Intelligent nutrition management method and system, intelligent bracelet and mobile terminal

Abstract

The invention relates to the field of health management and personalized nutrition guidance, and discloses an intelligent nutrition management method and system, an intelligent bracelet and a mobile terminal.The intelligent nutrition management method comprises the following steps that physiological parameters and behavior data of a user are collected in real time; according to the collected physiological parameters and behavior data, a dynamic physiological state model of the user is constructed, and the model describes the change of the physiological state of the user along with time; on the basis of the dynamic physiological state model of the user and a preset health target, personalized diet suggestions of the user are generated through an optimization algorithm; the diet suggestions generated through optimization are fed back to the user in a chart or character mode, the dynamic physiological state model and the diet suggestions are dynamically adjusted based on real-time feedback data of the user, and circulation optimization is achieved. According to the invention, dynamic monitoring and adjustment of the health state of the user can be realized, accurate and personalized diet suggestions are generated, and scientificity and real-time performance of health management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of health management and personalized nutrition guidance, and specifically to an intelligent nutrition management method, system, intelligent bracelet and mobile terminal. Background Art

[0002] With the continuous improvement of people's health awareness, the demand in the field of health management, especially dietary health management, is increasing day by day. At present, there are already some nutrition management tools on the market, which usually provide dietary advice by manually inputting the user's dietary information or simply using a general nutrition database. However, these existing technologies have certain limitations in practical applications.

[0003] Existing nutrition management solutions usually generate dietary advice based on standardized nutritional theories and combined with the basic information provided by users through questionnaires. Due to the lack of full consideration of individual differences among users, the generated advice cannot effectively meet the health needs of different users. At the same time, the recording of users' dietary information by these tools relies on manual input, which is not only a cumbersome process but also prone to input errors or omissions, further affecting the accuracy of diet management. In addition, existing technologies usually fail to integrate real-time physiological parameters and dynamic behavior data, which makes their monitoring and feedback capabilities for the actual health status of users relatively weak, and it is difficult to provide real-time and personalized guidance.

[0004] In terms of food intake recording, existing technologies rely more on manual estimation or direct invocation of data from standard databases, and fail to achieve accurate identification and quantification of food types and intakes. This deficiency results in relatively low accuracy of users' nutritional intake data, making it difficult for dietary advice to meet the requirements of refined management. At the same time, for users' exercise behaviors and physiological parameters, existing tools usually cannot effectively collect and integrate their dynamic changes, resulting in the lack of adaptability of nutrition management to the real-time status of users.

[0005] In summary, existing technologies have significant deficiencies in terms of personalization, real-time performance, and data collection and processing accuracy, which to a certain extent restricts the effectiveness and experience of users' dietary health management. Summary of the Invention

[0006] Aiming at the deficiencies of the existing technologies, the present invention provides an intelligent nutrition management method, system, intelligent bracelet and mobile terminal, which solves the problem that the existing nutrition management methods are not accurate and personalized enough in dietary advice due to the lack of real-time analysis and dynamic adjustment capabilities for individual differences among users.

[0007] To achieve the above objectives, the present invention is realized through the following technical solutions: An intelligent nutrition management method, including the following steps: Collect the physiological parameters and behavioral data of users in real time. The physiological parameters include blood glucose level, body fat percentage, and heart rate, and the behavioral data includes food intake information and exercise amount. Construct a dynamic physiological state model of the user based on the collected physiological parameters and behavioral data. The dynamic physiological state model is used to describe the change of the user's physiological state over time. Based on the user's dynamic physiological state model and the preset health goals, generate personalized diet recommendations for the user through an optimization algorithm; feedback the optimized diet recommendations to the user.

[0008] Preferably, the dynamic physiological state model is a non-linear dynamic model based on partial differential equations, which is used to describe the change of the user's physiological state parameters over time. The non-linear dynamic model includes: Set the user's physiological parameters as the state variable x(t), and the state variable includes the user's blood glucose level, body fat percentage, and heart rate; set the user's ingested nutrients as the control variable u(t), and the control variable includes the intake amounts of protein, fat, and carbohydrates. Set the user's exercise behavior as the external input w(t), and the external input includes the exercise amount and sleep duration. Establish a dynamic physiological state model of the user according to the following partial differential equation: Among them, f is the state transition function, which is used to describe the comprehensive influence of the state variable, control variable, and external input on the user's physiological state. Construct a dynamic change model of blood glucose level to describe the influence of the user's carbohydrate intake, exercise behavior, and natural blood glucose consumption on the blood glucose level: Among them, k 1 represents the natural blood glucose consumption coefficient, k 2 represents the influence coefficient of carbohydrate intake on the blood glucose level, k 3 represents the reduction coefficient of exercise behavior on the blood glucose level. Construct a dynamic change model of body fat percentage to describe the influence of the user's fat intake, exercise behavior, and natural body fat consumption on the body fat percentage: Among them, k 4 represents the natural body fat consumption coefficient, k 5 represents the influence coefficient of fat intake on the body fat percentage, k 6 represents the reduction coefficient of exercise behavior on the body fat percentage.

[0009] Preferably, the steps of generating personalized diet recommendations for the user through an optimization algorithm based on the user's dynamic physiological state model and the preset health goals include: Define a health objective function to represent the deviation between the user's current physiological state and the target physiological state. The objective function includes minimizing the cumulative value of the deviation of the user's current physiological parameters from the preset healthy target state and optimizing the constraint on diet intake. The objective function is defined as: where \(x(t)\) represents the user's current physiological state parameters, \(x target represents the user's target physiological state parameters, \(u(t)\) represents the diet intake variables, including the intakes of protein, fat, and carbohydrates, and \(\alpha\) is the weight parameter; Construct the Hamiltonian function to combine the health objective function and the user's dynamic physiological state model, which is defined as: where \(\lambda\) represents the adjoint variable, describing the sensitivity of the health objective function to the state variable, and \(f(x(t), u(t), w(t))\) is the dynamic physiological state model; Solve the optimal diet intake strategy through the optimal control algorithm. The steps include: Calculate the dynamic changes of the state variables, satisfying: Calculate the dynamic changes of the adjoint variables, satisfying: Solve the optimal diet intake variables according to the optimality conditions: Generate personalized diet recommendations for the user based on the calculation results of the optimization algorithm.

[0010] Preferably, the optimization algorithm is dynamically adjusted by combining the user's behavior data and physiological parameters collected in real time, specifically including: Periodically collect and update the user's physiological state parameters; Calibrate the dynamic physiological state model based on the latest data; Re-optimize the diet intake strategy according to the calibrated model.

[0011] Preferably, the food intake information is collected through a camera combined with image recognition technology, and the image recognition technology is used to identify food types and estimate food portions.

[0012] Preferably, the optimized diet recommendations include: The specific intake time of each food; The target intake of each nutrient; Dynamically adjust the intake recommendations in combination with the user's daily exercise amount.

[0013] Preferably, the method further includes a step of dynamically adjusting the dynamic physiological state model and diet recommendations based on the user's real-time feedback data to form a cyclic optimization, specifically including: Periodically collect the user's real-time feedback data, where the feedback data includes the user's latest physiological parameters and behavior data; Update the state variables and model parameters of the dynamic physiological state model based on the real-time feedback data, specifically including: Update the user's physiological parameters and adjust the initial value of the state variable x(t) to reflect the latest physiological state; Correct the parameters in the dynamic model according to the feedback data, where the parameters include the natural blood glucose consumption coefficient, the influence coefficients of exercise on blood glucose and body fat percentage, and the effect coefficients of ingested nutrients on the physiological state; Re-optimize the user's health objective function according to the updated dynamic physiological state model, and generate a new diet intake strategy by solving the optimal control algorithm; Compare the deviation between the user's actual physiological state and the preset target state. If the deviation exceeds the threshold range, start the fast adjustment mechanism and adjust the diet intake recommendation and intake time according to the latest optimization result; Feed back the updated diet recommendation to the user, and display the latest trend of the health state and the adjustment basis of the optimization plan in the form of a chart to complete the cyclic optimization.

[0014] The present invention also provides an intelligent nutrition management system, which includes: A data collection module for real-time collecting the user's physiological parameters and behavior data, where the physiological parameters include blood glucose level, body fat percentage, and heart rate, and the behavior data includes food intake information and exercise amount; A dynamic modeling module for constructing the user's dynamic physiological state model based on the collected physiological parameters and behavior data, where the model describes the change of the user's physiological state over time; An optimization algorithm module for generating the user's personalized diet recommendation according to the dynamic physiological state model and the user's health objective; A feedback module for feeding back the optimized diet recommendation to the user in the form of a chart or text; An adjustment module for dynamically updating the dynamic physiological state model and diet recommendation based on the user's real-time feedback data to achieve cyclic optimization.

[0015] The present invention also provides an intelligent bracelet, which includes: A physiological data collection unit for collecting the user's blood glucose level, heart rate, and body fat percentage; A data transmission unit for transmitting the collected physiological parameter data to the dynamic modeling module of the intelligent nutrition management system; a display unit for displaying health status data and information related to dynamically adjusted dietary recommendations to the user in real time.

[0016] The present invention also provides a mobile terminal, which includes: A camera for recording the user's food intake information and transmitting the information to the intelligent nutrition management system for analysis and processing; A data interaction module for receiving the dietary recommendations optimized and generated by the intelligent nutrition management system and transmitting the user's real-time feedback data to the adjustment module of the system; A display module for displaying the user's daily nutrition intake trend, intake recommendations, and changes in real-time health status in the form of charts or text.

[0017] The present invention provides an intelligent nutrition management method, system, intelligent bracelet, and mobile terminal. It has the following beneficial effects: 1. Through the dynamic physiological state model, the present invention combines the real-time collected user physiological parameters and behavior data to generate personalized dietary recommendations. Compared with the traditional solutions that rely on static health data and general nutrition standards, the present invention can update the model in real time and optimize the recommendations according to the individual differences of users, effectively improving the accuracy and adaptability of dietary guidance and meeting the health management needs of different users.

[0018] 2. The present invention collects key physiological data such as the user's blood glucose level, body fat percentage, and heart rate through the intelligent bracelet and mobile terminal, and dynamically updates the model and dietary plan through the real-time feedback mechanism. It realizes the continuous tracking and real-time adjustment of the user's health status, ensures that the dietary recommendations are always consistent with the actual health needs of the user, and thus improves the scientificity and real-time nature of health management.

[0019] 3. Through the display module and interaction module of the mobile terminal, the present invention can intuitively display the user's daily nutrition intake trend, changes in health status, and personalized dietary recommendations, and support the user to give feedback on the actual intake situation. This function enhances the user's participation and management awareness, helps the user more easily understand and implement the nutrition management plan, and improves the effectiveness of health intervention.

[0020] 4. Through image recognition technology and sensor integration, the present invention automatically records the user's food intake information and exercise amount without the need for the user to manually input data, thus significantly reducing the usage threshold. At the same time, the optimization algorithm and adjustment module of the system can automatically generate dietary recommendations and perform dynamic optimization, enabling the user to conveniently obtain real-time health guidance.

[0021] 5. The present invention realizes the closed-loop design of health management by collecting real-time feedback data of users and dynamically correcting model parameters and diet plans in combination with a cyclic optimization mechanism. This mechanism not only improves the system's efficiency in achieving health goals but also can adapt to the long-term changes in users' health status, contributing to users forming a sustainable healthy lifestyle. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a schematic flowchart of the method of the present invention; Figure 2 is a schematic structural diagram of the system of the present invention; Figure 3 is a schematic structural diagram of the smart bracelet of the present invention; Figure 4 is a schematic structural diagram of the mobile terminal of the present invention.

[0023] Among them, 10 is the intelligent nutrition management system; 11 is the data collection module; 12 is the dynamic modeling module; 13 is the optimization algorithm module; 14 is the feedback module; 15 is the adjustment module; 20 is the smart bracelet; 21 is the physiological data collection unit; 22 is the data transmission unit; 23 is the display unit; 30 is the mobile terminal; 31 is the camera; 32 is the data interaction module; 33 is the display module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] Please refer to the attached Figure 1 , the present invention provides an intelligent nutrition management method, aiming to realize the dynamic monitoring of users' health status and personalized diet management, by constructing a dynamic physiological state model of users and generating personalized diet suggestions for users in combination with an optimization algorithm. The present invention realizes the intelligent management of health goals by collecting users' physiological parameters and behavior data in real time and dynamically updating the model and diet plan.

[0026] As Figure 1 shown, the intelligent nutrition management method may include the following steps: S1. Collect users' physiological parameters and behavior data in real time; S2. Construct a dynamic physiological state model of users according to the collected data; S3. Generate personalized diet suggestions for users based on the dynamic physiological state model of users and preset health goals; S4. Feed the optimized diet recommendations back to the user.

[0027] The following elaborates on each step of this method in detail.

[0028] In this embodiment, step S1 of the intelligent nutrition management method aims to collect the user's physiological parameters and behavioral data in real time, providing the basic input for subsequent construction of a dynamic physiological state model and optimization of diet recommendations. The collected data mainly includes the user's physiological parameters (such as blood glucose level, body fat percentage, and heart rate) and behavioral data (such as food intake information and exercise volume). These data are obtained and transmitted in real time through intelligent devices and terminals.

[0029] As an option, the user's physiological parameters are collected in real time by an intelligent bracelet, a continuous blood glucose monitoring device, or other wearable devices. Specifically, the collected physiological parameters include the following: Blood glucose level: Obtain the dynamic change value of the user's blood glucose concentration through a continuous blood glucose monitoring device, with a sampling frequency of once per minute, to reflect the user's immediate metabolic state. It should be noted that the collection of this data can be achieved through micro-sensor technology and a wireless transmission module. The sensor will measure the blood glucose level by interacting with interstitial fluid through the skin and record it in the form of a time series.

[0030] Body fat percentage: Measure the body fat percentage through an intelligent bracelet or a body fat scale using bioelectrical impedance technology. The sampling frequency can be once a day or set to a higher frequency according to the user's needs. As an option, the body fat percentage data can be combined with the user's height and weight for calculation to dynamically adjust the user's dietary needs.

[0031] Heart rate: Real-time monitor the heart rate through the optical sensor (such as a sensor based on PPG technology) in the intelligent bracelet, with a sampling frequency of once per second. The dynamic change of the heart rate can reflect the user's exercise state or emotional fluctuations and is used to assist in evaluating the user's immediate health status.

[0032] In a possible implementation, the user's behavioral data is collected through the cooperation of a mobile terminal and an intelligent bracelet. Specifically, the collection of behavioral data includes the following: Food intake information: Record the types and intake portions of the user's meals through the camera of the mobile terminal combined with image recognition technology. Exemplarily, the image recognition technology can process the captured food images based on a trained deep learning model (such as a convolutional neural network), match the food types with a preset nutrition database, and identify the nutritional components such as calories, proteins, fats, and carbohydrates of the food. It should be noted that after the images captured by the camera are transmitted to the server, the intake portion of each food is calculated in combination with a weight estimation algorithm, which can be completed by manually inputting weight information or with the help of an intelligent dinner plate for portion estimation.

[0033] Exercise volume: The accelerometer and gyroscope in the smart bracelet are used to record the user's exercise data, including the number of steps, exercise time, and exercise intensity. Specifically, the user's exercise data can estimate the calories burned during exercise through a calorie consumption model, which calculates the calorie consumption value based on the user's weight, exercise type, and duration, and is used to dynamically adjust the diet plan subsequently.

[0034] It should be noted that the physiological parameters and behavior data collected in this embodiment are stored in the form of a time series and transmitted to the cloud or local data processing unit through a wireless transmission module (such as Wi-Fi or Bluetooth). The data processing unit will format and normalize the data to ensure the consistency and availability of the data. For example, outliers (such as data loss or abnormal deviation values caused by sensor failures) will be removed through statistical methods. The processed data will be used as the input for subsequent dynamic model construction and optimization algorithms.

[0035] In some embodiments, to ensure the stability and accuracy of data collection, the system can set up a data redundancy collection mechanism. For example, the blood glucose level and body fat percentage data of the user can be cross-validated through different devices (such as a smart bracelet and a body fat scale). When there is a large deviation between the collection results of the two, the system will prompt the user to re-measure.

[0036] It can be understood that the physiological parameters and behavior data collected in this step are the basis for subsequent modeling and optimization algorithms, and their accuracy and real-time nature directly affect the performance of the entire system and the effectiveness of the suggestions. For example, inaccurate food intake information will lead to deviations in the calculation of the user's nutritional intake, and the lack of exercise data may not reflect the user's actual energy consumption status.

[0037] As an option, to improve the intelligence of data collection, the system can integrate multiple data collection methods. For example, by combining the smart bracelet worn by the user and the camera of the mobile terminal, comprehensive data of the user can be obtained through multi-sensor fusion technology, and at the same time, the computing power of the cloud server is used for real-time processing and synchronization.

[0038] By achieving dynamic, efficient, and multi-dimensional data acquisition in actual operation, it provides sufficient input data support for subsequent model construction and optimization algorithms.

[0039] In this embodiment, step S2 of the intelligent nutrition management method is used to construct a dynamic physiological state model of the user based on the physiological parameters and behavior data collected in real time. This model aims to describe the dynamic changes of the user's physiological state over time and provide support for generating personalized diet suggestions for subsequent optimization algorithms.

[0040] It should be noted that the dynamic physiological state model is constructed based on partial differential equations (PDEs) and is used to describe the dynamic changes of physiological parameters (such as blood glucose level, body fat percentage, and heart rate) under the influence of external factors such as dietary intake and exercise behavior.

[0041] As an option, the dynamic physiological state model takes time t as the independent variable, sets the user's physiological parameters as the state variable x(t), the user's dietary intake as the control variable u(t), and the behavior data such as the user's exercise behavior as the external input w(t). In this case, the change in the user's physiological state can be represented by the following partial differential equation: where f is the state transition function that describes the relationship between the state variable x(t), the control variable u(t), and the external input w(t).

[0042] In a possible implementation, the state variable x(t) of the dynamic physiological state model includes the following parameters: Blood glucose level x 血糖 (t), which is used to reflect the user's instantaneous blood glucose dynamics; Body fat percentage x 体脂率 (t), which is used to reflect the user's fat metabolism state; Heart rate x 心率 (t), which is used to describe the user's cardiovascular health state.

[0043] Exemplarily, the control variable u(t) represents the user's nutrient intake, specifically including: Protein intake u 蛋白质 (t); Fat intake u 脂肪 (t); Carbohydrate intake u 碳水 (t).

[0044] The external input w(t) represents the user's behavior data, specifically including: Exercise intensity w 运动 (t); Sleep duration w 睡眠 (t).

[0045] Specifically, the state transition function f in the dynamic physiological state model is defined based on the user's metabolic rules and behavior influence factors. For example, the dynamic change of blood glucose level can be expressed as: where: k 1 represents the rate coefficient of natural blood glucose consumption; k 2Represents the growth coefficient of carbohydrate intake on blood glucose level; k 3 Represents the rate coefficient of exercise behavior on the decrease of blood glucose level.

[0046] Similarly, the dynamic change of body fat percentage can be expressed as: Where: k 4 Represents the rate coefficient of natural body fat consumption; k 5 Represents the influence coefficient of fat intake on the increase of body fat percentage; k 6 Represents the rate coefficient of exercise behavior on the decrease of body fat percentage.

[0047] As an option, the model parameter k 1 , k 2 , k 3 , k 4 , k 5 , k 6 The specific values can be obtained by fitting the user's historical data or can be initially set based on experimental data. It should be noted that these parameters can be dynamically adjusted with the input of the user's real-time data to adapt to individual differences.

[0048] In some embodiments, to ensure the real-time performance and accuracy of the model, the dynamic physiological state model can be initialized in combination with the user's historical health data. For example, the user's historical blood glucose data can be used to fit the parameters k 1 and k 2 , so as to better reflect the user's metabolic law. In addition, the model can dynamically adjust the parameters k 3 , k 6 according to the user's long-term exercise records to optimize the model's reflection of the impact of exercise.

[0049] It can be understood that the core of the dynamic physiological state model lies in the mathematical description of the changes in the user's physiological state, and its accuracy and real-time performance directly affect the effect of subsequent optimization algorithms. Therefore, the implementation of the model needs to be flexible and extensible to meet the individualized needs of different users.

[0050] It should be noted that the dynamic physiological state model in this embodiment can also be extended in combination with other physiological data (such as blood pressure, blood oxygen saturation), but these extensions do not affect the basic principles and implementation methods of the embodiments of the present invention.

[0051] In this embodiment, step S3 of the intelligent nutrition management method generates personalized diet recommendations for the user by using an optimization algorithm based on the user's dynamic physiological state model and preset health goals. The core of this step lies in constructing a health objective function and combining it with the dynamic physiological state model to solve for the optimal control strategy, thereby generating a diet plan that meets the user's health needs.

[0052] As an option, the health objective function is used to describe the deviation between the user's actual physiological state and the preset health goals, and to control the impact of dietary intake behavior on the optimization results. Specifically, the health objective function can be defined in the following form: J = ∫ 0 T [∥x(t) - z target ∥ 2 + α∥u(t)∥ 2 dt Where: x(t) is the user's dynamic physiological state variable, including blood glucose level, body fat percentage, and heart rate; x target is the user's health target state, such as the ideal blood glucose level and target body fat percentage; u(t) is the user's dietary intake variable, including the intakes of protein, fat, and carbohydrates; α is the control weight parameter, which is used to balance the weights between physiological state adjustment and dietary intake behavior.

[0053] In a possible implementation, the optimization of the objective function is achieved by constructing the Hamiltonian function, which is used to describe the relationship between the health objective deviation, dietary intake behavior, and the dynamic physiological state model. The Hamiltonian function is defined as: Where: λ is the adjoint variable, which is used to describe the sensitivity of the health objective deviation to the user's physiological state; f(x(t), u(t), w(t)) is the state transition function of the dynamic physiological state model, which represents the change of the user's physiological state over time.

[0054] It should be noted that to solve for the optimal dietary intake strategy, it is necessary to solve it in combination with the optimality conditions of the Hamiltonian function. Specifically, the solution process includes the following three parts: State equation: Used to describe the change of the user's physiological state variable over time, expressed as: Adjoint equation: Used to describe the change of the adjoint variable over time, expressed as: Optimality conditions: used to determine the optimal diet intake strategy for the user, expressed as: Exemplarily, during the solution process, the above equation can be iteratively calculated by numerical methods (such as gradient descent method or projection algorithm) to generate the optimal diet intake strategy u * (t). As an option, the iterative process can update the initial conditions according to the user's real-time physiological parameters, thereby ensuring the accuracy and real-time nature of the results.

[0055] Specifically, the generated diet recommendations include the following: The specific intake amount of each food, for example, the protein intake is 50 grams, the carbohydrate intake is 100 grams, and the fat intake is 20 grams; The specific intake time for each meal, for example, breakfast is consumed at 8 am, and the proportion of carbohydrates, proteins, and fats is adjusted to suit the user's health goals; The recommended types of food for each meal, for example, it is recommended to consume whole grains, low-fat dairy products, and lean meats.

[0056] In some embodiments, to further improve the personalization degree of the optimization results, the diet plan can be dynamically adjusted by combining the user's exercise amount and sleep data. For example, when the user's exercise data indicates a high exercise intensity on the same day, the intake ratios of carbohydrates and proteins can be appropriately increased to meet their energy requirements.

[0057] It should be noted that the personalized diet recommendations generated in this embodiment can be fed back to the user through a mobile terminal in the form of charts or texts, so that the user can intuitively understand the diet plan and its health significance. In addition, the dynamic update mechanism of the diet recommendations can ensure that they adapt to the changes in the user's real-time health status.

[0058] It can be understood that the optimization algorithm is the core of this embodiment. By combining the dynamic physiological state model and health goals, it generates a highly personalized diet plan through iterative calculation, providing a scientific basis for the user's health management.

[0059] In this embodiment, step S4 of the intelligent nutrition management method feeds back the optimized and generated personalized diet recommendations to the user through a mobile terminal or other interactive devices. The purpose of this step is to present the calculation results of the optimization algorithm to the user in an intuitive and convenient manner, enabling the user to manage their daily diet based on the provided diet recommendations and making real-time adjustments according to the user's feedback data when necessary.

[0060] As an option, the feedback forms of diet suggestions include charts, text descriptions, and visual interactive interfaces. Specifically, the optimized diet suggestion content may include the following items: The intake amount of each nutrient, such as the specific grams of protein, fat, and carbohydrates; The types of foods recommended for each meal, such as oats, eggs, and milk are recommended for breakfast; The specific intake time for each meal, such as having breakfast at 8 am, lunch at 1 pm, and dinner is recommended to be completed before 6 pm.

[0061] In a possible implementation, the mobile terminal is used to display the detailed information of the daily diet plan. Exemplarily, the mobile terminal can generate the following content: A time-sharing chart showing the comparison between the calorie intake suggestions and the targets for each meal of the user; A diet plan list showing the types and portions of foods required for each meal in chronological order; A text explanation for the user's health goals, such as "To achieve the goal of reducing body fat percentage, it is recommended to reduce the fat intake and appropriately increase the protein intake".

[0062] It should be noted that the feedback data is not limited to static display, but can be dynamically adjusted in combination with the user's real-time data. For example, when there are significant fluctuations in the user's blood sugar level or exercise amount, the system can dynamically modify the diet suggestions based on the real-time output of the optimization algorithm. For example, if the user's exercise intensity is higher than expected, the system can recommend increasing the carbohydrate intake in real time.

[0063] As an option, the personalized diet suggestions in the feedback can be pushed to the user through message notifications or in-app prompts. Specifically, when the user is about to start a certain meal, the system can send a reminder message containing the recommended types and portions of foods. For example, the notification content can be "For dinner, it is recommended to have 200 grams of chicken breast, 50 grams of brown rice, and 150 grams of broccoli".

[0064] In some embodiments, in order to enhance the user experience, the feedback of diet suggestions can also include educational content, such as providing detailed information about the nutritional components of foods, scientific suggestions for healthy eating, or dietary taboos. Exemplarily, the user can click on a specific diet suggestion to view the scientific basis behind the suggestion, such as "Increasing protein intake helps to enhance muscle mass".

[0065] It can be understood that the display interface of the mobile terminal should present the optimization results in a user-friendly manner, avoiding overly complex interface designs that reduce the user's willingness to use. For example, the chart form of display should adopt a clear color scheme and layout, and the numerical information should be accurate and concise.

[0066] It is understandable that the display interface of the mobile terminal should present the optimization results in a user-friendly manner, avoiding overly complex interface designs that may reduce the user's willingness to use. For example, in the form of charts, clear color schemes and layouts should be adopted, and numerical information should be accurate and concise.

[0067] It should be noted that the feedback of dietary recommendations is not only a one-way output process, but a two-way interaction process between the user and the system. The user's feedback data (such as actual intake data) will be transmitted back to the adjustment module of the system in real time for correcting the dynamic physiological state model and optimizing the algorithm, so as to achieve continuous optimization and closed-loop management of dietary recommendations.

[0068] As an option, the feedback of dietary recommendations can also be achieved through intelligent devices such as voice assistants. For example, the system can remind the user of the intake plan in voice form and record the actual intake according to the user's voice feedback. This can further reduce the complexity of user operations.

[0069] The dietary recommendation feedback mechanism provided in this embodiment fully combines the output results of the optimization algorithm and the user interaction requirements, and can achieve precise, personalized and dynamic display of the diet plan.

[0070] Generally speaking, the present invention collects the user's physiological parameters and behavior data in real time, describes the change of the user's physiological state over time based on the dynamic physiological state model, and combines the health goals to generate personalized dietary recommendations through an optimization algorithm. The dietary recommendations are fed back to the user in the form of charts or text through the mobile terminal, and support dynamic adjustment according to real-time data, realizing personalized and dynamic health management. This method can accurately reflect the individual differences of users, provide scientific and sustainable dietary guidance for users, and improve the efficiency and effect of health management.

[0071] As a preferred embodiment of the present invention, the method further includes the step of dynamically adjusting the dynamic physiological state model and dietary recommendations based on the user's real-time feedback data, and continuously improving the accuracy and personalization level of dietary recommendations by forming a cyclic optimization mechanism. The specific implementation method is as follows: In this embodiment, the real-time feedback data of the user is periodically collected as the basic input for dynamic adjustment. The feedback data includes the user's latest physiological parameters and behavior data, where the physiological parameters can be blood glucose level, body fat percentage and heart rate collected by a smart bracelet, and the behavior data includes the user's actual food intake and exercise amount. It should be noted that the real-time feedback data is stored in the form of a time series, and after being formatted and normalized by the data processing unit, it is input into the dynamic physiological state model.

[0072] In a possible implementation, the state variables and model parameters of the dynamic physiological state model are updated based on real-time feedback data. Specifically, the physiological parameters of the user are updated, and the latest physiological state is reflected by adjusting the initial values of the state variables. For example, when the user's latest blood glucose level is higher than the model prediction value, the system will update the initial value of x 血糖 (t) in the model according to the real-time data. In addition, the parameters in the dynamic model are corrected based on the user's feedback data, such as the natural blood glucose consumption coefficient k 1 , the influence coefficient k 3 of exercise on blood glucose, the effect coefficient k 2 of carbohydrate intake on blood glucose, and the body fat percentage-related parameters k 4 , k 5 and k 6 . It should be noted that the parameter correction can be achieved through machine learning algorithms, such as using the user's historical data to fit and dynamically correct the model parameters.

[0073] As an option, the user's health objective function is re-optimized according to the updated dynamic physiological state model. The optimization process includes re-solving the objective function through an optimal control algorithm to generate a new diet intake strategy.

[0074] Exemplarily, after the optimization is completed, the system will compare the deviation between the user's actual physiological state and the preset target state. If the deviation exceeds the preset threshold range, the system will activate a quick adjustment mechanism to make the user's health state return to the target range faster by adjusting the latest generated diet intake strategy (including food types, portions, and intake times). For example, when it is detected that the user's blood glucose level is significantly higher than the target value, the system may immediately adjust the carbohydrate intake for the next meal and send the modified diet advice to the user through the mobile terminal.

[0075] It should be noted that feeding back the updated diet advice to the user is the last step of the cyclic optimization process. The optimization results are presented in the form of charts or text, intuitively showing the latest trends of the user's health state and the basis for adjusting the diet advice. For example, the chart can show the comparison between the user's current blood glucose level and the target blood glucose range, the proportion of nutrients after the intake adjustment, and the expected change trend of the health state in the future.

[0076] In a possible implementation, the cyclic optimization is completed through the cooperation of a smart bracelet and a mobile terminal. The user can view the real-time updated diet advice through the interface and feedback the actual execution situation through an interactive method. For example, the user can mark in the interface whether they have followed the advice for intake or manually adjust the intake data, and the system will correct the model and optimize the advice again according to the new feedback data to ensure the real-time and effectiveness of the dynamic adjustment.

[0077] It can be understood that the dynamic adjustment mechanism in this embodiment can continuously track and dynamically optimize the user's health status by periodically collecting feedback data, updating model parameters, and optimizing the health objective function, thereby ensuring the accuracy and personalization of dietary recommendations and meeting the user's health management needs. The above cyclic optimization steps provide closed-loop support for the entire intelligent nutrition management method and are an important guarantee for realizing real-time adjustment and personalized management.

[0078] Please refer to the attached Figure 2 , the present invention also provides an intelligent nutrition management system 10, which includes a data collection module 11, a dynamic modeling module 12, an optimization algorithm module 13, a feedback module 14, and an adjustment module 15. Each module cooperates with each other to jointly realize the intelligent nutrition management of users. Specifically as follows: Data collection module 11, this module is used to collect the physiological parameters and behavior data of users in real time. Physiological parameters include but are not limited to blood glucose level, body fat percentage, and heart rate, and these data are obtained through collection devices such as smart bracelets, body fat scales, or continuous blood glucose monitoring devices. Behavior data includes the user's food intake information and exercise amount, where the food intake information can be collected through the camera of the mobile terminal combined with image recognition technology, and the exercise amount can be recorded through the accelerometer and gyroscope in the smart bracelet. The collected data will be transmitted to the system through the wireless transmission module to provide support for subsequent processing.

[0079] Dynamic modeling module 12, this module constructs a dynamic physiological state model of the user based on the physiological parameters and behavior data provided by the data collection module. The model is used to describe the dynamic changes of the user's physiological state over time. This module can initialize the model according to the user's historical health data and dynamically update it in combination with real-time data. After the model is constructed, it will provide an input basis for the optimization algorithm module.

[0080] Optimization algorithm module 13, this module generates personalized dietary recommendations according to the user's dynamic physiological state model generated by the dynamic modeling module and the user's preset health goals. The optimization algorithm module calculates the user's dietary intake strategy by comparing the user's current physiological state with the health goals and combining the health management requirements. The dietary recommendations include the types of foods, intake portions, and specific intake times for each meal, providing accurate health diet guidance for users.

[0081] Feedback module 14, this module feedbacks the dietary recommendations generated by the optimization algorithm module to the user in a user-friendly form. The dietary recommendations can be displayed on the mobile terminal in the form of charts or text, and the content includes the daily nutritional intake trend, specific details of the intake recommendations, and the change trend of the health status. This module supports the interaction operation between the user and the system, for example, allowing the user to mark whether the intake plan is completed or manually adjust the actual intake data.

[0082] Adjustment Module 15. This module is used to dynamically update the dynamic physiological state model and dietary recommendations based on the user's real-time feedback data, so as to achieve cyclic optimization. The real-time feedback data includes the user's latest physiological parameters and behavioral data, such as the user's actual intake and exercise volume. The adjustment module recalculates the health goals by correcting the state variables and parameters of the dynamic model and generates updated dietary recommendations. This module supports a rapid adjustment mechanism. When the user's actual physiological state deviates from the target range, it can timely modify the recommended content to ensure the personalization and accuracy of diet management.

[0083] The various modules cooperate through data streams. The data acquisition module provides real-time data support for the dynamic modeling module. The dynamic modeling module provides a model basis for the optimization algorithm module. The dietary recommendations generated by the optimization algorithm module are transmitted to the user through the feedback module. The user's feedback data is then used by the adjustment module to update the results of the dynamic modeling module and the optimization algorithm module. The entire system forms a closed loop to ensure the dynamic and real-time operation of the system.

[0084] The system of this embodiment can be used to execute the above method embodiment, and its principle and technical effects are similar, so they will not be elaborated here.

[0085] Please refer to the appendix Figure 3 , The present invention also provides a smart bracelet 20, which is used to collect the user's physiological parameters, transmit data and display the user's health status and dietary recommendations in real time. The smart bracelet includes a physiological data acquisition unit 21, a data transmission unit 22 and a display unit 23. Each unit cooperates with each other to realize the dynamic monitoring and feedback of the user's health data. Specifically as follows: Physiological Data Acquisition Unit 21. This unit is used to collect the user's blood glucose level, heart rate and body fat percentage in real time. The collection of blood glucose level is realized through a built-in continuous blood glucose monitoring module, which can collect data by interacting with interstitial fluid through the skin; the collection of heart rate is completed through an optical heart rate sensor, and the PPG (Photoplethysmography) technology is used to obtain the user's heart rate signal; the collection of body fat percentage is completed through bioelectrical impedance technology, and the bracelet calculates the body fat percentage by measuring the change of the user's skin resistance. The acquisition unit supports high-frequency sampling, and the specific sampling frequency can be configured according to the user's needs, such as once per second or once per minute.

[0086] Data Transmission Unit 22. This unit is used to transmit the collected physiological parameter data to the dynamic modeling module of the intelligent nutrition management system. The data transmission method supports wireless communication, including protocols such as Bluetooth, Wi-Fi or NFC. The specific transmission method can be selected according to the connection requirements between the smart bracelet and the intelligent nutrition management system. During the transmission process, the data transmission unit formats and encrypts the collected data to ensure the security and compatibility of data transmission. This unit supports seamless connection with a variety of smart devices (such as mobile terminals or servers) and can ensure the real-time nature of data transmission.

[0087] A display unit 23, which is used to display health status data and information related to dynamically adjusted dietary recommendations to the user in real time. The health status data includes the current blood glucose level, heart rate, and body fat percentage. The display unit presents the health status trend in a graphical manner through a user-friendly interface, and the user can intuitively view the relevant information through the bracelet screen. In addition, the display unit is also used to display the dynamically adjusted dietary recommendations generated by the intelligent nutrition management system, specifically including the recommended food types, intake portions, and intake times for each meal. The display unit supports touch operations, and the user can view more detailed health data and dietary recommendations by swiping or clicking.

[0088] The smart bracelet in this embodiment can be used to execute the above method embodiment, and its principle and technical effects are similar, which will not be elaborated here.

[0089] Please refer to the appendix Figure 4 , the present invention also provides a mobile terminal 30, which is used to collect the user's food intake information, receive and feedback data, and display the user's nutritional intake trend and health status. The mobile terminal includes a camera 31, a data interaction module 32, and a display module 33. Each module works together to achieve efficient interaction between the user and the intelligent nutrition management system. Specifically as follows: A camera 31, which is used to record the user's food intake information and transmit the recorded information to the intelligent nutrition management system for analysis and processing. The camera can identify the food type by taking pictures of the food eaten by the user and combining the preset deep learning model and image recognition technology, and estimate the food portion and calories. It should be noted that to improve the recognition accuracy, the camera can work together with a weight estimation device (such as a smart plate or a manual input system) to further improve the accuracy of the food intake data. The camera supports high-definition shooting, can clearly capture the food feature information, and reduces the bandwidth requirements for data transmission and processing through a compression algorithm.

[0090] A data interaction module 32, which is used to realize the two-way data transmission between the mobile terminal and the intelligent nutrition management system. Specifically, this module receives the personalized dietary recommendations optimized by the intelligent nutrition management system, such as the recommended food types, intake portions, and intake times. At the same time, this module can also transmit the user's real-time feedback data to the adjustment module of the intelligent nutrition management system. For example, the user can manually input the actual intake portion of the food or mark whether they have eaten according to the recommendation through the mobile terminal, and this module will upload these data in real time for updating the dynamic physiological state model of the system. The data interaction module supports multiple wireless communication methods, including Wi-Fi, Bluetooth, and mobile networks, to ensure the stability and real-time nature of data transmission.

[0091] Display module 33. This unit is used to display the user's daily nutritional intake trend, intake recommendations, and changes in real-time health status in the form of charts or text. Specifically, the display module can intuitively display the comparison between the calories, proteins, fats, and carbohydrates actually consumed by the user and the target intake values in the form of a time-sharing graph. In addition, the display module can also provide detailed dietary advice content, such as recommended foods and intake times for each meal. It should be noted that the display module supports an interactive function, and the user can view more detailed health status information, such as the recent blood glucose change trend or the dynamic change of body fat percentage, through click or swipe operations.

[0092] Through the organic combination of the camera, data interaction module, and display module in this embodiment, the mobile terminal realizes the efficient collection of the user's food intake data, the feedback of personalized dietary advice, and the dynamic display of the health status, providing a comprehensive nutritional management interaction platform for the user. The efficient cooperation of the above functional modules enables the mobile terminal to play an important role in the intelligent nutritional management system, improving the practicality and user experience of the overall system.

[0093] The mobile terminal in this embodiment can be used to execute the above method embodiment, and its principle and technical effect are similar, so they will not be elaborated here.

[0094] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent nutrition management method, characterized in that: The following steps are involved: Collecting the user's physiological parameters and behavioral data in real time, wherein the physiological parameters include blood sugar level, body fat percentage and heart rate, and the behavioral data includes food intake information and exercise volume; Constructing a dynamic physiological state model of the user based on the collected physiological parameters and behavior data, wherein the dynamic physiological state model is used to describe changes in the user's physiological state over time; Generate personalized dietary recommendations for users through optimization algorithms based on the user's dynamic physiological state model and preset health goals; The optimized dietary recommendations are fed back to the user.

2. The intelligent nutrition management method according to claim 1, characterized in that: The dynamic physiological state model is a nonlinear dynamic model based on partial differential equations, which is used to describe the changes of the user's physiological state parameters over time. The nonlinear dynamic model includes: The user's physiological parameters are set as state variables x(t), wherein the state variables include the user's blood sugar level, body fat percentage, and heart rate; the user's intake of nutrients is set as control variables u(t), wherein the control variables include the intake of protein, fat, and carbohydrates; The user's exercise behavior is set as an external input w(t), wherein the external input includes the amount of exercise and the length of sleep; The user's dynamic physiological state model is established according to the following partial differential equation: Among them, f is the state transfer function, which is used to describe the comprehensive impact of state variables, control variables and external inputs on the user's physiological state; Build a dynamic change model of blood sugar levels to describe the impact of users' carbohydrate intake, exercise behavior, and natural blood sugar consumption on blood sugar levels: Among them, k1 represents the natural consumption coefficient of blood sugar, k2 represents the influence coefficient of carbon water intake on blood sugar level, and k3 represents the reduction coefficient of exercise behavior on blood sugar level; Construct a dynamic change model of body fat percentage to describe the impact of user fat intake, exercise behavior, and natural body fat consumption on body fat percentage: Among them, k4 represents the natural consumption coefficient of body fat, k5 represents the influence coefficient of fat intake on body fat rate, and k6 represents the reduction coefficient of exercise behavior on body fat rate.

3. The intelligent nutrition management method according to claim 1, characterized in that: The step of generating personalized dietary recommendations for the user through an optimization algorithm based on the user's dynamic physiological state model and preset health goals includes: Define a health objective function to represent the deviation between the user's current physiological state and the target physiological state. The objective function includes minimizing the cumulative value of the user's current physiological parameters deviating from the preset health target state and the constrained optimization of dietary intake. The objective function is defined as: Among them, x(t) represents the user's current physiological state parameter, x target represents the user's target physiological state parameter, u(t) represents the dietary intake variable, including the intake of protein, fat and carbohydrates, and α is the weight parameter; Construct a Hamiltonian function to combine the health objective function and the user's dynamic physiological state model, which is defined as: Among them, λ represents the concomitant variable, describing the sensitivity of the health objective function to the state variable, and f(x(t),u(t),w(t)) is the dynamic physiological state model; The optimal dietary intake strategy is solved by the optimal control algorithm, and the steps include: Calculate the dynamic changes of state variables to satisfy: Calculate the dynamic changes of the adjoint variables to satisfy: According to the optimality condition, solve for the optimal dietary intake variable: Generate personalized dietary recommendations for users based on the calculation results of the optimization algorithm.

4. The intelligent nutrition management method according to claim 3, characterized in that: The optimization algorithm is dynamically adjusted by combining the user behavior data and physiological parameters collected in real time, specifically including: Periodically collect and update the user's physiological state parameters; Correction of dynamic physiological state models based on the latest data; Dietary intake strategies were reoptimized based on the adjusted model.

5. The intelligent nutrition management method according to claim 1, characterized in that: The food intake information is collected through a camera combined with image recognition technology, and the image recognition technology is used to identify food types and estimate food portions.

6. The intelligent nutrition management method according to claim 1, characterized in that: The optimized dietary recommendations include: The specific time of intake of each food; target intake for each nutrient; Dynamically adjust intake recommendations based on the user's daily exercise volume.

7. The intelligent nutrition management method according to claim 1, characterized in that: The method further includes a step of dynamically adjusting the dynamic physiological state model and dietary recommendations based on the user's real-time feedback data to form a cyclic optimization, specifically including: Periodically collect real-time feedback data from users, including the latest physiological parameters and behavioral data of users; Updating the state variables and model parameters of the dynamic physiological state model based on the real-time feedback data specifically includes: Update the user's physiological parameters and adjust the initial value of the state variable x(t) to reflect the latest physiological state; Correcting parameters in the dynamic model according to the feedback data, the parameters include the natural consumption coefficient of blood sugar, the influence coefficient of exercise on blood sugar and body fat rate, and the effect coefficient of nutrient intake on physiological state; Re-optimize the user's health objective function based on the updated dynamic physiological state model and generate a new dietary intake strategy by solving the optimal control algorithm; Compare the deviation between the user's actual physiological state and the preset target state. If the deviation exceeds the threshold range, activate the rapid adjustment mechanism to adjust the dietary intake recommendations and intake time according to the latest optimization results; The updated dietary recommendations are fed back to users, and the latest trends in health status and the basis for adjusting the optimization plan are displayed in the form of charts to complete the optimization cycle.

8. An intelligent nutrition management system, used to execute the intelligent nutrition management method according to any one of claims 1 to 7, characterized in that: The system comprises: A data collection module is used to collect the user's physiological parameters and behavioral data in real time, wherein the physiological parameters include blood sugar level, body fat percentage and heart rate, and the behavioral data includes food intake information and exercise amount; A dynamic modeling module, used to build a dynamic physiological state model of the user based on the collected physiological parameters and behavioral data, wherein the model describes the changes of the user's physiological state over time; An optimization algorithm module, used to generate personalized dietary recommendations for the user based on the dynamic physiological state model and the user's health goals; A feedback module, used for feeding back the optimized dietary suggestions to the user in the form of charts or texts; The adjustment module is used to dynamically update the dynamic physiological state model and dietary recommendations based on the user's real-time feedback data to achieve cyclic optimization.

9. A smart bracelet for executing the smart nutrition management method according to any one of claims 1 to 7, characterized in that: The smart bracelet comprises: A physiological data collection unit, which is used to collect the user's blood sugar level, heart rate, and body fat percentage; A data transmission unit, used for transmitting the collected physiological parameter data to the system for dynamic modeling; The display unit is used to display health status data and information related to dynamically adjusted dietary recommendations to the user in real time.

10. A mobile terminal for executing the intelligent nutrition management method according to any one of claims 1 to 7, characterized in that: The mobile terminal comprises: A camera, used to record the user's food intake information and transmit the information to the system for analysis and processing; A data interaction module, used to receive dietary suggestions generated by the intelligent nutrition management system and transmit the user's real-time feedback data to the adjustment module of the system; The display module is used to display the user's daily nutritional intake trends, intake recommendations, and real-time health status changes in the form of charts or text.

Images