A fat reduction management system, method, terminal device and storage medium

Abstract

The application discloses a fat-reducing management system and method, a terminal device and a storage medium. The system comprises a data acquisition module, which is used for periodically acquiring multi-dimensional body parameters of a user, wherein the multi-dimensional body parameters at least include body weight, body fat rate, muscle mass and basal metabolism; a dynamic optimization module, which is used for dynamically calculating and updating core control parameters for guiding fat reduction according to the change trend of the multi-dimensional body parameters, wherein the core control parameters at least include an energy gap preset value and / or a fat-reducing cycle prediction value; a scheme generation module, which is used for generating a diet scheme and / or an exercise scheme corresponding to the core control parameters according to the core control parameters; and an output module, which is used for outputting the core control parameters and / or the diet scheme and / or the exercise scheme. The data acquisition module is further used for continuously acquiring new multi-dimensional body parameters after the user executes the diet scheme and / or the exercise scheme, and the dynamic optimization module updates the core control parameters according to the new multi-dimensional body parameters.

Description

Technical Field

[0001] This application relates to the field of data management technology, specifically to a weight loss management system, method, terminal device, and storage medium. Background Technology

[0002] Obesity has become a significant public health issue, and weight management is an important component of the healthy lifestyle advocated by the state. With increasing health awareness, more and more users are using smart devices and health management tools for weight loss management. However, existing weight loss management technologies still have the following shortcomings:

[0003] Currently, most weight loss programs rely primarily on weight changes to assess their effectiveness, neglecting key indicators such as body fat percentage and muscle mass, which better reflect changes in body composition. This single-dimensional assessment method fails to accurately reflect a user's true weight loss status, easily leading to muscle loss or weight rebound during the weight loss process, thus affecting the sustainability of the weight loss results.

[0004] In terms of energy management, existing health management tools generally use fixed values ​​or one-time settings based on initial conditions to determine the energy deficit, making it difficult to adjust according to changes in the user's physical condition. Due to the lack of a flexible adjustment mechanism for the energy deficit, users are prone to experiencing stagnation or fluctuations in weight loss during the execution of a weight loss program, making it difficult to consistently achieve the expected goals.

[0005] In terms of cycle prediction, existing tools lack the ability to effectively predict weight loss cycles. Users can only understand their past weight loss progress through historical data, but cannot know the approximate time required to reach their target weight loss status. This lack of clear goal expectations affects users' confidence in weight loss and long-term adherence to the plan to some extent.

[0006] Regarding dietary recommendations, existing programs are mostly pre-made recipes with fixed calories and nutritional combinations, offering limited food variety and failing to meet users' needs for dietary diversity. Meanwhile, exercise recommendations often only display exercise duration and calories burned, lacking effective coordination with the diet plan. This results in a disconnect between diet and exercise management, making it difficult to accurately control overall fat loss results.

[0007] Furthermore, existing weight loss management technologies generally lack dynamic adjustment mechanisms based on continuous monitoring data. After a user obtains a weight loss plan, the system struggles to continuously optimize the plan based on changes in the user's physical condition after implementation, thus failing to achieve truly personalized dynamic management.

[0008] In summary, existing weight loss management technologies have shortcomings in data utilization, dynamic adjustment, cycle prediction, and program synergy, and urgently need improvement.

[0009] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the Invention

[0010] To address the aforementioned technical problems, this application provides a weight loss management system, method, terminal device, and storage medium to solve the problem that existing weight loss programs suffer from unstable results and difficulty in long-term adherence due to the lack of dynamic adjustment mechanisms and personalized coordination.

[0011] This application provides a weight loss management system, which includes:

[0012] The data acquisition module is used to periodically acquire the user's multidimensional body parameters, which include at least weight, body fat percentage, muscle mass, and basal metabolic rate.

[0013] The dynamic optimization module is used to dynamically calculate and update the core control parameters for guiding fat loss based on the changing trends of the multidimensional body parameters. The core control parameters include at least a preset energy deficit value and / or a predicted fat loss cycle value.

[0014] The plan generation module is used to generate a diet plan and / or exercise plan corresponding to the core control parameters based on the core control parameters.

[0015] The output module is used to output the core control parameters and / or the diet plan and / or the exercise plan.

[0016] Preferably, the dynamic optimization module includes:

[0017] The energy gap calculation unit is used to filter out the recording days that meet the preset fat loss conditions based on the changing trends of the multidimensional body parameters, and to determine the preset energy gap value for the next cycle based on the energy gap data of the selected recording days.

[0018] The fat loss day prediction unit is used to determine the fat reduction trend and fat increase trend based on the changing trends of the multidimensional body parameters, and predict the target number of days required to reach the preset fat loss state based on the trends.

[0019] Preferably, when the energy gap calculation unit determines the preset value of the energy gap for the next cycle, it performs the following steps:

[0020] Determine the trend of fat changes based on weight and body fat percentage over a continuous period;

[0021] Recording days with negative changes in fat and an energy deficit that met preset criteria from the previous day were selected.

[0022] The average energy gap of the day before the selected record date is used as the preset energy gap value for the next cycle.

[0023] Preferably, when the fat loss day prediction unit predicts the target number of days required to reach the preset fat loss state, it performs the following steps:

[0024] Obtain data on changes in fat levels over the past period;

[0025] Calculate the mean amount of fat loss and the mean amount of fat gain separately;

[0026] Based on the average amount of fat loss and the average amount of fat gain, the target number of days required to reach the preset fat loss state is predicted.

[0027] Preferably, the scheme generation module includes:

[0028] The diet plan generation unit is used to generate a diet plan corresponding to the core control parameters based on the core control parameters and a preset food data set.

[0029] The motion scheme generation unit is used to generate a motion scheme corresponding to the core control parameters based on the core control parameters.

[0030] Preferably, when the diet plan generation unit generates a diet plan, it performs the following steps:

[0031] Based on the preset energy deficit value, combined with the user's basal metabolic rate and energy expenditure during exercise, the required dietary energy intake for the day is determined.

[0032] Foods that meet the nutritional matching rules are selected from the preset food data set to generate a diet plan.

[0033] Preferably, when the motion scheme generation unit generates a motion scheme, it performs the following steps:

[0034] Obtain the energy consumption per unit time for each exercise in the exercise library;

[0035] The required energy consumption for exercise is determined based on the preset energy gap value.

[0036] The exercise plan is generated by matching multiple exercises and their corresponding suggested durations from the exercise library.

[0037] This application also provides a weight loss management method, the weight loss management method comprising:

[0038] The system periodically acquires the user's multidimensional body parameters, which include at least weight, body fat percentage, muscle mass, and basal metabolic rate.

[0039] Based on the changing trends of the multidimensional body parameters, the core control parameters for guiding fat loss are dynamically calculated and updated. The core control parameters include at least a preset energy deficit value and / or a predicted fat loss cycle value.

[0040] Based on the core control parameters, generate a diet plan and / or exercise plan corresponding to the core control parameters;

[0041] Output the core control parameters and / or the diet plan and / or the exercise plan.

[0042] Preferably, the step of dynamically calculating and updating the core control parameters for guiding fat loss based on the changing trends of the multidimensional body parameters includes:

[0043] Based on the changing trends of the multidimensional body parameters, record days that meet the preset fat loss conditions are selected, and the preset energy deficit value for the next cycle is determined based on the energy deficit data of the selected record days; and / or,

[0044] Based on the changing trends of the multidimensional body parameters, the trends of fat reduction and fat increase are determined, and the target number of days required to reach the preset fat loss state is predicted based on the trends.

[0045] Preferably, the step of generating a diet plan and / or exercise plan corresponding to the core control parameters includes:

[0046] Based on the core control parameters and a preset food data set, generate a diet plan corresponding to the core control parameters; and / or,

[0047] Based on the core control parameters, a motion scheme corresponding to the core control parameters is generated.

[0048] This application also provides a terminal device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the weight loss management method as described above.

[0049] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the weight loss management method described above.

[0050] Beneficial effects:

[0051] This invention continuously monitors a user's body data, including weight, body fat percentage, muscle mass, and basal metabolic rate, dynamically calculating and updating preset energy deficit values ​​and predicted weight loss cycles. Based on these core control parameters, it generates a synergistically matched diet and exercise plan, continuously collecting new data after the user implements it, forming a closed-loop optimization mechanism. This plan can dynamically adjust the weight loss strategy according to changes in individual physical condition, achieving precise control; it enhances user goal expectation and adherence by predicting the weight loss cycle; diet and exercise work synergistically, avoiding fragmented plans; and it generates plans based on everyday ingredients and common exercises, making it easy to stick to long-term, significantly improving weight loss results and user experience. Attached Figure Description

[0052] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0053] Figure 1 This is a schematic diagram of the structure of the weight loss management system provided in the embodiments of this application;

[0054] Figure 2 This is a flowchart illustrating the weight loss management method provided in an embodiment of this application.

[0055] The realization of the objectives, functional features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and textual descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0056] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0057] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0058] It should be understood that although the terms first, second, third, etc., may be used herein to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this document, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if," as used herein, can be interpreted as "when," "when," or "in response to determination." Furthermore, as used herein, the singular forms "a," "an," and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising," "including," indicate the presence of the stated feature, step, operation, element, component, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or" and "and / or" as used herein are to be interpreted as inclusive, or mean any one or any combination thereof. Therefore, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A, B, and C". Exceptions to this definition will only occur if the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0059] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0060] It should be noted that step designations such as S110 and S120 are used in this document for the purpose of more clearly and concisely describing the corresponding content, and do not constitute a substantial limitation on the order. In specific implementation, those skilled in the art may execute S120 first and then S110, etc., but these should all be within the protection scope of this application.

[0061] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0062] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0063] refer to Figure 1 As shown in the illustration, this application provides a weight loss management system, which includes a data acquisition module, a dynamic optimization module, a plan generation module, and an output module. The weight loss management system uses the data acquisition module to periodically acquire multi-dimensional body parameters such as the user's weight, body fat percentage, muscle mass, and basal metabolic rate. The dynamic optimization module dynamically calculates and updates core control parameters for guiding weight loss, such as energy deficit and preset values, and predicted weight loss cycles, based on the changing trends of these multi-dimensional body parameters. The plan generation module then generates corresponding diet and / or exercise plans based on the latest core control parameters. The weight loss management system further uses the output module to output the generated preset energy deficit, predicted weight loss cycles, diet plans, and exercise plans, allowing users to understand their weight loss status and expectations, and serving as a reference for executing weight loss activities.

[0064] In the embodiments of this application, the data acquisition module serves as the system's data entry point, undertaking the functions of acquiring and preprocessing multi-dimensional body parameters of the user. In this embodiment, the data acquisition module solves the technical problems of single data acquisition, poor continuity, and insufficient accuracy in traditional weight loss management systems through multi-source data fusion, intelligent acquisition strategies, and data quality enhancement mechanisms. This provides a high-quality data foundation for subsequent dynamic optimization, while adapting to different users' usage habits, device conditions, and application scenarios, ensuring the continuity, accuracy, and completeness of the data source. In this embodiment, the data acquisition module supports the collaborative work of multiple acquisition methods and uses a data fusion algorithm to uniformly process heterogeneous data from different sources, with different precision, and different frequencies, forming a complete time series of user body data.

[0065] In one exemplary implementation, the data acquisition module connects to the body fat measurement device via wireless communication. The body fat measurement device employs bioelectrical impedance analysis (BIA) technology; the user simply stands barefoot on the device surface, and the device completes the measurement within seconds. The system supports various brands and models of body fat scales, acquiring measurement data through a unified interface protocol. Users do not need to manually input data, achieving seamless data collection. The collected multidimensional body parameters include at least weight, body fat percentage, muscle mass, and basal metabolic rate. The data collection period is set daily, and the system encourages users to measure at a fixed time (e.g., on an empty stomach in the morning) to eliminate interference from factors such as diet and exercise.

[0066] In one exemplary implementation, the data acquisition module interfaces with wearable devices such as smart bracelets and smartwatches to acquire behavioral data such as the user's heart rate, exercise expenditure, sleep quality, and steps. Some high-end devices have built-in bioelectrical impedance sensors that can estimate trends in body fat percentage and muscle mass. Unlike the daily discrete measurements of body fat scales, wearable devices provide minute-level continuous data, enabling the system to capture the user's daily activity patterns, exercise intensity, and recovery status, providing data support for refined calculations of energy expenditure.

[0067] In one exemplary implementation, the data acquisition module can also support user-inputted or smart tape measure measurements of waist, hip, and thigh circumference. The system incorporates several clinically validated body fat percentage estimation models (such as the US Navy body fat percentage calculation method and the Durnin-Womersley skinfold thickness method). Based on the user-inputted circumference and skinfold thickness data, combined with gender, age, and height, it automatically selects and converts the appropriate model. This method is simple and easy to use, suitable for daily monitoring or as a cross-validation method for body fat scale data.

[0068] In this embodiment, to address the inconsistent data quality issues arising from improper user operation, missing equipment, or inconsistent measurement times in traditional data acquisition, the data acquisition module employs a built-in anomaly detection mechanism to perform real-time quality assessments, including anomaly detection and correction, on the acquired data. For data exceeding reasonable physiological ranges (e.g., weight fluctuations exceeding 5% within 24 hours), data significantly deviating from the trend (e.g., sudden changes in body fat percentage exceeding 3 percentage points), or data contradicting multiple source data (e.g., weight gain with a significant decrease in circumference), the data acquisition module automatically marks them as suspicious data and triggers a verification mechanism. One verification mechanism in this embodiment includes prompting the user to confirm measurement conditions, requesting a remeasurement, or invoking other acquisition methods for cross-validation. Through these mechanisms, the risk of data contamination due to equipment malfunction, improper operation, or environmental interference can be significantly reduced.

[0069] Furthermore, the collected raw data undergoes standardization processing to form a unified feature representation, which is then used by the dynamic optimization module.

[0070] First, since data from different acquisition methods have different timestamps, the data acquisition module projects all data onto a unified time-series grid (e.g., daily as the smallest time unit). For data measured multiple times within the same day, a weighted average is calculated based on the measurement time weight; for data with missing time points, spline interpolation is used for smoothing.

[0071] Secondly, the data acquisition module extracts key features from the raw data that reflect changes in body condition, including: the rate of fat change (the slope of change in fat mass per unit time), the ratio of muscle to fat change (measuring the quality of fat loss), the magnitude of weight fluctuations (reflecting water balance), and basal metabolic trends. These dynamic features are more predictive than the raw measurements, providing a quantitative basis for the dynamic adjustment of the preset energy deficit.

[0072] Through the above methods, the data acquisition module achieves high-quality and continuous collection of users' multi-dimensional body parameters, providing accurate, complete, and time-series input data for the dynamic optimization module, effectively solving the technical problems of single data collection, poor continuity, and insufficient accuracy in traditional weight loss management systems.

[0073] In this embodiment, the data acquisition module is also used to continue to acquire new multidimensional body parameters after the user executes the diet plan and / or exercise plan, and to update the core control parameters according to the new multidimensional body parameters through the dynamic optimization module.

[0074] In the embodiments of this application, the dynamic optimization module, as the core computing engine of the weight loss management system, is responsible for dynamically generating core control parameters based on the user's historical body data. In this embodiment, the dynamic optimization module solves the technical problems of rigid energy deficit settings and unpredictable weight loss cycles in traditional weight loss management systems through adaptive screening mechanisms, periodic dynamic adjustments, and multi-dimensional prediction models, providing accurate and personalized control parameters for the plan generation module.

[0075] In this embodiment, the dynamic optimization module includes two sub-modules: an energy deficit calculation unit and a fat loss days prediction unit. The energy deficit calculation unit dynamically determines the preset energy deficit value for the next stage based on the user's historical body data; the fat loss days prediction unit predicts the time required for the user to reach their fat loss goal based on historical fluctuations in fat changes. The two units operate independently but collaboratively, forming the core control parameter generation mechanism.

[0076] Since the energy deficit in a weight loss program should not be a fixed value, but rather dynamically adjusted based on changes in the user's recent physical condition, this energy deficit calculation unit achieves dynamic calculation and updating of the preset energy deficit value through the following steps:

[0077] The energy deficit calculation unit reads the user's multidimensional body parameter data over a continuous period from the storage module, including weight, body fat percentage, muscle mass, and basal metabolic rate. The weight loss management system constructs the user's multidimensional body parameter sequence on a daily basis, forming a continuous historical record. In this embodiment, the weight loss management system can also construct the user's multidimensional body parameter sequence on a weekly or monthly basis; the periodicity is not specifically limited here.

[0078] For each recording day, the energy deficit calculation unit calculates the daily energy deficit. This calculation is based on the user's dietary energy intake, exercise energy expenditure, and basal metabolic rate. One embodiment of the calculation formula is: Daily Energy Deficit = Dietary Energy Intake - Exercise Energy Expenditure - Basal Metabolic Rate. Dietary energy intake can be obtained through user photo recognition or manual input; exercise energy expenditure can be obtained through wearable devices or exercise records; and the basal metabolic rate is measured by a body fat scale or calculated based on user parameters.

[0079] Daily fat change is calculated based on daily weight and body fat percentage: Fat change = Daily weight × Daily body fat percentage - Previous day's weight × Previous day's body fat percentage. A positive value indicates an increase in fat that day; a negative value indicates a decrease in fat that day. Further calculations are made to determine the energy values ​​corresponding to fat and muscle changes. The energy from fat changes is obtained by multiplying the fat change by the energy equivalent coefficient of fat; the energy from muscle changes is obtained by multiplying the muscle mass change by the energy equivalent coefficient of protein. These energy equivalent coefficients are determined based on the physiological principles of human energy metabolism and reflect the different contributions of adipose and muscle tissue to energy balance.

[0080] The energy deficit calculation unit also incorporates an adaptive filtering mechanism to select record days from historical multidimensional body parameter data that accurately reflect the user's fat loss status. The filtering criteria include two dimensions:

[0081] First, the change in fat percentage must be negative, meaning that fat actually decreased on that day. This condition ensures that the selected record days have a positive fat-loss effect.

[0082] Second, the sum of the previous day's energy deficit and the energy changes from fat and muscle on the current day must be greater than 0. This condition signifies that the body's energy system possesses a temporary energy storage device, referred to in this system as the "rapid energy pool." Its capacity can increase or decrease depending on the body's condition. Theoretically, the change in the rapid energy pool's capacity is equivalent to the previous day's energy deficit minus the sum of the energy changes from fat and muscle on the current day. When this value is greater than 0, it means that the capacity of the "rapid energy pool" has increased, requiring the use of stored energy to replenish it, i.e., through the breakdown of fat for energy.

[0083] When both of the above conditions are met, the recording date is marked as a valid recording date. This dual screening mechanism ensures that the data used to calculate the preset energy deficit is of high quality, avoiding noise interference caused by inaccurate user diet records, exercise measurement errors, or fluctuations in body hydration.

[0084] By calculating the average energy deficit of the day before all valid recording dates, this average is used as the preset energy deficit value for the next time period. The length of the time period can be set according to the actual application scenario, such as 7 days or 15 days. This dynamic update mechanism allows the preset energy deficit value to be continuously optimized according to changes in the user's physical condition: for example, when the user's fat loss is progressing well, the energy deficit is maintained or moderately increased; or, for example, when the user enters a plateau, it is automatically adjusted according to the screening criteria to avoid fat loss stagnation caused by a fixed energy deficit.

[0085] In this embodiment, the energy deficit calculation unit also adopts differentiated calculation strategies according to different user states. For example, in the initial stage (no historical data), a preset initial value based on the user's basal metabolism and activity level is used to ensure that the system can still be started when there is no historical data. For example, in the normal fat loss stage, the calculation is performed according to the above dynamic update mechanism to achieve synchronous adjustment of energy deficit and physical state. For another example, in the data missing period, the preset energy deficit value of the most recent effective period is used, combined with trend correction, to ensure the availability of the system when data is discontinuous.

[0086] In this embodiment, based on historical fluctuations in fat changes, the number of days required for a user to reach a fat loss state is predicted, providing the user with a clear target expectation. This fat loss day prediction unit achieves fat loss cycle prediction through the following steps:

[0087] This tool retrieves data on changes in body fat over a specific period. This period can be set according to actual needs, such as half a month or one month. The data includes the complete cycle of the user's body fat gain and loss, reflecting the natural fluctuations during the fat loss process.

[0088] The data on changes in body fat were decomposed into two components: a decreasing trend and an increasing trend. For days with negative changes in body fat, the absolute value represents a decreasing trend; for days with positive changes in body fat, the value represents an increasing trend.

[0089] The mean amount of fat loss and the mean amount of fat gain are calculated separately. In this embodiment, these two indicators together form the basis for predicting the fat loss cycle.

[0090] A predefined fat loss state is defined as a cumulative fat reduction reaching a preset percentage threshold. In this embodiment, a fat loss state is defined as a cumulative fat reduction percentage greater than 50%, meaning that within a complete cycle, the user's total fat reduction exceeds the total fat gain, achieving net fat reduction. In one implementation, this threshold can be personalized according to the user's goals.

[0091] Based on the average amount of fat loss and the average amount of fat gain, this model predicts the target number of days needed to achieve a fat loss state. The core logic of the prediction is that fat loss and fat gain trends alternate cyclically. Specifically, it uses the average change in fat amount from the previous cycle to predict the number of days needed to achieve a fat loss state in the next cycle, calculating the target number of days needed to achieve a cumulative fat loss percentage > 50%. The specific prediction logic is: Target fat loss days = Average fat gain × Total number of days in the predicted cycle / (Average fat gain - Average fat loss). The physical meaning of this model is that users need to strive to achieve a sufficient number of fat loss days so that the accumulated fat loss is sufficient to offset the fat gain, resulting in a net reduction.

[0092] This embodiment also supports forecasts at different time scales, and can output forecast results for 15 days, 30 days, or custom periods according to user needs. Multi-time scale forecasting allows users to choose appropriate period targets based on their own circumstances, enhancing the achievability of the goals and user confidence.

[0093] In the embodiments of this application, the dynamic optimization module also employs a closed-loop iterative mechanism. Instead of calculating the core control parameters all at once, the module continuously updates the parameters based on newly collected body data after the user completes the weight loss program. Specifically, after the user completes a weight loss program for a given period, the data acquisition module obtains new multidimensional body parameters. The dynamic optimization module then re-executes the above calculation process: updating the daily screening results of valid records, recalculating the average energy deficit, and re-predicting the weight loss cycle. This rolling iterative mechanism allows the core control parameters to continuously optimize in accordance with changes in the user's physical condition, avoiding the problem of gradually diminishing weight loss effects caused by fixed parameters in traditional programs.

[0094] In the embodiments of this application, the scheme generation module, as the system's execution layer, is responsible for outputting specific and executable diet and exercise schemes based on the core control parameters generated by the dynamic optimization module. This module solves the technical problems of traditional weight loss management systems, such as a single diet scheme and a disconnect between exercise recommendations and energy goals, through an intelligent nutrient matching mechanism and a reverse energy consumption matching mechanism, thereby achieving synergistic optimization of diet and exercise schemes.

[0095] In this embodiment, the plan generation module includes two sub-modules: a diet plan generation unit and an exercise plan generation unit. The diet plan generation unit is responsible for generating nutritionally balanced and diverse weight-loss meal plans based on a preset energy deficit value; the exercise plan generation unit is responsible for generating exercise plans with a variety of exercises and reasonable durations based on the preset energy deficit value. These two units operate independently but share the same core control parameters, ensuring consistency between diet and exercise in terms of energy goals.

[0096] Since a weight-loss diet should not be a pre-made menu with fixed calories, but rather should dynamically calculate the required daily energy intake based on the user's preset energy deficit, basal metabolic rate, and exercise expenditure, and select foods that meet nutritional matching rules from a preset food data set to create diverse dietary plans, the diet plan generation unit first calculates the required daily energy intake based on the preset energy deficit output by the dynamic optimization module, combined with the user's basal metabolic rate and exercise expenditure. One implementation formula is: Daily energy intake = Daily energy deficit preset value + Exercise expenditure + Basal metabolic rate. This calculation ensures that the daily energy intake forms a closed loop with the energy deficit target, exercise expenditure, and basal metabolic rate, making energy balance quantifiable and controllable.

[0097] A pre-defined food dataset is constructed, including a food database and its corresponding nutritional information labels. The food database covers most ingredients found in daily diets, including staple foods, vegetables, fruits, meat, eggs, dairy products, soy products, and seafood. Each food item's carbohydrate, protein, and fat content per unit weight, as well as its total calories, are recorded. Furthermore, based on the proportions of carbohydrate, protein, and fat providing energy, foods are categorized and labeled, forming a three-tiered labeling system: L-type, N-type, and H-type.

[0098] Tag type Carbohydrate energy ratio Protein energy ratio Fat as a source of energy Nutritional characteristics Category L (low proportion) Below the preset lower limit Below the preset lower limit Below the preset lower limit The proportion of single nutrients is low N-type (Normal Proportion Class) Within the preset range Within the preset range Within the preset range Balanced nutrient ratio Category H (High Proportion Category) Exceeding the preset upper limit Exceeding the preset upper limit Exceeding the preset upper limit High proportion of single nutrients

[0099] This labeling system simplifies the complex nutrient ratios into three categories of labels, providing a concise interface for subsequent matching and combination.

[0100] Furthermore, after establishing nutritional component matching rules, a balanced daily diet plan can be achieved through combinations of different labels. The core logic of the matching rules is that when different food labels are combined, their overall nutritional component labels follow a combination pattern. A specific implementation method is as follows:

[0101] When L-type foods are combined with H-type foods, the overall label is N-type, meaning that the high and low complementarity can achieve a normal ratio.

[0102] When L-type foods are combined with N-type foods, the overall label is L-type, meaning that the combination of low and normal proportions still leans towards the low proportion.

[0103] When H-category foods are combined with N-category foods, the overall label is H-category, meaning that even when high proportions are combined with normal proportions, the overall label still leans towards the high proportion.

[0104] When combining foods of the same category, the label remains unchanged.

[0105] Based on the above rules, multiple daily nutrient matching results are preset, including NNN (all three nutrients are in normal proportions), NLN (normal carbohydrates, low protein, normal fat), and NNL (normal carbohydrates, normal protein, low fat) combinations.

[0106] In this embodiment, the diet plan generation unit completes the process of generating a diet plan by following these steps:

[0107] The required dietary energy intake is calculated based on the preset energy deficit for the day, and the total calorie target is determined. This target serves as the overall constraint for food selection.

[0108] The food selection unit selects foods that meet the label requirements for each meal from the food database and optimizes their combinations. The goals of combination optimization include: ensuring the total calories of the meal meet the allocation target, ensuring the nutritional composition ratio of the meal meets the label requirements, and diversifying the food types to avoid monotony. The meal plan generation unit uses a heuristic search algorithm to generate multiple alternative plans while satisfying the constraints.

[0109] Output a complete diet plan, including a food list for each meal, suggested portion sizes, cooking methods, and nutritional analysis.

[0110] In a preferred embodiment, to meet users' needs for dietary diversity, the diet plan generation unit adopts the following strategy:

[0111] Strategy content Effect Same tag replacement Foods in the same label category can be substituted for each other. While maintaining nutritional balance, increase the freedom of choice. Rotation Recommendations The system records users' recent dietary choices and prioritizes recommending foods they haven't eaten before. Avoid a monotonous diet and improve long-term adherence. Preference for learning The system learns users' food preferences and gradually optimizes the recommendation results. Improve user satisfaction Seasonal adaptation Recommendations of seasonal ingredients based on season and region. Improve the availability and freshness of ingredients Cultural adaptation Supports recipe generation for different food cultures (Chinese, Western, vegetarian, etc.). Meet the needs of different user groups

[0112] In this embodiment, the recommended exercise for fat loss should not only show the calories burned, but should also match the type and duration of exercise in reverse according to the preset energy deficit value to ensure that exercise consumption is accurately aligned with the fat loss goal.

[0113] Therefore, before generating an exercise plan, the exercise plan generation unit first pre-defines an exercise library covering common exercise types such as aerobic exercise, strength training, and flexibility training. Each exercise has a calibrated energy consumption value per unit time. The energy consumption value calibration comprehensively considers exercise intensity, metabolic equivalent (MET), and user weight factors, and the calculation formula is: Energy consumption per unit time = Metabolic equivalent × User weight × Exercise duration. For different users, the exercise plan generation unit automatically adjusts the energy consumption calculation based on their weight to achieve personalized matching. Furthermore, based on the preset energy deficit value output by the dynamic optimization module, the required exercise energy consumption is determined.

[0114] Specifically, the motion plan generation unit generates specific motion plans according to the following process:

[0115] First, determine the total energy expenditure target based on the required energy consumption for motion. This target serves as the overall constraint for motion matching.

[0116] Second, select suitable sports from the sports database. Selection criteria include: no contraindications for the user, availability of sports equipment, and suitability for the sports setting (e.g., home, gym, outdoors).

[0117] Third, the selected sports activities are combined and optimized. The goals of combination optimization include: making the total energy consumption of the combined sports approach the target value, diversifying the types of sports to avoid monotony, and ensuring that users have a sufficient number of combination options to choose from. The sports plan generation unit uses a knapsack algorithm or a greedy strategy to generate multiple sports combination schemes.

[0118] Fourth, it provides complete exercise plans, including multiple optional exercise combinations. Each combination details the exercise activities, suggested duration, estimated energy expenditure, and precautions. Users can choose the most suitable combination based on their schedule, exercise preferences, and venue conditions.

[0119] In this embodiment, to meet users' needs for diverse exercise options, the exercise plan generation unit adopts the following strategy:

[0120] Strategy content Effect Combination Recommendation Combine various exercises into a complete program, such as warm-up + main exercise + stretching. Provide scientific and comprehensive exercise guidance Duration Flexibility Allows users to adjust the duration of a single exercise within a preset time range. Adapting to different users' schedules Intensity grading The same exercise offers three intensity options: low, medium, and high. Suitable for users with different fitness levels Scene adaptation Filter sports based on the user's selected sports scenario (home, gym, outdoors). Improve the feasibility of the solution Preference for learning The system learns users' preferences for exercise type, duration, and intensity, and gradually optimizes recommendations. Improve user satisfaction and compliance

[0121] In embodiments of this application, the solution generation module also employs differentiated generation strategies based on different user states:

[0122] Application scenarios Generation Strategy Technical effect initial stage Provide a default solution and gradually introduce personalized adjustments. Reduce the cognitive burden on users and enable them to get started quickly. Normal fat loss phase Dynamically generate schemes based on core control parameters Achieve precise control Plateau period Adjust your diet (e.g., increase the proportion of protein) and exercise methods (e.g., increase strength training). Break through the weight loss plateau Data missing period Generate approximate solutions based on historical solutions Ensure system availability User feedback period Adjust the plan based on user feedback (e.g., reduce exercise duration if user feedback indicates the exercise intensity is too high). Improve user satisfaction and compliance

[0123] In summary, the solution generation module provided in this application realizes the dynamic generation and collaborative optimization of diet and exercise plans, effectively solving the technical problems of single diet plans and disconnected exercise recommendations in traditional weight loss management systems, and providing users with personalized, diversified and executable weight loss guidance plans.

[0124] refer to Figure 2 As shown in the embodiment of this application, a fat loss management method is provided. This method is executed by a computer program on a user terminal device (such as a smartphone) and / or a cloud server. The user periodically measures body parameters through a body fat scale, and the following steps are automatically executed through the terminal device and / or cloud server to realize the dynamic generation and closed-loop optimization of the fat loss plan.

[0125] S1. Periodically acquire the user's multidimensional body parameters, which include at least weight, body fat percentage, muscle mass, and basal metabolic rate.

[0126] In the embodiments of this application, when managing the user's weight loss process through the weight loss management system, it is first necessary to periodically acquire the user's multidimensional body parameters. The data acquisition methods for these multidimensional body parameters include, but are not limited to, body fat scale measurement, wearable device synchronization, circumference measurement conversion, and other methods, in order to adapt to different users' usage habits and equipment conditions.

[0127] In a preferred embodiment, the user terminal device is periodically connected to the body fat measurement device via wireless communication to acquire the user's multidimensional body parameters. In this embodiment, the body fat measurement device employs bioelectrical impedance analysis (BIA) technology. For example, the user stands barefoot on the device surface, and the device completes the measurement within seconds, automatically acquiring the user's weight, body fat percentage, muscle mass, and basal metabolic rate. The data collection period is set to daily, and users are encouraged to perform measurements at a fixed time (such as on an empty stomach in the morning) to eliminate interference from factors such as diet and exercise on the measurement results.

[0128] When the user is not using the body fat scale, other data collection methods can be switched. For example, the user can manually input waist circumference, hip circumference, and other measurements, and the system will estimate body fat percentage using a clinically validated regression model.

[0129] Each acquired multidimensional body parameter is associated with the collection timestamp and stored in the database. Each data record includes fields such as measurement date, collection method, weight, body fat percentage, muscle mass, and basal metabolic rate. The user's body data sequence is constructed in chronological order to form a historical data curve at continuous time points.

[0130] S2. Based on the historical trends of the multidimensional body parameters, dynamically calculate and update the core control parameters for guiding fat loss. The core control parameters include at least the preset energy deficit value and / or the predicted fat loss cycle value.

[0131] In the embodiments of this application, after obtaining the user's multidimensional body parameters, the core control parameters are further dynamically calculated and updated based on the changing trends of the user's multidimensional body parameters. These core control parameters include a preset energy deficit value and a predicted fat loss cycle value.

[0132] In a preferred embodiment, when dynamically calculating the preset energy deficit value, the daily energy deficit is first calculated. For each recording day, the energy deficit is calculated based on the user's dietary energy intake, exercise energy expenditure, and basal metabolic rate, according to the formula "Daily Energy Deficit = Dietary Energy Intake - Exercise Energy Expenditure - Basal Metabolic Rate". Dietary energy intake can be obtained through user photo recognition or manual input, while exercise energy expenditure can be obtained through wearable devices or exercise records.

[0133] Daily fat change is calculated based on daily weight and body fat percentage: Fat change = Daily weight × Daily body fat percentage - Previous day's weight × Previous day's body fat percentage. A positive value indicates an increase in fat that day; a negative value indicates a decrease in fat that day. Further calculations are made to determine the energy values ​​corresponding to fat changes and muscle changes, and the energy conversion coefficient is determined based on the physiological principles of human energy metabolism.

[0134] Valid recording days are selected based on two criteria: First, the change in body fat is negative, meaning that body fat actually decreased on that day; second, the energy deficit from the previous day is greater than the sum of the energy from the change in body fat and the energy from the change in body muscle on that day, indicating that the energy deficit set the previous day is sufficient to cover the energy required for the changes in body composition on that day. A recording day is marked as valid when both conditions are met.

[0135] The system calculates the average energy deficit for the day preceding all valid record dates and uses this average as the preset energy deficit value for the next time period. The length of the time period can be set according to the actual application scenario, such as 7 days or 15 days. This dynamic update mechanism allows the preset energy deficit value to be continuously optimized as the user's physical condition changes.

[0136] In a preferred implementation, when dynamically calculating the predicted value of the fat loss cycle, data on fat changes over a past period are obtained. This period can be set according to actual needs, such as half a month or one month. Further, the fat change data is decomposed into two components: a decreasing trend and an increasing trend. For days with negative fat changes, their absolute values ​​constitute the fat decreasing trend; for days with positive fat changes, their values ​​constitute the fat increasing trend. The average fat decrease and the average fat increase are calculated separately. In this embodiment, the average fat decrease reflects the user's average fat loss ability per unit time; the average fat increase reflects the user's tendency to rebound fat when not strictly controlling diet or exercise. Further, based on the average fat decrease and the average fat increase, the target number of days required to reach the fat loss state is predicted. The fat loss state is predefined as the cumulative fat loss reaching a preset percentage threshold, for example, a cumulative fat loss percentage greater than 50%. The core logic of the prediction is based on a rate difference model: the target number of days equals the number of days to be predicted multiplied by the ratio of the average fat increase to the difference in the rate of decrease. It supports predictions at different time scales and can output prediction results for 15 days, 30 days, or a custom period according to user needs. In this embodiment, a rolling prediction mechanism is further adopted, and the prediction model is adaptively corrected based on the actual changes in fat after each prediction. When the actual fat loss progress is faster than the prediction, the subsequent prediction days are automatically shortened; when the actual progress is slower than the prediction, the system extends the prediction days and prompts the user to check the implementation status of the fat loss plan.

[0137] S3. Based on the core control parameters, generate a diet plan and / or exercise plan corresponding to the core control parameters.

[0138] In the embodiments of this application, after obtaining the core control parameters through the above steps, a specific executable diet plan is output based on the core control parameters and executed according to the following steps:

[0139] Based on the preset energy deficit value, combined with the user's basal metabolic rate and energy expenditure through exercise, the required daily dietary energy intake is calculated: Daily dietary energy intake = Daily energy deficit preset value + Energy expenditure through exercise + Basal metabolic rate. This calculation ensures that the daily dietary energy intake forms a closed loop with the energy deficit target, exercise expenditure, and basal metabolic rate.

[0140] A pre-defined food dataset is used, including a food database and its corresponding nutrition facts labels. The food database covers most ingredients in daily diets, and each food item records its carbohydrate, protein, fat content, and total calories per unit weight. Foods are categorized and labeled according to the proportions of carbohydrate, protein, and fat they provide, forming a three-tiered labeling system: L (low proportion), N (normal proportion), and H (high proportion).

[0141] A nutrient matching rule was established. When L-type foods are combined with H-type foods, the overall label is N-type; when L-type foods are combined with N-type foods, the overall label is L-type; when H-type foods are combined with N-type foods, the overall label is H-type; when foods of the same category are combined, the label remains unchanged. Based on the above rule, several daily nutrient matching results were preset, including NNN (normal proportions of the three nutrients), NLN (normal carbohydrates, low protein, normal fat), and NNL (normal carbohydrates, normal protein, low fat), etc.

[0142] Based on the user's selected daily nutrient matching mode, the system selects foods from the food database that meet the label requirements for each meal and optimizes their combinations. The optimization goals include: ensuring the total calories of the meal meet the allocation target, ensuring the nutritional composition ratio of the meal meets the label requirements, and diversifying the food types to avoid monotony. A heuristic search algorithm is used to generate multiple alternatives while satisfying constraints. A complete dietary plan is then output, including a food list for each meal, suggested portion sizes, cooking methods, and nutritional analysis. Users can choose from multiple plans based on their own tastes and can also replace foods in the plans with the same label.

[0143] In the embodiments of this application, after obtaining the core control parameters through the above steps, a specific executable motion scheme is output based on the core control parameters and executed according to the following steps:

[0144] The system includes a pre-set exercise library covering common types of exercise such as aerobic exercise, strength training, and flexibility training. Each exercise has a calibrated energy consumption value per unit of time, which takes into account exercise intensity, metabolic equivalent, and user weight.

[0145] The required energy expenditure for exercise is determined based on the preset energy deficit. This determination considers the portion of the energy deficit already covered by the dietary plan, ensuring that exercise expenditure and dietary restrictions work synergistically to achieve the overall energy deficit target. The calculation formula is: Required energy expenditure for exercise = Preset daily energy deficit - Dietary adjustment contribution.

[0146] The system selects suitable sports from a sports database, considering criteria such as no contraindications for the user, availability of sports equipment, and suitability for the sports environment. The selected sports are then combined and optimized using a knapsack algorithm or a greedy strategy to generate multiple sports combination schemes. This aims to ensure that the total energy expenditure of the combined exercises approaches the target value while maintaining a diverse range of sports.

[0147] It outputs complete exercise plans, including a variety of optional exercise combinations. Each combination details the exercise, suggested duration, expected energy expenditure, and precautions. Users can choose the most suitable combination based on their time schedule, exercise preferences, and venue conditions.

[0148] S4. Output the core control parameters and / or the diet plan and / or the exercise plan.

[0149] In the embodiments of this application, by displaying core control parameters to the user, including the preset energy deficit value and the predicted fat loss cycle value, the user understands the fat loss goals set by the system and the expected time to achieve them. Simultaneously, the system displays the diet and exercise plans generated by the plan generation module, clearly presenting information such as the food list for each meal, cooking suggestions, nutritional analysis, and the specific duration and expected energy expenditure of each exercise. Users can view plan details, select different plans, adjust plans, or confirm execution through the output interface. The system records the user's selections and execution status as a basis for subsequent optimization.

[0150] S5. After the user executes the diet plan and / or exercise plan, continue to acquire new multidimensional body parameters, and update the core control parameters based on the new multidimensional body parameters.

[0151] In the embodiments of this application, after receiving the diet and exercise plans generated by the system, the user follows the plans. During the execution, the user continues to measure body data daily using a body fat scale, or provides new multidimensional body parameters through other data collection methods.

[0152] After the user completes the program, new body data will continue to be acquired, including weight, body fat percentage, muscle mass, and basal metabolic rate. This new data will then be merged with historical data to form an updated body data sequence.

[0153] Based on the new multidimensional body parameters, the calculation process for core control parameters is re-executed: the daily energy deficit is recalculated, valid recording days are re-selected, and the average energy deficit is recalculated as the preset value for the next time period; data on changes in body fat are re-acquired, the average amount of fat loss and gain is recalculated, and the fat loss cycle is re-predicted. Based on the updated core control parameters, new diet and exercise plans are generated.

[0154] This process repeats continuously, forming a complete closed loop of "parameter acquisition → core parameter calculation and update → plan generation → output → execution → parameter acquisition again". This closed-loop optimization mechanism ensures that the weight loss plan can be continuously adjusted according to changes in the user's physical condition, avoiding the problem of gradually diminishing weight loss effects caused by fixed parameters in traditional plans.

[0155] One embodiment:

[0156] The weight loss management system associates each set of multidimensional body parameters acquired with the collection timestamp and stores them in the database. For example, in October 2024, the system recorded continuous data for the client from October 1st to October 15th. Some of the data is shown below:

[0157] date Weight(kg) Body fat percentage (%) Muscle mass (kg) Basal metabolic rate (kcal) 10 / 1 75.2 28.5 52.3 1680 10 / 2 75.0 28.4 52.4 1682 10 / 3 74.9 28.3 52.4 1682 ... ... ... ... ... 10 / 15 74.2 27.8 52.6 1688

[0158] This weight loss management system constructs a sequence of users' body parameters in chronological order, forming historical data curves at continuous time points, providing a data foundation for subsequent dynamic optimization.

[0159] This weight loss management system uses a dynamic optimization module to dynamically calculate and update core control parameters based on the user's historical body parameters, including preset energy deficit values ​​and predicted weight loss cycle values.

[0160] Dynamically calculate the preset energy deficit value:

[0161] First, calculate the daily energy deficit. Taking October 1st as an example, the user's dietary energy intake was 1850 kcal, exercise energy expenditure was 200 kcal, and basal metabolic rate was 1680 kcal. Therefore, the daily energy deficit = 1850 - 200 - 1680 = -30 kcal. Perform the same calculation for each recording day.

[0162] Calculate the daily change in body fat based on daily weight and body fat percentage. Taking October 2nd as an example, the change in body fat = 75.0 × 28.4% - 75.2 × 28.5% = 21.30 - 21.43 = -0.13 kg, indicating a decrease of 0.13 kg in body fat that day. Further calculate the energy changes from fat and muscle changes. Energy change from fat = -0.13 × 9000 = -1170 kcal; energy change from muscle = 52.4 - 52.3 = 0.1 kg, energy change from muscle = 0.1 × 4000 = 400 kcal.

[0163] Valid record days are selected. The selection criteria include two dimensions: First, the change in fat percentage is negative, meaning there was an actual reduction in fat on that day; second, the sum of the energy deficit from the previous day minus the energy from the change in fat percentage and the energy from the change in muscle mass on that day is greater than 0. For example, on October 2nd, the energy deficit from the previous day (October 1st) was -30 kcal. The sum of the energy from the change in fat percentage and the energy from the change in muscle mass on that day was -1170 + 400 = -770 kcal. Since -30 - (-770) > 0, October 2nd meets the selection criteria.

[0164] Data from October 1st to October 15th was filtered, resulting in 10 valid recording days. The average energy deficit for the day before these 10 valid recording days was calculated, yielding a result of -0.48 (kcal). The weight loss management system used this average as the preset energy deficit value for October 16th to October 31st. Similarly, the system filtered data from October 16th to October 31st, calculating an average energy deficit of -0.55, which was used as the preset value for November 1st to November 15th. The weight loss management system continuously performed these calculations, and the results are shown in the table below:

[0165] Time period Daily fat change Previous day's energy gap - Current day's energy gap (ΔE_fat + ΔE_muscle) Average energy gap of the previous day 10 / 1~15 <0 >0 -0.48 10 / 16~31 <0 >0 -0.55 11 / 1~15 <0 >0 -0.55 11 / 16~30 <0 >0 -0.52 12 / 1~15 <0 >0 -0.49 12 / 16~31 <0 >0 -0.54

[0166] Dynamic calculation of predicted fat loss cycle values:

[0167] The fat loss management system retrieves data on changes in body fat over a past period. Taking October 16th to October 31st as an example, the daily changes in body fat during this period are shown in the table below:

[0168] date Change in fat content (kg) 10 / 16 -0.12 10 / 17 -0.15 10 / 18 +0.08 10 / 19 -0.11 ... ... 10 / 31 +0.09

[0169] The data on changes in body fat were broken down into decreasing and increasing trends. For days with negative changes in body fat, the absolute value represents a decreasing trend; for days with positive changes in body fat, the value represents an increasing trend.

[0170] The mean fat loss and mean fat gain were calculated separately. Over the 15 days from October 16th to October 31st, the total fat loss was -0.865 kg, with a mean fat loss of -0.124 kg / day; the total fat gain was 1.063 kg, with a mean fat gain of 0.118 kg / day.

[0171] Based on the average amount of fat loss and the average amount of fat gain, predict the target number of days required to reach a fat loss state. A fat loss state is defined as a cumulative fat loss percentage greater than 50%, meaning that within a cycle, the total amount of fat loss exceeds the total amount of fat gain. The prediction formula is: Target number of days = (Average fat gain × Number of days to be predicted) / (Average fat gain - Average fat loss). If the number of days to be predicted is set to 15 days, then the target number of days = (0.118 × 15) / (0.118 + 0.124) = 1.77 / 0.242 ≈ 7.3 days.

[0172] In this embodiment, the weight loss management system also employs a rolling prediction mechanism to predict for each time period, and the results are shown in the table below:

[0173] Time period Mean amount of fat reduction Mean increase in fat Forecast target number of days (days) 10 / 16~31 -0.124 0.118 6.7 11 / 1~15 -0.119 0.096 7.3 11 / 16~30 -0.114 0.096 6.7 12 / 1~15 -0.106 0.115 7.3 12 / 16~31 -0.129 0.116 8.3

[0174] Furthermore, the weight loss management system, through the plan generation module, outputs specific and executable diet and exercise plans based on the core control parameters generated by the dynamic optimization module, as detailed below.

[0175] The generation of the diet plan:

[0176] Taking November 1st to November 15th as an example, the preset energy deficit value output by the weight loss management system is -0.55 (meaning a daily energy deficit of 550kcal is required). If the user's daily exercise energy expenditure is 200kcal and the basal metabolic rate is 1680kcal, then the required dietary energy intake for that day = -550 + 200 + 1680 = 1330kcal.

[0177] A pre-defined food dataset is provided, including a food database and its corresponding nutritional information labels. The system categorizes and labels foods based on their energy content (carbohydrate, protein, and fat).

[0178] Category L (low proportion): Carbohydrates <35% of energy, protein <15% of energy, fat <25% of energy.

[0179] Category N (Normal Proportion): Carbohydrates provide 35%–55% of energy, protein provides 15%–35%, and fat provides 25%–35%.

[0180] Category H (High Proportion Category): Carbohydrates provide >55% of energy, protein provides >35%, and fat provides >35% of energy.

[0181] The system presets daily nutrient composition matching results, including three combination modes: NNN, NLN, and NNL. Users select the NNL mode (normal carbohydrates, normal protein, low fat content).

[0182] The weight loss management system selects food combinations that meet label requirements for each meal from a food database and adjusts portion sizes to ensure the comprehensive nutrition label complies with NNL (Nutritional Content Labeling).

[0183] For example, a breakfast might consist of: 50g of oatmeal (approximately 66% carbohydrates, 15% protein, and 9% fat); 200ml of skim milk (55% carbohydrates, 40% protein, and 5% fat); and 2 egg whites (5% carbohydrates, 90% protein, and 5% fat).

[0184] Total calories are approximately 480 kcal: of which carbohydrates: oatmeal provides approximately 132 kcal, milk provides approximately 44 kcal, and egg white provides approximately 4 kcal, totaling approximately 180 kcal, accounting for 37.5% (N); protein: oatmeal provides approximately 30 kcal, milk provides approximately 32 kcal, and egg white provides approximately 72 kcal, totaling approximately 134 kcal, accounting for 27.9% (N); fat: oatmeal provides approximately 18 kcal, milk provides approximately 4 kcal, and egg white provides approximately 4 kcal, totaling approximately 26 kcal, accounting for 5.4% (L).

[0185] For example, lunch consists of: 150g brown rice (70% carbohydrates, 8% protein, 2% fat); 100g roasted chicken breast (0% carbohydrates, 80% protein, 20% fat); and 200g steamed broccoli (40% carbohydrates, 30% protein, 30% fat). Adjusting the portions: 120g brown rice (approximately 200 kcal carbohydrates), 120g chicken breast (approximately 115 kcal protein), and 200g broccoli (approximately 15 kcal fat, 30 kcal carbohydrates, and 20 kcal protein).

[0186] The total calories are approximately 520 kcal (the portion size can be increased or other foods added as the lunch target is 970 kcal). To achieve the energy target, add a quinoa salad (50g quinoa, 100g mixed vegetables, a small amount of vinaigrette dressing). Calculations show that the total calories reach 950 kcal, while maintaining 45% carbohydrates, 30% protein, and 15% fat, which meets the NDL (Neutral Nutrition Law). The final lunch plan is: 120g brown rice + 120g grilled chicken breast + 200g steamed broccoli + quinoa salad.

[0187] For example, dinner could be: 100g purple sweet potato: 85% carbohydrates, 5% protein, 10% fat; 150g steamed fish: 0% carbohydrates, 80% protein, 20% fat; 200g garlic lettuce: 70% carbohydrates, 10% protein, 20% fat. Calculations: Purple sweet potato provides approximately 85 kcal of carbohydrates and 5 kcal of protein; fish provides approximately 120 kcal of protein; lettuce provides a small amount.

[0188] The total calories are approximately 350 kcal, which needs to be increased. Add 100g of tofu (10% carbohydrates, 60% protein, 30% fat) and a small amount of olive oil. The final total calories are approximately 700 kcal, with carbohydrates accounting for approximately 40%, protein approximately 35%, and fat approximately 25% (close to the upper limit of L, which can be reduced to 22% by reducing the amount of oil). Final dinner option: 100g purple sweet potato + 150g steamed fish + 200g garlic lettuce + 100g cold tofu salad.

[0189] This weight loss management system provides a complete diet plan, including a food list for each meal, suggested portion sizes, and nutritional analysis. Users can choose to substitute items with the same label according to their own tastes, such as replacing whole wheat bread with oatmeal, or steamed fish with steamed shrimp.

[0190] Generate motion plans:

[0191] This weight loss management system has a pre-set exercise library covering common exercise types, and each exercise has its energy consumption value per unit of time. For example, for a user weighing 75kg, the energy consumption for some exercises is as follows:

[0192] sports Metabolic equivalent (MET) Energy consumption per unit time (kcal / 30min) jogging 7.0 262 Hurry up 4.5 168 swim 8.0 300 Cycling 6.0 225 Strength training 5.0 188

[0193] The system filters available exercises from the exercise library, performs combination optimizations, and generates multiple exercise combination schemes.

[0194] Option 1: Jog for 30 minutes (burns 262kcal)

[0195] Option 2: 30 minutes of brisk walking + 20 minutes of strength training (burns 168 + 125 = 293 kcal)

[0196] Option 3: Swim for 20 minutes + cycle for 20 minutes (burns 200 + 150 = 350 kcal)

[0197] Option 4: Brisk walking for 45 minutes (burns 252kcal)

[0198] After the weight loss management system outputs a complete exercise plan, users can choose the most suitable combination plan based on their own time schedule, exercise preferences and venue conditions.

[0199] Furthermore, the weight loss management system presents the generated results to the user through an output module. The output method is a mobile application display interface.

[0200] The system displays the core control parameters output by the dynamic optimization module: "The preset energy deficit for this period (November 1st to November 15th) is 550 kcal / day. Based on your historical data, it is estimated that you will reach a fat loss state (cumulative fat reduction greater than 50%) in approximately 7 days." It also displays diet and exercise plans, clearly presenting information such as food lists for each meal, cooking suggestions, nutritional analysis, and the specific duration and estimated energy expenditure of each exercise session. Users can view plan details, select different plans, adjust plans, or confirm execution through the output interface. The fat loss management system records user choices and execution status as a basis for subsequent optimization.

[0201] From November 1st to November 15th, users followed the diet and exercise plans generated by the weight loss management system. During this period, users continued to use the body fat scale to measure their body data daily.

[0202] The weight loss management system acquires new body data from users between November 1st and November 15th, including daily weight, body fat percentage, muscle mass, and basal metabolic rate. This new data is then merged with historical data to create an updated body data sequence.

[0203] The dynamic optimization module re-executes the calculation process of the core control parameters based on the new multidimensional body parameters:

[0204] The weight loss management system filtered data from November 1st to November 15th, selecting 12 valid recording days. The average energy deficit for the day before these 12 valid recording days was calculated, resulting in -0.55 kcal. This average was used as the preset energy deficit value for November 16th to November 30th.

[0205] The weight loss management system retrieved data on fat changes from November 1st to November 15th, calculating an average fat loss of -0.119 kg / day and an average fat gain of 0.096 kg / day. These values ​​were then used in the prediction formula.

[0206] Target number of days = (0.096 × 15) / (0.096 + 0.119) = 1.44 / 0.215 ≈ 6.7 days.

[0207] The plan generation module generates a new diet and exercise plan based on the updated preset energy deficit value (-0.55). The weight loss management system outputs the new plan to the user and prompts: "The preset energy deficit value for this period (November 16 to November 30) remains at -550kcal / day. Based on your weight loss data, you need to reach a weight loss state for 7 days in the next half month."

[0208] This cycle repeats continuously, forming a complete closed loop of "obtaining parameters → calculating and updating core parameters → generating a plan → outputting → executing → obtaining parameters again," ensuring that the weight loss plan can be continuously optimized as the user's physical condition changes.

[0209] Through the above specific implementation methods, the fat loss management method of the present invention realizes dynamic closed-loop management based on continuous body fat monitoring, effectively solving the problems of rigid energy deficit setting, unpredictable fat loss cycle, monotonous diet plan, and disconnected exercise recommendations in the prior art.

[0210] This application also provides a terminal device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the weight loss management method described above.

[0211] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the weight loss management method described above.

[0212] In summary, the technical solution disclosed in this application has the following beneficial effects:

[0213] Precision: By continuously monitoring users' body data such as weight, body fat percentage, muscle mass, and basal metabolism, the system dynamically calculates the preset energy deficit and predicts the fat loss cycle, making the fat loss plan more in line with the user's real changes in body condition and avoiding the problem of unstable fat loss effect caused by fixed energy deficit in traditional plans.

[0214] Dynamic closed-loop: After the user executes the weight loss plan, the system continuously acquires new body data and updates the core control parameters accordingly, forming a closed-loop optimization mechanism of "monitoring → calculation → adjustment → execution → re-monitoring" to ensure that the weight loss plan can be continuously optimized according to changes in the body's condition and avoid weight loss stagnation or plateaus.

[0215] Synergy: Both the diet plan and the exercise plan are generated based on the same core control parameter (preset energy deficit value), which makes diet management, exercise management and fat loss goals synergistic, avoiding the problem of diet and exercise being separated in traditional plans, and improving the precise control of the overall fat loss effect.

[0216] Predictability: By predicting the weight loss cycle, users can obtain an approximate time required to reach their weight loss goals. Clear goal expectations help improve users' confidence in weight loss and long-term adherence.

[0217] Personalization: Based on continuous body fat monitoring data of individual users, a weight loss plan is dynamically generated, so that the energy deficit setting, diet recommendation and exercise recommendation are all individualized, realizing a truly personalized weight loss management.

[0218] Lifestyle-oriented: Diet plans are generated based on a preset set of food data and nutrient matching rules, covering most of the ingredients in daily diets; exercise plans are generated based on the unit time energy consumption value of common exercises in the exercise library, enabling users to manage fat loss while maintaining their daily eating habits and exercise preferences, making it easy to stick to in the long term.

[0219] Continuous accumulation of data value: The body data that users continuously accumulate during the execution of a weight loss program can be used by the system to more accurately calculate the preset energy deficit value and the predicted value of the weight loss cycle in the subsequent stages, so that the weight loss program can be continuously optimized as data accumulates.

[0220] It is understood that the above scenarios are merely examples and do not constitute a limitation on the application scenarios of the technical solutions provided in the embodiments of this application. The technical solutions of this application can also be applied to other scenarios. For example, as those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0221] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0222] The steps in the method of this application embodiment can be adjusted, combined, or deleted according to actual needs.

[0223] The units in the device of this application embodiment can be merged, divided, and deleted according to actual needs.

[0224] In this application, the same or similar terms, concepts, technical solutions and / or application scenario descriptions are generally described in detail only when they appear for the first time. When they appear again, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of this application, the same or similar terms, concepts, technical solutions and / or application scenario descriptions that are not described in detail later can be referred to their previous relevant detailed descriptions.

[0225] In this application, the descriptions of the various embodiments have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0226] The technical features of the present application can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present application.

[0227] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A weight loss management system, characterized in that, The weight loss management system includes: The data acquisition module is used to periodically acquire the user's multidimensional body parameters, which include at least weight, body fat percentage, muscle mass, and basal metabolic rate. The dynamic optimization module is used to dynamically calculate and update the core control parameters for guiding fat loss based on the changing trends of the multidimensional body parameters. The core control parameters include at least a preset energy deficit value and / or a predicted fat loss cycle value. The plan generation module is used to generate a diet plan and / or exercise plan corresponding to the core control parameters based on the core control parameters. The output module is used to output the core control parameters and / or the diet plan and / or the exercise plan.

2. The weight loss management system according to claim 1, characterized in that, The dynamic optimization module includes: The energy gap calculation unit is used to filter out the recording days that meet the preset fat loss conditions based on the changing trends of the multidimensional body parameters, and to determine the preset energy gap value for the next cycle based on the energy gap data of the selected recording days. The fat loss day prediction unit is used to determine the fat reduction trend and fat increase trend based on the changing trends of the multidimensional body parameters, and predict the target number of days required to reach the preset fat loss state based on the trends.

3. The weight loss management system according to claim 2, characterized in that, When the energy gap calculation unit determines the preset value of the energy gap for the next cycle, it performs the following steps: Determine the trend of fat changes based on weight and body fat percentage over a continuous period; Recording days with negative changes in fat and an energy deficit that met preset criteria from the previous day were selected. The average energy gap of the day before the selected record date is used as the preset energy gap value for the next cycle.

4. The weight loss management system according to claim 2, characterized in that, When the fat loss days prediction unit predicts the target number of days required to reach the preset fat loss state, it performs the following steps: Obtain data on changes in fat levels over the past period; Calculate the mean amount of fat loss and the mean amount of fat gain separately; Based on the average amount of fat loss and the average amount of fat gain, the target number of days required to reach the preset fat loss state is predicted.

5. The weight loss management system according to claim 1, characterized in that, The scheme generation module includes: The diet plan generation unit is used to generate a diet plan corresponding to the core control parameters based on the core control parameters and a preset food data set. The motion scheme generation unit is used to generate a motion scheme corresponding to the core control parameters based on the core control parameters.

6. The weight loss management system according to claim 5, characterized in that, When the diet plan generation unit generates a diet plan, it performs the following steps: Based on the preset energy deficit value, combined with the user's basal metabolic rate and energy expenditure during exercise, the required dietary energy intake for the day is determined. Foods that meet the nutritional matching rules are selected from the preset food data set to generate a diet plan.

7. The weight loss management system according to claim 5, characterized in that, When the motion scheme generation unit generates a motion scheme, it performs the following steps: Obtain the energy consumption per unit time for each exercise in the exercise library; The required energy consumption for exercise is determined based on the preset energy gap value. The exercise plan is generated by matching multiple exercises and their corresponding suggested durations from the exercise library.

8. A weight loss management method, characterized in that, The weight loss management method includes: The system periodically acquires the user's multidimensional body parameters, which include at least weight, body fat percentage, muscle mass, and basal metabolic rate. Based on the changing trends of the multidimensional body parameters, the core control parameters for guiding fat loss are dynamically calculated and updated. The core control parameters include at least a preset energy deficit value and / or a predicted fat loss cycle value. Based on the core control parameters, generate a diet plan and / or exercise plan corresponding to the core control parameters; Output the core control parameters and / or the diet plan and / or the exercise plan.

9. The weight loss management method according to claim 8, characterized in that, The step of dynamically calculating and updating the core control parameters for guiding fat loss based on the changing trends of the multidimensional body parameters includes: Based on the changing trends of the multidimensional body parameters, record days that meet the preset fat loss conditions are selected, and the preset energy deficit value for the next cycle is determined based on the energy deficit data of the selected record days; and / or, Based on the changing trends of the multidimensional body parameters, the trends of fat reduction and fat increase are determined, and the target number of days required to reach the preset fat loss state is predicted based on the trends.

10. The weight loss management method according to claim 8, characterized in that, The step of generating a diet plan and / or exercise plan corresponding to the core control parameters includes: Based on the core control parameters and a preset food data set, generate a diet plan corresponding to the core control parameters; and / or, Based on the core control parameters, a motion scheme corresponding to the core control parameters is generated.

11. A terminal device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the program, implements the weight loss management method according to any one of claims 8 to 10.

12. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the weight loss management method as described in any one of claims 8 to 10.

Images