Method and system for generating personalized nutrition scheme for height increase

Abstract

The invention discloses a personalized nutrition scheme generation method and system for height increase, and relates to the field of health management, and the method comprises the steps: collecting static biological data, parent height data, health background questionnaire data and intestinal flora samples of a user, calculating the genetic target height and basal metabolic rate of the user according to the static biological data and the parent height data, generating a personal file of the user; extracting height, weight and leg length data of the user from a personal file of the user, obtaining stress distribution of a lower limb epiphyseal plate of the user under different exercise types through biomechanical simulation, and generating a personalized exercise scheme according to a stress distribution result; and estimating daily energy consumption according to the basal metabolic rate and the personalized exercise scheme to obtain the daily total energy demand of the user. According to the method, the problem of insufficient scheme accuracy and adaptability caused by neglecting individual nutrition absorption difference and biomechanical response characteristics in a traditional method is effectively solved.

Description

Technical Field

[0001] This invention relates to the field of health management, and in particular to a method and system for generating personalized nutrition plans for height growth. Background Technology

[0002] With the digital development of health management, personalized nutrition plans for promoting height in adolescents have gradually gained attention. By collecting basic data such as age, height, and weight of users and combining them with genetic target height calculation models, a comprehensive plan including dietary recommendations and exercise guidance is generated. It is usually based on the dietary nutrient reference intake standard, estimates the total energy requirement according to the user's basal metabolic rate and activity level, and allocates macronutrients in a fixed proportion. In terms of exercise, a preset exercise library is often used to match and recommend exercises according to the user's age preferences, such as recommending common vertical exercises such as rope skipping and basketball. This has achieved a leap from general advice to preliminary personalization, providing users with a basic framework with certain reference value.

[0003] However, the existing methods mentioned above still have limitations in terms of the accuracy and adaptability of the generated plans. The core problem is that they fail to fully consider the differences in individual physiological absorption and exercise response characteristics, resulting in limited plan effectiveness. Existing technologies rely on nutrient allocation models based on population averages and standard exercise recommendations, without integrating user gut microbiota metagenomic analysis data to assess nutrient absorption efficiency, nor introducing biomechanical simulation to quantify the stress stimulation effect of exercise on individual epiphyseal plates. For users with lactase gene defects or low calcium absorption efficiency, uniform dairy intake recommendations may not effectively promote bone growth. For individuals with significant differences in lower limb biomechanical structure, uniform rope skipping exercise may not produce optimal bone stress stimulation or may even pose a risk of injury. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method for generating personalized nutrition plans for height growth, which solves the problem of insufficient accuracy and adaptability of the plans caused by not taking into account individual differences in nutrient absorption and biomechanical response characteristics.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for generating a personalized nutrition plan for height growth, which includes collecting the user's static biological data, parents' height data, health background questionnaire data and gut microbiota samples, calculating the user's genetic target height and basal metabolic rate based on the static biological data and parents' height data, and generating a user personal profile.

[0008] The system extracts users' height, weight, and leg length data from their personal profiles, uses biomechanical simulation to obtain the stress distribution of the user's lower limb epiphyseal plates under different exercise types, and generates personalized exercise plans based on the stress distribution results.

[0009] Daily energy consumption is estimated based on basal metabolic rate and personalized exercise program to obtain the user's total daily energy requirement. Combined with metagenomic analysis of gut microbiota samples, the user's target daily nutrient requirement is obtained.

[0010] Based on the target nutrient requirements and personalized exercise program, a daily diet plan is developed, including the types, portions, and timing of food intake. This plan is then integrated with the personalized exercise program to form a daily action plan, from which planned nutritional data and planned exercise data are extracted.

[0011] Obtain actual execution data of users' daily action plans, compare the actual execution data with planned nutrition data and planned exercise data, and dynamically adjust the daily action plans based on the comparison results.

[0012] As a preferred embodiment of the personalized nutrition plan generation method for height growth described in this invention, the method includes: collecting the user's static biological data, parents' height data, health background questionnaire data, and gut microbiota samples; calculating the user's genetic target height and basal metabolic rate based on the static biological data and parents' height data; and generating a user profile, comprising the following steps.

[0013] The user interface guides users to input static biological data, parents' height data, health background questionnaire data, and gut microbiota samples.

[0014] The range of genetic target height was obtained by processing the father's and mother's height data using the Coleman formula.

[0015] The Mifflin-St Jeor formula was used to process static biological data and calculate the basal metabolic rate.

[0016] The static biological data, father's height data, mother's height data, health background questionnaire data, gut microbiota sample identifiers, genetic target height range, and basal metabolic rate values ​​are combined to form a user profile.

[0017] As a preferred embodiment of the personalized nutrition plan generation method for height growth described in this invention, the method includes: extracting the user's height, weight, and leg length data from the user's personal profile; obtaining the stress distribution of the user's lower limb epiphyseal plates under different exercise types through biomechanical simulation; and generating a personalized exercise plan based on the stress distribution results, including the following steps.

[0018] The system locates user height, weight, and leg length data through user profiles.

[0019] Based on the general anatomical parameters and material properties of bones in healthy adolescents, a biomechanical model of the lower limb skeleton was constructed. The elastic modulus of the bone was set to 16 GPa and the Poisson's ratio was set to 0.3. The geometric models of the epiphyseal plate, diaphysis and articular surfaces of the lower limb skeleton were constructed using finite element analysis software. The model was verified using static and dynamic load conditions. By comparing the data from in vitro mechanical experiments, the corrected biomechanical model of the lower limb skeleton was obtained.

[0020] The user's height, weight, and leg length data are input into the corrected lower limb skeletal biomechanical model. The stress state of the user's bones under different movements is simulated through biomechanical simulation to obtain the stress distribution of the user's lower limb epiphyseal plate under different movement types.

[0021] By analyzing the stress distribution cloud maps of the epiphyseal plates of the user's lower limbs under different types of exercise, a personalized exercise plan can be generated.

[0022] As a preferred embodiment of the personalized nutrition plan generation method for height growth described in this invention, the method includes: estimating daily energy consumption based on basal metabolic rate and personalized exercise plan to obtain the user's total daily energy requirement; and combining this with metagenomic analysis of gut microbiota samples to obtain the user's target daily nutrient requirements, comprising the following steps:

[0023] The basal metabolic rate is added to the energy consumption value of the exercise in the personalized exercise plan to obtain the daily energy consumption. The energy surplus value required for height growth is added to the daily energy consumption to obtain the user's total daily energy requirement.

[0024] Bioinformatics analysis methods were used to analyze the metagenomic sequencing reports of gut microbiota samples, extract the abundance information of functional genes related to nutrient metabolism, and use multiple linear regression to evaluate and obtain personalized absorption parameters such as protein absorption efficiency coefficient and calcium absorption efficiency coefficient.

[0025] The user's daily total energy requirement is allocated according to the proportion of nutrients, and then calibrated by personalized absorption parameters such as protein absorption efficiency coefficient and calcium absorption efficiency coefficient to obtain the user's target daily nutrient requirement.

[0026] As a preferred embodiment of the personalized nutrition plan generation method for height growth described in this invention, the method includes: developing a daily dietary plan based on the target nutrient requirements and a personalized exercise plan, specifying the types, quantities, and timing of food intake; and integrating this daily dietary plan with the personalized exercise plan into a daily action plan, comprising the following steps:

[0027] The personalized exercise plan is analyzed using natural language processing methods to obtain information on exercise time and intensity, and the day is divided into a pre-exercise window, a post-exercise window, and a non-exercise window.

[0028] The target nutrient requirements are allocated differently according to different nutrient windows using a dynamic nutrient allocation formula.

[0029] Based on the nutrient amount allocated during the window period, the food nutrient database is queried to match food types and portions, and the eating time points for each meal are determined to generate a daily diet plan with food types, weight portions and eating time points.

[0030] By setting user-configurable daily start and end times, a complete timeline sequence from morning to night can be established.

[0031] The eating times of all meals in the daily diet plan and the execution time of the exercise segment in the personalized exercise plan are mapped onto a complete timeline sequence from morning to night. Time conflicts on the timeline sequence are detected. When a conflict is detected, the eating time is postponed to 45 minutes after the end of exercise. All the adjusted eating events and exercise events are integrated into a daily action plan in chronological order.

[0032] As a preferred embodiment of the method for generating a personalized nutrition plan for height growth according to the present invention, the method includes the following steps: extracting planned nutrition data and planned exercise data from the daily action plan.

[0033] The daily action plan is analyzed using structured data parsing methods to obtain dietary execution instructions. The types and quantities of all planned food intakes are extracted from the dietary execution instructions. The food nutrient database is queried to convert the types and quantities of planned food intakes into planned nutritional data.

[0034] The exercise execution instructions obtained from the daily action plan are parsed using regular expression matching methods, and the exercise type and duration data are extracted from the exercise execution instructions.

[0035] Based on the formula for calculating exercise metabolic equivalent, the data on exercise type and duration are converted into planned exercise data.

[0036] As a preferred embodiment of the personalized nutrition plan generation method for height growth described in this invention, the method includes: obtaining actual execution data of the user's daily action plan, comparing the actual execution data with the daily action plan, and dynamically adjusting the daily action plan based on the comparison results, comprising the following steps:

[0037] By combining manual input from users with automatic data collection from wearable devices, the system records data on the types and amounts of food consumed by users, as well as the types and durations of exercise completed.

[0038] Convert the actual types and amounts of food consumed into actual nutritional data, convert the actual types and durations of exercise into actual exercise consumption data, calculate the difference between the actual nutritional data and the planned nutritional data in the daily action plan, and calculate the difference between the actual exercise consumption data and the planned exercise data in the daily action plan.

[0039] Based on the differences between actual and planned nutritional data, and between actual and planned exercise data, adjust the food portion and exercise duration in the daily action plan for the following day.

[0040] Secondly, the present invention provides a personalized nutrition plan generation system for height growth, comprising,

[0041] The data acquisition module collects the user's static biological data, parents' height data, health background questionnaire data, and gut microbiota samples. Based on the static biological data and parents' height data, it calculates the user's genetic target height and basal metabolic rate, and generates the user's personal profile.

[0042] The personalized exercise program generation module extracts the user's height, weight, and leg length data from the user's personal profile, obtains the stress distribution of the user's lower limb epiphyseal plate under different exercise types through biomechanical simulation, and generates a personalized exercise program based on the stress distribution results.

[0043] The nutrition requirements module estimates daily energy consumption based on basal metabolic rate and personalized exercise plan to obtain the user's total daily energy requirement. Combined with metagenomic analysis of gut microbiota samples, it obtains the user's target daily nutrient requirements.

[0044] The daily action plan synthesis module develops a daily diet plan based on the target nutrient requirements and personalized exercise plan, specifying the types, portions, and timing of food intake. It integrates the daily diet plan with the personalized exercise plan into a daily action plan, extracting planned nutrient data and planned exercise data from the daily action plan.

[0045] The dynamic adjustment module obtains the actual execution data of the user's daily action plan, compares the actual execution data with the planned nutrition data and planned exercise data, and dynamically adjusts the daily action plan based on the comparison results.

[0046] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the method for generating a personalized nutrition program for height growth as described in the first aspect of the present invention.

[0047] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for generating a personalized nutrition plan for height growth as described in the first aspect of the present invention.

[0048] The beneficial effects of this invention are as follows: By collecting multi-dimensional static and dynamic biological data of users and constructing personal profiles, a personalized exercise program that fits the individual's skeletal stress response characteristics is generated based on biomechanical simulation. After calibrating nutrient absorption efficiency by combining gut microbiota metagenomic analysis, the daily target nutrient requirements are accurately calculated. Then, a daily diet plan that is coordinated with the time-series exercise program is formulated and integrated into an action plan. Finally, through dynamic comparison and feedback adjustment of actual execution data and plan data, a closed-loop personalized intervention is achieved, from genetic potential assessment, physiological characteristic quantification, nutrition and exercise coordination to dynamic optimization. This effectively solves the problem of insufficient accuracy and adaptability of the program caused by traditional methods that ignore individual differences in nutrient absorption and biomechanical response characteristics. Attached Figure Description

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 A flowchart illustrating the method for generating personalized nutrition plans for height growth.

[0051] Figure 2 A schematic diagram of a system for generating personalized nutrition plans for height growth.

[0052] Figure 3 This is an illustration of a user's personal profile.

[0053] Figure 4 A diagram illustrating the target nutrient requirements. Detailed Implementation

[0054] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0055] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0056] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0057] Reference Figures 1-4 This is one embodiment of the present invention, which provides a method for generating a personalized nutrition plan for height growth, including the following steps:

[0058] S1. Collect the user's static biological data, parents' height data, health background questionnaire data, and gut microbiota samples. Calculate the user's genetic target height and basal metabolic rate based on the static biological data and parents' height data, and generate the user's personal profile.

[0059] S1.1 Guide users to input static biological data, parents' height data, health background questionnaire data, and gut microbiota samples through the user interface.

[0060] Furthermore, the user interface displays a multi-step data collection wizard. First, the static biological data section provides input fields for age, gender, current height, and current weight, requiring users to fill them in one by one. Then, the parental height data section provides separate input boxes for the father's and mother's heights, with centimeter unit prompts. The health background questionnaire data section is presented in a grouped selection format, including single-choice questions on dietary preferences, multiple-choice questions on common food allergies, and a slider for self-assessment of gastrointestinal absorption function. Finally, it clearly guides users to use the included dedicated sampling tool to complete the collection of gut microbiota samples. After the user completes all field inputs and submits the form, the static biological data, parental height data, and health background questionnaire data are recorded. The gut microbiota sample identifier is generated during the mailing process and associated with the user's account.

[0061] S1.2. The Coleman formula is used to calculate and process the father's height data and the mother's height data to obtain the genetic target height range.

[0062] The expression for the genetic target height range is:

[0063] ;

[0064] in, This represents the genetic target height range. For the father's height, For the mother's height.

[0065] Furthermore, the system reads the input father's and mother's height data, substitutes them into the Coleman formula for calculation, and calculates the father's height data, mother's height data, and thirteen centimeters, then divides by two. The calculation result is recorded as the genetic target height range, thus completing the calculation and output of the genetic target height range.

[0066] S1.3. The Mifflin-St Jeor formula was used to process static biological data and calculate the basal metabolic rate.

[0067] The numerical expression for basal metabolic rate is:

[0068] ;

[0069] in, Basal metabolic rate (BMR) values For weight, For height, For age.

[0070] Furthermore, the system reads the weight, height, and age data from the input static biological data, substitutes these data into the Mifflin-St. Jeor formula for calculation. The Mifflin-St. Jeor formula is calculated by multiplying the weight data by 10, adding 6.25, multiplying the height data by 5, multiplying the age data by 5, and then adding 5. The result is recorded as the basal metabolic rate value, thus completing the calculation and output of the basal metabolic rate value.

[0071] S1.4. Combine static biological data, father's height data, mother's height data, health background questionnaire data, gut microbiota sample identifiers, genetic target height range, and basal metabolic rate values ​​to form a user profile.

[0072] Furthermore, static biological data, father's height data, mother's height data, health background questionnaire data, gut microbiota sample identifiers, genetic target height range, and basal metabolic rate values ​​are integrated according to a preset data structure. The static biological data includes age, gender, current height, and current weight fields. Father's and mother's height data are stored in centimeters. The health background questionnaire data includes dietary preferences, a list of allergic foods, and a self-assessment level of gastrointestinal function. The gut microbiota sample identifiers are associated with laboratory test numbers. The genetic target height range is stored in a numerical range format. The basal metabolic rate values ​​are recorded in kilocalories, generating a user profile.

[0073] S2. Extract the user's height, weight, and leg length data from the user's personal profile, obtain the stress distribution of the user's lower limb epiphyseal plate under different exercise types through biomechanical simulation, and generate a personalized exercise plan based on the stress distribution results.

[0074] S2.1 Locate user height, weight, and leg length data through user profile.

[0075] Furthermore, the system accesses the structured data set stored in the user's personal profile, parses the data structure of the user's personal profile to locate the static biological data partition, and extracts the specific values ​​of the user's height and weight data from it; at the same time, it accesses the health background questionnaire data partition in the user's personal profile, reads the user's leg length data record from the lower limb biometrics item, and finally completes the location and data extraction of the three parameters of user height, user weight and user leg length data.

[0076] S2.2. Based on the general anatomical parameters and material properties of bones in healthy adolescents, a biomechanical model of the lower limb skeleton was constructed. The elastic modulus of the bone was set to 16 GPa and the Poisson's ratio was set to 0.3. The lower limb skeleton biomechanical model was constructed using finite element analysis software to build geometric models of the epiphyseal plate, diaphysis and articular surfaces. Static and dynamic load conditions were used for verification. By comparing in vitro mechanical experimental data, the corrected lower limb skeleton biomechanical model was obtained.

[0077] Furthermore, in the finite element analysis software environment, a biomechanical geometric model of the lower limb skeleton, including the epiphyseal plate, diaphysis, and articular surfaces, was established based on the general anatomical parameters and material properties of the skeleton in healthy adolescents. The elastic modulus of the skeleton was set to 16 gigapascals, and the Poisson's ratio was set to 0.3. The mechanical response was simulated by applying static and dynamic load conditions to the geometric model, and the strain distribution data of the simulation output was obtained. The simulated strain distribution data was compared point by point with the real bone strain data collected through in vitro mechanical experiments. By iteratively adjusting the boundary constraint parameters and material constitutive parameters of the geometric model, a lower limb skeleton biomechanical model verified and corrected by experimental data was obtained.

[0078] It should be noted that the in vitro mechanical experimental data comes from the mechanical test results of healthy adolescent bone samples recorded in publicly available literature. The test uses an electronic universal testing machine to conduct axial compression and bending experiments on bone samples in a standard laboratory environment. The micro-strain values ​​under different load conditions are collected by strain gauges to form a quantifiable mechanical response dataset.

[0079] S2.3 Input the user's height data, weight data, and leg length data into the corrected lower limb skeletal biomechanical model. Simulate the stress state of the user's bones under different movements through biomechanical simulation to obtain the stress distribution of the user's lower limb epiphyseal plate under different movement types.

[0080] Furthermore, user height, weight, and leg length data are imported as input parameters into a lower limb skeletal biomechanical model that has been validated and corrected using experimental data. The mechanical response process of the skeletal system under three typical sports conditions—rope skipping, running, and basketball—is simulated in finite element analysis software. The stress distribution cloud map of the user's lower limb epiphyseal plate under different sports types is calculated by the solver, thus completing the quantitative analysis of the sports biomechanical response.

[0081] It should be noted that the motion type parameters are derived from the standard motion pattern library recognized in the field of sports science. This library defines the dynamic characteristics and kinematic parameters of various basic motions, providing accurate motion input conditions for biomechanical simulation.

[0082] S2.4 Analyze the stress distribution cloud map of the user's lower limb epiphyseal plate under different types of exercise to generate a personalized exercise plan.

[0083] Furthermore, the stress distribution cloud map of the user's lower limb epiphyseal plate under different exercise types is analyzed. The maximum compressive stress value and the maximum shear stress value in the stress distribution cloud map are extracted. The maximum compressive stress value is compared with the optimal compressive stress range that promotes bone growth, and the maximum shear stress value is compared with the safety threshold. Exercise types with maximum compressive stress values ​​within the optimal compressive stress range and maximum shear stress values ​​below the safety threshold are selected. Based on the exercise intensity and time parameters corresponding to the exercise type, a personalized exercise plan including specific exercise form, exercise frequency and duration is generated.

[0084] It should be noted that the setting of the movement type for the safety threshold is based on the dynamic characteristic analysis of different movement modes in sports biomechanics research, by establishing a standard movement library and defining the range of mechanical parameters corresponding to each movement.

[0085] S3. Estimate daily energy consumption based on basal metabolic rate and personalized exercise plan to obtain the user's total daily energy requirement. Combined with metagenomic analysis of gut microbiota samples, obtain the user's target daily nutrient requirements.

[0086] S3.1 Add the basal metabolic rate value to the energy consumption value of the exercise in the personalized exercise plan to obtain the daily energy consumption. Add the energy surplus value required for height growth to the daily energy consumption to obtain the user's total daily energy requirement.

[0087] Furthermore, the system reads the basal metabolic rate (BMR) value recorded in the user's personal profile and analyzes the estimated energy consumption for each exercise in the personalized exercise plan. The BMR value is then summed with the estimated energy consumption for all exercises in the personalized exercise plan to obtain a daily energy consumption estimate. Referring to the energy supplementation recommendations for the height growth stage in the Adolescent Growth and Development Nutrition Guidelines, a corresponding energy surplus value is added to the daily energy consumption estimate.

[0088] S3.2. The metagenomic sequencing report of the gut microbiota sample was analyzed using bioinformatics analysis methods to extract the abundance information of functional genes related to nutrient metabolism. The protein absorption efficiency coefficient and calcium absorption efficiency coefficient were evaluated using multiple linear regression to obtain personalized absorption parameters.

[0089] Furthermore, bioinformatics analysis was performed on the metagenomic sequencing reports of gut microbiota samples. Gene annotation tools were used to identify functional gene sequences related to protein metabolism and calcium metabolism, and the abundance information of these functional genes was quantified by counting reads. The abundance information of functional genes related to protein metabolism and calcium metabolism was used as independent variables to establish a multiple linear regression model for fitting analysis. Personalized absorption parameters such as protein absorption efficiency coefficient and calcium absorption efficiency coefficient were obtained from the multiple linear regression model to complete the quantitative assessment of the individual nutritional absorption characteristics of users.

[0090] S3.3. Allocate the user's total daily energy requirement according to the nutrient ratio, and calibrate it with personalized absorption parameters such as protein absorption efficiency coefficient and calcium absorption efficiency coefficient to obtain the user's target daily nutrient requirement.

[0091] Furthermore, the user's daily total energy requirement is allocated according to the recommended proportions of macronutrients in the Dietary Reference Intakes to derive the initial requirements for protein, fat, and carbohydrates. The initial protein requirement is multiplied by the protein absorption efficiency coefficient to obtain the calibrated target protein requirement, and the initial calcium requirement is multiplied by the calcium absorption efficiency coefficient to obtain the calibrated target calcium requirement. This generates the user's daily target nutrient requirements, which include the calibrated values ​​for all macronutrients and key minerals.

[0092] S4. Based on the target nutrient requirements and personalized exercise plan, develop a daily diet plan that includes the types, portions, and timing of food intake. Integrate the daily diet plan with the personalized exercise plan into a daily action plan.

[0093] S4.1 Use natural language processing to analyze personalized exercise plans, obtain exercise time and intensity information, and divide each day into pre-exercise window, post-exercise window and non-exercise window.

[0094] Furthermore, natural language processing technology is used to analyze the text descriptions in personalized exercise plans, identifying the start time, duration, and intensity of the exercise. Based on the start time and duration, the specific time range for each exercise period is calculated. Each exercise period is then divided into three time intervals: the pre-exercise window, the post-exercise window, and the non-exercise window. The pre-exercise window is defined as the period one to two hours before the start time, the post-exercise window is defined as the period within forty-five minutes after the end time, and the non-exercise window is any time other than the pre-exercise and post-exercise windows. This completes the daily time window division based on personalized exercise plans.

[0095] S4.2. The target nutrient requirements are allocated differently according to different window periods using a dynamic nutrient allocation formula.

[0096] The expression for differential allocation is,

[0097] ;

[0098] in, For the first The sports window period allocated to the first Planned intake of various nutrients For the first The baseline distribution of each nutrient throughout the day For the first The intensity coefficient of adjacent motion segments within a motion window period. For the first Type fortification coefficient of each nutrient For motion windows, It is a nutrient.

[0099] Furthermore, a dynamic nutrient allocation formula is used to differentiate the target nutrient requirements according to different window periods. The calculation process of the dynamic nutrient allocation formula is to multiply the basic nutrient allocation for each window period by the exercise intensity coefficient and the nutrient type enhancement coefficient to obtain the final nutrient allocation for the window period. The exercise intensity coefficient is determined based on the intensity description information of the corresponding exercise period in the personalized exercise plan, and the nutrient type enhancement coefficient sets different enhancement weights for different windows based on the principles of sports nutrition, thus completing the differentiated allocation of the target nutrient requirements in the pre-exercise window, post-exercise window and non-exercise window.

[0100] S4.3. Based on the nutrient amount allocated during the window period, query the food nutrient database to match food types and portions, determine the eating time for each meal, and generate a daily diet plan with food types, weight portions, and eating time.

[0101] Furthermore, based on the amounts of nutrients such as protein, carbohydrates, and fat allocated in the pre-exercise window, post-exercise window, and non-exercise window, the system queries the nutritional composition data of various foods in the food nutrient composition database to match the types of foods and corresponding weight portions that meet the nutrient requirements of each window period. Combining the specific time ranges of the pre-exercise window, post-exercise window, and non-exercise window, the system determines the specific eating times for each meal, such as breakfast, snacks, lunch, post-exercise snacks, and dinner, and generates a complete daily diet plan that includes specific food types, precise weight portions, and clear eating times for all meals.

[0102] S4.4. By setting the user-configurable daily start and end times, a complete timeline sequence from morning to night is established.

[0103] Furthermore, by receiving the user-defined daily start and end times, a continuous time series from the daily start to the daily end is generated in minutes. The time series covers the complete daily activity period specified by the user, forming a complete timeline sequence from morning to night.

[0104] S4.5 Map the eating times of all meals in the daily diet plan to the execution time of the exercise segment in the personalized exercise plan onto a complete timeline sequence from morning to night. Detect time conflicts on the timeline sequence. When a conflict is detected, postpone the eating time to 45 minutes after the end of the exercise. Integrate all the adjusted eating events and exercise events into a daily action plan in chronological order.

[0105] Furthermore, the meal times of all meals in the daily diet plan are mapped to the start and end times of each exercise segment in the personalized exercise plan onto a complete timeline sequence from morning to night. Each meal time is checked to see if it falls within any exercise time segment. When an overlap or conflict is detected between a meal time and an exercise time segment, the meal time is reset to a time coordinate 45 minutes after the end time of the corresponding exercise time segment. All meal and exercise events are then sorted and integrated according to the adjusted time points to generate a complete daily action plan that is conflict-free in the time dimension and conforms to the synergistic principle of sports nutrition.

[0106] S5. Extract planned nutrition data and planned exercise data from the daily action plan.

[0107] S5.1. Use structured data parsing methods to parse the daily action plan to obtain dietary execution instructions. Extract the types and quantities of all planned food intake from the dietary execution instructions. Query the food nutrient database to convert the types and quantities of planned food intake into planned nutritional data.

[0108] Furthermore, structured data parsing methods are used to analyze the dietary execution instructions in the daily action plan, extracting the names of all planned food items and their corresponding weight data. The nutritional content of the corresponding food is then queried from the food nutrition database. The weight of each planned food item is multiplied by its nutritional content to obtain the intake of various nutrients such as protein, carbohydrates, and fat. Finally, the nutrient intake of all planned foods is summed to obtain the planned nutritional data, completing the conversion from food instructions to nutritional data.

[0109] S5.2 Use regular expression matching to parse the exercise execution instructions obtained from the daily action plan, and extract the exercise type and exercise duration data from the exercise execution instructions.

[0110] Furthermore, regular expression matching methods are used to parse the exercise execution instruction text in the daily action plan. By using predefined exercise type pattern matching rules, exercise type names such as rope skipping, running, and basketball are identified, and exercise duration values ​​are extracted by using duration pattern matching rules. Exercise type data and exercise duration data are accurately separated from exercise execution instructions.

[0111] S5.3. Based on the exercise metabolic equivalent calculation formula, convert the exercise type and duration data into planned exercise data.

[0112] The expression for planned exercise data is,

[0113] ;

[0114] in, For planning exercise data, This is the exercise metabolic equivalent value. This refers to the duration of the movement.

[0115] Furthermore, based on the exercise metabolic equivalent calculation formula, the exercise type and duration data are converted into planned exercise data. First, the metabolic equivalent value corresponding to the exercise type is obtained by consulting the standard metabolic equivalent value reference table. Then, the metabolic equivalent value is multiplied by the user's weight data, and then multiplied by the exercise duration data in hours to calculate the planned exercise data, which is the estimated value of exercise energy consumption, thus completing the quantitative conversion from exercise instructions to energy data.

[0116] S6. Obtain the actual execution data of the user's daily action plan, compare the actual execution data with the daily action plan, and dynamically adjust the daily action plan based on the comparison results.

[0117] S6.1 Records data on the types and amounts of food consumed by the user, as well as the type and duration of exercise completed, by combining manual input by the user with automatic data collection by wearable devices.

[0118] Furthermore, users manually record the types and portions of food they actually consume at each meal through a mobile application. The wearable device automatically monitors and records the type and duration of exercise the user completes. The mobile application provides a food database selection interface and portion input controls for accurately recording dietary data. The wearable device identifies exercise patterns and records start and end times through motion sensors. The manually entered dietary data and the exercise data collected by the device together constitute the user's actual execution data set, completing a comprehensive record of the execution of the daily action plan.

[0119] S6.2 Convert the actual food types and quantities into actual nutritional data, convert the actual exercise types and durations into actual exercise consumption data, calculate the difference between the actual nutritional data and the planned nutritional data in the daily action plan, and calculate the difference between the actual exercise consumption data and the planned exercise data in the daily action plan.

[0120] Actual nutritional data and planned nutritional data are expressed as follows:

[0121] ;

[0122] in, For the first The difference between the actual intake and the planned intake of a nutrient. For the first The actual intake of each nutrient For the first Planned intake of various nutrients.

[0123] The expression for the difference between the actual energy expenditure during exercise and the planned energy expenditure during exercise is as follows.

[0124] ;

[0125] in, This is the difference between the actual energy expenditure during exercise and the planned energy expenditure during exercise. For actual motion data, For planned exercise data;

[0126] Furthermore, the actual food types and quantities are converted against a food nutrient database. By querying the nutrient content of each food and multiplying it by the actual intake quantity, the total amount of nutrients such as protein, carbohydrates, and fat ingested is calculated, forming the actual nutritional data. The actual exercise type and duration data are substituted into the exercise metabolic equivalent calculation formula. By querying the metabolic equivalent value corresponding to the exercise type and calculating it with the user's weight and exercise duration data, the actual exercise consumption data is obtained. The values ​​of each nutrient in the actual nutritional data are subtracted from the planned nutritional data in the daily action plan to obtain the difference in intake of each nutrient. The actual exercise consumption data is subtracted from the planned exercise data in the daily action plan to obtain the difference in exercise consumption, thus completing all difference calculations.

[0127] S6.3. Based on the difference between actual nutritional data and planned nutritional data, and the difference between actual exercise consumption data and planned exercise data, adjust the food portion and exercise duration in the daily action plan for the next day.

[0128] Furthermore, based on the differences between actual and planned nutritional data, as well as the differences between actual and planned exercise data, the food portions and exercise durations in the daily action plan for the following day are adjusted accordingly. When actual nutritional data is lower than planned nutritional data, the corresponding food portions for the following day are increased proportionally to the difference; when actual nutritional data is higher than planned nutritional data, the corresponding food portions for the following day are decreased proportionally to the difference; when actual exercise data is lower than planned exercise data, the exercise duration for the following day is increased proportionally to the difference; when actual exercise data is higher than planned exercise data, the exercise duration for the following day is decreased proportionally to the difference or the original plan is maintained, generating an adjusted daily action plan for the following day, thus completing dynamic optimization based on execution feedback.

[0129] This embodiment also provides a personalized nutrition plan generation system for height growth, including: a data acquisition module, which collects the user's static biological data, parents' height data, health background questionnaire data and gut microbiota samples, calculates the user's genetic target height and basal metabolic rate based on the static biological data and parents' height data, and generates a user personal profile;

[0130] The personalized exercise program generation module extracts the user's height, weight, and leg length data from the user's personal profile, obtains the stress distribution of the user's lower limb epiphyseal plate under different exercise types through biomechanical simulation, and generates a personalized exercise program based on the stress distribution results.

[0131] The nutrition requirements module estimates daily energy consumption based on basal metabolic rate and personalized exercise plan to obtain the user's total daily energy requirement. Combined with metagenomic analysis of gut microbiota samples, it obtains the user's target daily nutrient requirements.

[0132] The daily action plan synthesis module develops a daily diet plan based on the target nutrient requirements and personalized exercise plan, specifying the types, portions, and timing of food intake. It integrates the daily diet plan with the personalized exercise plan into a daily action plan, extracting planned nutrient data and planned exercise data from the daily action plan.

[0133] The dynamic adjustment module obtains the actual execution data of the user's daily action plan, compares the actual execution data with the planned nutrition data and planned exercise data, and dynamically adjusts the daily action plan based on the comparison results.

[0134] This embodiment also provides a computer device applicable to the method for generating personalized nutrition plans for height growth, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the method for generating personalized nutrition plans for height growth as proposed in the above embodiment.

[0135] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0136] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the method for generating a personalized nutrition plan for height growth as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0137] In summary, this invention collects multi-dimensional static and dynamic biological data from users to construct personal profiles. Based on biomechanical simulation, it generates personalized exercise programs that match the individual's skeletal stress response characteristics. After calibrating nutrient absorption efficiency through gut microbiota metagenomic analysis, it accurately calculates the daily target nutrient requirements. Subsequently, it formulates a daily dietary plan that coordinates with the time-seriesd exercise program and integrates it into an action plan. Finally, through dynamic comparison and feedback adjustments between actual execution data and planned data, it achieves a closed-loop personalized intervention across the entire chain, from genetic potential assessment, physiological characteristic quantification, nutritional exercise coordination to dynamic optimization. This effectively solves the problem of insufficient accuracy and adaptability of traditional methods due to neglecting individual differences in nutrient absorption and biomechanical response characteristics.

[0138] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for generating a personalized nutrition plan for height growth, characterized in that: include, Collect users’ static biological data, parents’ height data, health background questionnaire data and gut microbiota samples. Calculate users’ genetic target height and basal metabolic rate based on static biological data and parents’ height data, and generate users’ personal profiles. The system extracts users' height, weight, and leg length data from their personal profiles, uses biomechanical simulation to obtain the stress distribution of the user's lower limb epiphyseal plates under different exercise types, and generates personalized exercise plans based on the stress distribution results. Daily energy consumption is estimated based on basal metabolic rate and personalized exercise program to obtain the user's total daily energy requirement. Combined with metagenomic analysis of gut microbiota samples, the user's target daily nutrient requirement is obtained. Based on the target nutrient requirements and personalized exercise program, a daily diet plan is developed, including the types, portions, and timing of food intake. This plan is then integrated with the personalized exercise program to form a daily action plan, from which planned nutritional data and planned exercise data are extracted. Obtain actual execution data of users' daily action plans, compare the actual execution data with planned nutrition data and planned exercise data, and dynamically adjust the daily action plans based on the comparison results.

2. The method for generating a personalized nutrition plan for height growth as described in claim 1, characterized in that: The system collects users' static biological data, parents' height data, health background questionnaire data, and gut microbiota samples. Based on the static biological data and parents' height data, it calculates the user's genetic target height and basal metabolic rate, generating a user profile. Includes the following steps, The user interface guides users to input static biological data, parents' height data, health background questionnaire data, and gut microbiota samples. The range of genetic target height was obtained by processing the father's and mother's height data using the Coleman formula. The Mifflin-St Jeor formula was used to process static biological data and calculate the basal metabolic rate. The static biological data, father's height data, mother's height data, health background questionnaire data, gut microbiota sample identifiers, genetic target height range, and basal metabolic rate values ​​are combined to form a user profile.

3. The method for generating a personalized nutrition plan for height growth as described in claim 2, characterized in that: The system extracts users' height, weight, and leg length data from their personal profiles. Through biomechanical simulation, it obtains the stress distribution of the user's lower limb epiphyseal plates under different exercise types. Based on the stress distribution results, it generates personalized exercise plans, including the following steps. The system locates user height, weight, and leg length data through user profiles. Based on the general anatomical parameters and material properties of bones in healthy adolescents, a biomechanical model of the lower limb skeleton was constructed. The elastic modulus of the bone was set to 16 GPa and the Poisson's ratio was set to 0.

3. The geometric models of the epiphyseal plate, diaphysis and articular surfaces of the lower limb skeleton were constructed using finite element analysis software. The model was verified using static and dynamic load conditions. By comparing the data from in vitro mechanical experiments, the corrected biomechanical model of the lower limb skeleton was obtained. The user's height, weight, and leg length data are input into the corrected lower limb skeletal biomechanical model. The stress state of the user's bones under different movements is simulated through biomechanical simulation to obtain the stress distribution of the user's lower limb epiphyseal plate under different movement types. By analyzing the stress distribution cloud maps of the epiphyseal plates of the user's lower limbs under different types of exercise, a personalized exercise plan can be generated.

4. The method for generating a personalized nutrition plan for height growth as described in claim 3, characterized in that: Daily energy expenditure is estimated based on basal metabolic rate and personalized exercise plan to determine the user's total daily energy requirement. Combined with metagenomic analysis of gut microbiota samples, the user's target daily nutrient requirements are determined, including the following steps. The basal metabolic rate is added to the energy consumption value of the exercise in the personalized exercise plan to obtain the daily energy consumption. The energy surplus value required for height growth is added to the daily energy consumption to obtain the user's total daily energy requirement. Bioinformatics analysis methods were used to analyze the metagenomic sequencing reports of gut microbiota samples, extract the abundance information of functional genes related to nutrient metabolism, and use multiple linear regression to evaluate and obtain personalized absorption parameters such as protein absorption efficiency coefficient and calcium absorption efficiency coefficient. The user's daily total energy requirement is allocated according to the proportion of nutrients, and then calibrated by personalized absorption parameters such as protein absorption efficiency coefficient and calcium absorption efficiency coefficient to obtain the user's target daily nutrient requirement.

5. The method for generating a personalized nutrition plan for height growth as described in claim 4, characterized in that: Based on the target nutrient requirements and personalized exercise plan, a daily dietary plan is developed, specifying the types, portions, and timing of food intake. This plan is then integrated with the personalized exercise plan into a daily action plan, including the following steps: The personalized exercise plan is analyzed using natural language processing methods to obtain information on exercise time and intensity, and the day is divided into a pre-exercise window, a post-exercise window, and a non-exercise window. The target nutrient requirements are allocated differently according to different nutrient windows using a dynamic nutrient allocation formula. Based on the nutrient amount allocated during the window period, the food nutrient database is queried to match food types and portions, and the eating time points for each meal are determined to generate a daily diet plan with food types, weight portions and eating time points. By setting user-configurable daily start and end times, a complete timeline sequence from morning to night can be established. The eating times of all meals in the daily diet plan and the execution time of the exercise segment in the personalized exercise plan are mapped onto a complete timeline sequence from morning to night. Time conflicts on the timeline sequence are detected. When a conflict is detected, the eating time is postponed to 45 minutes after the end of exercise. All the adjusted eating events and exercise events are integrated into a daily action plan in chronological order.

6. The method for generating a personalized nutrition plan for height growth as described in claim 5, characterized in that: Extract planned nutrition data and planned exercise data from the daily action plan, including the following steps: The daily action plan is analyzed using structured data parsing methods to obtain dietary execution instructions. The types and quantities of all planned food intakes are extracted from the dietary execution instructions. The food nutrient database is queried to convert the types and quantities of planned food intakes into planned nutritional data. The exercise execution instructions obtained from the daily action plan are parsed using regular expression matching methods, and the exercise type and duration data are extracted from the exercise execution instructions. Based on the formula for calculating exercise metabolic equivalent, the data on exercise type and duration are converted into planned exercise data.

7. The method for generating a personalized nutrition plan for height growth as described in claim 6, characterized in that: Obtain the actual execution data of the user's daily action plan, compare the actual execution data with the daily action plan, and dynamically adjust the daily action plan based on the comparison results. This includes the following steps. By combining manual input from users with automatic data collection from wearable devices, the system records data on the types and amounts of food consumed by users, as well as the types and durations of exercise completed. Convert the actual types and amounts of food consumed into actual nutritional data, convert the actual types and durations of exercise into actual exercise consumption data, calculate the difference between the actual nutritional data and the planned nutritional data in the daily action plan, and calculate the difference between the actual exercise consumption data and the planned exercise data in the daily action plan. Based on the differences between actual and planned nutritional data, and between actual and planned exercise data, adjust the food portion and exercise duration in the daily action plan for the following day.

8. A system for generating personalized nutrition plans for height growth, based on the method for generating personalized nutrition plans for height growth according to any one of claims 1 to 7, characterized in that: include, The data acquisition module collects the user's static biological data, parents' height data, health background questionnaire data, and gut microbiota samples. Based on the static biological data and parents' height data, it calculates the user's genetic target height and basal metabolic rate, and generates the user's personal profile. The personalized exercise program generation module extracts the user's height, weight, and leg length data from the user's personal profile, obtains the stress distribution of the user's lower limb epiphyseal plate under different exercise types through biomechanical simulation, and generates a personalized exercise program based on the stress distribution results. The nutrition requirements module estimates daily energy consumption based on basal metabolic rate and personalized exercise plan to obtain the user's total daily energy requirement. Combined with metagenomic analysis of gut microbiota samples, it obtains the user's target daily nutrient requirements. The daily action plan synthesis module develops a daily diet plan based on the target nutrient requirements and personalized exercise plan, specifying the types, portions, and timing of food intake. It integrates the daily diet plan with the personalized exercise plan into a daily action plan, extracting planned nutrient data and planned exercise data from the daily action plan. The dynamic adjustment module obtains the actual execution data of the user's daily action plan, compares the actual execution data with the planned nutrition data and planned exercise data, and dynamically adjusts the daily action plan based on the comparison results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method for generating a personalized nutrition program for height growth as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the method for generating a personalized nutrition program for height growth as described in any one of claims 1 to 7.

Images