A method for evaluating and managing body fat percentage (BMI) and the effect of Zhanwei capsule based on intelligent monitoring

Abstract

The present invention discloses a method for evaluating and managing body fat rate (BMI) and the effect of Zhanwei capsule based on intelligent monitoring, which relates to the technical field of body fat rate (BMI) and the effect of Zhanwei capsule, and includes the following steps: using intelligent monitoring technology to track the changes in the patient's body fat rate after using Zhanwei capsule in real time, dynamically record and continuously update relevant data, and build a comprehensive and systematic body fat rate data set to provide accurate data support for subsequent analysis and management. The present invention uses intelligent monitoring technology to collect body fat rate and visceral fat data, predicts the risk of hidden decrease in basal metabolic rate through support vector machine, and combines clustering algorithm to subdivide metabolic problem types, providing a basis for personalized intervention, making up for the deficiencies of existing technologies in dynamic monitoring and risk classification, significantly improving the accuracy of metabolic management, reducing the risk of obesity-related diseases, and optimizing patients' body fat rate and metabolic health.

Description

Technical Field

[0001] The present invention relates to the technical field of body fat percentage (BMI) and stomach-sucking capsule effect evaluation, and in particular to a body fat percentage (BMI) and stomach-sucking capsule effect evaluation and management method based on intelligent monitoring. Background Art

[0002] Body fat percentage (BMI) and Zhanwei Capsule effect evaluation and management based on intelligent monitoring refers to the use of advanced intelligent monitoring technology to track and analyze individual body fat percentage (BMI) in real time, and to conduct comprehensive evaluation and management in combination with the effect of Zhanwei Capsule. This process includes collecting the user's weight, height, body fat and other data through smart devices or sensors, calculating the BMI value, and evaluating the trend of body fat changes; at the same time, by analyzing the role of Zhanwei Capsule (such as the occupancy of gastric contents, the duration of satiety, etc.), the effectiveness of Zhanwei Capsule in weight management is judged. Based on machine learning or data models, the system can intelligently identify the rules of user body fat changes, dynamically adjust the monitoring frequency or capsule usage plan, so as to achieve personalized and scientific weight and health management goals.

[0003] The prior art has the following deficiencies:

[0004] When the existing technology manages body fat percentage (BMI) and the effect of Zhanwei Capsules based on intelligent monitoring, it is usually difficult to accurately capture the hidden decline of the patient's basal metabolic rate (BMR) through abnormal changes in body fat percentage in a timely manner. Long-term use of Zhanwei Capsules may lead to a gradual decline in BMR, and this process is difficult to effectively detect through conventional monitoring methods in the short term due to the hidden changes. The reduction in BMR will significantly weaken the body's energy consumption capacity, causing the body fat percentage (BMI) to rebound rapidly after the capsule is discontinued, which will not only offset the previous fat reduction results, but may also cause metabolic disorders and significantly increase the risk of obesity-related diseases (such as type 2 diabetes and cardiovascular disease).

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method for evaluating and managing the effect of body fat rate BMI and stomach capsule based on intelligent monitoring, using intelligent monitoring technology to collect and dynamically track data such as patient body fat rate, body fat distribution and visceral fat ratio in real time, forming a systematic body fat rate data set, and predicting the potential implicit decline of the patient's basal metabolic rate through a support vector machine model. At the same time, combined with a clustering algorithm, the metabolic change pattern within a number of time windows is deeply analyzed, and the patient's metabolic problems are subdivided into three types: continuous type, short-term recovery type and continuous change type, providing a scientific basis for personalized intervention measures, effectively making up for the deficiencies of the existing technology in the dynamic monitoring of the implicit decline of the basal metabolic rate, risk classification and intervention optimization, and significantly improving the accuracy and efficiency of metabolic management, reducing the risk of obesity-related diseases, thereby comprehensively optimizing the patient's body fat rate and metabolic health management effect, to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above-mentioned purpose, the present invention provides the following technical solution: a method for evaluating and managing body fat percentage (BMI) and Zhanwei capsule effect based on intelligent monitoring, comprising the following steps:

[0008] Intelligent monitoring technology is used to track the changes in body fat percentage of patients after using the Zhanwei Capsule in real time, dynamically record and continuously update relevant data, and build a comprehensive and systematic body fat percentage data set to provide accurate data support for subsequent analysis and management;

[0009] The collected patient body fat percentage information is constructed into an analysis set, from which the key data of abnormal changes in body fat percentage related to the implicit decrease in basal metabolic rate are extracted. Within the selected fixed time window, the extracted key data are feature analyzed to generate quantitative evaluation indicators, and the implicit decrease in the patient's basal metabolic rate is preliminarily quantified;

[0010] The quantified evaluation index is input into the pre-trained support vector machine model, and the model is used to predict the hidden decrease in the patient's basal metabolic rate;

[0011] Based on the prediction results of the support vector machine model, it can intelligently identify whether the patient has a potential hidden decrease in basal metabolic rate, and preliminarily classify the patient's overall metabolic status as "normal" or "potential risk";

[0012] When a patient is identified to have a potential recessive decrease in basal metabolic rate, the patient is continuously monitored, and the metabolic rate change results predicted by the support vector machine model are obtained within several selected fixed time windows to form a dynamically changing data sequence. The clustering algorithm is used to conduct a comprehensive analysis of the metabolic rate prediction results within several fixed time windows, and the patient's potential recessive decrease in basal metabolic rate is further divided into three types: continuous type, short-term recovery type, and continuous change type, revealing its change pattern;

[0013] According to the results of cluster analysis, targeted countermeasures are taken for different types of hidden decline.

[0014] Preferably, the body fat percentage of the patient after using the Zhanwei capsule is tracked in real time by intelligent monitoring technology, and the specific steps are as follows:

[0015] Wear or use smart monitoring devices to record the patient's physiological data in real time and transmit the collected data to a central database or patient management platform via wireless technology;

[0016] The collected data is input into the system for preprocessing, including denoising, outlier removal and unit unification, to improve data quality;

[0017] Generate a dynamic trend chart of body fat percentage based on the patient's historical data and real-time data collection, and visualize the change pattern, making it convenient for patients and medical staff to view at any time;

[0018] When the body fat percentage is detected to exceed the preset body fat percentage threshold, an alarm is triggered and a personalized reminder is sent to the patient or medical staff.

[0019] Preferably, key data of abnormal changes in body fat percentage related to the implicit decrease in basal metabolic rate are extracted, wherein the extracted key data include the degree of fluctuation of the visceral fat ratio between multiple monitoring time points and the cumulative proportion of the time period when the body fat percentage change tends to zero. Within a selected fixed time window, characteristic analysis is performed on the extracted degree of fluctuation of the visceral fat ratio between multiple monitoring time points and the cumulative proportion of the time period when the body fat percentage change tends to zero, and a visceral fat ratio fluctuation factor and a body fat percentage stagnation factor are generated respectively. The implicit decrease in the patient's basal metabolic rate is preliminarily quantified through the quantified visceral fat ratio fluctuation factor and body fat percentage stagnation factor evaluation indicators.

[0020] Preferably, the visceral fat ratio fluctuation factor and the body fat percentage stagnation factor, which are quantified based on the fluctuation degree of the visceral fat ratio between multiple monitoring time points and the cumulative ratio of the time period in which the body fat percentage change tends to zero, are input into a pre-trained support vector machine model, and a decline risk assessment index is generated by the support vector machine model, and the implicit decline in the patient's basal metabolic rate is predicted based on the decline risk assessment index.

[0021] Preferably, the decline risk assessment index generated when predicting the latent decline in the basal metabolic rate of the patient by the pre-trained support vector machine model within a fixed time window is compared and analyzed with the pre-set decline risk assessment index reference threshold, and the overall metabolic status of the patient is preliminarily classified. The specific classification steps are as follows:

[0022] If the decline risk assessment index is greater than the decline risk assessment index reference threshold, the patient’s overall metabolic status is preliminarily classified as “potential risk”;

[0023] If the downside risk assessment index is less than or equal to the downside risk assessment index reference threshold, the patient's overall metabolic status is preliminarily classified as "normal".

[0024] Preferably, a clustering algorithm is used to comprehensively analyze the metabolic rate prediction results within several fixed time windows to further divide the potential hidden decrease in the basal metabolic rate of the patient. The specific steps are as follows:

[0025] When it is identified that the patient has a potential for latent decrease in basal metabolic rate, the patient's decline risk assessment index is generated by the support vector machine model in several subsequent selected fixed time windows. The generated decline risk assessment index is arranged in chronological order to form a dynamically changing data sequence. The expression of the dynamically changing data sequence is: ,in, It is a dynamically changing data series, including the timestamp of each fixed time window and the corresponding decline risk assessment index. is the timestamp of the nth fixed time window, is the decline risk assessment index of the nth fixed time window, reflecting the risk level of hidden decline in metabolic rate during this time period, and m is the number of selected fixed time windows;

[0026] Feature extraction is performed on the dynamic data sequence, and the dynamic features of the downside risk assessment index in each fixed time window are calculated. The rate of change of the downside risk assessment index, the fluctuation range of the downside risk assessment index, and the cumulative change of the downside risk assessment index are extracted. The calculation expression of the rate of change of the downside risk assessment index is: , the calculation expression of the fluctuation range of the downside risk assessment index is: , the calculation expression of the cumulative change of the decline risk assessment index is: ,in, is the rate of change of the descent risk assessment index within a fixed time window, reflecting the speed at which the descent risk assessment index increases or decreases. To reduce the volatility of risk assessment index and quantify the stability of data, To reduce the cumulative change in the risk assessment index and assess the severity of the overall change, It is the mean of the downside risk assessment index in the dynamically changing data series, which is used to calculate the fluctuation range;

[0027] The extracted characteristics of the rate of change of the downside risk assessment index, the fluctuation range of the downside risk assessment index, and the cumulative change of the downside risk assessment index are used to , the k-means clustering algorithm was used to perform pattern recognition on the patients’ dynamic data, and the patients’ potential basal metabolic rate recessive decrease was further divided into the following three types:

[0028] like , then the patient's potential basal metabolic rate recessive decrease is further divided into persistent type;

[0029] like , then the patient's potential basal metabolic rate recessive decline is further divided into short-term recovery type;

[0030] like , then the patient's potential basal metabolic rate recessive decline is further divided into continuous change type;

[0031] in, It is the reference threshold of fluctuation amplitude, which is preset to judge the stability of data. It is the reference threshold of the cumulative change, which is preset to evaluate the severity of data changes.

[0032] Preferably, within a selected fixed time window, the specific steps of performing characteristic analysis on the fluctuation degree of the extracted visceral fat ratio between multiple monitoring time points to generate a visceral fat ratio fluctuation factor are as follows:

[0033] In the selected fixed time window, the values ​​of the visceral fat ratio at each time point are collected, the change gradient between adjacent time points is calculated, and the change gradient is accumulated to calculate the total change gradient of the visceral fat ratio in the fixed time window. The calculation formula for the total change gradient of the visceral fat ratio is: ,in: is the total change gradient of visceral fat ratio, is the visceral fat ratio at time point i, For time point The visceral fat ratio is the time interval between adjacent time points, is the weight coefficient, which indicates the influence of the change of time point i on the overall gradient, and N is the total number of monitoring time points in the fixed time window;

[0034] In the same fixed time window, the fluctuation range of visceral fat changes was calculated, and the square sum of the fluctuation range was used to measure the significance of the fluctuation. The calculation expression of the fluctuation range of visceral fat changes was: ,in: is the fluctuation range of visceral fat, , are the maximum and minimum values ​​of the visceral fat ratio within a fixed time window, is the priority coefficient of time point i, indicating the importance of fluctuation at that time point;

[0035] The visceral fat ratio fluctuation factor is generated by combining the total change gradient of the visceral fat ratio and the fluctuation amplitude of the visceral fat ratio. The significance of the fluctuation characteristics is amplified in the form of an exponential. The generation expression of the visceral fat ratio fluctuation factor is: ,in: is the visceral fat ratio fluctuation factor, It is a nonlinear adjustment factor that amplifies or smoothes the overall impact of fluctuations. is the sensitivity adjustment coefficient, which controls the comprehensive weight of fluctuation and gradient in a fixed time window. K is the window length influencing factor, which is defined as the total number of monitoring time points N and the time interval in a fixed time window. The product of, that is: .

[0036] Preferably, within a selected fixed time window, the specific steps of performing characteristic analysis on the extracted cumulative proportion of the time period in which the body fat percentage change tends to zero to generate the body fat percentage stagnation factor are as follows:

[0037] In the selected fixed time window, the time period when the body fat percentage changes tend to zero is screened out, and the cumulative proportion of the time period when the body fat percentage changes tend to zero is calculated by the following formula: ,in: is the cumulative proportion of the time period when the body fat percentage changes towards zero, is the rate of change of body fat percentage, is the set of time periods when the rate of change of body fat percentage tends to zero, that is, time period, is the preset body fat percentage change rate threshold, which is used to define the condition for the body fat percentage change to approach zero. F is the body fat percentage value, and W is the selected fixed time window. is a very small positive number to prevent the denominator from being zero;

[0038] The cumulative proportion of the time period when the body fat percentage changes to zero Perform nonlinear weight adjustment to generate the body fat percentage stagnation factor. The expression of the body fat percentage stagnation factor generated by nonlinear weight adjustment is: ,in: It is a body fat percentage stagnation factor, a preliminary indicator to quantify the hidden decrease in the patient's basal metabolic rate. and Adjustment coefficient, used to control the sensitivity and proportional distribution of nonlinear weights, is an exponential term, emphasizing the nonlinear effect of the cumulative ratio on the body fat percentage stagnation factor. For logarithmic terms, balance the weight distribution and avoid over-sensitivity of exponential terms.

[0039] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0040] The present invention uses intelligent monitoring technology to collect and dynamically track data such as the patient's body fat rate, body fat distribution, and visceral fat ratio in real time, forming a systematic body fat rate data set, and predicting the patient's potential hidden decrease in basal metabolic rate through a support vector machine model. At the same time, combined with a clustering algorithm, it deeply analyzes the metabolic change patterns within several time windows, and subdivides the patient's metabolic problems into three types: continuous, short-term recovery, and continuous change, providing a scientific basis for personalized intervention measures, effectively making up for the deficiencies of existing technologies in dynamic monitoring of hidden decreases in basal metabolic rate, risk classification, and intervention optimization, and can significantly improve the accuracy and efficiency of metabolic management, reduce the risk of obesity-related diseases, and thus comprehensively optimize the patient's body fat rate and metabolic health management effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0042] Figure 1 The present invention is a method flow chart of a method for evaluating and managing the body fat percentage BMI and the effect of the stomach-sucking capsule based on intelligent monitoring. DETAILED DESCRIPTION

[0043] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0044] The present invention provides Figure 1 The method for evaluating and managing body fat percentage (BMI) and the effect of the stomach capsule based on intelligent monitoring includes the following steps:

[0045] Through intelligent monitoring technology, the patient's body fat percentage (BMI) is tracked in real time after using the Zhanwei Capsule, and the patient's weight, body fat distribution, visceral fat ratio and other indicators are dynamically recorded, and the data is continuously updated. All data are systematically stored to form a comprehensive body fat percentage data set;

[0046] Real-time tracking ensures that the dynamic changes of the patient's body fat percentage are captured, providing a comprehensive and accurate data basis for subsequent analysis. High-frequency data collection can reveal subtle trends and avoid missing important information due to low-frequency monitoring.

[0047] The patient's body fat percentage (BMI) is tracked in real time through intelligent monitoring technology after using the Zhanwei Capsule. The specific steps are as follows:

[0048] Patients wear or use smart monitoring devices (such as smart scales, body fat analyzers or wearable devices) to record real-time physiological data such as weight, body fat percentage, muscle mass, visceral fat percentage, etc. The device transmits the collected data to a central database or patient management platform via wireless technology (such as Bluetooth or Wi-Fi).

[0049] This step is the basis of the entire monitoring process, ensuring that all relevant data can be collected and transmitted in a timely and accurate manner, providing high-quality raw data support for subsequent analysis.

[0050] The collected data are input into the system for preprocessing, including denoising, outlier removal and unit unification.

[0051] Data preprocessing can improve data quality, avoid erroneous analysis due to collection errors or equipment problems, and enhance monitoring accuracy.

[0052] Based on the patient's historical data and real-time collected data, a dynamic trend chart of body fat percentage (BMI) is generated, and the change pattern is visualized, making it convenient for patients and medical staff to view at any time.

[0053] Through dynamic trend analysis, potential problems with the patient's body fat percentage (such as slowing changes or abnormal rebound) can be quickly discovered, providing a scientific basis for subsequent management and adjustment. Visual display improves the readability of data and facilitates understanding and decision-making.

[0054] When the system detects that the body fat percentage exceeds the preset body fat percentage threshold, an alarm is triggered and personalized reminders are sent to the patient or medical staff. These reminders may include suggestions for improved diet, exercise plan adjustments, or prompts for further medical examinations.

[0055] Alarm mechanisms and personalized reminders ensure that problems can be discovered and handled in a timely manner, avoiding abnormal body fat percentage in patients.

[0056] The collected patient body fat percentage information is constructed into an analysis set, from which the key data of abnormal changes in body fat percentage related to the implicit decrease in basal metabolic rate (BMR) are extracted. Within the selected fixed time window, the extracted key data are feature analyzed to generate quantitative evaluation indicators, and the implicit decrease in the patient's basal metabolic rate is preliminarily quantified. The quantified evaluation indicators are input into the pre-trained support vector machine model, and the model is used to predict the implicit decrease in the patient's basal metabolic rate;

[0057] The construction of the analysis set transforms messy data into a meaningful feature set, while key data extraction can focus on those highly relevant changes and eliminate redundant information, thereby improving the efficiency and accuracy of the analysis.

[0058] The setting of a fixed time window ensures the continuity and timeliness of data analysis, while quantitative evaluation can provide standardized input for the support vector machine model, ensuring the consistency and scientificity of the prediction results.

[0059] Extract key data of abnormal changes in body fat percentage related to the implicit decrease in basal metabolic rate, where the extracted key data include the fluctuation degree of visceral fat ratio between multiple monitoring time points and the cumulative proportion of time periods when the body fat percentage changes tend to zero. Within the selected fixed time window, perform feature analysis on the extracted fluctuation degree of visceral fat ratio between multiple monitoring time points and the cumulative proportion of time periods when the body fat percentage changes tend to zero, and generate visceral fat ratio fluctuation factor and body fat percentage stagnation factor respectively. Preliminary quantification of the implicit decrease in the patient's basal metabolic rate is achieved through the quantified visceral fat ratio fluctuation factor and body fat percentage stagnation factor evaluation indicators.

[0060] When the visceral fat ratio fluctuates greatly between multiple monitoring time points, it may indicate a potential hidden decrease in the patient's basal metabolic rate (BMR). The accumulation of visceral fat is usually closely related to an imbalance in energy metabolism, especially when the BMR decreases. The body will preferentially store excess energy as visceral fat, which has a higher metabolic activity and therefore increases the degree of fluctuation. In addition, a decrease in BMR may lead to reduced fat metabolism efficiency, causing fat to be redistributed in the visceral area, further exacerbating fluctuations. Abnormal fluctuations in the visceral fat ratio are not only an early signal of a hidden decrease in BMR, but may also indicate a higher risk of metabolic disorders, such as insulin resistance and metabolic syndrome, so it requires high attention and targeted intervention measures.

[0061] The specific steps of generating the visceral fat ratio fluctuation factor by characteristic analysis of the fluctuation degree of the extracted visceral fat ratio between multiple monitoring time points within the selected fixed time window are as follows:

[0062] In the selected fixed time window, the values ​​of the visceral fat ratio at each time point are collected, the change gradient between adjacent time points is calculated, and the change gradient is accumulated to calculate the total change gradient of the visceral fat ratio in the fixed time window. The calculation formula for the total change gradient of the visceral fat ratio is: ,in: is the total change gradient of visceral fat ratio, is the visceral fat ratio at time point i, For time point The visceral fat ratio is the time interval between adjacent time points, is the weight coefficient, which indicates the influence of the change of time point i on the overall gradient, and N is the total number of monitoring time points in the fixed time window;

[0063] The visceral fat ratio refers to the ratio of the amount of fat around the internal organs of the human body to the total amount of body fat, and is used to measure the degree of fat accumulation in the visceral area. Visceral fat is a type of fat that exists in the abdominal cavity and surrounds important organs (such as the liver, pancreas, and kidneys). Unlike subcutaneous fat, it has higher metabolic activity and has a greater impact on human health. The visceral fat ratio is measured by professional body fat analysis equipment or smart monitoring equipment, and is usually closely related to overall health status, metabolic function, and the risk of related diseases (such as insulin resistance, fatty liver, and cardiovascular disease). This indicator is of great significance in weight management and metabolic health assessment, especially in monitoring changes in basal metabolic rate and the risk of metabolic disorders.

[0064] This step captures the dynamic trend of fat percentage changes by calculating the gradient of fat percentage changes, highlighting the impact of fast-changing time points on the gradient, and helps to quantify the severity of fat changes within a fixed time window.

[0065] In the same fixed time window, the fluctuation range of visceral fat changes was calculated, and the square sum of the change range was used to measure the significance of the fluctuation. The calculation expression of the fluctuation range of visceral fat changes was: ,in: is the fluctuation range of visceral fat, , are the maximum and minimum values ​​of the visceral fat ratio within a fixed time window, is the priority coefficient of time point i, indicating the importance of fluctuation at that time point;

[0066] Priority coefficient refers to the weight value used to measure the degree of influence of a certain data point or specific factor on the overall result during data analysis or calculation. It reflects the difference in importance of different data points or factors, and is usually assigned according to the target or feature distribution in a specific scenario. For example, in time series analysis, priority coefficients can be used to highlight the impact of key time points in order to conduct a more accurate analysis of the core areas of trend changes. Priority coefficients can be set in a variety of ways and can be dynamically adjusted according to data distribution, change rate, abnormal point characteristics or user needs, thereby optimizing the flexibility and applicability of the calculation model and improving the accuracy and scientificity of the results.

[0067] The influence of the extreme points of visceral fat ratio within a fixed time window is strengthened by calculating the sum of squares of fluctuations, and combined with the priority coefficient , highlighting the fluctuation characteristics of key time points and providing precise features for the generation of visceral fat ratio fluctuation factors.

[0068] The visceral fat ratio fluctuation factor is generated by combining the total change gradient of the visceral fat ratio and the fluctuation amplitude of the visceral fat ratio. The significance of the fluctuation characteristics is amplified in the form of an exponential. The generation expression of the visceral fat ratio fluctuation factor is: ,in: is the visceral fat ratio fluctuation factor, It is a nonlinear adjustment factor that amplifies or smoothes the overall impact of fluctuations. is the sensitivity adjustment coefficient, which controls the comprehensive weight of fluctuation and gradient in a fixed time window. K is the window length influencing factor, which is defined as the total number of monitoring time points N and the time interval in a fixed time window. The product of, that is: ;

[0069] This step combines the total change gradient of the visceral fat ratio and the fluctuation amplitude of the visceral fat ratio to generate a quantified visceral fat ratio fluctuation factor. It uses nonlinear adjustment and logarithmic amplification to enhance the sensitivity to extreme changes, providing an accurate indicator for the initial assessment of the hidden decrease in the patient's basal metabolic rate.

[0070] It can be seen from the visceral fat ratio fluctuation factor that within the selected fixed time window, the larger the performance value of the visceral fat ratio fluctuation factor generated by the characteristic analysis of the fluctuation degree of the extracted visceral fat ratio between multiple monitoring time points, the more drastic the fluctuation degree of the visceral fat ratio between multiple monitoring time points, indicating that the patient's metabolic balance may be more disturbed, thus reflecting the greater risk of hidden decrease in basal metabolic rate (BMR). Conversely, when the performance value of the visceral fat ratio fluctuation factor is small, it means that the visceral fat ratio changes relatively smoothly, and the dynamic characteristics of fat metabolism tend to be normal, indicating that the risk of hidden decrease in the patient's basal metabolic rate is low. Therefore, the visceral fat ratio fluctuation factor plays a key quantitative role in assessing the risk of hidden decrease in the patient's basal metabolic rate and is an important reference indicator for identifying potential metabolic problems.

[0071] When the cumulative proportion of time periods in which a patient's body fat percentage changes toward zero is high, it usually indicates that there may be a potential hidden decrease in their basal metabolic rate (BMR). The change in body fat percentage tending toward zero means that the patient's fat metabolism efficiency is significantly reduced, and even under normal dietary restrictions or exercise, fat consumption almost stops. This phenomenon is usually due to the decrease in BMR, which weakens the body's energy consumption ability and enters "energy saving mode" (Metabolic Adaptation) to adapt to long-term insufficient calorie intake or metabolic regulation disorders. Over time, this decrease in metabolic efficiency will not only hinder the further decomposition of fat, but may also cause problems such as an increase in the proportion of visceral fat and weight rebound. It is a signal that metabolic health needs to focus on.

[0072] The specific steps for generating the body fat percentage stagnation factor by feature analysis of the extracted cumulative proportion of the time period when the body fat percentage change tends to zero within the selected fixed time window are as follows:

[0073] In the selected fixed time window, the time period when the body fat percentage changes tend to zero is screened out, and the cumulative proportion of the time period when the body fat percentage changes tend to zero is calculated by the following formula: ,in: is the cumulative proportion of the time period when the body fat percentage changes towards zero, is the rate of change of body fat percentage, is the set of time periods when the rate of change of body fat percentage tends to zero, that is, time period, is the preset body fat percentage change rate threshold, which is used to define the condition for the body fat percentage change to approach zero. F is the body fat percentage value, and W is the selected fixed time window. is a very small positive number to prevent the denominator from being zero;

[0074] Passing the selected body fat percentage change rate threshold , the time period when the body fat percentage change rate is close to zero can be extracted, and the cumulative proportion of the time period when the body fat percentage change tends to zero can be calculated , providing basic data for generating body fat percentage stagnation factors.

[0075] The cumulative proportion of the time period when the body fat percentage changes to zero Perform nonlinear weight adjustment to generate the body fat percentage stagnation factor. The expression of the body fat percentage stagnation factor generated by nonlinear weight adjustment is: ,in: It is a body fat percentage stagnation factor, a preliminary indicator to quantify the hidden decrease in the patient's basal metabolic rate. and Adjustment coefficient, used to control the sensitivity and proportional distribution of nonlinear weights, is an exponential term, emphasizing the nonlinear effect of the cumulative ratio on the body fat percentage stagnation factor. For logarithmic terms, balance the weight distribution and avoid over-sensitivity of exponential terms;

[0076] Nonlinear weight adjustment can amplify the impact of the cumulative proportion of body fat percentage approaching zero on metabolic problems, and the generated body fat percentage stagnation factor can better reflect the severity of the patient's decreased metabolic efficiency.

[0077] It can be seen from the body fat percentage stagnation factor that within the selected fixed time window, the larger the performance value of the body fat percentage stagnation factor generated by the feature analysis of the extracted cumulative proportion of time periods when the body fat percentage changes tend to zero, the higher the cumulative proportion of time periods when the patient's body fat percentage changes tend to zero, which means that the patient's fat metabolism efficiency is significantly reduced. Fat consumption stagnation is a typical signal of a hidden decrease in basal metabolic rate (BMR). Therefore, the larger the body fat percentage stagnation factor, the higher the risk of a hidden decrease in the basal metabolic rate. On the contrary, a smaller body fat percentage stagnation factor indicates that the body fat percentage changes are relatively active, the fat metabolism is relatively normal, and the risk of a hidden decrease in the basal metabolic rate is low. The body fat percentage stagnation factor can intuitively quantify the severity of the patient's metabolic problems, providing an important reference for early intervention and personalized management.

[0078] The visceral fat ratio fluctuation factor and body fat percentage stagnation factor, which are quantified based on the fluctuation degree of visceral fat ratio between multiple monitoring time points and the cumulative ratio of the time period when the body fat percentage changes approach zero, are input into the pre-trained support vector machine model. The decline risk assessment index is generated by the support vector machine model, and the implicit decline in the patient's basal metabolic rate is predicted based on the decline risk assessment index.

[0079] The pre-trained Support Vector Machine (SVM) model is a mathematical model optimized and trained by a specific algorithm based on historical data, and is used for classification or regression tasks. In this scenario, the goal of the SVM model is to learn the complex nonlinear relationship between the two key features, the visceral fat ratio fluctuation factor and the body fat percentage stagnation factor, and the risk of a hidden decrease in basal metabolic rate. The training process requires a historical dataset containing a large amount of patient data. The dataset needs to contain the feature inputs of each patient (visceral fat ratio fluctuation factor and body fat percentage stagnation factor) and the corresponding label outputs (whether there is a risk of a hidden decrease in basal metabolic rate and its severity). Through training, the SVM model can find an optimal hyperplane or decision boundary to maximize the correctness of the classification results or the accuracy of the prediction results.

[0080] Specifically, the SVM model maps the input low-dimensional features to a high-dimensional space through kernel functions (such as Gaussian kernels and RBF kernels) to capture the complex interaction between visceral fat ratio fluctuations and body fat percentage stagnation. This mapping allows the model to find an optimal hyperplane in high-dimensional space that classifies patients with different risks of latent metabolic rate decline. For example, the model may find through learning that high visceral fat ratio fluctuations and high body fat percentage stagnation often correspond to a higher risk of latent metabolic rate decline. After training is completed, the model can directly make rapid predictions on newly input data (visceral fat ratio fluctuation factors and body fat percentage stagnation factors) to generate a decline risk assessment index.

[0081] The pre-trained SVM model can achieve efficient and accurate risk prediction, and does not need to be trained from scratch when applied. During the evaluation phase, the trained model only needs to input new patient data to quickly generate a decline risk assessment index, thereby predicting the possibility of hidden decline in basal metabolic rate and its risk level. This pre-training process ensures the model's understanding of complex nonlinear relationships and reduces the computational burden during real-time prediction. The kernel method of the support vector machine gives it a significant advantage in processing small sample data or low feature dimensions. In this scenario, there are only two input features (visceral fat ratio fluctuation factor and body fat percentage stagnation factor), so the SVM can obtain higher generalization ability with less data training.

[0082] In addition, the pre-training process requires standardization of input features to ensure the scale consistency of the two indexes during model training and application, and to avoid affecting the learning effect of the decision boundary due to differences in the range of characteristic values. The pre-trained model can also optimize hyperparameters (such as penalty coefficients and kernel parameters) through cross-validation and other techniques to improve the model's predictive accuracy and robustness. Ultimately, the pre-trained SVM model can not only accurately generate a decline risk assessment index, but also provide a quantitative assessment of the patient's implicit decline in basal metabolic rate through the risk index, providing a scientific basis for clinical intervention and personalized management.

[0083] The support vector machine model is not specifically limited here, and can realize the visceral fat ratio fluctuation factor and body fat percentage stagnation factor Conduct comprehensive analysis to generate a decline risk assessment index The support vector machine model can be used. In order to realize the technical solution of the present invention, the present invention provides a specific implementation method; reducing the risk assessment index The resulting calculation formula is: , where , Visceral fat ratio fluctuation factor and body fat percentage stagnation factor The weight factor of , The weight factor is a numerical coefficient used in the calculation formula to measure the contribution of different indicators to the final result. and They respectively represent the relative importance of the visceral fat ratio fluctuation factor and the body fat percentage stagnation factor to the decline risk assessment index. These weight factors reflect the different degrees of influence of the two indicators on the risk of hidden decline in the patient's basal metabolic rate by setting different numerical values. The value of the weight factor is usually based on historical data analysis or expert experience to ensure that the model can more accurately and comprehensively evaluate the role of the two indicators. Among them, and The values ​​of are greater than zero, and and The specific proportion of the indicators determines which indicator has a greater impact on the final result. This setting can flexibly adjust the sensitivity of the model to meet the risk assessment needs in different scenarios.

[0084] It can be seen from the decline risk assessment index that, within the selected fixed time window, the greater the performance value of the visceral fat ratio fluctuation factor generated by characteristic analysis of the fluctuation degree of the extracted visceral fat ratio between multiple monitoring time points, the greater the performance value of the body fat rate stagnation factor generated by characteristic analysis of the cumulative proportion of the time period in which the extracted body fat rate change tends to zero, that is, the greater the performance value of the decline risk assessment index generated when predicting the implicit decline in the patient's basal metabolic rate through a pre-trained support vector machine model within the fixed time window, the higher the risk of the patient's implicit decline in basal metabolic rate, and vice versa.

[0085] Based on the prediction results of the support vector machine model, it can intelligently identify whether the patient has a potential hidden decrease in basal metabolic rate, and preliminarily classify the patient's overall metabolic status as "normal" or "potential risk";

[0086] The decline risk assessment index generated by predicting the latent decline in the patient's basal metabolic rate through the pre-trained support vector machine model within a fixed time window is compared and analyzed with the pre-set decline risk assessment index reference threshold to preliminarily classify the patient's overall metabolic status. The specific classification steps are as follows:

[0087] If the decline risk assessment index is greater than the decline risk assessment index reference threshold, the patient's overall metabolic status is preliminarily classified as "potential risk", indicating that the patient has a potential hidden decline in basal metabolic rate;

[0088] If the downward risk assessment index is less than or equal to the downward risk assessment index reference threshold, the patient's overall metabolic condition is preliminarily classified as "normal", indicating that the patient's basal metabolic rate is normal.

[0089] The intelligent recognition function can convert the prediction results into intuitive risk signals, making it easier for medical staff or patients to quickly understand the existence and possibility of metabolic problems and provide guidance for the next step of action.

[0090] When a patient is identified to have a potential recessive decrease in basal metabolic rate, the patient is continuously monitored, and the metabolic rate change results predicted by the support vector machine model are obtained within several selected fixed time windows to form a dynamically changing data sequence. The clustering algorithm is used to conduct a comprehensive analysis of the metabolic rate prediction results within several fixed time windows, and the patient's potential recessive decrease in basal metabolic rate is further divided into three types: continuous type, short-term recovery type, and continuous change type, revealing its change pattern;

[0091] The clustering algorithm is used to comprehensively analyze the metabolic rate prediction results within several fixed time windows, and the potential basal metabolic rate recessive decrease of patients is further divided. The specific steps are as follows:

[0092] When it is identified that the patient has a potential for latent decrease in basal metabolic rate, the patient's decline risk assessment index is generated by the support vector machine model in several subsequent selected fixed time windows. The generated decline risk assessment index is arranged in chronological order to form a dynamically changing data sequence. The expression of the dynamically changing data sequence is: ,in, It is a dynamically changing data series, including the timestamp of each fixed time window and the corresponding decline risk assessment index. is the timestamp of the nth fixed time window, is the decline risk assessment index of the nth fixed time window, reflecting the risk level of hidden decline in metabolic rate during this time period, and m is the number of selected fixed time windows;

[0093] The construction of dynamically changing data series captures the changing trend of the patient's decline risk assessment index over time, providing a basis for subsequent feature extraction and cluster analysis, while improving the analysis quality of the data by eliminating outliers.

[0094] Feature extraction is performed on the dynamic data sequence, and the dynamic features of the downside risk assessment index in each fixed time window are calculated. The rate of change of the downside risk assessment index, the fluctuation range of the downside risk assessment index, and the cumulative change of the downside risk assessment index are extracted. The calculation expression of the rate of change of the downside risk assessment index is: , the calculation expression of the fluctuation range of the downside risk assessment index is: , the calculation expression of the cumulative change of the decline risk assessment index is: ,in, is the rate of change of the descent risk assessment index within a fixed time window, reflecting the speed at which the descent risk assessment index increases or decreases. To reduce the volatility of risk assessment index and quantify the stability of data, To reduce the cumulative change in the risk assessment index and assess the severity of the overall change, It is the mean of the downside risk assessment index in the dynamically changing data series, which is used to calculate the fluctuation range;

[0095] Feature extraction transforms data sequences into a multidimensional feature space, which can clearly reflect the changing trend, fluctuation and cumulative change of the decline risk assessment index, and lay a data foundation for cluster analysis.

[0096] The extracted characteristics of the rate of change of the downside risk assessment index, the fluctuation range of the downside risk assessment index, and the cumulative change of the downside risk assessment index are used to , the k-means clustering algorithm was used to perform pattern recognition on the patients’ dynamic data, and the patients’ potential basal metabolic rate recessive decrease was further divided into the following three types:

[0097] like , it indicates that the fluctuation of the decline risk assessment index is small and the cumulative change is low, indicating that the metabolic status is continuously at risk, and the patient's potential basal metabolic rate recessive decline is further divided into the persistent type;

[0098] like , it indicates that the decline risk assessment index has significantly decreased within some fixed time windows, and the metabolic status has temporarily improved, and the patient's potential basal metabolic rate recessive decline is further divided into the transient recovery type;

[0099] like , it indicates that the decline risk assessment index fluctuates greatly and the cumulative change is high, and the metabolic status has unstable and continuous changes, so the patient's potential basal metabolic rate recessive decline is further divided into the continuous change type;

[0100] in, It is the reference threshold of fluctuation amplitude, which is preset to judge the stability of data. It is the reference threshold of the cumulative change, which is preset to evaluate the severity of data changes.

[0101] Through the clustering algorithm, multi-dimensional features are comprehensively analyzed to accurately identify the patterns of metabolic changes in patients, providing a scientific basis for further intervention and management.

[0102] Continuous monitoring ensures that the development trend of metabolic problems is captured, providing complete dynamic data for the next comprehensive analysis to avoid misjudgment due to single time point data. Cluster analysis can classify complex metabolic problems into clear types through data aggregation and pattern recognition, making it easier to develop targeted intervention measures and avoid one-size-fits-all solutions.

[0103] According to the results of cluster analysis, take targeted response measures for different types of hidden decline;

[0104] It is crucial to take personalized intervention measures for different types of hidden decreases in basal metabolic rate to ensure that the intervention plan can accurately match the patient's specific metabolic condition, maximize the management effect, prevent further aggravation of metabolic disorders, and optimize the patient's long-term body fat percentage and overall metabolic health.

[0105] 1. Measures to deal with persistent problems:

[0106] For patients with persistent metabolic decline, intervention strategies to enhance metabolism are given priority. This includes adjusting the diet structure and increasing the intake of high-protein, low-calorie foods to promote muscle maintenance and fat metabolism. At the same time, develop an exercise plan suitable for the patient's physical condition, especially one that includes high-intensity interval training (HIIT) or a combination of aerobic and resistance training to enhance the basal metabolic rate. In addition, nutritional supplements (such as L-carnitine or conjugated linoleic acid) can also be combined to assist in improving fat burning and energy metabolism.

[0107] 2. Measures to deal with short-term recovery problems:

[0108] For patients whose metabolic status shows a transient recovery, the focus of intervention is to consolidate the recovery effect and prevent metabolic regression. Close attention should be paid to nutritional support during the recovery period, such as supplementation of trace elements such as vitamin D, magnesium, and iron, as well as antioxidants that promote recovery (such as vitamin E or coenzyme Q10). In addition, metabolic activity can be maintained by periodically adjusting the patient's dietary calorie intake (such as using carbohydrate cycling), while moderate exercise advice can be given to stabilize metabolic efficiency.

[0109] 3. Solutions to continuously changing problems:

[0110] For patients with a continuous and changing metabolic decline, the monitoring frequency should be increased and a dynamic adjustment plan should be developed. This includes increasing the density of monitoring windows, recording changes in key indicators such as the patient's body fat percentage and visceral fat percentage in real time, and identifying potential risk peaks. At the same time, dynamically adjust diet and exercise intervention plans, such as combining personalized dietary nutrition assessments and real-time heart rate monitoring to adjust exercise intensity. In addition, behavioral interventions (such as stress management or sleep optimization) can be combined to reduce the impact of external factors on metabolic fluctuations.

[0111] By implementing personalized intervention measures for different types of patients, we can not only accurately solve current metabolic problems, but also effectively prevent potential metabolic disorders and improve the effects of long-term body fat percentage and metabolic health management. This program reflects the comprehensiveness and accuracy of metabolic management through scientific classification and targeted intervention, providing patients with the best health support.

[0112] The present invention uses intelligent monitoring technology to collect and dynamically track data such as the patient's body fat rate, body fat distribution, and visceral fat ratio in real time, forming a systematic body fat rate data set, and predicting the patient's potential hidden decrease in basal metabolic rate through a support vector machine model. At the same time, combined with a clustering algorithm, the metabolic change pattern within a number of time windows is deeply analyzed, and the patient's metabolic problems are subdivided into three types: continuous, short-term recovery, and continuous change. This provides a scientific basis for personalized intervention measures, effectively making up for the deficiencies of existing technologies in dynamic monitoring of hidden decreases in basal metabolic rate, risk classification, and intervention optimization, and can significantly improve the accuracy and efficiency of metabolic management, reduce the risk of obesity-related diseases, and thus comprehensively optimize the patient's body fat rate and metabolic health management effects.

[0113] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0114] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

[0115] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for evaluating and managing body fat percentage (BMI) and the effect of Zhanwei capsule based on intelligent monitoring, characterized in that: The following steps are involved: Intelligent monitoring technology is used to track the changes in body fat percentage of patients after using the Zhanwei Capsule in real time, dynamically record and continuously update relevant data, and build a comprehensive and systematic body fat percentage data set to provide accurate data support for subsequent analysis and management; The collected patient body fat percentage information is constructed into an analysis set, from which the key data of abnormal changes in body fat percentage related to the implicit decrease in basal metabolic rate are extracted. Within the selected fixed time window, the extracted key data are feature analyzed to generate quantitative evaluation indicators, and the implicit decrease in the patient's basal metabolic rate is preliminarily quantified; The quantified evaluation index is input into the pre-trained support vector machine model, and the model is used to predict the hidden decrease in the patient's basal metabolic rate; Based on the prediction results of the support vector machine model, it can intelligently identify whether the patient has a potential hidden decrease in basal metabolic rate, and preliminarily classify the patient's overall metabolic status as "normal" or "potential risk"; When a patient is identified to have a potential recessive decrease in basal metabolic rate, the patient is continuously monitored, and the metabolic rate change results predicted by the support vector machine model are obtained within several selected fixed time windows to form a dynamically changing data sequence. The clustering algorithm is used to conduct a comprehensive analysis of the metabolic rate prediction results within several fixed time windows, and the patient's potential recessive decrease in basal metabolic rate is further divided into three types: continuous type, short-term recovery type, and continuous change type, revealing its change pattern; According to the results of cluster analysis, take targeted response measures for different types of hidden decline; Extract key data of abnormal changes in body fat percentage related to the implicit decrease in basal metabolic rate, where the extracted key data include the fluctuation degree of visceral fat ratio between multiple monitoring time points and the cumulative proportion of time periods when the body fat percentage change tends to zero. Within the selected fixed time window, perform feature analysis on the fluctuation degree of the extracted visceral fat ratio between multiple monitoring time points and the cumulative proportion of time periods when the body fat percentage change tends to zero, and generate visceral fat ratio fluctuation factors and body fat percentage stagnation factors respectively. Preliminarily quantify the implicit decrease in the patient's basal metabolic rate through the quantified visceral fat ratio fluctuation factor and body fat percentage stagnation factor evaluation indicators; The fluctuation degree of visceral fat ratio between multiple monitoring time points and the cumulative ratio of the time period when the body fat percentage change tends to zero are quantified, and the visceral fat ratio fluctuation factor and the body fat percentage stagnation factor are input into the pre-trained support vector machine model. The support vector machine model is used to generate a decline risk assessment index, and the implicit decline of the patient's basal metabolic rate is predicted based on the decline risk assessment index. The clustering algorithm is used to comprehensively analyze the metabolic rate prediction results within several fixed time windows, and the potential basal metabolic rate recessive decrease of patients is further divided. The specific steps are as follows: When it is identified that the patient has a potential for latent decrease in basal metabolic rate, the patient's decline risk assessment index is generated by the support vector machine model in several subsequent selected fixed time windows. The generated decline risk assessment index is arranged in chronological order to form a dynamically changing data sequence. The expression of the dynamically changing data sequence is: ,in, It is a dynamically changing data series, including the timestamp of each fixed time window and the corresponding decline risk assessment index. is the timestamp of the nth fixed time window, is the decline risk assessment index of the nth fixed time window, reflecting the risk level of hidden decline in metabolic rate during this time period, and m is the number of selected fixed time windows; Feature extraction is performed on the dynamic data sequence, and the dynamic features of the downside risk assessment index in each fixed time window are calculated. The rate of change of the downside risk assessment index, the fluctuation range of the downside risk assessment index, and the cumulative change of the downside risk assessment index are extracted. The calculation expression of the rate of change of the downside risk assessment index is: , the calculation expression of the fluctuation range of the downside risk assessment index is: , the calculation expression of the cumulative change of the decline risk assessment index is: ,in, is the rate of change of the descent risk assessment index within a fixed time window, reflecting the speed at which the descent risk assessment index increases or decreases. To reduce the volatility of risk assessment index and quantify the stability of data, To reduce the cumulative change in the risk assessment index and assess the severity of the overall change, It is the mean of the downside risk assessment index in the dynamically changing data series, which is used to calculate the fluctuation range; The extracted characteristics of the rate of change of the downside risk assessment index, the fluctuation range of the downside risk assessment index, and the cumulative change of the downside risk assessment index are used to , the k-means clustering algorithm was used to perform pattern recognition on the patients’ dynamic data, and the patients’ potential basal metabolic rate recessive decrease was further divided into the following three types: like , then the patient's potential basal metabolic rate recessive decrease is further divided into persistent type; like , then the patient's potential basal metabolic rate recessive decline is further divided into short-term recovery type; like , then the patient's potential basal metabolic rate recessive decline is further divided into continuous change type; in, It is the reference threshold of fluctuation amplitude, which is preset to judge the stability of data. It is the reference threshold of the cumulative change, which is preset to evaluate the severity of data changes.

2. A method for evaluating and managing body fat percentage (BMI) and the effect of Zhanwei capsule based on intelligent monitoring according to claim 1, characterized in that: The patient's body fat percentage after using the Zhanwei Capsule is tracked in real time through intelligent monitoring technology. The specific steps are as follows: Wear or use smart monitoring devices to record the patient's physiological data in real time and transmit the collected data to a central database or patient management platform via wireless technology; The collected data is input into the system for preprocessing, including denoising, outlier removal and unit unification, to improve data quality; Generate a dynamic trend chart of body fat percentage based on the patient's historical data and real-time data collection, and visualize the change pattern, making it convenient for patients and medical staff to view at any time; When the body fat percentage is detected to exceed the preset body fat percentage threshold, an alarm is triggered and a personalized reminder is sent to the patient or medical staff.

3. The method for evaluating and managing body fat percentage (BMI) and the effect of Zhanwei capsule based on intelligent monitoring according to claim 1, characterized in that: The decline risk assessment index generated by predicting the latent decline in the patient's basal metabolic rate through the pre-trained support vector machine model within a fixed time window is compared and analyzed with the pre-set decline risk assessment index reference threshold to preliminarily classify the patient's overall metabolic status. The specific classification steps are as follows: If the decline risk assessment index is greater than the decline risk assessment index reference threshold, the patient's overall metabolic status is preliminarily classified as "potential risk"; If the downside risk assessment index is less than or equal to the downside risk assessment index reference threshold, the patient's overall metabolic status is preliminarily classified as "normal".

4. The method for evaluating and managing body fat percentage (BMI) and the effect of Zhanwei capsule based on intelligent monitoring according to claim 1, characterized in that: The specific steps of generating the visceral fat ratio fluctuation factor by characteristic analysis of the fluctuation degree of the extracted visceral fat ratio between multiple monitoring time points within the selected fixed time window are as follows: In the selected fixed time window, the values ​​of the visceral fat ratio at each time point are collected, the change gradient between adjacent time points is calculated, and the change gradient is accumulated to calculate the total change gradient of the visceral fat ratio in the fixed time window. The calculation formula for the total change gradient of the visceral fat ratio is: ,in: is the total change gradient of visceral fat ratio, is the visceral fat ratio at time point i, For time point The visceral fat ratio is the time interval between adjacent time points, is the weight coefficient, which indicates the influence of the change of time point i on the overall gradient, and N is the total number of monitoring time points in the fixed time window; In the same fixed time window, the fluctuation range of visceral fat changes was calculated, and the square sum of the change range was used to measure the significance of the fluctuation. The calculation expression of the fluctuation range of visceral fat changes was: ,in: is the fluctuation range of visceral fat, , are the maximum and minimum values ​​of the visceral fat ratio within a fixed time window, is the priority coefficient of time point i, indicating the importance of fluctuation at that time point; The visceral fat ratio fluctuation factor is generated by combining the total change gradient of the visceral fat ratio and the fluctuation amplitude of the visceral fat ratio. The significance of the fluctuation characteristics is amplified in the form of an exponential. The generation expression of the visceral fat ratio fluctuation factor is: ,in: is the visceral fat ratio fluctuation factor, It is a nonlinear adjustment factor that amplifies or smoothes the overall impact of fluctuations. is the sensitivity adjustment coefficient, which controls the comprehensive weight of fluctuation and gradient in a fixed time window. K is the window length influencing factor, which is defined as the total number of monitoring time points N and the time interval in a fixed time window. The product of, that is: .

5. The method for evaluating and managing body fat percentage (BMI) and the effect of Zhanwei capsule based on intelligent monitoring according to claim 1, characterized in that: The specific steps for generating the body fat percentage stagnation factor by feature analysis of the extracted cumulative proportion of the time period when the body fat percentage change tends to zero within the selected fixed time window are as follows: In the selected fixed time window, the time period when the body fat percentage changes tend to zero is screened out, and the cumulative proportion of the time period when the body fat percentage changes tend to zero is calculated by the following formula: ,in: is the cumulative proportion of the time period when the body fat percentage changes towards zero, is the rate of change of body fat percentage, is the set of time periods when the rate of change of body fat percentage tends to zero, that is, time period, is the preset body fat percentage change rate threshold, which is used to define the condition for the body fat percentage change to approach zero. F is the body fat percentage value, and W is the selected fixed time window. It is a very small positive number to prevent the denominator from being zero; The cumulative proportion of the time period when the body fat percentage changes to zero Perform nonlinear weight adjustment to generate the body fat percentage stagnation factor. The expression of the body fat percentage stagnation factor generated by nonlinear weight adjustment is: ,in: It is a body fat percentage stagnation factor, a preliminary indicator to quantify the hidden decrease in the patient's basal metabolic rate. and Adjustment coefficient, used to control the sensitivity and proportional distribution of nonlinear weights, is an exponential term, emphasizing the nonlinear effect of the cumulative ratio on the body fat percentage stagnation factor. For logarithmic terms, balance the weight distribution and avoid over-sensitivity of exponential terms.

Images