; the recovery phase oscillation frequency represents the degree of repeated rises or secondary fluctuations in blood glucose during the recovery process; the steady-state fluctuation parameter represents the degree of fluctuation in blood glucose within the steady-state window after recovery; the rhythm recovery parameter represents the degree of coupling between recovery ability and diurnal rhythm; the recovery slope parameter represents the rate of blood glucose decline after the peak; the baseline deviation represents the degree of deviation of blood glucose from the individual baseline during the recovery process; and the recovery completion rate represents the proportion of the population that recovers to the target steady-state range within a preset time. The aforementioned recovery kinetic parameters characterize the speed, stability, integrity, and rhythm of the subjects' blood glucose recovery process from different dimensions.

[0049] The data processing module then determines the blood glucose recovery status based on blood glucose recovery data, dynamic physiological characteristics, and extracted recovery kinetic parameters. Blood glucose recovery status characterizes the quality of a subject's blood glucose recovery ability and the characteristics of the recovery process, specifically categorized into several types, including rapid recovery, delayed recovery, oscillating recovery, incomplete recovery, and compensatory recovery. Rapid recovery indicates that the subject has good recovery ability, with blood glucose quickly and stably returning to the baseline range; delayed recovery indicates a significantly prolonged recovery time and slower recovery speed, but ultimately returns to baseline levels; oscillating recovery indicates repeated fluctuations in blood glucose during the recovery process, with unstable recovery and multiple increases or decreases; incomplete recovery indicates that the subject failed to return to the baseline steady-state range, with blood glucose still deviating from the individual baseline after recovery, indicating significant defects in the recovery process; compensatory recovery indicates that the subject's blood glucose can return to the target range, but the recovery time is prolonged, the recovery area is increased, or the steady-state fluctuation is increased, indicating a compensatory burden in the recovery process. By classifying blood glucose recovery status as described above, the data processing module can assess the subject's recovery ability and recovery behavior characteristics from multiple perspectives, such as recovery speed and stability, providing basic information on the recovery dimensions for subsequent overall metabolic assessment.

[0050] In practice,

[0051] in: Blood sugar has returned to normal. This refers to a blood glucose recovery event; This represents continuous dynamic blood glucose characteristics; To recover the set of dynamic parameters.

[0052] Furthermore, in one specific implementation, the data processing module identifies the recovery type corresponding to each blood glucose recovery event based on the blood glucose recovery data, and determines the recovery risk value corresponding to each blood glucose recovery event according to the preset recovery type-risk level mapping relationship.

[0053] The data processing module's process of determining the blood glucose recovery status based on blood glucose recovery data also includes: setting a recovery load value LR(e) for different recovery phenotypes. An exemplary assignment method is: 0 for cooperative recovery, 1 for recovery stress, 2 for compensatory recovery, 3 for delayed recovery, 4 for oscillating recovery, and 5 for incomplete recovery. It should be noted that the recovery risk level is used to represent the relative degree of recovery abnormality corresponding to different recovery types and is not used as a clinical disease diagnosis result. In other embodiments, the recovery risk value corresponding to different recovery types can also be determined based on sample statistical results, expert-defined rules, or a trained risk mapping model.

[0054] For day d, the daily recovery load is calculated based on all blood glucose recovery events on that day:

[0055] Where, n d Let q be the number of GRE scores identified on day d. e Let be the event confidence or event importance weight of the e-th GRE, and LR(e) be the recovery load value of the corresponding recovery phenotype.

[0056] In one implementation, if no valid GRE is identified on a given day, the recovery load for that day is marked as a missing value, and the statistical value from the adjacent valid window is used, or it is not included in the calculation for that day. For the k-th trend assessment window, the mean recovery load IR(k) and the recovery load slope KR(k) are calculated respectively. The proportion of abnormal recovery events is also calculated.

[0057] Here, NGRE represents the total number of valid GREs within the trend assessment window. This calculation method transforms the blood glucose recovery status from a classification result into a numerical recovery load indicator and a trend quantification parameter, providing quantitative input for the recovery dimension of subsequent overall metabolic assessment.

[0058] In an optional implementation, the data processing module determines multimodal trend deviation parameters based on dynamic physiological characteristics and behavioral event characteristics. Specifically, the data processing module first extracts multiple sets of dynamic feature values ​​from the dynamic physiological characteristics and behavioral event characteristics. These multiple sets of dynamic feature values ​​are a quantitative representation of the subject's physiological and behavioral state, and may include PPG trend values, HRV trend values, sleep trend values, activity level trend values, exercise behavior trend values, and rhythm trend values. Among them, the PPG trend value is used to characterize the change trend of the subject's photoplethysmography (PPG) signal over time, reflecting the cardiovascular activity state; the HRV trend value is used to characterize the change trend of the subject's heart rate variability over time, reflecting the autonomic nervous system regulation function; the sleep trend value is used to characterize the change trend of the subject's sleep duration, sleep quality, and sleep regularity over time; the activity level trend value is used to characterize the change trend of the subject's daily activity intensity and activity duration over time; the exercise behavior trend value is used to characterize the change trend of the subject's exercise frequency, exercise intensity, and exercise duration over time; and the rhythm trend value is used to characterize the change trend of the stability and regularity of the subject's diurnal rhythm over time. The aforementioned dynamic characteristic values ​​reflect the temporal changes in the physiological and behavioral states of the subjects from multiple dimensions, including cardiovascular status, autonomic nervous function, sleep patterns, activity intensity, motor behavior, and rhythmic characteristics.

[0059] The data processing module then compares the aforementioned sets of dynamic feature values ​​with their corresponding historical baseline values ​​to determine the degree of deviation of each dynamic feature value. Each dynamic feature value corresponds to a set of historical baseline values, which include the historical baseline mean and the historical baseline standard deviation. The historical baseline mean represents the average level of the dynamic feature value of the subject over a historical period, and the historical baseline standard deviation represents the fluctuation range of the dynamic feature value over a historical period. The data processing module calculates the difference between the current dynamic feature value and the historical baseline mean, and then divides it by the historical baseline standard deviation to obtain the degree of deviation of the dynamic feature value. This degree of deviation is used to quantify the extent to which the current dynamic feature value deviates from its historical normal level. When the degree of deviation is positive, it indicates that the current dynamic feature value is higher than the historical baseline mean; when the degree of deviation is negative, it indicates that the current dynamic feature value is lower than the historical baseline mean. The larger the absolute value of the degree of deviation, the greater the degree of deviation of the current dynamic feature value from the historical baseline. This degree of deviation can help determine whether the subject's physiological state has deviated abnormally.

[0060] The data processing module then determines the multimodal trend deviation parameter based on the degree of deviation of each dynamic feature value and its corresponding weight. Each dynamic feature value corresponds to a feature weight, which is used to characterize the relative importance of the dynamic feature value in assessing multimodal trend deviation. The feature weights of different dynamic feature values ​​can be preset according to their correlation with metabolic assessment. For example, PPG trend values ​​and HRV trend values ​​can be assigned higher weights than sleep trend values ​​and circadian rhythm trend values ​​because cardiovascular status and autonomic nervous function have a more direct correlation with metabolic regulation capacity. The data processing module multiplies the degree of deviation of each dynamic feature value by its corresponding feature weight and then sums them to obtain the multimodal trend deviation parameter. This multimodal trend deviation parameter is used to comprehensively measure the overall deviation of the subject's current multimodal physiological and behavioral state from its own historical baseline. When the parameter approaches zero, it indicates that the subject's current multimodal physiological and behavioral state is basically consistent with the historical baseline. When the parameter is large, it indicates that the subject's current multimodal physiological and behavioral state has significantly deviated from its normal range. The multimodal trend deviation parameters determined by the above method can comprehensively quantify the magnitude of changes in the physiological and behavioral states of subjects from multiple dimensions, providing a quantitative basis for identifying metabolic abnormality trends.

[0061] In practical implementation:

[0062] in: Multimodal trend deviation parameter; The first in the current time window One dynamic feature value; : Individual historical baseline mean; : Individual historical baseline standard deviation; Feature weights.

[0063] Based on trend changes, they are divided into the following three levels:

[0064] Furthermore, in one specific implementation, the data processing module acquires multimodal physiological data within the d-th daily analysis window and extracts multiple daily dynamic features from the multimodal physiological data. These multiple daily dynamic features may include at least two of the following: heart rate features, heart rate variability features, blood oxygenation features, sleep features, activity features, and circadian rhythm features. For example, in a specific implementation, heart rate, HRV, blood oxygenation, sleep, activity level, and circadian rhythm-related dynamic features are extracted within each daily analysis window and standardized based on the individual's historical baseline.

[0065] The standardized deviation of the i-th dynamic feature on day d is:

[0066] Where Xi(d) is the i-th dynamic feature value on the d-th day; The mean of the i-th characteristic during the individual's baseline period; represents the standard deviation of the i-th characteristic during the individual's baseline period; To prevent the default positive number with a denominator of zero.

[0067] In one implementation, the deviation values ​​are oriented in a unified manner based on the relationship between each feature and the direction of metabolic abnormality:

[0068] Where si takes the value 1 or -1, such that "Unified" indicates a change in an unfavorable direction.

[0069] Furthermore, daily multimodal physiological deviation parameters are calculated based on the abnormal deviations corresponding to multiple daily dynamic features:

[0070] Where m is the number of multimodal dynamic features used; The weight of the i-th feature is given; the sum of all weights is 1. The weights can be determined based on the correlation, regression coefficients, feature importance, or expert priors in the training samples. For the k-th trend assessment window, the multimodal deviation mean IM(k) and the multimodal deviation slope KM(k) are calculated.

[0071] In an optional implementation, the data processing module determines behavioral impact parameters based on the characteristics of behavioral events. Specifically, the data processing module first determines sub-impact parameters for each behavioral event based on its characteristics. These sub-impact parameters characterize the direction and degree of influence of the behavioral event on metabolic trends. Behavioral events include types such as sleep behavior, exercise behavior, dietary behavior, stress behavior, and drug intervention behavior, each corresponding to its own sub-impact parameters. Specifically, the sub-impact parameters for sleep behavior characterize the degree of influence of sleep duration, sleep quality, or sleep regularity on the subject's metabolic trends. For example, insufficient sleep can lead to a decline in metabolic regulation, while regular sleep is beneficial for metabolic stability. The sub-impact parameters for exercise behavior characterize the degree of influence of exercise type, exercise intensity, or exercise frequency on the subject's metabolic trends. For example, aerobic exercise helps improve insulin sensitivity, while high-intensity interval training may cause stress-induced blood glucose fluctuations. The sub-impact parameters for dietary behavior characterize the degree of influence of the timing, duration, or composition of food intake on the subject's metabolic trends. For example, a high-carbohydrate diet can lead to a significant increase in postprandial blood glucose, while a low-carbohydrate diet is beneficial for maintaining stable blood glucose levels. Sub-influence parameters of stress behavior are used to characterize the extent to which stressful events or psychological stress affect the metabolic trends of subjects. For example, long-term stress can lead to elevated cortisol levels, thereby affecting glucose and lipid metabolism. Sub-influence parameters of pharmacological intervention behavior are used to characterize the extent to which drug type, drug dosage, or timing of drug administration affect the metabolic trends of subjects. For example, insulin drugs can effectively lower blood glucose, while some hormonal drugs may cause elevated blood glucose.

[0072] For each behavioral event, the data processing module can determine its sub-influence parameters based on at least one of the following: the direction of behavioral change, the magnitude of behavioral change, the duration of behavioral change, and the degree of correlation between the behavioral event and dynamic metabolic changes. Specifically, the direction of behavioral change indicates whether the behavioral event has a positive or negative impact on the metabolic trend; the magnitude of behavioral change indicates the magnitude of the impact on the metabolic trend; the duration of behavioral change indicates the persistence of the impact on the metabolic trend; and the degree of correlation between the behavioral event and dynamic metabolic changes indicates the correlation between the change in the behavioral event and the dynamic metabolic changes. The data processing module then fuses the sub-influence parameters of each behavioral event to obtain the overall behavioral influence parameters. The fusion of sub-influence parameters can be achieved using weighted summation, weighted averaging, or logical combinations based on preset rules. Specifically, each sub-influence parameter can correspond to a fusion weight, which can be preset based on the frequency, intensity, or degree of influence of the behavioral event on metabolism within a preset time period. The data processing module multiplies each sub-influence parameter by its corresponding fusion weight and then sums them to obtain the behavioral influence parameters. These behavioral impact parameters comprehensively characterize the direction and extent of influence of various external behavioral factors on the metabolic trends of subjects, including the direction and extent of influence of sleep behavior, exercise behavior, dietary behavior, stress behavior, and drug intervention behavior on metabolic trends. Through these behavioral impact parameters, the data processing module can identify which behaviors have a positive impact on metabolic trends, which behaviors have a negative impact, and the degree of their respective impacts, thus providing a reference for behavioral interventions in metabolic health management.

[0073] In practice,

[0074] in: Parameters affecting sleep; For parameters affecting motion; Parameters related to the influence of diet; Parameters affected by pressure; These are parameters related to the effects of drugs. Furthermore, in one specific implementation, the effects of sleep, exercise, diet, stress, and drug intervention on dynamic metabolic state and recovery behavior state are calculated separately. Taking type j behavior as an example, a preset time window after the behavioral event is first determined, and the dynamic metabolic risk value, recovery load, and multimodal deviation parameters before and after the behavior are compared to obtain the behavioral effect size.

[0075] in, The dynamic state risk change before and after the j-th type of behavior; To restore the load change before and after the j-th type of behavior; The multimodal deviation changes before and after the j-th type of behavior; Preset weights.

[0076] After unifying the directions, let This indicates that the behavior is associated with improved metabolism. This indicates that the behavior is associated with metabolic deterioration.

[0077] Further combining the frequency of behavior occurrence, duration, and association stability, the behavioral impact parameters are calculated:

[0078] in: Normalized values ​​for the frequency or duration of the behavior; Confidence level of the association between behavioral and metabolic indicators; Let be the behavioral influence parameter for the j-th type of behavior.

[0079] The overall behavioral impact parameters are:

[0080] in, Weights for different categories of behavior.

[0081] In an alternative implementation:

[0082] in: The main trend in overall metabolism; It is a dynamic metabolic state; Blood sugar has returned to normal. For parameters affecting behavior; This is the multimodal trend deviation parameter. The overall metabolic trend is used to characterize the subject's current metabolic state, the source of abnormal recovery behavior, and the direction of influence of behavioral factors. It is divided into five categories according to the overall metabolic change trend:

[0083] Furthermore, in practical implementation, based on dynamic state changes, recovery load changes, multimodal physiological deviation changes, and behavioral influence parameters, the total metabolic trend index for the k-th trend assessment window is calculated:

[0084] in: The slope represents the risk of dynamic metabolic state. To restore the load slope; For multimodal deviation slope; The percentage of abnormal recovery events; This is a parameter affecting overall behavior. For the corresponding weights.

[0085] In one exemplary implementation, the weights can be set to 0.30, 0.30, 0.15, 0.15 and 0.10 respectively; in practical applications, they can also be determined based on the labeled training set using logistic regression, decision trees, support vector machines or other machine learning methods.

[0086] To avoid misjudgment of the trend due to random fluctuations in a single window, the smoothed trend value of (h) consecutive trend evaluation windows is calculated:

[0087] in, The smoothing coefficient is between 0 and 1.

[0088] In one exemplary implementation, the determination rule is as follows.

[0089] 1. Overall metabolic state is stable. The overall metabolic state of output is stable when the following conditions are met:

[0090] Furthermore, the dynamic state risk, recovery load, and multimodal deviation did not continuously exceed their respective abnormal thresholds.

[0091] 2. There is a trend towards adaptive improvement in metabolic state. The output metabolic state shows a tendency to improve when the following conditions are met:

[0092] Furthermore, at least one of the dynamic state risk slope and the recovery load slope is less than zero, and this condition persists for at least two consecutive trend assessment windows.

[0093] 3. The metabolic state shows a progressively deteriorating trend. The metabolic state exhibits a progressively deteriorating trend when the following conditions are met:

[0094] and satisfy

[0095] And the slope of dynamic state risk , Restoring load slope or multimodal deviation slope At least two of the criteria must be met, and there must be at least two consecutive trend assessment windows.

[0096] 4. The metabolic state exhibits a tendency towards recovery stress. When the recovery load slope or the proportion of abnormal recovery events exceeds a preset threshold, but the dynamic state risk has not yet reached the condition of progressive deterioration, the output metabolic state shows a trend of recovery pressure.

[0097] For example: or

[0098] and:

[0099] This indicates that the recovery load has been continuously increasing, but the overall dynamic metabolic state has not yet shown synchronous deterioration.

[0100] 5. The metabolic state exhibits a tendency for behavioral disturbances. When the abnormal total metabolic indicators are mainly concentrated in the short-term effect window after the behavioral event, and the absolute value of the behavioral impact parameter exceeds the preset threshold, but the slope of the dynamic state and the slope of the recovery load do not reach the long-term deterioration condition after removing the behavioral effect window, the output metabolic state shows a behavioral perturbation trend.

[0101] For example:

[0102] Furthermore, the slope of the dynamic state risk after removing the behavior disturbance window satisfies: |KS′(k)|<θS Wherein, KS′(k) represents the dynamic state risk slope recalculated after removing the time window of the action.

[0103] Based on the above criteria, short-term changes caused by short-term sleep deprivation, short-term dietary abnormalities, changes in exercise load, or stress events can be distinguished from a persistent trend of metabolic deterioration.

[0104] In an optional implementation, the system further includes an impact analysis module, which is communicatively connected to the data processing module. This module receives metabolic assessment results generated by the data processing module and performs behavioral impact analysis based on the metabolic assessment results to output the correlation between behavior and metabolic trends.

[0105] Specifically, the impact analysis module, based on the dynamic metabolic state, blood glucose recovery state, multimodal trend deviation parameters, and behavioral impact parameters already determined in the metabolic assessment results, further analyzes the causal relationship between various external behavioral factors and metabolic trends in depth. This includes sleep-related trend analysis, exercise-related trend analysis, diet-related trend analysis, stress-related trend analysis, and intervention-related trend analysis. Specifically, sleep-related trend analysis assesses the direction and extent of the impact of sleep duration, sleep regularity, and sleep quality on metabolic trends; exercise-related trend analysis assesses the direction and extent of the impact of exercise frequency, exercise intensity, and exercise type on metabolic trends; diet-related trend analysis assesses the direction and extent of the impact of meal timing, food composition, and meal regularity on metabolic trends; stress-related trend analysis assesses the direction and extent of the impact of stress factors such as mental stress and emotional fluctuations on metabolic trends; and intervention-related trend analysis assesses the direction and extent of the impact of medications or other interventions on metabolic trends.

[0106] The impact analysis module can identify the specific behavioral categories that lead to changes in the current metabolic trend, and quantify the direction of the impact of the behavior on recovery stress, dynamic stability, and overall metabolic trend. It ultimately outputs the correlation between the behavior and the metabolic trend. This correlation may include information such as the direction of behavioral change, the magnitude of the change, the duration of the change, and the significance of the behavior's impact on the metabolic trend. This information is presented to the user in the form of visual reports, trend graphs, or suggestions, thus providing clear guidance for the subject's personalized health management and behavioral adjustment.

[0107] Furthermore, in specific implementation, after determining the metabolic trend type, the various behavioral influence parameters (B_j) are sorted according to their absolute values, and one or more behavioral factors with the highest correlation strength are selected as candidate influence factors.

[0108] The output should include at least: the current metabolic trend type; the direction of change in dynamic metabolic state; the direction of change in recovery load; the proportion of abnormal recovery events; the main associated behavioral factors; the direction of behavioral influence; the duration of behavioral influence; and the confidence level of the results.

[0109] For example, when the recovery load slope is positive and the proportion of abnormal recovery events continues to rise in two consecutive 7-day trend assessment windows, while the dynamic state risk slope has not increased significantly, and the decrease in sleep duration has a high temporal correlation with the increase in recovery load, the output "There is a trend of recovery pressure in metabolic state" is output, and "sleep changes" are marked as the main associated behavioral factors.

[0110] This implementation method determines the overall metabolic trend by considering the slope, persistence, and proportion of abnormal events within a continuous time window, rather than relying solely on a combination of states at a single moment. This allows it to distinguish between different change patterns such as temporary behavioral disturbances, persistent recovery pressures, progressive deterioration, and adaptive improvement.

[0111] Figure 2 The diagram illustrates a flowchart of a metabolic assessment method provided in an embodiment of this application, wherein the method includes steps S101-S103; specifically: S101. Static physiological parameters are collected through a static data acquisition module; wherein, the static physiological parameters characterize the basal metabolic features at the first collection time under fasting conditions; S102. Dynamic monitoring data and blood glucose recovery data are collected through the dynamic data acquisition module; wherein, the dynamic monitoring data represents the dynamic behavioral characteristics of the second consecutive acquisition time series during the dynamic behavior process; S103. The static physiological parameters, the dynamic monitoring data, and the blood glucose recovery data are correlated and calculated by the data processing module to obtain the metabolic assessment results.

[0112] The dynamic monitoring data includes dynamic physiological characteristics and behavioral event characteristics; the metabolic assessment results obtained by correlating and calculating the static physiological parameters, the dynamic monitoring data, and the blood glucose recovery data through the data processing module include: The dynamic metabolic state is determined based on the static physiological parameters and the dynamic physiological characteristics. Based on the blood glucose recovery data, determine the blood glucose recovery status; The multimodal trend deviation parameter is determined based on multiple sets of dynamic feature values ​​and their corresponding historical baseline values. Based on the characteristics of the behavioral events, determine the behavioral impact parameters; The metabolic assessment results are generated based on the dynamic metabolic state, the blood glucose recovery state, the multimodal trend deviation parameter, and the behavioral influence parameter.

[0113] The step of determining the dynamic metabolic state based on the static physiological parameters and the dynamic physiological characteristics includes: Calculate the triglyceride-glucose index based on the aforementioned static physiological parameters; Determine the consistency score between the dynamic physiological characteristics and the triglyceride-glucose index; The dynamic metabolic state is determined based on the triglyceride-glucose index and the consistency score.

[0114] Determining the blood glucose recovery status based on the blood glucose recovery data includes: Recovery kinetic parameters are extracted from the dynamic physiological characteristics and the blood glucose recovery data; The blood glucose recovery status is determined based on the blood glucose recovery data, the dynamic physiological characteristics, and the recovery kinetic parameters.

[0115] The step of determining the multimodal trend deviation parameter based on multiple sets of dynamic feature values ​​and their corresponding historical baseline values ​​includes: Based on the dynamic physiological characteristics and the behavioral event characteristics, multiple sets of dynamic feature values ​​are extracted; The multiple sets of dynamic feature values ​​are compared with their respective historical baseline values ​​to determine the degree of deviation of each dynamic feature value. The multimodal trend deviation parameter is determined based on the degree of deviation of each dynamic feature value and its corresponding weight.

[0116] The step of determining the behavioral impact parameters based on the behavioral event characteristics includes: Based on the characteristics of each behavioral event, the sub-influence parameters of each behavioral event are determined. The sub-influence parameters of each behavioral event are fused together to obtain the behavioral influence parameters.

[0117] The method also includes performing behavioral impact analysis based on the metabolic assessment results through an impact analysis module, and outputting the correlation between behavior and metabolic trends.

[0118] like Figure 3 As shown, this application provides an electronic device for performing the metabolic assessment method described in this application. The device includes a memory, a processor, a bus, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the metabolic assessment method described above.

[0119] Specifically, the aforementioned memory and processor can be general-purpose memory and processor, without any specific limitations. When the processor runs the computer program stored in the memory, it can execute the aforementioned metabolic evaluation method.

[0120] Corresponding to the metabolic assessment method in this application, this application embodiment also provides a computer storage medium storing a computer program, which is executed by a processor to perform the steps of the above-described metabolic assessment method.

[0121] Specifically, the storage medium can be a general-purpose storage medium, such as a removable disk or hard disk, and when the computer program on the storage medium is run, it can perform the metabolic evaluation method described above.

[0122] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. The system embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interface; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0123] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0124] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0125] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0126] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0127] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A system for metabolic assessment, characterized in that, include: A static data acquisition module is used to acquire static physiological parameters; wherein, the static physiological parameters characterize the basal metabolic features at the first acquisition time under fasting conditions; A dynamic data acquisition module is used to acquire dynamic monitoring data and blood glucose recovery data; wherein, the dynamic monitoring data represents the dynamic behavioral characteristics of a second consecutive acquisition time series during a dynamic behavior process; The data processing module is used to perform correlation calculations on the static physiological parameters, the dynamic monitoring data, and the blood glucose recovery data to obtain metabolic assessment results.

2. The system according to claim 1, characterized in that, The dynamic monitoring data includes dynamic physiological characteristics and behavioral event characteristics; The data processing module is used to perform correlation calculations on the static physiological parameters, the dynamic monitoring data, and the blood glucose recovery data to obtain metabolic assessment results, including: The dynamic metabolic state is determined based on the static physiological parameters and the dynamic physiological characteristics. Based on the blood glucose recovery data, determine the blood glucose recovery status; The multimodal trend deviation parameter is determined based on multiple sets of dynamic feature values ​​and their corresponding historical baseline values. Based on the characteristics of the behavioral events, determine the behavioral impact parameters; The metabolic assessment results are generated based on the dynamic metabolic state, the blood glucose recovery state, the multimodal trend deviation parameter, and the behavioral influence parameter.

3. The system according to claim 2, characterized in that, The step of determining the dynamic metabolic state based on the static physiological parameters and the dynamic physiological characteristics includes: Calculate the triglyceride-glucose index based on the aforementioned static physiological parameters; Determine the consistency score between the dynamic physiological characteristics and the triglyceride-glucose index; The dynamic metabolic state is determined based on the triglyceride-glucose index and the consistency score.

4. The system according to claim 2, characterized in that, Determining the blood glucose recovery status based on the blood glucose recovery data includes: Recovery kinetic parameters are extracted from the dynamic physiological characteristics and the blood glucose recovery data; The blood glucose recovery status is determined based on the blood glucose recovery data, the dynamic physiological characteristics, and the recovery kinetic parameters.

5. The system according to claim 2, characterized in that, The step of determining the multimodal trend deviation parameter based on multiple sets of dynamic feature values ​​and their corresponding historical baseline values ​​includes: Based on the dynamic physiological characteristics and the behavioral event characteristics, multiple sets of dynamic feature values ​​are extracted; The multiple sets of dynamic feature values ​​are compared with their respective historical baseline values ​​to determine the degree of deviation of each dynamic feature value. The multimodal trend deviation parameter is determined based on the degree of deviation of each dynamic feature value and its corresponding weight.

6. The system according to claim 2, characterized in that, The step of determining the behavioral impact parameters based on the behavioral event characteristics includes: Based on the characteristics of each behavioral event, sub-influence parameters for each behavioral event are determined; wherein, the sub-influence parameters characterize the direction and degree of influence of the behavioral event on the metabolic trend. The sub-influence parameters of each behavioral event are fused together to obtain the behavioral influence parameters.

7. The system according to claim 1, characterized in that, The system also includes: The impact analysis module is used to perform behavioral impact analysis based on the metabolic assessment results and output the correlation between behavior and metabolic trends.

8. A method for metabolic assessment, characterized in that, The method includes: Static physiological parameters are collected through a static data acquisition module; wherein, the static physiological parameters characterize the basal metabolic features at the first acquisition time under fasting conditions. Dynamic monitoring data and blood glucose recovery data are collected through a dynamic data acquisition module; wherein, the dynamic monitoring data represents the dynamic behavioral characteristics of a second consecutive acquisition time series during the dynamic behavior process; The data processing module performs correlation calculations on the static physiological parameters, the dynamic monitoring data, and the blood glucose recovery data to obtain metabolic assessment results.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine instructions that the processor executes. When the electronic device is running, the processor communicates with the memory via the bus. When the machine instructions are executed by the processor, they perform the steps of the metabolic assessment method as described in claim 8.

10. A computer storage medium, characterized in that, The computer storage medium stores a computer program that, when executed by a processor, performs the steps of the metabolic assessment method as described in claim 8.

Images