Intelligent nutrition intervention method based on underlying logic

Abstract

The invention relates to the technical field of intelligent health management, in particular to an intelligent nutrition intervention method based on underlying logic, which comprises the following steps: acquiring serum triglyceride, atherophilic lipoprotein cholesterol, anti-arterial lipoprotein cholesterol and total cholesterol concentration, collecting exhaled carbon dioxide release amount, and monitoring fatty acid oxidation rate. According to the method, through blood fat metabolism monitoring data, extraction of blood fat fluctuation characteristics, recognition of key abnormal time points, combination of fatty acid oxidation rate change, quantification of individual metabolic capability, adjustment of dietary fat composition, dietary fiber proportion and protein collocation, optimization of blood fat metabolism states and calculation of fat oxidation rate fluctuation, the fat oxidation rate fluctuation is calculated. According to the method, the influence of the feeding time on the blood fat change is evaluated, the optimal feeding time interval is matched, the dietary intake and the metabolic rhythm are coordinated, a personalized dietary adjustment scheme and the optimal feeding time are synthesized, the individual metabolic demand is matched, the pertinence and the adaptation degree of nutrition intervention are improved, and errors caused by intervention scheme generalization are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent health management, and particularly to an intelligent nutrition intervention method based on underlying logic. Background Art

[0002] The technical field of intelligent health management includes methods for collecting, analyzing, and intervening in health data based on information technology and artificial intelligence. The core content of this technical field is to use information and communication technology, sensing devices, data modeling, and intelligent decision-making systems to dynamically monitor, evaluate, and guide the health status of individuals or groups. Generally speaking, this technical field covers a variety of intelligent health management methods, including physiological parameter monitoring, disease prediction, intelligent diagnosis and treatment assistance, personalized health intervention, and health behavior guidance. Through data mining, health modeling, pattern recognition, and automated intervention, etc., this field provides individualized health management solutions, which are applicable to multiple application scenarios such as chronic disease management, sports rehabilitation, and nutrition intervention.

[0003] Among them, the intelligent nutrition intervention method refers to providing an individualized dietary plan and nutritional intake guidance for an individual based on the individual's physiological indicators, health data, and eating habits, through data analysis, nutritional model construction, and intelligent recommendation algorithms. The implementation of this method usually includes health data collection, nutritional requirement assessment, food composition analysis, nutritional intake planning, and individualized dietary plan generation. Specifically, the intelligent nutrition intervention method uses physiological sensors to obtain the individual's real-time health data, and combines with a nutrition database and a human metabolism model to calculate the energy and micronutrient supply required by the individual. Through food composition analysis methods, the nutritional composition of foods is identified, and combined with intelligent optimization algorithms, the optimal dietary structure is matched, and finally a nutrition intervention plan that meets the individual's health needs is generated.

[0004] The prior art relies on static physiological parameter collection and fails to track the dynamic changes of blood lipid metabolism in real time, resulting in the difficulty of accurately matching the dietary plan to individual needs. The identification of abnormal blood lipids is based on fixed measurements, which may ignore critical change moments and affect the accuracy of intervention. The dietary optimization method mainly relies on general nutritional models and does not fully combine individual metabolic characteristics, resulting in insufficient plan adaptability. The impact of eating time on blood lipid metabolism has not been effectively evaluated, and there is a lack of guidance on the optimal eating time sequence, which affects the effect of nutritional intervention. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose an intelligent nutrition intervention method based on underlying logic.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: An intelligent nutrition intervention method based on underlying logic, comprising the following steps: S1: Obtain the serum triglyceride, pro-atherogenic lipoprotein cholesterol, anti-atherogenic lipoprotein cholesterol, and total cholesterol concentrations, collect the exhaled carbon dioxide release amount, monitor the fatty acid oxidation rate, record the serum ketone body level, analyze the change in liver lipid storage, and record the eating time to form blood lipid metabolism monitoring data; S2: Based on the blood lipid metabolism monitoring data, extract the blood lipid change curves before, during, and after a meal, calculate the fluctuation rate of blood lipid parameters, determine whether it exceeds the threshold, screen the abnormal time points of blood lipid parameters, calculate the change gradient of the fatty acid oxidation rate, evaluate the blood lipid decline rate, analyze the individual lipid metabolism ability, and generate the blood lipid metabolism deviation degree; S3: Based on the blood lipid metabolism deviation degree, adjust the dietary fat composition when the serum triglyceride exceeds the standard, increase the soluble dietary fiber when the pro-atherogenic lipoprotein cholesterol exceeds the standard, and optimize the ratio of protein to antioxidant foods when the anti-atherogenic lipoprotein cholesterol is low to obtain personalized dietary adjustment parameters; S4: Based on the blood lipid metabolism deviation degree, call the individual diet timing data in the intelligent nutrition intervention, analyze the blood lipid change trend, calculate the fluctuation range of the fat oxidation rate, and calculate the optimal eating time interval; S5: Call the personalized dietary adjustment parameters and the optimal eating time interval, compare with the individual eating records, judge the matching situation of the intake structure and time, and calculate the eating behavior matching degree.

[0007] As a further solution of the present invention, the blood lipid metabolism monitoring data includes serum triglyceride concentration, pro-atherogenic lipoprotein cholesterol concentration, anti-atherogenic lipoprotein cholesterol concentration, total cholesterol concentration, exhaled carbon dioxide release amount, fatty acid oxidation rate, serum ketone body level, change in liver lipid storage, and eating time. The blood lipid metabolism deviation degree includes triglyceride metabolism deviation degree, pro-atherogenic lipoprotein cholesterol metabolism deviation degree, anti-atherogenic lipoprotein cholesterol metabolism deviation degree, and total cholesterol metabolism deviation degree. The personalized dietary adjustment parameters include dietary fat composition adjustment parameters, soluble dietary fiber intake parameters, and protein to antioxidant food ratio optimization parameters. The optimal eating time interval includes the optimal breakfast eating time interval, the optimal lunch eating time interval, and the optimal dinner eating time interval. The eating behavior matching degree includes eating structure matching degree and eating time matching degree.

[0008] As a further solution of the present invention, the obtaining steps of the blood lipid metabolism monitoring data are specifically as follows: S101: Obtain the serum triglyceride, pro-atherogenic lipoprotein cholesterol, anti-atherogenic lipoprotein cholesterol, and total cholesterol concentrations, collect the exhaled carbon dioxide release amount, monitor the fatty acid oxidation rate, record the serum ketone body level, analyze the change in liver lipid storage, and record the eating time, extract multiple data, perform standardization processing, calculate the change trend of multiple indicators, and obtain blood lipid metabolism change parameters; S102: Based on the lipid metabolism variation parameters, calculate the influencing factors of fatty acid oxidation rate, extract the change trend of fatty acid oxidation rate, establish the dynamic change relationship of fatty acid oxidation rate, and use the formula: ; Obtain the fatty acid oxidation rate change coefficient through calculation, analyze the changes under different feeding times and blood lipid levels, and obtain the fluctuation range of fatty acid oxidation rate; Wherein, represents the fatty acid oxidation rate change coefficient, represents the serum triglyceride concentration, represents the anti-atherogenic lipoprotein cholesterol concentration, represents the pro-atherogenic lipoprotein cholesterol concentration, represents the exhaled carbon dioxide release amount, represents the lipid metabolism correlation constant, represents the serum ketone body level, represents the liver lipid storage amount, represents the sample quantity; S103: Invoke the fluctuation range of the fatty acid oxidation rate, analyze its distribution on the feeding time axis, calculate the maximum change interval, and at the same time combine the key indicators of the lipid metabolism variation parameters to establish the metabolic time sequence trend and obtain the lipid metabolism monitoring data.

[0009] As a further solution of the present invention, the obtaining steps of the lipid metabolism deviation degree are specifically as follows: S201: Based on the lipid metabolism monitoring data, extract the blood lipid change curves before, during, and after meals, calculate the change trend of blood lipid parameters within different time periods, and at the same time invoke the set blood lipid parameter fluctuation threshold, compare the blood lipid change amplitudes at multiple time points, screen the blood lipid parameter fluctuation intervals exceeding the threshold, and obtain the blood lipid parameter abnormal time points; S202: Invoke the data at the abnormal blood lipid parameter time points, calculate the changes in fatty acid oxidation rate before and after the time points, and use the formula: ; Calculate the fatty acid oxidation rate change gradient, and compare it with the blood lipid decline threshold to obtain the blood lipid decline rate; Wherein, represents the fatty acid oxidation rate change gradient, represents the fatty acid oxidation rate at the th moment, represents the calculation interval step number of the fatty acid oxidation rate change, represents the total cholesterol change amount at the th time step, represents the number of time steps referred to when calculating the blood lipid decline rate; S203: Calculate the individual lipid metabolism ability based on the change gradient of the fatty acid oxidation rate and the blood lipid decline rate, combine the data of the abnormal time point of the blood lipid parameter, compare the blood lipid changes of different individuals during the same monitoring period, calculate the deviation degree of the blood lipid metabolism change, and obtain the blood lipid metabolism deviation degree.

[0010] As a further aspect of the present invention, the steps for obtaining the personalized dietary adjustment parameters are specifically as follows: S301: Based on the blood lipid metabolism deviation degree, detect the levels of serum triglyceride, pro-atherogenic lipoprotein cholesterol, and anti-atherogenic lipoprotein cholesterol, obtain the blood lipid deviation parameters, calculate the excess deviation amount of serum triglyceride, the excess deviation amount of pro-atherogenic lipoprotein cholesterol, and the low deviation amount of anti-atherogenic lipoprotein cholesterol, and combine the individual physiological data and dietary intake to establish a blood lipid metabolism deviation matrix; S302: Invoke the blood lipid metabolism deviation matrix, for the excess deviation amount of serum triglyceride, adjust the dietary fat composition, calculate the optimized fatty acid intake parameters based on the differential fatty acid ratio and triglyceride metabolism characteristics, and calculate the required supplement amount of soluble dietary fiber under the excess deviation amount of pro-atherogenic lipoprotein cholesterol, adjust the synergistic relationship between multiple nutrients, and use the formula: ; Calculate the optimized coefficient of fatty acid intake and the correction value of fiber supplement to obtain the optimized fatty acid ratio and fiber supplement amount; Wherein, represents the adjusted value of fatty acid intake, represents the current triglyceride level, represents the target triglyceride level, represents the fatty acid adjustment coefficient, represents the fatty acid type the influence coefficient on metabolism, represents the fatty acid type the intake amount of, represents the number of fatty acid types, represents the current intake amount of soluble dietary fiber, represents the target intake amount of soluble dietary fiber; S303: Invoke the optimized fatty acid ratio and fiber supplement amount, for the low deviation amount of anti-atherogenic lipoprotein cholesterol, calculate the optimized ratio of protein and the adjustment amount of antioxidant foods, combine the individual basal metabolic rate and energy requirements, and correct the ratio of protein and antioxidant substances intake to obtain the personalized dietary adjustment parameters.

[0011] As a further aspect of the present invention, the steps for obtaining the optimal eating time interval are specifically as follows: S401: Based on the lipid metabolism deviation degree, call the individual dietary time series data, extract the dietary intake time series and the ingested nutrient components, calculate the blood lipid change rate at multiple time points, compare the blood lipid fluctuation values, screen the data points within the time series where the blood lipid fluctuation amplitude exceeds the target range, and construct a blood lipid change trend curve; S402: Based on the blood lipid change trend curve, calculate the fluctuation amplitude of the fat oxidation rate in different time periods, using the formula: ; Calculate the fat oxidation fluctuation amplitude and generate a fat oxidation fluctuation coefficient; Wherein, represents the fat oxidation fluctuation coefficient, represents the fat oxidation rate at the k-th time point, represents the total number of measurement time points, represents the ingested calories at the l-th time point; S403: Based on the fat oxidation fluctuation coefficient, screen the minimum fluctuation interval, extract the corresponding eating time period, and call the blood lipid change trend curve for review to obtain the optimal eating time interval.

[0012] As a further solution of the present invention, the method further includes: S5: Call the personalized dietary adjustment parameters and the optimal eating time interval, compare with the individual eating records, judge the matching situation of the intake structure and time, and calculate the eating behavior matching degree; The eating behavior matching degree includes an eating structure matching degree and an eating time matching degree.

[0013] As a further solution of the present invention, the steps for obtaining the eating behavior matching degree are specifically: S501: Call the personalized dietary adjustment parameters and the optimal eating time interval, extract the intake time points and food types in the individual eating records, compare the dietary structure and recommended eating times at multiple time points, calculate the intake matching error in different time periods, and generate a dietary time matching error value; S502: Based on the dietary time matching error value, score each food type according to the time weight, using the formula: ; Calculate the eating matching degree score and generate an eating matching degree; Wherein, represents the eating matching degree score, represents the individual intake at the i-th moment, represents the recommended intake at the i-th moment, represents the total number of time points, Represents the length of the recommended eating time interval. represents the food adjustment weight at the jth moment, Represents the time point number within the recommended time interval; S503: Based on the eating matching degree, compare the matching degree threshold, determine whether the eating behavior meets the recommended standard, and obtain the eating behavior matching degree.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, blood lipid fluctuation characteristics are accurately extracted through blood lipid metabolism monitoring data, and key abnormal time points are identified. Combined with changes in fatty acid oxidation rate, the individual metabolic capacity is quantified, and the dietary fat composition, dietary fiber ratio and protein combination are adjusted in a targeted manner to optimize the blood lipid metabolism state. The fat oxidation rate fluctuations are dynamically calculated, the impact of meal time on blood lipid changes is evaluated, and the optimal meal time interval is matched to coordinate dietary intake with metabolic rhythm. The personalized dietary adjustment plan is combined with the optimal meal time to accurately match individual metabolic needs, improve the pertinence and adaptability of nutritional intervention, avoid errors caused by the generalization of intervention plans, and enhance the health regulation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the main steps of the present invention; Figure 2 A flow chart of the steps for obtaining blood lipid metabolism monitoring data of the present invention; Figure 3 The flowchart of the steps for obtaining the blood lipid metabolism deviation degree of the present invention; Figure 4 A flow chart of the steps for obtaining personalized dietary adjustment parameters of the present invention; Figure 5 This is a flow chart of the steps for obtaining the optimal eating time interval of the present invention; Figure 6 This is a flow chart of the steps for obtaining the matching degree of eating behavior of the present invention; Figure 7 It is the overall diagnosis and treatment flow chart of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. 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.

[0017] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0018] Embodiment 1 Please refer to Figure 1 , currently, clinical nutrition diagnosis and treatment face problems such as scattered physical sign data, extensive intervention strategies, lack of personalization, and shortage of professional human resources, resulting in a high incidence of chronic diseases related to nutrition and poor implementation of nutritional interventions. To improve the efficiency and accuracy of clinical nutritional interventions, this solution constructs an intelligent nutritional diagnosis and treatment logic model based on body composition, disease status, and multi-dimensional data fusion. It accurately collects body composition data through the body density method, combines individual dietary preferences, exercise levels, solar terms, and environmental characteristics, uses intelligent algorithms to calculate basal metabolism and total energy requirements, adjusts the energy structure according to body fat levels, determines the energy supply ratios of the three major nutrients, and details them into twelve categories of core food compositions. It integrates the theory of the homology of Chinese medicine and food and the solar term meridian model to establish a food selection mechanism. Through nutrient requirement matching, ingredient function ranking, recipe optimization recommendation, and preference feedback and re-optimization, an integrated nutritional intervention recommendation system is formed. Doctors can customize disease and requirement labels, dynamically adjust nutritional intervention plans, improve the compliance and implementation efficiency of the plans, and at the same time support structured data output and scientific research transformation applications. Based on the above logical system, an intelligent nutritional intervention method based on the underlying logic is further proposed, including the following steps: S1: Obtain the concentrations of serum triglyceride, pro-atherogenic lipoprotein cholesterol, anti-atherogenic lipoprotein cholesterol, and total cholesterol, collect the exhaled carbon dioxide release amount, monitor the fatty acid oxidation rate, record the serum ketone body level, analyze the changes in liver lipid storage, and record the eating time to form blood lipid metabolism monitoring data; S2: Based on the blood lipid metabolism monitoring data, extract the blood lipid change curves before, during, and after meals, calculate the fluctuation rate of blood lipid parameters, determine whether it exceeds the threshold, screen the abnormal time points of blood lipid parameters, calculate the change gradient of the fatty acid oxidation rate, evaluate the blood lipid decline rate, analyze the individual lipid metabolism ability, and generate the blood lipid metabolism deviation degree; S3: Based on the blood lipid metabolism deviation degree, adjust the dietary fat composition when serum triglyceride exceeds the standard, increase soluble dietary fiber when pro-atherogenic lipoprotein cholesterol exceeds the standard, and optimize the ratio of protein and antioxidant foods when anti-atherogenic lipoprotein cholesterol is low to obtain personalized dietary adjustment parameters; S4: Based on the degree of lipid metabolism deviation, call the individual dietary timing data in intelligent nutritional intervention, analyze the trend of blood lipid changes, calculate the fluctuation range of fat oxidation rate, and calculate the optimal eating time interval; S5: Call the personalized dietary adjustment parameters and the optimal eating time interval, compare with the individual eating records, judge the matching situation of the intake structure and time, and calculate the eating behavior matching degree.

[0019] In S3, the specific extraction of the blood lipid change curves before, during, and after meals lies in: based on the degree of lipid metabolism deviation, dynamically screen nutrients to adjust the dietary content, so as to achieve more personalized nutritional intervention. Specifically, when the serum triglyceride level exceeds the standard, the system will dynamically adjust the fat composition in the diet, reduce the intake of saturated fatty acids and trans fats, and increase the intake of unsaturated fatty acids (such as Omega-3 fatty acids); when the pro-atherogenic lipoprotein cholesterol exceeds the standard, increase the intake of soluble dietary fiber, such as the fiber from whole grains, vegetables, and fruits, which helps to lower cholesterol levels; when the anti-atherogenic lipoprotein cholesterol is low, the system will optimize the ratio of protein and antioxidant foods in the diet, and appropriately increase the intake of foods rich in antioxidant substances (such as vitamin C, E, β-carotene), such as berries, leafy vegetables, and nuts. These dynamic screenings and adjustments can help individuals obtain more effective interventions during the blood lipid changes, thereby promoting healthy lipid metabolism.

[0020] Blood lipid metabolism monitoring data includes serum triglyceride concentration, pro-atherogenic lipoprotein cholesterol concentration, anti-atherogenic lipoprotein cholesterol concentration, total cholesterol concentration, exhaled carbon dioxide release, fatty acid oxidation rate, serum ketone body level, liver lipid storage change, eating time. The degree of lipid metabolism deviation includes triglyceride metabolism deviation, pro-atherogenic lipoprotein cholesterol metabolism deviation, anti-atherogenic lipoprotein cholesterol metabolism deviation, total cholesterol metabolism deviation. Personalized dietary adjustment parameters include dietary fat composition adjustment parameters, soluble dietary fiber intake parameters, protein and antioxidant food ratio optimization parameters. The optimal eating time interval includes the optimal breakfast eating time interval, the optimal lunch eating time interval, and the optimal dinner eating time interval. The eating behavior matching degree includes eating structure matching degree and eating time matching degree.

[0021] Please refer to Figure 7, The intelligent nutrition intervention method based on underlying logic provides personalized nutrition intervention programs through comprehensive blood lipid metabolism monitoring and dynamic analysis. First, by collecting biomarkers such as serum triglyceride, cholesterol, fatty acid oxidation rate, serum ketone body level, and meal time, detailed blood lipid metabolism monitoring data is formed. Then, based on the blood lipid change curve and fatty acid oxidation rate change, the individual's lipid metabolism ability is evaluated, and the blood lipid fluctuation rate and deviation degree are calculated to identify abnormal time points. For these abnormalities, the dietary structure is intelligently adjusted, such as optimizing the dietary fat composition, increasing soluble dietary fiber, or adjusting the ratio of protein to antioxidant foods. In addition, by analyzing the individual's dietary time series data and blood lipid change trend, the meal time interval is optimized to ensure that the blood lipid change matches the meal timing, further improving the intervention effect. Finally, by combining personalized dietary adjustment parameters and the optimal meal timing, the meal behavior matching degree is calculated, thus achieving precise and efficient nutrition intervention. The innovation of this method lies in combining dynamic data analysis, personalized dietary intervention, and meal timing optimization to provide an all-round and intelligent nutrition intervention system.

[0022] Please refer to Figure 2 , The specific steps for obtaining blood lipid metabolism monitoring data are as follows: S101: Obtain serum triglyceride, pro-atherogenic lipoprotein cholesterol, anti-atherogenic lipoprotein cholesterol, total cholesterol concentration, collect exhaled carbon dioxide release, monitor fatty acid oxidation rate, record serum ketone body level, analyze liver lipid storage changes, and record meal time, extract multiple data, perform standardization processing, calculate the change trends of multiple indicators, and obtain blood lipid metabolism change parameters; First, collect blood samples from the subjects and obtain serum triglyceride ( ), pro-atherogenic lipoprotein cholesterol ( ), anti-atherogenic lipoprotein cholesterol ( ), and total cholesterol concentration ( ) through laboratory tests. Subsequently, collect exhaled samples and detect the release of exhaled carbon dioxide ( ) using an infrared carbon dioxide analyzer to characterize the dynamic changes of the fatty acid oxidation process. At the same time, use a serum ketone body detection kit to measure the serum ketone body level ( ). On the basis of obtaining blood lipid metabolism parameters, further combine liver biopsy or imaging techniques to evaluate the liver lipid storage ( ), and record the meal time of the subjects to establish a time axis association. After obtaining all the data, perform standardization processing on the original data, remove outliers and normalize it to make the data within the range of 0-1 for subsequent calculations. For example, for triglyceride data, assuming its original measured value range is [0.5, 3.0] mmol / L, the standardization formula is: ; Similarly, corresponding normalization operations are performed on other data items. The normalized data can be used to calculate the parameters of lipid metabolism changes. During the specific calculation process, by calculating the change rate of each blood lipid index over a period of time, data at multiple time points are extracted to calculate its change trend. Specifically, if a subject has measured concentrations of 2.0 mmol / L and 1.6 mmol / L at two time points respectively, then its change rate is: ; Similar calculations are also performed on other parameters such as etc., and the overall trend parameter is calculated based on the mean and standard deviation of the change rate. Finally, the parameter of lipid metabolism change is obtained. This result shows that the triglyceride level has decreased by 20% during the measurement period, indicating that the subject may have experienced a fat oxidation process and the lipid metabolism has been adjusted during this period. This value can be used as an important input parameter for subsequent calculation of the fatty acid oxidation rate and provide data support for subsequent metabolic analysis.

[0023] S102: Based on the parameter of lipid metabolism change, calculate the influencing factors of the fatty acid oxidation rate, extract the change trend of the fatty acid oxidation rate, and establish the dynamic change relationship of the fatty acid oxidation rate. Use the formula: ; Obtain the change coefficient of the fatty acid oxidation rate through calculation, analyze the changes under different feeding times and blood lipid levels, and obtain the fluctuation range of the fatty acid oxidation rate; Among them, represents the change coefficient of the fatty acid oxidation rate, represents the serum triglyceride concentration, represents the concentration of anti-atherogenic lipoprotein cholesterol, represents the concentration of pro-atherogenic lipoprotein cholesterol, represents the exhaled carbon dioxide release amount, represents the lipid metabolism correlation constant, represents the serum ketone body level, represents the liver lipid storage, represents the sample size; Specifically, based on the obtained data, the means of serum triglyceride ( ), anti-atherogenic lipoprotein cholesterol ( ), and pro-atherogenic lipoprotein cholesterol ( ) are extracted, and their contributions to the fatty acid oxidation rate are calculated in combination with the exhaled carbon dioxide release amount ( ). Use the formula: ; Among them, is a blood lipid metabolism related constant, which is determined by regression of previous experimental data. For example, select for calculation. Assume that the data of a certain subject at the measurement point is as follows: mmol / L, mmol / L - mmol / L, mmol / min, mmol / L, mmol Then the calculation process is as follows: ; ; ; The result shows that the coefficient of variation of fatty acid oxidation rate in the current metabolic state of the subject is 0.301. This value can be used to evaluate the fluctuation of fatty acid oxidation rate at different feeding times or metabolic states, and calculate its distribution trend in daily metabolism in combination with the time dimension, providing a calculation basis for subsequent analysis.

[0024] S103: Invoke the fluctuation range of fatty acid oxidation rate, analyze its distribution on the feeding time axis, calculate the maximum change interval, and at the same time, combine the key indicators of blood lipid metabolism change parameters to establish a metabolic time series trend and obtain blood lipid metabolism monitoring data.

[0025] First, define time points, such as 7:00 - 9:00 in the morning, 12:00 - 14:00 for lunch, and 18:00 - 20:00 for dinner. Select measured by multiple subjects at different time points, and calculate the maximum change interval. For example, the data of a certain subject at different time points are as follows: Table 1 Table of changes in fatty acid oxidation rate

[0026] As shown in Table 1, by calculating the fluctuation range of each time period, it can be found that the fatty acid oxidation rate is higher at noon and lower in the evening. Therefore, the key indicators of blood lipid metabolism change parameters, such as change trend, can be further combined to establish a metabolic time series trend. The specific process is as follows: 1. Calculate the change rate of at different time points and fit its change trend with a curve; 2. Use the numerical integration method to calculate the cumulative change value of fatty acid oxidation rate on the time axis; 3. Select the time period with the highest fluctuation amplitude, such as 12:00 - 14:00, and analyze whether there are peaks or valleys in the blood lipid changes during this time period; 4. Calculate the daily change parameters of fatty acid oxidation rate to quantify the metabolic time series trend.

[0027] Finally, the blood lipid metabolism monitoring data is established. The results show that the fatty acid oxidation rate reaches the maximum value during lunchtime, while it is relatively low in the evening, which may be related to food intake, energy consumption, and metabolic regulation mechanisms. This data can be used to optimize individualized dietary regulation strategies and serve as a parameter basis for subsequent metabolic interventions.

[0028] Please refer to Figure 3 , and the steps for obtaining the blood lipid metabolism deviation degree are specifically as follows: S201: Based on the blood lipid metabolism monitoring data, extract the blood lipid change curves before, during, and after meals, calculate the change trends of blood lipid parameters in different time periods, and at the same time call the set blood lipid parameter fluctuation thresholds, compare the blood lipid change amplitudes at multiple time points, screen the blood lipid parameter fluctuation intervals exceeding the thresholds, and obtain the abnormal time points of blood lipid parameters; First, extract the blood lipid change data of an individual at different stages before, during, and after meals. In this process, key blood lipid parameters need to be obtained, such as total cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), high-density lipoprotein cholesterol (HDL-C), and triglyceride (TG). The monitoring data of each parameter should have time series characteristics to ensure that its dynamic changes over time can be traced. For data collection in each time period, it should be carried out at fixed time intervals, for example, once every 5 minutes, and at least 30 time points should be recorded to obtain a relatively complete blood lipid change curve. Then, data analysis is performed on the obtained curve to calculate the change trends of each blood lipid parameter in different time periods. The specific operations include: calculating the change rate for each time period, using the change rate formula: ; For example, in the blood lipid monitoring of a certain subject, the total cholesterol (TC) before meal is measured to be 5.2 mmol / L, and the TC increases to 5.8 mmol / L 30 minutes after meal. The time interval is 30 minutes, then: ; Calculate the rate of change at different time points by analogy and draw a trend chart of the change. By setting the fluctuation threshold of blood lipid parameters, compare the amplitude of blood lipid changes at multiple time points, screen the fluctuation intervals of blood lipid parameters that exceed the threshold. The basis for setting the fluctuation threshold of blood lipid parameters usually adopts statistical methods, such as setting based on the standard deviation of historical data of healthy people. For example, if the normal fluctuation range of a certain blood lipid parameter is within ±0.5 mmol / L, then if the change amount of this parameter at a certain moment exceeds 0.5 mmol / L, it is determined that this moment is an abnormal fluctuation point. By screening these abnormal fluctuation points, further obtain the abnormal time points of blood lipid parameters. For example, in the monitoring data of a certain subject, if the change amount of TG at a certain time point is 0.7 mmol / L and the set threshold is 0.5 mmol / L, then this time point is marked as the abnormal time point of blood lipid parameters. Finally, obtain the data of all abnormal time points of blood lipid parameters for subsequent calculation of fatty acid oxidation rate. The result shows that the selected abnormal time points are critical moments in the blood lipid metabolism process, and these moments reflect the situation where the individual's blood lipid level changes exceed the normal range. The subsequent analysis of fatty acid oxidation rate will be based on these time points to further judge the specific degree of metabolic abnormality.

[0029] S202: Call the data in the abnormal time points of blood lipid parameters, calculate the change of fatty acid oxidation rate before and after the time point, and use the formula: ; Calculate the change gradient of fatty acid oxidation rate, and compare it with the blood lipid decline threshold to obtain the blood lipid decline rate; Among them, represents the change gradient of fatty acid oxidation rate, represents the fatty acid oxidation rate at the th moment, represents the number of steps in the calculation interval of the change of fatty acid oxidation rate, represents the total cholesterol change amount of the nd time step, represents the number of time steps referred to when calculating the blood lipid decline rate; First of all, the fatty acid oxidation rate (FAO) is defined as the rate at which fatty acids are oxidized per unit time. By using experimental detection methods, such as indirect calorimetry, the fatty acid oxidation rate data of individuals at different time points are measured. The number of FAO data points within the set time period is and calculate its change, using: ; Among them, represents the fatty acid oxidation rate at the th time point. For example, in a set of experimental data, the fatty acid oxidation rates are: ; Then the fatty acid oxidation rate change term: ; Let , then: ; Further calculate the blood lipid decline rate. Let the value of the total cholesterol change amount (ΔTC) in the monitoring time step be: ; Let , then: ; Finally, the calculation result of the fatty acid oxidation rate change gradient: ; This result indicates that there are certain fluctuations in the fatty acid oxidation ability of the individual, and the degree of this fluctuation will affect the blood lipid metabolism process. In the subsequent steps, it is necessary to further analyze the individual lipid metabolism ability in combination with the blood lipid decline rate.

[0030] S203: Based on the fatty acid oxidation rate change gradient and the blood lipid decline rate, calculate the individual lipid metabolism ability, combine the blood lipid parameter abnormal time point data, compare the blood lipid changes of different individuals in the same monitoring period, calculate the deviation degree of the blood lipid metabolism change, and obtain the blood lipid metabolism deviation degree.

[0031] Based on the above calculated fatty acid oxidation rate change gradient and blood lipid decline rate, further calculate the individual lipid metabolism ability, set the benchmark metabolism ability value. For example, based on the statistical data of healthy people, if the average TC decline rate of healthy people is 0.25 mmol / L, then the deviation degree calculation can be defined as: ; If the TC decline rate of subject C is 0.15 mmol / L, then: ; This result indicates that the blood lipid metabolism ability of subject C has a 40% deviation compared with the normal healthy level, indicating that its blood lipid metabolism process may be affected by external or internal factors, such as eating habits, exercise status or genetic factors. This value can be further used for individual metabolism assessment to develop corresponding adjustment plans.

[0032] Table 2: Experimental data

[0033] Table 2 lists the experimental data, and the results show that there are differences in lipid metabolism capabilities among different individuals. Individuals with a higher FAO change gradient usually correspond to a faster rate of blood lipid decline, while individuals with a larger deviation of blood lipid decline rate from the normal value have a higher degree of blood lipid metabolism deviation. These data can be used to further optimize personalized health management programs to adjust an individual's diet, exercise, and lifestyle habits.

[0034] Please refer to Figure 4 , and the steps for obtaining personalized dietary adjustment parameters are specifically as follows: S301: Based on the degree of blood lipid metabolism deviation, detect the levels of serum triglyceride, pro-atherogenic lipoprotein cholesterol, and anti-atherogenic lipoprotein cholesterol, obtain blood lipid deviation parameters, calculate the excess deviation amount of serum triglyceride, the excess deviation amount of pro-atherogenic lipoprotein cholesterol, and the low deviation amount of anti-atherogenic lipoprotein cholesterol, and establish a blood lipid metabolism deviation matrix in combination with individual physiological data and dietary intake; Measure the specific concentrations of serum triglyceride, pro-atherogenic lipoprotein cholesterol (ApoB-LDL), and anti-atherogenic lipoprotein cholesterol (ApoA1-HDL) respectively. After collecting the data of these indicators, compare them with the set physiological reference values and calculate the blood lipid deviation parameters for each item, that is, calculate the excess deviation amount of serum triglyceride, the excess deviation amount of pro-atherogenic lipoprotein cholesterol, and the low deviation amount of anti-atherogenic lipoprotein cholesterol respectively. Among them, the calculation method of the excess deviation amount is: compare the blood lipid level of the current individual with the target healthy level and calculate its relative deviation. For example, if the target upper limit of triglyceride is set at 1.7 mmol / L and the measured value of a certain subject is 2.5 mmol / L, the excess deviation amount of triglyceride is calculated as follows: ; Similarly, for the pro-atherogenic lipoprotein cholesterol (such as ApoB-LDL), the target upper limit is set at 3.0 mmol / L, and the measured value of a certain subject is 3.8 mmol / L, then the deviation amount is calculated as follows: ; For anti-atherogenic lipoprotein cholesterol (such as ApoA1-HDL), if the target lower limit is 1.0 mmol / L and the measured value of a certain subject is 0.7 mmol / L, then its low deviation amount is calculated as follows: ; Subsequently, combining the individual's physiological data (such as age, weight, gender, basal metabolic rate, etc.) and dietary intake (such as fat intake, ratio of saturated fatty acids to unsaturated fatty acids, dietary fiber intake, etc.), a blood lipid metabolism deviation matrix is constructed. The establishment of this matrix is based on the metabolic characteristics of different blood lipid parameters of the individual, associating the deviation of different blood lipid indicators with their dietary habits and nutritional metabolism capabilities. For example, for individuals with high fat intake but significantly elevated triglycerides, the adjustment of fatty acid ratio should be focused on, while for individuals with elevated pro-atherogenic lipoprotein cholesterol, the dietary fiber intake should be emphasized. Eventually, this blood lipid metabolism deviation matrix can be used for subsequent personalized dietary adjustment calculations.

[0035] S302: Invoke the blood lipid metabolism deviation matrix, adjust the dietary fat composition for the deviation of serum triglyceride exceeding the standard. Based on the differential fatty acid ratio and triglyceride metabolism characteristics, calculate the optimized fatty acid intake parameters, and calculate the required soluble dietary fiber supplementation amount under the deviation of pro-atherogenic lipoprotein cholesterol exceeding the standard, adjust the synergistic relationship among multiple nutrients, using the formula: ; Calculate the fatty acid intake optimization coefficient and fiber supplementation correction value, and obtain the optimized fatty acid ratio and fiber supplementation amount; Among them, represents the fatty acid intake adjustment value, represents the current triglyceride level, represents the triglyceride target level, represents the fatty acid adjustment coefficient, represents the fatty acid type the influence coefficient on metabolism, represents the fatty acid type intake amount, represents the number of fatty acid types, represents the current soluble dietary fiber intake, represents the target soluble dietary fiber intake; First, analyze the current dietary fat composition of the subject, extract the total fat intake per day of the subject and the fatty acid composition therein, including the ratios of saturated fatty acids (SFA), monounsaturated fatty acids (MUFA), and polyunsaturated fatty acids (PUFA), and calculate the metabolic load of the current fatty acid intake level. For example, assume that a subject's total daily fat intake is 80g, with SFA accounting for 40%, MUFA accounting for 35%, and PUFA accounting for 25%. If the study shows that high SFA intake is associated with an increase in triglyceride levels, the adjustment target for the subject's SFA intake can be set to no more than 30%. At this time, the optimized adjusted SFA intake should be calculated: ; Compared with its current SFA intake (80g × 40% = 32g), the reduction should be: ; Next, calculate the optimized fatty acid intake parameters using the formula: ; Where: is the current triglyceride level (such as 2.5 mmol / L), is the target triglyceride level (1.7 mmol / L), is the fatty acid adjustment coefficient, taking 0.5, is the influence coefficient of different fatty acids on metabolism. Assume they are 0.8 (SFA), 0.6 (MUFA), and 0.4 (PUFA) respectively, are the intakes of different fatty acids, which are 32g (SFA), 28g (MUFA), and 20g (PUFA) respectively, is the number of fatty acid types (3 types), is the current soluble dietary fiber intake (such as 15g), is the target soluble dietary fiber intake (such as 30g).

[0036] Substitute into the calculation: ; ; ; ; The calculation results show that the optimized coefficient of the subject's fatty acid intake is 8.23. At the same time, the supplementary requirement of soluble dietary fiber should be increased from the current 15g to the target 30g, that is, an additional 15g should be supplemented.

[0037] Table 3: Calculation Table of Optimized Dietary Parameters

[0038] As shown in Table 3, the personalized dietary adjustment plan is to reduce the SFA intake by 8g and increase the dietary fiber intake by 15g at the same time to achieve the goal of optimizing blood lipid metabolism.

[0039] S303: Call the optimized fatty acid ratio and fiber supplement amount, calculate the optimized protein ratio and the adjusted amount of antioxidant foods for the low deviation of anti-atherogenic lipoprotein cholesterol, and combine the individual basal metabolic rate and energy requirements to correct the ratio of protein and antioxidant substances intake to obtain personalized dietary adjustment parameters.

[0040] First, analyze the individual's current protein intake, including the total protein intake and its sources. For example, distinguish between plant protein and animal protein and calculate their respective intake proportions. For example, if a subject's total daily protein intake is 70 g, with 30 g of plant protein intake (accounting for 43%) and 40 g of animal protein intake (accounting for 57%). Combining with the metabolic characteristics of anti-arterial lipoprotein cholesterol, set the target protein optimization ratio. For example, if the goal is to increase the ApoA1-HDL level, the intake proportion of animal protein rich in essential amino acids should be appropriately increased. For example, the target is adjusted to 65% for animal protein and 35% for plant protein. Calculate the optimized intake as follows: ; ; Comparing with the current intake situation (40 g vs. 30 g), adjustments are needed: ; ; That is, 5.5 g of animal protein (such as fish and poultry protein) needs to be increased daily, and 5.5 g of plant protein (such as beans) needs to be reduced.

[0041] Next, for the adjustment amount of antioxidant foods, it is necessary to calculate the subject's current dietary antioxidant intakes (such as vitamins C, E, polyphenols) and compare the deviation between them and the recommended intake levels. For example, assume a subject's daily vitamin C intake is 50 mg, while the recommended intake is 100 mg, then calculate the supplementation requirement: ; Similarly, if the current vitamin E intake is 7 mg and the recommended intake is 15 mg, then its supplementation requirement: ; In addition, it is also necessary to evaluate polyphenol intake. For example, assume an individual's daily intake is 200 mg, while the recommended intake is 500 mg, then the supplementation requirement: ; Based on the above calculation results, fruits rich in vitamin C (such as citrus fruits), nuts rich in vitamin E (such as almonds), and tea or berry foods rich in polyphenols need to be added in the dietary adjustment.

[0042] Finally, combining with the individual's basal metabolic rate (BMR) and energy requirements, correct the ratio of protein and antioxidant intake. For example, if a subject's BMR is calculated as follows: ; Assume the subject weighs 70 kg, is 175 cm tall, and is 30 years old, then his BMR is calculated as follows: ; Calculate the total energy expenditure (TDEE) based on the activity level (assuming a moderate activity level with a coefficient of 1.55): ; On this basis, calculate the protein requirement according to the protein energy proportion of 15%: ; Combine the aforementioned optimization ratio, adjust the protein source to ensure meeting the individual's metabolic needs, and finally obtain personalized dietary adjustment parameters.

[0043] Table 4: Protein and Antioxidant Adjustment Table

[0044] As shown in Table 4, the adjustment plan includes increasing the intake of animal protein by 5.5 g, reducing the intake of plant protein by 5.5 g, and supplementing vitamin C, vitamin E, and polyphenolic antioxidants to optimize the ApoA1-HDL level and improve the individual's antioxidant capacity.

[0045] Please refer to Figure 5 , and the specific steps for obtaining the optimal eating time interval are as follows: S401: Based on the degree of lipid metabolism deviation, call the individual's dietary time series data, extract the dietary intake time series and the ingested nutrient components, calculate the blood lipid change rate at multiple time points, compare the blood lipid fluctuation values, screen the data points where the blood lipid fluctuation amplitude in the time series exceeds the target range, and construct a blood lipid change trend curve; First, call the individual's dietary time series data, extract each dietary intake time point in the dataset, and obtain the corresponding ingested nutrient components at this time point, including but not limited to specific values of fat, carbohydrates, protein, etc. Subsequently, combined with the individual's blood lipid monitoring data, calculate the change rate of blood lipid concentration at multiple time points, and use the time interval Calculate the blood lipid volatility between adjacent time points , and the calculation method is as follows: ; Among them, represents the blood lipid concentration at time point , with the unit of mmol / L, The value of can be 30 minutes or 1 hour, determined according to the data sampling frequency. After calculating all time points of mmol / L·h , data points with fluctuation amplitudes exceeding the target range are screened out, and the abnormal points are marked. Subsequently, based on the time-series blood lipid change data, a numerical fitting method is used to construct a blood lipid change trend curve. The curve is fitted with a quadratic polynomial or cubic spline interpolation to reflect the continuous change of blood lipid over time. Finally, a complete blood lipid change trend curve is formed. This trend curve is used for subsequent fat oxidation fluctuation analysis. The result shows that the overall trend of blood lipid fluctuation has been constructed, and by removing abnormal data points, the accuracy of fat oxidation rate calculation can be further improved, laying a foundation for the analysis of subsequent steps.

[0046] S402: Based on the blood lipid change trend curve, calculate the fluctuation amplitude of the fat oxidation rate in different time periods, using the formula: ; Calculate the fat oxidation fluctuation amplitude and generate a fat oxidation fluctuation coefficient; Among them, represents the fat oxidation fluctuation coefficient, represents the fat oxidation rate at the k-th time point, represents the total number of measurement time points, represents the calorie intake at the l-th time point; The specific steps are as follows: First, extract the data points from the blood lipid trend curve and calculate the fat oxidation rate at each time point , and its calculation method is: ; Among them, represents the fat oxidation rate conversion coefficient, with the unit of , and its value can be obtained by fitting experimental data. Assume its value is 0.8, is the basic blood lipid level. Assume its value is 1.2 mmol / L. When the blood lipid level at a certain time point is 1.5 mmol / L, the corresponding fat oxidation rate is: ; After calculating the fat oxidation rate at all time points, calculate the fat oxidation rate fluctuation amplitude: ; Among them, is the total number of measurement time points. For example, if there are 10 time points, then calculate for each adjacent pair of points. After summing, calculate the correction factor in combination with the calorie intake at all time points. Assume the calorie intake data is as follows: Table 5 Fat Oxidation Rate and Calorie Intake

[0047] Calculate the correction factor: ; Then calculate the change in the rate of fat oxidation: ; Finally, calculate the coefficient of variation of fat oxidation: ; The result shows that the fluctuation of the fat oxidation rate in the current time period is small, which means that the metabolic state in this time period is relatively stable and can be used as a candidate for the optimal feeding time period. A lower value indicates a smaller fluctuation in fat metabolism after food intake, thus providing a basis for screening the optimal feeding time period in the next step.

[0048] S403: Based on the coefficient of variation of fat oxidation, screen the minimum fluctuation interval, extract the corresponding feeding time period, call the trend curve of blood lipid change for verification, and obtain the optimal feeding time interval.

[0049] First, divide the coefficient of variation of fat oxidation at all time points into intervals. For example, if the coefficient of variation threshold is set , then select the time period that satisfies as the candidate interval. In this example, the calculated result of 9.43 meets the requirements. Therefore, further extract the corresponding time period, that is, all time points with small fluctuations in fat oxidation. As shown in the data in Table 5, the changes from time point 2 to 10 are small. Therefore, the optimal feeding time period can be determined as this time range. Finally, call the trend curve of blood lipid change for verification, compare the blood lipid change rate in the obtained time period. If it meets the target fluctuation range mmol / L·h , then finally determine this time period as the optimal feeding time interval. The result shows that the selected time period meets the requirements of blood lipid metabolism stability and has a small fluctuation in fat oxidation rate, so it can be used as an individualized optimal feeding time period. Eating within this time period can maximize the maintenance of metabolic stability and optimize the utilization efficiency of fat.

[0050] Please refer to Figure 6 , and the specific steps for obtaining the matching degree of eating behavior are as follows: S501: Call the personalized dietary adjustment parameters and the optimal feeding time interval, extract the intake time points and food types in the individual eating records, compare the dietary structure at multiple time points with the recommended feeding time, calculate the intake matching error in the differential time period, and generate a dietary time matching error value; First, read all the eating time points in the individual's eating record and arrange them in chronological order. Then, according to the personalized dietary adjustment parameters, classify and summarize the types of foods consumed at each eating time point and count their corresponding intakes. At the same time, compare with the recommended eating time intervals to find the time points in the individual's eating record that fall within and outside the recommended time intervals, and store these time points in two data sets respectively. For example, if an individual's eating time records are 08:00, 12:30, and 19:00, and the recommended optimal eating time intervals are 07:30 - 09:00, 12:00 - 13:00, and 18:30 - 20:00, then all the eating time points of this individual fall within the recommended time intervals and no additional adjustment is required. If the individual has an additional meal at 10:30, then this time point will be classified into the set of time points outside the recommended interval. Next, compare the intakes at the eating time points within the recommended time intervals with the recommended intakes, and calculate the intake deviation value for each time point. The specific calculation method is to subtract the corresponding recommended intake from the actual intake at each time point. For example, if the recommended breakfast intake is 400g and the actual intake is 500g, then the intake deviation value at this time point is +100g. For the intake time points outside the recommended time intervals, their intake deviation values need to be multiplied by an additional time deviation factor to amplify their impact on the overall matching degree. The time deviation factor can be calculated according to the length of time outside the recommended interval. For example, if the eating time at 10:30 exceeds the recommended breakfast time by 1.5 hours, then its time deviation factor can be set as , and then calculate the dietary time matching error value at this time point. The average value of the matching error values of all time points is the dietary time matching error value. This result indicates that there is a certain deviation between the individual's eating time points and the recommended time intervals, and the matching error value can be used for the calculation of the subsequent eating matching degree score to measure the rationality of the individual's eating behavior.

[0051] S502: Based on the dietary time matching error value, score each food type according to the time weight, using the formula: ; Calculate the eating matching degree score and generate the eating matching degree; Among them, represents the eating matching degree score, represents the individual intake at the i-th moment, represents the recommended intake at the i-th moment, represents the total number of time points, represents the length of the recommended eating time interval, represents the food adjustment weight at the j-th moment, represents the number of time points within the recommended time interval; Formula: ; First, the calculation method of the time weight needs to be determined. This time weight can be set according to the digestion cycle of food, the body's metabolic rhythm, and the degree of deviation of the eating time from the recommended time. For example, high-protein foods (such as eggs and fish) usually have a longer digestion time, and the time weight can be set higher, while carbohydrate foods (such as rice and noodles) are digested faster, and the time weight is relatively lower. Suppose an individual consumes a certain amount of eggs at 08:30 and additional carbohydrates at 10:30. Then, the time weight for eggs can be set to 1.2, and the time weight for carbohydrates can be set to 0.8. When calculating the eating matching score, the square of the difference between the intake at each matching time point and the recommended intake needs to be summed and then divided by the total number of matching time points. For example, in an individual's eating record for a certain meal, there are 3 matching time points, namely (08:00, 350g / 400g), (12:30, 420g / 400g), (19:00, 380g / 400g). Then, the calculation of its squared error term is , and then calculate , getting approximately 33.17. Then, calculate the average weight impact term of the recommended eating time interval length. Suppose the total length of the recommended eating time interval is 8 hours, then its impact term is calculated as . Suppose has an average value of 1.1, then the calculated value of this term is . Finally, calculate the eating matching score . This result indicates that the individual's eating time arrangement is highly consistent with the recommended time interval, indicating that their eating behavior is relatively reasonable. This scoring result will be used for subsequent comparison with the matching threshold to determine whether the individual's eating behavior meets the recommended standard.

[0052] S503: Based on the eating matching degree, compare with the matching threshold to determine whether the eating behavior meets the recommended standard and obtain the eating behavior matching degree.

[0053] First, the matching threshold needs to be set. This threshold can be obtained from long-term monitoring data. For example, after statistical analysis of the eating data of 1000 individuals, it is found that the range of eating matching scores of individuals who meet the recommended eating standards mainly falls between . Therefore, the eating matching threshold can be set to 2.5. If the eating matching score of an individual is lower than 2.5, it is determined that their eating behavior meets the recommended standard. If is higher than 2.5, it is determined that their eating behavior does not meet the recommended standard. For example, if the calculated of an individual is 1.89, then their eating behavior meets the recommended standard. If the If the calculated value is 3.2, it means that the individual's eating behavior fails to meet the recommended requirements and dietary adjustments are needed. For example, reduce extra eating outside peak hours or adjust the types of food to make the intake structure more in line with the recommended plan. This result shows that the comparison between the eating matching score of the individual and the set threshold determines whether the eating behavior is reasonable. If the matching score is within a reasonable range, it indicates that the individual's eating behavior meets the recommended standards. If the matching score is too high, it means that the individual's eating behavior deviates from the recommended standards and needs to be adjusted.

[0054] Table 6 Example of Calculating the Eating Matching Score

[0055] As shown in Table 6, the calculation of the eating matching score involves multiple steps, including deviation calculation, squared error calculation, and time weight correction. This score can be used to evaluate the reasonableness of an individual's eating behavior and to adjust the eating plan to match the recommended standards. This result shows that by calculating the matching score, the reasonableness of an individual's eating behavior can be quantified and the dietary plan can be optimized accordingly.

[0056] The above are only the preferred embodiments of the present invention and do not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent nutritional intervention method based on underlying logic, characterized in that, It includes the following steps: S1: Obtain the serum triglyceride, pro-atherogenic lipoprotein cholesterol, anti-atherogenic lipoprotein cholesterol, and total cholesterol concentrations, collect the exhaled carbon dioxide release amount, monitor the fatty acid oxidation rate, record the serum ketone body level, analyze the changes in liver lipid storage, and record the eating time to form blood lipid metabolism monitoring data; S2: Based on the blood lipid metabolism monitoring data, extract the blood lipid change curves before, during, and after meals, calculate the fluctuation rate of blood lipid parameters, determine whether it exceeds the threshold, screen the abnormal time points of blood lipid parameters, calculate the change gradient of the fatty acid oxidation rate, evaluate the blood lipid decline rate, analyze the individual lipid metabolism ability, and generate the blood lipid metabolism deviation degree; S3: Based on the blood lipid metabolism deviation degree, adjust the dietary fat composition when the serum triglyceride exceeds the standard, increase the soluble dietary fiber when the pro-atherogenic lipoprotein cholesterol exceeds the standard, and optimize the ratio of protein to antioxidant foods when the anti-atherogenic lipoprotein cholesterol is low to obtain personalized dietary adjustment parameters; S4: Based on the blood lipid metabolism deviation degree, call the individual diet timing data in the intelligent nutrition intervention, analyze the blood lipid change trend, calculate the fluctuation range of the fat oxidation rate, and calculate the optimal eating time interval.

2. The intelligent nutrition intervention method based on the underlying logic according to claim 1, wherein The blood lipid metabolism monitoring data includes serum triglyceride concentration, pro-atherogenic lipoprotein cholesterol concentration, anti-atherogenic lipoprotein cholesterol concentration, total cholesterol concentration, exhaled carbon dioxide release amount, fatty acid oxidation rate, serum ketone body level, liver lipid storage change, and eating time. The blood lipid metabolism deviation degree includes triglyceride metabolism deviation degree, pro-atherogenic lipoprotein cholesterol metabolism deviation degree, anti-atherogenic lipoprotein cholesterol metabolism deviation degree, and total cholesterol metabolism deviation degree. The personalized dietary adjustment parameters include dietary fat composition adjustment parameters, soluble dietary fiber intake parameters, and protein to antioxidant food ratio optimization parameters. The optimal eating time interval includes the optimal breakfast eating time interval, the optimal lunch eating time interval, and the optimal dinner eating time interval.

3. The intelligent nutrition intervention method based on the underlying logic according to claim 2, wherein The specific steps for obtaining the blood lipid metabolism monitoring data are as follows: S101: Obtain the serum triglyceride, pro-atherogenic lipoprotein cholesterol, anti-atherogenic lipoprotein cholesterol, and total cholesterol concentrations, collect the exhaled carbon dioxide release amount, monitor the fatty acid oxidation rate, record the serum ketone body level, analyze the changes in liver lipid storage, and record the eating time, extract multiple data, perform standardization processing, calculate the change trends of multiple indicators, and obtain blood lipid metabolism change parameters; S102: Based on the blood lipid metabolism change parameters, calculate the influencing factors of the fatty acid oxidation rate, extract the change trend of the fatty acid oxidation rate, establish the dynamic change relationship of the fatty acid oxidation rate, and use the formula: ； Perform operations to obtain the fatty acid oxidation rate change coefficient, analyze the changes under different eating times and blood lipid levels, and obtain the fatty acid oxidation rate fluctuation range; Among them, represents the coefficient of change in fatty acid oxidation rate, represents the serum triglyceride concentration, represents the concentration of anti-atherogenic lipoprotein cholesterol, represents the concentration of pro-atherogenic lipoprotein cholesterol, represents the exhaled carbon dioxide release, represents the blood lipid metabolism correlation constant, represents the serum ketone body level, represents the liver lipid storage, represents the number of samples; S103: Call the fatty acid oxidation rate fluctuation range, analyze its distribution on the eating time axis, calculate the maximum change interval, and at the same time combine the key indicators of the blood lipid metabolism change parameters to establish a metabolic time sequence trend to obtain the blood lipid metabolism monitoring data.

4. The intelligent nutrition intervention method based on the underlying logic according to claim 3, wherein The specific steps for obtaining the blood lipid metabolism deviation degree are as follows: S201: Based on the blood lipid metabolism monitoring data, extract the blood lipid change curves before, during, and after meals, calculate the change trends of blood lipid parameters in different time periods, and at the same time call the set blood lipid parameter fluctuation thresholds, compare the blood lipid change amplitudes at multiple time points, screen the blood lipid parameter fluctuation intervals exceeding the thresholds, and obtain the abnormal time points of blood lipid parameters; S202: Call the data at the abnormal time points of the blood lipid parameters, calculate the change of the fatty acid oxidation rate before and after the time points, and use the formula: ； Calculate the change gradient of the fatty acid oxidation rate, and compare it with the blood lipid decline threshold to obtain the blood lipid decline rate; in, represents the gradient of fatty acid oxidation rate, Representative The fatty acid oxidation rate at the time represents the number of calculation interval steps for the change of fatty acid oxidation rate, Representative The change in total cholesterol in time steps, Represents the time step number used as reference when calculating the rate of blood lipid reduction; S203: Based on the change gradient of the fatty acid oxidation rate and the blood lipid decline rate, calculate the individual lipid metabolism ability, combine the data of the abnormal time points of the blood lipid parameters, compare the blood lipid changes of different individuals in the same monitoring period, calculate the deviation degree of the blood lipid metabolism change, and obtain the blood lipid metabolism deviation degree.

5. The intelligent nutrition intervention method based on the underlying logic according to claim 4, wherein The specific steps for obtaining the personalized dietary adjustment parameters are as follows: S301: Based on the blood lipid metabolism deviation degree, detect the levels of serum triglyceride, pro-atherogenic lipoprotein cholesterol, and anti-atherogenic lipoprotein cholesterol, obtain the blood lipid deviation parameters, calculate the excessive deviation amount of serum triglyceride, the excessive deviation amount of pro-atherogenic lipoprotein cholesterol, and the low deviation amount of anti-atherogenic lipoprotein cholesterol, and combine the individual physiological data and dietary intake to establish a blood lipid metabolism deviation matrix; S302: Call the blood lipid metabolism deviation matrix, for the excessive deviation amount of serum triglyceride, adjust the dietary fat composition, based on the different fatty acid ratios and triglyceride metabolism characteristics, calculate the optimized fatty acid intake parameters, and calculate the soluble dietary fiber supplement demand under the excessive deviation amount of pro-atherogenic lipoprotein cholesterol, adjust the synergistic relationship between multiple nutrients, and use the formula: ； Calculate the optimized coefficient of fatty acid intake and the correction value of fiber supplement to obtain the optimized fatty acid ratio and fiber supplement amount; Among them, represents the adjusted value of fatty acid intake, represents the current triglyceride level, represents the target triglyceride level, represents the fatty acid adjustment coefficient, represents the type of fatty acid influence coefficient on metabolism, represents the type of fatty acid intake amount, represents the number of fatty acid types, represents the current intake of soluble dietary fiber, represents the target intake of soluble dietary fiber; S303: Call the optimized fatty acid ratio and fiber supplement amount, for the low deviation amount of anti-atherogenic lipoprotein cholesterol, calculate the optimized ratio of protein and the adjustment amount of antioxidant foods, combine the individual basal metabolic rate and energy requirements, and correct the ratio of protein and antioxidant substances intake to obtain the personalized dietary adjustment parameters.

6. The intelligent nutrition intervention method based on the underlying logic according to claim 5, wherein The specific steps for obtaining the optimal eating time interval are as follows: S401: Based on the blood lipid metabolism deviation degree, call the individual diet timing data, extract the diet intake time series and the ingested nutrient components, calculate the blood lipid change rate at multiple time points, compare the blood lipid fluctuation values, screen the data points within the time series whose blood lipid fluctuation amplitude exceeds the target range, and construct a blood lipid change trend curve; S402: Based on the blood lipid change trend curve, calculate the fluctuation amplitude of the fatty acid oxidation rate in different time periods, and use the formula: ； Calculate the fatty acid oxidation fluctuation amplitude and generate a fatty acid oxidation fluctuation coefficient; Among them, represents the coefficient of variation of fat oxidation, represents the fat oxidation rate at the k-th time point, represents the total number of measurement time points, represents the calorie intake at the l-th time point; S403: Based on the fatty acid oxidation fluctuation coefficient, screen the minimum fluctuation interval, extract the corresponding eating time period, and call the blood lipid change trend curve for review to obtain the optimal eating time interval.

7. The intelligent nutritional intervention method based on underlying logic according to claim 6, characterized in that The method further includes: S5: Call the personalized dietary adjustment parameters and the optimal eating time interval, compare with the individual eating records, judge the matching situation of the intake structure and time, and calculate the eating behavior matching degree; The eating behavior matching degree includes the eating structure matching degree and the eating time matching degree.

8. The intelligent nutrition intervention method based on the underlying logic according to claim 7, characterized in that, The specific steps for obtaining the eating behavior matching degree are as follows: S501: Call the personalized dietary adjustment parameters and the optimal eating time interval, extract the intake time points and food types in the individual eating records, compare the dietary structure at multiple time points with the recommended eating time, calculate the intake matching error in the differential time period, and generate a dietary time matching error value; S502: Based on the dietary time matching error value, score each food type according to the time weight, and use the formula: ； Calculate the eating matching degree score and generate the eating matching degree; Among them, represents the eating matching degree score, represents the individual intake at the i-th moment, represents the recommended intake at the i-th moment, represents the total number of time points, represents the length of the recommended eating time interval, represents the food adjustment weight at the j-th moment, represents the number of time points within the recommended time interval; S503: Based on the eating matching degree, compare with the matching degree threshold, judge whether the eating behavior meets the recommended standard, and obtain the eating behavior matching degree.

Images