BMI intelligent management evaluation method for treatment effect and body fat rate of adjustable stomach capsule

Abstract

The invention discloses an adjustable stomach capsule treatment effect and body fat rate BMI intelligent management evaluation method, and relates to the technical field of stomach capsule treatment management, and the method comprises the following steps: setting an initial capacity adjustment amplitude and an initial capacity adjustment frequency of an adjustable stomach capsule according to basic health data of a patient; dynamic changes of gastric contents are monitored in real time through a built-in sensor of the gastric capsule, and monitoring data are sent to external equipment based on a wireless transmission technology. Through real-time data acquisition, feature quantitative analysis and intelligent prediction of a machine learning model, a sharp increment stage and a smooth increment stage can be distinguished in time, capacity adjustment amplitude and frequency are adaptively optimized through a fuzzy reasoning algorithm, a strategy of small-amplitude and high-frequency adjustment is adopted, and the capacity adjustment efficiency is improved. Not only is the discomfort of a patient possibly caused by sharp increase of stomach contents effectively relieved, but also the stability and individuation of the treatment process are ensured, and the safety, comfort and effect of treatment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of regulating gastric capsule treatment management, and in particular to an intelligent management and evaluation method for regulating gastric capsule treatment effect and body fat rate (BMI). Background Art

[0002] The evaluation of the therapeutic effect of the adjustable gastric capsule and the intelligent management of body fat percentage (BMI) is a comprehensive health management method based on modern medical technology. It uses intelligent devices to monitor and analyze the changes in the patient's body fat percentage (Body Fat Percentage) and body mass index (BMI) during the treatment with the adjustable gastric capsule, and evaluates the therapeutic effect and its impact on the patient's health.

[0003] The adjustable gastric capsule is a medical device used to treat obesity. It is placed in the stomach and its capacity can be adjusted as needed to help patients control their food intake and achieve their weight loss goals. The evaluation of treatment effects not only relies on traditional weight indicators, but also combines the intelligent management of body fat percentage and BMI (body mass index). Body fat percentage reflects the proportion of body fat, while BMI is a health indicator calculated based on height and weight. The intelligent management and evaluation system uses advanced sensing technology and data analysis to monitor the patient's body fat percentage and BMI changes in real time, and provide personalized feedback and adjustment suggestions. This comprehensive evaluation method can accurately track the patient's health status, dynamically optimize the adjustment strength and treatment plan of the gastric capsule, ensure the safety and effectiveness of the weight loss process, and ultimately help patients achieve their ideal weight and body composition ratio and improve their overall health level.

[0004] The prior art has the following deficiencies:

[0005] The adjustable gastric capsule adjustment method in the prior art usually adopts a staged fixed setting form, such as a fixed volume adjustment range and volume adjustment frequency. Its role is to set a stable volume within a specific time period according to the patient's treatment goals and adaptation conditions, so as to reduce the risks and discomfort caused by frequent adjustments and ensure the safety and effectiveness of treatment. However, when the patient accidentally overeats, the fixed gastric capsule cannot dynamically adjust the volume to adapt to the rapid increase in gastric contents, resulting in a sharp increase in intragastric pressure. The patient may experience symptoms such as extreme bloating, severe pain, nausea and vomiting. In severe cases, acute gastric dilation can compress surrounding organs, cause blood flow obstruction, and even cause gastric wall rupture (gastric perforation), which is life-threatening.

[0006] 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

[0007] The purpose of the present invention is to provide an intelligent management and evaluation method for the therapeutic effect of an adjustable gastric capsule and body fat rate (BMI). Through real-time data acquisition, feature quantification analysis and intelligent prediction of a machine learning model, it can timely distinguish the surge stage and the gentle increment stage, and adaptively optimize the capacity adjustment amplitude and frequency through a fuzzy reasoning algorithm. The strategy of small amplitude and high frequency adjustment is adopted, which not only effectively alleviates the discomfort that may occur to patients due to the surge in gastric contents, but also ensures the stability and personalization of the treatment process, improves the safety, comfort and effect of the treatment, and provides scientific and intelligent technical support for patient health management to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above-mentioned purpose, the present invention provides the following technical solution: a method for intelligent management and evaluation of adjustable gastric capsule treatment effect and body fat rate BMI, comprising the following steps:

[0009] According to the patient's basic health data, the initial volume adjustment range and initial volume adjustment frequency of the adjustable gastric capsule are set;

[0010] The built-in sensor of the gastric capsule monitors the dynamic changes of gastric contents in real time, and sends the monitoring data to external devices based on wireless transmission technology, providing comprehensive support for subsequent analysis;

[0011] The real-time acquired gastric content data is sorted and preprocessed to extract key features that can reflect the increase in gastric content. The extracted key features are put into the monitoring window for analysis and quantification, and the quantified indicators are used to reflect the increase in the patient's gastric content.

[0012] The quantified indicators are input as feature vectors into the pre-trained machine learning model to intelligently predict the incremental changes in gastric contents. Through model analysis, the future trend of gastric contents changes can be accurately predicted, and the rules and patterns of incremental changes can be identified in advance.

[0013] According to the prediction results of the machine learning model, the increase in gastric contents is divided into a surge phase and a gentle increase phase;

[0014] For the gastric content increment during the gentle increment phase, continue to maintain the set initial volume adjustment range and initial volume adjustment frequency to ensure the smooth progress of the treatment process;

[0015] During the surge phase, the volume adjustment amplitude and frequency of the gastric capsule are adaptively adjusted based on the fuzzy inference algorithm in combination with the prediction results of the machine learning model. Small amplitude and high frequency adjustments are used to gradually optimize the capacity and reduce the patient's discomfort.

[0016] Preferably, the initial capacity adjustment amplitude refers to the specific capacity value that is increased or decreased each time the capacity of the adjustable gastric capsule is adjusted;

[0017] The frequency of initial volume adjustment refers to the time interval for adjusting the gastric capsule volume in the initial stage of treatment, that is, how often the gastric capsule volume is adjusted.

[0018] Preferably, key features that can reflect the increase in gastric contents are extracted, wherein the extracted features include the relative growth rate of gastric contents volume expansion and the change rate of gastric acid secretion. The extracted relative growth rate of gastric contents volume expansion and the change rate of gastric acid secretion are put into a monitoring window for analysis and quantification, and a gastric volume expansion reference value and a gastric acid secretion response reference value are generated respectively. The quantified gastric volume expansion reference value and gastric acid secretion response reference value reflect the patient's gastric contents increase.

[0019] Preferably, the relative growth rate of the expansion of the gastric content volume and the rate of change of the gastric acid secretion are analyzed and quantified to generate a gastric volume expansion reference value and a gastric acid secretion response reference value as feature vectors, which are input into a pre-trained machine learning model. The content increment index is generated by the machine learning model, and the incremental change of the gastric content is intelligently predicted based on the content increment index, so as to accurately predict the future trend of the change of the gastric content and identify the law and pattern of the incremental change in advance.

[0020] Preferably, the content increment index generated when the incremental change of the gastric contents is intelligently predicted by the pre-trained machine learning model is compared and analyzed with a preset content increment index reference threshold, and the incremental situation of the gastric contents is divided. The specific division steps are as follows:

[0021] If the content increment index is greater than the content increment index reference threshold, the increment of gastric contents is classified as a surge stage;

[0022] If the content increment index is less than or equal to the content increment index reference threshold, the increment of the gastric contents is classified as a gentle increment stage.

[0023] Preferably, the specific steps of putting the extracted relative growth rate of the expansion of the gastric content volume into the monitoring window for analysis and quantification to generate a reference value of the gastric volume expansion are as follows:

[0024] The relative growth rate change data of gastric content volume expansion were extracted, and the relative growth rate of volume expansion was defined as the rate of change of the current volume relative to the volume at the previous moment. Normalization was performed to eliminate the influence of individual differences on the results. The calculation expression of the relative growth rate of volume expansion was: ,in: is the relative growth rate of volume expansion, is the current measured volume of gastric contents, is the volume of gastric contents measured last time, is the patient's individual baseline volume, is a small constant used to avoid the denominator being zero;

[0025] The extracted relative growth rate data is placed in the monitoring window, and the contribution of the growth rate change to the intragastric pressure is accumulated to calculate the cumulative value of volume expansion and quantify the cumulative effect of the growth rate. The calculation expression of the cumulative value of volume expansion is: ,in, is the cumulative value of volume expansion, reflecting the cumulative effect of the change in growth rate on the gastric environment, W is the time span of the monitoring window, is the nonlinear amplification term of the volume expansion acceleration, is a nonlinear adjustment index used to enhance the weight of abnormal changes. is the patient's response coefficient, reflecting the sensitivity of individual stomach wall elasticity to changes in expansion;

[0026] Based on the cumulative value of volume expansion, combined with the individual characteristic parameters of the patient, the reference value of intragastric volume expansion is generated to quantify and reflect the increment of gastric contents. The expression for generating the reference value of intragastric volume expansion is: ,in, Expanded reference value for gastric volume, is the gastric content characteristic coefficient, which indicates the influence weight of the patient's gastric content type. is the patient's maximum stomach volume, is an exponential adjustment factor that controls the nonlinear effect of the maximum volume on volume expansion. It is a natural logarithmic function, which is used to compress the intragastric volume, expand the growth range of the reference value, and prevent data imbalance.

[0027] Preferably, the specific steps of putting the extracted gastric acid secretion rate of change into the monitoring window for analysis and quantification to generate a gastric acid secretion response reference value are as follows:

[0028] Calculate the rate of change of gastric acid secretion. The rate of change of gastric acid secretion is a basic parameter that reflects the dynamic changes of gastric contents. It is used to capture the degree of stimulation of gastric contents on gastric acid gland secretion. The calculation expression is: ,in, It is the total amount of gastric acid secreted in the stomach at a certain moment, indicating the total amount of acid secreted by the gastric glands. is the rate of change of gastric acid secretion, describing the changing trend of gastric acid secretion per unit time. is the sampling time interval, which is used to calculate the rate of change between two consecutive data points;

[0029] In order to enhance the nonlinear response to the rate of change of gastric acid, a dynamic weight is introduced to amplify the effect of gastric acid change by combining power function and exponential function. The generation expression of dynamic weight is: ,in, is a dynamic weight, which is used to adjust the sensitivity in subsequent calculations. k is a weight adjustment factor, which is used to control the growth rate. is the absolute value of the rate of change of gastric acid secretion, ensuring that both positive and negative changes are included in the calculation. is the nonlinear sensitivity coefficient, which is used to further adjust the response of the weight to the rate of change of gastric acid;

[0030] The dynamic weight, gastric acid secretion rate of change and basal secretion are combined to generate a comprehensive gastric acid secretion response reference value. The generation expression of the gastric acid secretion response reference value is: ,in, It is a reference value for gastric acid secretion response, used to quantify the response of gastric acid secretion changes to the increase in gastric contents. is the weight amplification factor, further enhancing the impact of dynamic weights in drastic changes. It is the initial baseline value of gastric acid secretion, which represents the patient's basal secretion without stimulation and is used to correct individual differences.

[0031] Preferably, for the surge stage, the volume adjustment amplitude and volume adjustment frequency of the gastric capsule are adaptively adjusted based on the fuzzy inference algorithm in combination with the prediction results of the machine learning model. The specific steps are as follows:

[0032] The content increment surge deviation is calculated by the incremental deviation between the content increment index and the content increment index reference threshold, which accurately reflects the patient's current gastric content increment change. The calculation expression of the content increment surge deviation is: ,in, is the currently calculated content increment index, which comprehensively reflects the dynamic changes of gastric content increment. is the reference threshold of the content increment index, indicating the boundary between the steady stage and the surge stage. The deviation of the increase in content is increased sharply;

[0033] Through the fuzzy inference algorithm, a nonlinear mapping is established between the output of the content increment surge deviation and the capacity adjustment amplitude, and the established expression is: ,in, The capacity adjustment reference value generated by fuzzy reasoning, , , are the membership functions, which respectively indicate that the deviation of the increase in content belongs to the low, medium and high degree of increase. , , is the capacity adjustment range corresponding to the fuzzy rules, which are adapted to the demands of low, medium and high surge levels respectively;

[0034] Combining the fuzzy reasoning results and the deviation of the increase in content, the capacity adjustment range and capacity adjustment frequency are dynamically adjusted. The adjustment expression is: ,in, The final capacity adjustment range is proposed based on the initial range and fuzzy rules. is the initial volume adjustment range, which is the basic value set at the beginning of treatment. is the sensitivity factor, which is used to adjust the weight of the fuzzy rule on the capacity amplitude. The final capacity adjustment frequency is dynamically adjusted according to the surge degree, reflecting the real-time adaptability of the capacity adjustment frequency to the changing needs of gastric contents. The frequency of initial volume adjustment is the basic value set at the beginning of treatment. is the frequency modulation gain factor, which is used to enhance the sensitivity of frequency adjustment to surge response.

[0035] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0036] The present invention can timely distinguish the surge stage and the gentle increment stage through real-time data collection, feature quantification analysis and intelligent prediction of machine learning models, and adaptively optimize the capacity adjustment amplitude and frequency through fuzzy reasoning algorithm. It adopts a strategy of small amplitude and high frequency adjustment, which not only effectively alleviates the discomfort that may occur to patients due to the surge of gastric contents, but also ensures the stability and personalization of the treatment process, improves the safety, comfort and effectiveness of the treatment, and provides scientific and intelligent technical support for patient health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] 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.

[0038] Figure 1 The present invention is a method flow chart of a method for adjusting the treatment effect of a gastric capsule and the body fat rate BMI intelligent management evaluation method. DETAILED DESCRIPTION

[0039] 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.

[0040] The present invention provides Figure 1The method for evaluating the therapeutic effect of an adjustable gastric capsule and the body fat rate (BMI) intelligent management includes the following steps:

[0041] According to the patient's basic health data (such as weight, height, gastric capacity tolerance, eating habits, etc.), set the initial capacity adjustment range and initial capacity adjustment frequency of the adjustable gastric capsule;

[0042] For example, the initial volume adjustment amplitude can be set to increase or decrease by 10 ml each time, and the initial volume adjustment frequency can be once or twice a day. These initial parameters are usually determined by the doctor in combination with the patient's treatment goals and current gastric function status to ensure that the device adapts to the patient's basic needs.

[0043] The initial volume adjustment range refers to the specific volume value that is increased or decreased each time the volume of the adjustable gastric capsule is adjusted. For example, the doctor can set each adjustment of the gastric capsule volume to increase or decrease by 10 ml, 15 ml or other suitable values ​​according to the patient's gastric capacity tolerance and treatment goals. The setting of this range needs to take into account the patient's physical condition, including gastric tolerance, dietary behavior, and the progress of the weight loss treatment plan. Reasonable setting of the volume adjustment range can ensure that the patient adapts to the gastric capsule in the early stage of treatment, while avoiding discomfort or insufficient treatment effect caused by excessive or small adjustment range.

[0044] In actual application, the size of the adjustment range directly affects the patient's sense of fullness and the effect of food intake control. Too large an adjustment range may cause a sharp change in gastric pressure, increasing the risk of gastric discomfort in patients; too small an adjustment range may prolong the treatment cycle and reduce treatment efficiency. By setting the initial capacity adjustment range scientifically and reasonably, patients can gradually adapt to the existence and function of the gastric capsule.

[0045] The initial capacity adjustment frequency refers to the time interval for adjusting the gastric capsule capacity in the early stage of treatment, that is, how often the gastric capsule capacity is adjusted. For example, the doctor can set the adjustment once or twice a day according to the patient's treatment goals and gastric condition to ensure that the capacity of the gastric capsule is consistent with the dynamic changes of the patient's gastric contents. The setting of the adjustment frequency requires a balance between the treatment effect and the patient's comfort. Too frequent adjustments may increase discomfort, while too few adjustments may not effectively limit food intake. The reasonable setting of the initial capacity adjustment frequency is particularly important for the initial adaptation stage of treatment. Through a relatively stable adjustment frequency, patients can gradually adapt to the changes in the capacity of the gastric capsule and establish a balance with the treatment equipment.

[0046] The built-in sensor of the gastric capsule monitors the dynamic changes of gastric contents in real time, and sends the monitoring data to external devices (such as smart terminals or medical servers) based on wireless transmission technology, providing comprehensive support for subsequent analysis;

[0047] The dynamic changes of gastric contents can be monitored in real time through the built-in sensors of the gastric capsule. A variety of sensing technologies can be used to work together to obtain comprehensive intragastric data. First, the pressure sensor is a core technology commonly used in gastric capsules. It can sense the pressure changes in the stomach in real time and reflect the increase or decrease in the volume of gastric contents. For example, the volume of gastric contents increases after eating, resulting in increased intragastric pressure. The sensor can record this dynamic process and provide direct data support for evaluating the intragastric environment. Secondly, volume sensors or fluid sensors can directly evaluate the volume of the contents by detecting the occupancy rate of the intragastric space. Through these sensors, the gastric capsule can capture subtle changes, especially volume changes caused by highly expansive foods.

[0048] In addition, chemical sensors can monitor the pH value and composition changes of gastric juice, which is important for determining the type of gastric contents (such as solid, liquid or gas). Different foods will cause different changes in gastric juice secretion levels and pH. By obtaining these data through chemical sensors, the properties of the food and the state of the digestion process can be further inferred. Accelerometers and motion sensors can also be built into the gastric capsule to monitor the mechanical movement of the stomach, such as peristaltic strength and frequency. This information can indirectly infer the physical properties and emptying rate of the contents.

[0049] The above are just some examples of real-time monitoring of dynamic changes in gastric contents, and are not exhaustive. Since these are all existing technologies, they will not be described in detail here.

[0050] In order to convert the data collected by the sensor into meaningful information, the wireless transmission module transmits the monitoring data to external devices (such as smartphones or medical cloud platforms) in real time. After being processed by intelligent algorithms, these data can generate a dynamic curve of changes in gastric contents, providing real-time feedback and guidance for patients' treatment. With these technologies working together, the gastric capsule can comprehensively and dynamically monitor the status of gastric contents, thereby optimizing treatment plans and improving patient safety and comfort.

[0051] The real-time acquired gastric content data is sorted and preprocessed to extract key features that can reflect the increase in gastric content. The extracted key features are put into a monitoring window (such as 5 minutes, 30 minutes or 1 hour) for analysis and quantification. The quantified indicators reflect the patient's gastric content increase.

[0052] The collation and preprocessing of the real-time gastric content data mainly include denoising, outlier detection and elimination, data format standardization, time series alignment, data interpolation and missing value filling. Denoising is used to filter out noise data caused by sensor errors or environmental interference; outlier detection eliminates abnormal data to ensure the accuracy of the analysis results; data format standardization unifies data in different units or formats for subsequent processing; time series alignment ensures the consistency of multidimensional data on the time axis; interpolation and filling solve the problem of missing data caused by sensor failure or transmission interruption. Through these collation and preprocessing steps, the quality and reliability of the data can be significantly improved, providing a stable and accurate data foundation for subsequent analysis and model prediction.

[0053] The key features that can reflect the increase in gastric contents are extracted, wherein the extracted features include the relative growth rate of gastric contents volume expansion and the change rate of gastric acid secretion. The extracted relative growth rate of gastric contents volume expansion and the change rate of gastric acid secretion are put into the monitoring window for analysis and quantification, and the reference value of gastric volume expansion and the reference value of gastric acid secretion response are generated respectively. The quantified reference value of gastric volume expansion and the reference value of gastric acid secretion response reflect the increase in gastric contents of the patient.

[0054] When the relative growth rate of the patient's gastric content volume expansion is large, it indicates that the patient's gastric content increment is large. This is because the volume expansion of gastric contents directly reflects the amount of food or liquid ingested and the effect of expansive foods. The relative growth rate of volume expansion indicates the rate at which the volume of gastric contents increases per unit time. If the rate is significantly higher than normal, it may indicate that the patient has ingested a large amount of food or expansive food (such as high-fiber or carbonated beverages). This situation is usually accompanied by an increase in intragastric pressure, which may cause the patient to have an increased sense of fullness, discomfort, or other digestive system reactions. Therefore, the relative growth rate of volume expansion is a key parameter for evaluating the increment of gastric contents, and can promptly reflect abnormal changes in the patient's diet.

[0055] The specific steps of putting the extracted relative growth rate of gastric content volume expansion into the monitoring window for analysis and quantification to generate a reference value of gastric volume expansion are as follows:

[0056] The relative growth rate change data of gastric content volume expansion were extracted, and the relative growth rate of volume expansion was defined as the rate of change of the current volume relative to the volume at the previous moment. Normalization was performed to eliminate the influence of individual differences on the results. The calculation expression of the relative growth rate of volume expansion was: ,in: is the relative growth rate of volume expansion, is the current measured volume of gastric contents, is the volume of gastric contents measured last time, is the patient's individual baseline volume, usually the volume of gastric contents at the initial state, is a small constant used to avoid the denominator being zero;

[0057] This step captures the dynamic changes of volume expansion, quantifies the incremental change trend between each measurement, and provides basic data for subsequent analysis.

[0058] The extracted relative growth rate data is placed in the monitoring window, and the contribution of the growth rate change to the intragastric pressure is accumulated to calculate the cumulative value of volume expansion and quantify the cumulative effect of the growth rate. The calculation expression of the cumulative value of volume expansion is: ,in, is the cumulative value of volume expansion, reflecting the cumulative effect of the change in growth rate on the gastric environment, W is the time span of the monitoring window, is the nonlinear amplification term of the volume expansion acceleration, is a nonlinear adjustment index used to enhance the weight of abnormal changes. is the patient-specific response factor, reflecting the sensitivity of individual gastric wall elasticity to changes in expansion;

[0059] This step captures the cumulative effect of growth rate over a time span, highlights the impact of significant changes on gastric status, and provides core data for generating the final index.

[0060] Based on the cumulative value of volume expansion, combined with the individual characteristic parameters of the patient, the reference value of intragastric volume expansion is generated to quantify and reflect the increment of gastric contents. The expression for generating the reference value of intragastric volume expansion is: ,in, Expanded reference value for gastric volume, is the gastric content characteristic coefficient, which indicates the influence weight of the patient's gastric content type (such as liquid, solid), is the patient's maximum stomach volume, is an exponential adjustment factor that controls the nonlinear effect of the maximum volume on volume expansion. It is a natural logarithmic function, which is used to compress the intragastric volume, expand the growth range of the reference value, and prevent data imbalance;

[0061] By generating the final volume expansion index, the dynamic characteristics of the increase in gastric contents are comprehensively reflected, the incremental risk under abnormal expansion conditions is clarified, and an accurate basis is provided for adjusting the strategy.

[0062] It can be seen from the reference value of intragastric volume expansion that the relative growth rate of the extracted gastric content volume expansion is put into the monitoring window for analysis and quantification. The larger the performance value of the reference value of intragastric volume expansion generated, the higher the patient's gastric content increment is, and vice versa. This is because the reference value of intragastric volume expansion combines multidimensional parameters such as the relative growth rate of gastric content volume expansion, time cumulative effect, and individual characteristics. Through nonlinear amplification and quantification processing, it can accurately reflect the incremental changes of gastric contents within a certain time window. Higher reference values ​​of intragastric volume expansion are usually caused by significant volume expansion growth rates and cumulative effects, such as rapid increase in gastric contents caused by ingesting a large amount of expansive food or eating quickly. Lower reference values ​​of intragastric volume expansion indicate that the changes in gastric contents are relatively stable or the increments are small, such as eating a small amount of food or normal emptying during digestion. Therefore, the reference value of intragastric volume expansion can be used as a core indicator for evaluating the incremental changes in patients' gastric contents.

[0063] When the patient's gastric acid secretion changes at a faster rate, it usually indicates a larger increase in gastric contents. This is because gastric acid secretion is directly driven by the stimulation of gastric contents. When gastric contents increase rapidly, especially when high-protein, high-fat or distending foods enter the stomach, the gastric acid glands will accelerate the secretion of gastric acid to promote digestion. This rapid change in gastric acid secretion is usually closely related to the volume, type and digestive needs of gastric contents, reflecting a significant increase in gastric contents. By monitoring the changes in gastric acid secretion rate in real time, the increase in gastric contents can be indirectly evaluated, providing a scientific basis for adjusting the capacity of the gastric capsule and avoiding discomfort or complications caused by excessive gastric contents.

[0064] The specific steps of putting the extracted gastric acid secretion rate into the monitoring window for analysis and quantification to generate a gastric acid secretion response reference value are as follows:

[0065] Calculate the rate of change of gastric acid secretion. The rate of change of gastric acid secretion is a basic parameter that reflects the dynamic changes of gastric contents. It is used to capture the degree of stimulation of gastric contents on gastric acid gland secretion. The calculation expression is: ,in, It is the total amount of gastric acid secreted in the stomach at a certain moment, indicating the total amount of acid secreted by the gastric glands. is the rate of change of gastric acid secretion, describing the changing trend of gastric acid secretion per unit time. is the sampling time interval, which is used to calculate the rate of change between two consecutive data points;

[0066] By calculating the rate of change of gastric acid secretion, the immediate response of gastric glands to changes in gastric contents can be quantified. Rapidly increasing gastric contents (such as high-protein, high-expanding foods) will significantly stimulate gastric acid secretion. The rate of change of high gastric acid secretion can accurately reflect the incremental dynamics of gastric contents and provide key input for subsequent analysis.

[0067] In order to enhance the nonlinear response to the rate of change of gastric acid, a dynamic weight is introduced to amplify the effect of gastric acid change by combining power function and exponential function. The generation expression of dynamic weight is: ,in, is a dynamic weight, which reflects the significance of the rate of change of gastric acid and is used to adjust the sensitivity in subsequent calculations. k is a weight adjustment factor, which is used to control the growth rate. A larger k will make the weight of a small change more significant. is the absolute value of the rate of change of gastric acid secretion, ensuring that both positive and negative changes are included in the calculation. is a nonlinear sensitivity coefficient, which is used to further adjust the response of the weight to the rate of change of gastric acid.

[0068] This step combines the change in gastric acid secretion rate with nonlinear amplification by generating dynamic weights, making the response to significant changes (such as a sharp increase in gastric acid secretion) more sensitive, thereby capturing the physiological significance of drastic changes. This nonlinear weight can effectively highlight the significant features of the surge phase of gastric contents.

[0069] The dynamic weight, gastric acid secretion rate of change and basal secretion are combined to generate a comprehensive gastric acid secretion response reference value. The generation expression of the gastric acid secretion response reference value is: ,in, It is a reference value for gastric acid secretion response, used to quantify the response of gastric acid secretion changes to the increase in gastric contents. is the weight amplification factor, further enhancing the impact of dynamic weights in drastic changes. The initial baseline value of gastric acid secretion, which indicates the patient's basal secretion without stimulation, is used to correct individual differences;

[0070] By combining dynamic weights, baseline secretion volume, and rate of change, the gastric acid secretion response reference value can comprehensively quantify the dynamic changes in gastric acid secretion and amplify the impact of significant changes. The combination of exponential and logarithmic functions not only ensures a stable response to small changes, but also highlights the physiological significance of drastic changes, forming an accurate and dynamic comprehensive indicator that directly reflects the incremental situation of the patient's gastric contents.

[0071] It can be seen from the gastric acid secretion response reference value that the larger the performance value of the gastric acid secretion response reference value generated by putting the extracted gastric acid secretion change rate into the monitoring window for analysis and quantification, the higher the patient's gastric content increment is usually, and vice versa. This is because the rate of change of gastric acid secretion is an important parameter reflecting the dynamic changes of gastric contents. When the gastric contents increase rapidly (such as high-protein or highly expansive food intake), it will stimulate the gastric glands to significantly increase gastric acid secretion, resulting in an accelerated rate of change, thereby obtaining a higher gastric acid secretion response reference value through exponential calculation. On the contrary, when the gastric contents change slowly or less, the rate of change of gastric acid secretion is low, and the gastric acid secretion response reference value also decreases accordingly. Therefore, the size of the gastric acid secretion response reference value can be used as an important quantitative indicator to measure the increment of gastric contents.

[0072] The quantified indicators are input as feature vectors into the pre-trained machine learning model to intelligently predict the incremental changes in gastric contents. Through model analysis, the future trend of gastric contents changes can be accurately predicted, and the rules and patterns of incremental changes can be identified in advance.

[0073] The relative growth rate of gastric content volume expansion and the rate of change of gastric acid secretion are analyzed and quantified to generate gastric volume expansion reference value and gastric acid secretion response reference value as feature vectors which are input into a pre-trained machine learning model. The content increment index is generated by the machine learning model, and the incremental change of gastric contents is intelligently predicted based on the content increment index. The future changing trend of gastric contents is accurately predicted, and the rules and patterns of incremental changes are identified in advance.

[0074] A pre-trained machine learning model refers to an algorithm model that has been learned, optimized, and verified through a large amount of historical data before it is officially applied. The core purpose of this model is to extract potential rules and patterns from the input feature vectors (such as reference values ​​for intragastric volume expansion and gastric acid secretion response), and then realize the intelligent prediction of incremental changes in gastric contents. During the training process, the model establishes a mapping relationship between input features and target outputs by processing labeled historical data (including the changing characteristics of gastric contents and the corresponding incremental change trends). For example, for gastric content data, the model can learn the correlation between the rate of change of gastric acid secretion and the growth rate of volume expansion and the surge or slowdown of gastric contents, as well as how to predict future dynamics based on these changes.

[0075] The training process usually includes data preprocessing, feature extraction, model building, hyperparameter optimization, and model evaluation. The data used may include the dynamic characteristics of gastric contents of different patients, the actual gastric content increments, and related environmental or behavioral factors (such as diet type, time interval, etc.). Through repeated iterations and verification, the model can continuously optimize the prediction ability, thereby achieving high-precision prediction in practical applications. Such a trained model can not only process multi-dimensional feature data, but also cope with complex nonlinear relationships, enabling it to accurately predict the changing trend of gastric contents and identify incremental patterns.

[0076] The role of the pre-trained machine learning model in this application is mainly reflected in two aspects: intelligent prediction and pattern recognition. First, by inputting feature vectors (such as reference values ​​for intragastric volume expansion and gastric acid secretion response), the model can predict the future dynamic changes in the patient's gastric contents based on historically learned patterns. For example, when the gastric acid secretion response reference value and the intragastric volume expansion reference value reach a certain threshold at the same time, the model may predict that the patient's gastric contents are about to enter a surge stage and provide a corresponding incremental value (content increment index). This predictive capability can help doctors or systems adopt adjustment strategies at an early stage, such as dynamically adjusting the capacity or frequency of gastric capsules to avoid discomfort or risks caused by a surge in gastric contents.

[0077] Secondly, the machine learning model can automatically extract potential rules and patterns from complex, multi-dimensional feature data. For example, it can recognize that certain combinations of features (such as the coexistence of high volume expansion and rapid changes in gastric acid secretion) usually indicate rapid growth of gastric contents, while a single feature change may only indicate a small fluctuation. By accurately identifying these patterns, the model can provide personalized and forward-looking prediction results, greatly improving the scientificity and effectiveness of the adjustment strategy. At the same time, the model's training process can also evaluate the importance of features, helping to determine which features contribute most to the prediction of incremental changes, thereby optimizing future data collection and model design. This intelligent prediction system based on prior training provides strong technical support for more efficient and accurate dynamic adjustment of gastric capsules.

[0078] The machine learning model is not specifically limited here, and can achieve the expansion of the intragastric volume reference value Reference values ​​for gastric acid secretion response Comprehensive analysis to generate content increment index In order to realize the technical solution of the present invention, the present invention provides a specific implementation method; the content increment index The generated expression is:

[0079]

[0080] , where , Reference values ​​for gastric volume expansion Reference values ​​for gastric acid secretion response The preset scaling factor of , Both are greater than 0.

[0081] It can be seen from the content increment index that the greater the performance value of the gastric volume expansion reference value generated by putting the relative growth rate of the extracted gastric content volume expansion into the monitoring window for analysis and quantification, the greater the performance value of the gastric acid secretion response reference value generated by putting the extracted gastric acid secretion change rate into the monitoring window for analysis and quantification. That is, the greater the performance value of the content increment index generated when the incremental change of gastric contents is intelligently predicted by the pre-trained machine learning model, the higher the patient's gastric content increment, and vice versa.

[0082] According to the prediction results of the machine learning model, the increase in gastric contents is divided into a surge phase and a gentle increase phase;

[0083] The content increment index generated by intelligently predicting the incremental change of gastric contents through the pre-trained machine learning model is compared and analyzed with the pre-set content increment index reference threshold, and the incremental situation of gastric contents is divided. The specific division steps are as follows:

[0084] If the content increment index is greater than the content increment index reference threshold, the increment of gastric contents is classified as a surge stage;

[0085] If the content increment index is less than or equal to the content increment index reference threshold, the increment of the gastric contents is classified as a gentle increment stage.

[0086] The surge phase is usually characterized by a rapid increase in gastric content volume or pressure, while the gradual increase phase indicates a more stable change in gastric contents.

[0087] For the gastric content increment during the gentle increment phase, continue to maintain the set initial volume adjustment range and initial volume adjustment frequency to ensure the smooth progress of the treatment process;

[0088] When the increase in gastric contents is in the slow stage (i.e., the increase changes are small and stable), there is no need to frequently or significantly adjust the capacity of the gastric capsule. Instead, continue to adjust it according to the initial volume adjustment range and initial volume adjustment frequency set at the beginning of treatment. For example, maintain a volume adjustment of 10 ml each time, and the adjustment frequency is once or twice a day. This strategy aims to avoid discomfort or complexity caused by excessive adjustment, while ensuring that the patient's stomach adapts to the treatment device and maintains the stability and continuity of the treatment effect, thereby preparing for possible subsequent surge stages or dynamic adjustments. In this way, the patient's comfort can be guaranteed and the utilization of treatment resources can be optimized during the steady increase stage.

[0089] During the surge phase, the volume adjustment amplitude and frequency of the gastric capsule are adaptively adjusted based on the fuzzy inference algorithm in combination with the prediction results of the machine learning model. The volume is gradually optimized by a small amplitude and high frequency adjustment method to reduce the patient's discomfort.

[0090] For the surge phase, combined with the prediction results of the machine learning model, the volume adjustment amplitude and frequency of the gastric capsule are adaptively adjusted based on the fuzzy inference algorithm. The specific steps are as follows:

[0091] The content increment surge deviation is calculated by the incremental deviation between the content increment index and the content increment index reference threshold, which accurately reflects the patient's current gastric content increment change. The calculation expression of the content increment surge deviation is: ,in, is the currently calculated content increment index, which comprehensively reflects the dynamic changes of gastric content increment. is the reference threshold of the content increment index, indicating the boundary between the steady stage and the surge stage. The deviation of the increase in content is increased sharply;

[0092] By calculating the deviation between the content increment index and the content increment index reference threshold, the dynamic change degree of the current gastric contents can be clarified, laying the foundation for the subsequent regulation of the volume adjustment amplitude and volume adjustment frequency.

[0093] Through the fuzzy inference algorithm, a nonlinear mapping is established between the output of the content increment surge deviation and the capacity adjustment amplitude, and the established expression is: ,in, The capacity adjustment reference value generated by fuzzy reasoning, , , are the membership functions, which respectively indicate that the deviation of the increase in content belongs to the low, medium and high degree of increase. , , is the capacity adjustment range corresponding to the fuzzy rules, which are adapted to the demands of low, medium and high surge levels respectively;

[0094] Through the fuzzy reasoning algorithm, a flexible nonlinear relationship is established between the surge degree and the capacity adjustment recommendation, so that the system can give an adaptable adjustment strategy for different surge intensities, thereby improving the accuracy of dynamic response.

[0095] Combining the fuzzy reasoning results and the deviation of the increase in content, the capacity adjustment range and capacity adjustment frequency are dynamically adjusted. The adjustment expression is: ,in, The final capacity adjustment range is proposed based on the initial range and fuzzy rules. is the initial volume adjustment range, which is the basic value set at the beginning of treatment. is the sensitivity factor, which is used to adjust the weight of the fuzzy rule on the capacity amplitude. The final capacity adjustment frequency is dynamically adjusted according to the surge degree, reflecting the real-time adaptability of the capacity adjustment frequency to the changing needs of gastric contents. The frequency of initial volume adjustment is the basic value set at the beginning of treatment. is the frequency modulation gain factor, which is used to enhance the sensitivity of frequency adjustment to surge response.

[0096] Through dynamic adjustment, the system adopts small-amplitude and high-frequency adjustments during the surge phase to quickly adapt to changes in gastric contents, reduce patient discomfort, and ensure the scientific nature and adaptability of the adjustments.

[0097] By combining the prediction results of the machine learning model with the fuzzy reasoning algorithm, the changing trend of the gastric content surge stage can be accurately identified, and the capacity adjustment amplitude and frequency of the gastric capsule can be dynamically adjusted, and the capacity can be gradually optimized by small amplitude and high frequency adjustment. In this way, while quickly adapting to the changes in gastric contents, the discomfort or risks caused by large adjustments can be avoided, the comfort and safety of the patient can be guaranteed, and the scientific regulation of the treatment process can be achieved, thereby improving the effect and accuracy of the treatment.

[0098] Through the above scheme, the intelligent management and evaluation method of adjustable gastric capsule treatment effect and body fat rate BMI has achieved full process optimization from real-time monitoring to intelligent adjustment, effectively solving the problem that the traditional stage-based fixed setting cannot dynamically respond to changes in gastric contents. By combining the patient's basic health data, scientifically setting the initial adjustment parameters, and using built-in sensors and wireless transmission technology to collect dynamic data of gastric contents in real time, this method can provide comprehensive information on changes in the gastric environment, laying the foundation for subsequent accurate analysis and decision-making. Based on the key features extracted by data collation and preprocessing, and the intelligent prediction of the pre-trained machine learning model, the system can identify the law and trend of gastric content increment in advance, and accurately divide the incremental stage into a surge stage and a gentle stage. For the gentle stage, the initial parameter settings are maintained to ensure stable progress of treatment; for the surge stage, the capacity adjustment amplitude and frequency are dynamically optimized through the fuzzy reasoning algorithm, and a small amplitude and high frequency adjustment strategy is adopted to gradually adapt to the rapidly changing gastric contents. This method not only significantly improves the system's sensitive response to the surge stage, but also avoids the discomfort or risk caused by excessive adjustment. At the same time, it effectively guarantees the safety and comfort of patient treatment through precise dynamic optimization. In addition, this method uses personalized adjustment strategies to make the treatment plan more suitable for the patient's physiological characteristics and actual needs, further improving the treatment effect and patient compliance. While achieving dynamic regulation, it also provides scientific support for the patient's long-term health management, reflecting the important value of modern intelligent medical technology in gastric capsule treatment.

[0099] 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.

[0100] 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.

[0101] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0102] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0103] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0106] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for intelligent management and evaluation of the therapeutic effect of gastric capsule and body fat rate BMI, characterized in that: The following steps are involved: According to the patient's basic health data, the initial volume adjustment range and initial volume adjustment frequency of the adjustable gastric capsule are set; The built-in sensor of the gastric capsule monitors the dynamic changes of gastric contents in real time, and sends the monitoring data to external devices based on wireless transmission technology, providing comprehensive support for subsequent analysis; The real-time acquired gastric content data is sorted and preprocessed to extract key features that can reflect the increase in gastric content. The extracted key features are put into the monitoring window for analysis and quantification, and the quantified indicators are used to reflect the increase in the patient's gastric content. The quantified indicators are input as feature vectors into the pre-trained machine learning model to intelligently predict the incremental changes in gastric contents. Through model analysis, the future trend of gastric contents changes is accurately predicted, and the rules and patterns of incremental changes are identified in advance. According to the prediction results of the machine learning model, the increase in gastric contents is divided into a surge phase and a gentle increase phase; For the gastric content increment during the gentle increment phase, continue to maintain the set initial volume adjustment range and initial volume adjustment frequency to ensure the smooth progress of the treatment process; During the surge phase, the capacity adjustment amplitude and frequency of the gastric capsule are adaptively adjusted based on the fuzzy inference algorithm in combination with the prediction results of the machine learning model. Small amplitude and high frequency adjustments are used to gradually optimize the capacity and reduce the patient's discomfort.

2. The method for intelligent management and evaluation of the therapeutic effect of an adjustable gastric capsule and body fat percentage (BMI) according to claim 1, characterized in that: The initial capacity adjustment range refers to the specific capacity value that is increased or decreased each time the capacity of the adjustable gastric capsule is adjusted; The frequency of initial volume adjustment refers to the time interval for adjusting the gastric capsule volume in the initial stage of treatment, that is, how often the gastric capsule volume is adjusted.

3. The method for intelligent management and evaluation of the therapeutic effect of an adjustable gastric capsule and body fat percentage (BMI) according to claim 1, characterized in that: The key features that can reflect the increase in gastric contents are extracted, wherein the extracted features include the relative growth rate of gastric contents volume expansion and the change rate of gastric acid secretion. The extracted relative growth rate of gastric contents volume expansion and the change rate of gastric acid secretion are put into the monitoring window for analysis and quantification, and the reference value of gastric volume expansion and the reference value of gastric acid secretion response are generated respectively. The quantified reference value of gastric volume expansion and the reference value of gastric acid secretion response reflect the increase in gastric contents of the patient.

4. The method for intelligent management and evaluation of the therapeutic effect of an adjustable gastric capsule and body fat percentage (BMI) according to claim 3, characterized in that: The relative growth rate of gastric content volume expansion and the rate of change of gastric acid secretion are analyzed and quantified to generate gastric volume expansion reference value and gastric acid secretion response reference value as feature vectors which are input into a pre-trained machine learning model. The content increment index is generated by the machine learning model, and the incremental change of gastric contents is intelligently predicted based on the content increment index. The future changing trend of gastric contents is accurately predicted, and the rules and patterns of incremental changes are identified in advance.

5. The method for intelligent management and evaluation of the therapeutic effect of an adjustable gastric capsule and body fat percentage (BMI) according to claim 4, characterized in that: The content increment index generated by intelligently predicting the incremental change of gastric contents through the pre-trained machine learning model is compared and analyzed with the pre-set content increment index reference threshold to divide the incremental situation of gastric contents. The specific division steps are as follows: If the content increment index is greater than the content increment index reference threshold, the increment of gastric contents is classified as a surge stage; If the content increment index is less than or equal to the content increment index reference threshold, the increment of the gastric contents is classified as a gentle increment stage.

6. The method for intelligent management and evaluation of the therapeutic effect of an adjustable gastric capsule and body fat percentage (BMI) according to claim 3, characterized in that: The specific steps of putting the extracted relative growth rate of gastric content volume expansion into the monitoring window for analysis and quantification to generate a reference value of gastric volume expansion are as follows: The relative growth rate of gastric content volume expansion was extracted, and the relative growth rate of volume expansion was defined as the rate of change of the current volume relative to the volume at the previous moment. Normalization was performed to eliminate the influence of individual differences on the results. The calculation expression of the relative growth rate of volume expansion was: ,in: is the relative growth rate of volume expansion, is the current measured volume of gastric contents, is the volume of gastric contents measured last time, is the patient's individual baseline volume, is a small constant used to avoid the denominator being zero; The extracted relative growth rate data is placed in the monitoring window, and the contribution of the growth rate change to the intragastric pressure is calculated by cumulative calculation, and the cumulative value of volume expansion is calculated to quantify the cumulative effect of the growth rate. The calculation expression of the cumulative value of volume expansion is: ,in, is the cumulative value of volume expansion, reflecting the cumulative effect of the change in growth rate on the gastric environment, W is the time span of the monitoring window, is the nonlinear amplification term of the volume expansion acceleration, is a nonlinear adjustment index used to enhance the weight of abnormal changes. is the patient's response coefficient, reflecting the sensitivity of individual stomach wall elasticity to changes in expansion; Based on the cumulative value of volume expansion, combined with the individual characteristic parameters of the patient, the reference value of intragastric volume expansion is generated to quantify and reflect the incremental situation of gastric contents. The expression for generating the reference value of intragastric volume expansion is: ,in, Expanded reference value for gastric volume, is the gastric content characteristic coefficient, which indicates the influence weight of the patient's gastric content type. is the patient's maximum stomach volume, is an exponential adjustment factor that controls the nonlinear effect of the maximum volume on volume expansion. It is a natural logarithmic function, which is used to compress the growth range of the intragastric volume and expand the reference value.

7. The method for intelligent management and evaluation of the therapeutic effect of an adjustable gastric capsule and body fat percentage (BMI) according to claim 3, characterized in that: The specific steps of putting the extracted gastric acid secretion rate into the monitoring window for analysis and quantification to generate a gastric acid secretion response reference value are as follows: Calculate the rate of change of gastric acid secretion. The rate of change of gastric acid secretion is a basic parameter that reflects the dynamic changes of gastric contents. It is used to capture the degree of stimulation of gastric contents on gastric acid gland secretion. The calculation expression is: ,in, It is the total amount of gastric acid secreted in the stomach at a certain moment, indicating the total amount of acid secreted by the gastric glands. is the rate of change of gastric acid secretion, describing the changing trend of gastric acid secretion per unit time. is the sampling time interval, which is used to calculate the rate of change between two consecutive data points; In order to enhance the nonlinear response to the rate of change of gastric acid, a dynamic weight is introduced to amplify the effect of gastric acid change by combining power function and exponential function. The generation expression of dynamic weight is: ,in, is a dynamic weight, which is used to adjust the sensitivity in subsequent calculations. k is a weight adjustment factor, which is used to control the growth rate. is the absolute value of the rate of change of gastric acid secretion, ensuring that both positive and negative changes are included in the calculation. is the nonlinear sensitivity coefficient, which is used to further adjust the response of the weight to the rate of change of gastric acid; The dynamic weight, gastric acid secretion rate of change and basal secretion are combined to generate a comprehensive gastric acid secretion response reference value. The generation expression of the gastric acid secretion response reference value is: ,in, It is a reference value for gastric acid secretion response, used to quantify the response of gastric acid secretion changes to the increase in gastric contents. is the weight amplification factor, further enhancing the impact of dynamic weights in drastic changes. It is the initial baseline value of gastric acid secretion, which represents the patient's basal secretion without stimulation and is used to correct individual differences.

8. The method for intelligent management and evaluation of the therapeutic effect of an adjustable gastric capsule and body fat percentage (BMI) according to claim 5, characterized in that: For the surge phase, combined with the prediction results of the machine learning model, the volume adjustment amplitude and frequency of the gastric capsule are adaptively adjusted based on the fuzzy inference algorithm. The specific steps are as follows: The content increment surge deviation is calculated by the incremental deviation between the content increment index and the content increment index reference threshold value, which accurately reflects the patient's current gastric content increment change. The calculation expression of the content increment surge deviation is: ,in, is the currently calculated content increment index, which comprehensively reflects the dynamic changes of gastric content increment. is the reference threshold of the content increment index, indicating the boundary between the steady stage and the surge stage. The deviation of the increase in content is increased sharply; Through the fuzzy inference algorithm, a nonlinear mapping is established between the output of the content increment surge deviation and the capacity adjustment amplitude, and the established expression is: ,in, The capacity adjustment reference value generated by fuzzy reasoning, , , are the membership functions, which respectively indicate that the deviation of the increase in content belongs to the low, medium and high degree of increase. , , is the capacity adjustment range corresponding to the fuzzy rules, which are adapted to the demands of low, medium and high surge levels respectively; Combining the fuzzy reasoning results and the deviation of the increase in content, the capacity adjustment range and capacity adjustment frequency are dynamically adjusted. The adjustment expression is: ,in, The final capacity adjustment range is proposed based on the initial range and fuzzy rules. is the initial volume adjustment range, which is the basic value set at the beginning of treatment. is the sensitivity factor, which is used to adjust the weight of the fuzzy rule on the capacity amplitude. The final capacity adjustment frequency is dynamically adjusted according to the surge degree, reflecting the real-time adaptability of the capacity adjustment frequency to the changing needs of gastric contents. The frequency of initial volume adjustment is the basic value set at the beginning of treatment. is the frequency modulation gain factor, which is used to enhance the sensitivity of frequency adjustment to surge response.

Images