A pregnancy weight evaluation and intervention tracking intelligent management system

Abstract

The present application relates to the field of intelligent medical technology, in particular to a pregnant period weight evaluation and intervention tracking intelligent management system, comprising: a whole pregnancy cycle data acquisition module for acquiring pregnant women's whole pregnancy cycle body weight composition, diet and exercise behavior, and maternal and infant health index data; a filing module for constructing a structured individual health record and generating a standardized weight management monitoring data set; an intelligent weight evaluation and intervention scheme generation module for performing pregnant women's gestational age adaptation correlation influence evaluation and generating gestational age stage and daily personalized weight intervention schemes; a real-time intervention tracking and risk early warning module for performing real-time evaluation, generating visual tracking correction prompts, and adjusting intervention intensity by grade through a contrast learning algorithm; and a compliance management and scheme iteration optimization module for generating multi-scene reminders and iteratively updating a basic framework of the next day's generated scheme. Thus, the problems of difficulty in adapting to the differentiated needs of different pregnant women and difficulty in timely responding to unexpected situations during pregnancy in the prior art are solved.

Description

Technical Field

[0001] This invention relates to the field of smart healthcare technology, specifically to an intelligent management system for pregnancy weight assessment and intervention tracking. Background Technology

[0002] Pregnancy weight gain is a core indicator reflecting the nutritional status of pregnant women and the growth and development of the fetus. Reasonable weight gain during pregnancy is crucial for reducing the risk of pregnancy complications and ensuring maternal and infant safety. Existing pregnancy weight management technologies have formed a certain application system and play a key role. Traditional weight monitoring methods, through standardized weighing procedures and recording methods, help pregnant women and medical staff monitor weight changes in real time. Combined with recommended gestational weight gain standards, they can preliminarily determine whether weight gain is within a reasonable range and promptly detect abnormalities such as excessively rapid or slow weight gain, providing basic support for preventing gestational diabetes, gestational hypertension, macrosomia, and fetal growth restriction. Meanwhile, the application of information technology has further enriched management methods. The integration of various pregnancy management apps, electronic medical tools, and wearable devices with information platforms enables convenient recording, preliminary analysis, and basic health guidance of weight data, compensating for the shortcomings of traditional management methods in terms of convenience. This has alleviated the shortage of obstetric human resources to some extent and provided pregnant women with more flexible weight management approaches. Furthermore, existing nutritional guidance and behavioral intervention methods also provide basic references for pregnant women to adjust their diet and exercise habits, helping to achieve scientific management of pregnancy weight.

[0003] While existing pregnancy weight management technologies possess basic control capabilities, they still have numerous shortcomings in practical application, failing to meet the demands for precise and personalized intelligent management. Firstly, current technologies lack the ability to integrate and collect multi-source data throughout the entire pregnancy cycle. Most can only collect single-data points like weight, failing to simultaneously acquire crucial information such as the pregnant woman's body composition, dietary and exercise behaviors, and maternal and infant health indicators. Furthermore, they lack standardized, structured individual health records and pregnancy-specific data correlation and verification mechanisms, making it difficult to create standardized weight management monitoring datasets, resulting in insufficient data support and inaccurate results. Secondly, current technologies cannot achieve precise assessment and personalized plan generation tailored to gestational age. They rely heavily on universal standards and lack gestational age adaptive meta-learning algorithms. They cannot comprehensively assess weight gain trends, risk grading, and the impact on maternal and infant health by incorporating individual pregnant woman characteristics. They also cannot generate personalized intervention plans for different gestational stages and daily periods, making it difficult to adapt to the diverse needs of different pregnant women. Furthermore, existing technologies lack real-time intervention tracking and dynamic risk warning mechanisms. They cannot use comparative learning algorithms to evaluate the effectiveness of intervention programs in real time and generate corrective prompts, nor can they combine dynamic safety thresholds during pregnancy to analyze data such as weight fluctuations and changes in body composition to adjust the intensity of interventions accordingly. This makes it difficult to respond promptly to unexpected situations during pregnancy. In addition, existing technologies lack a sound adherence management and iterative optimization mechanism. They do not break down intervention program implementation periods according to the pregnant woman's daily routine and do not provide reminders for multiple scenarios. They also cannot receive feedback from pregnant women and combine weight change data to conduct effect reviews and iterative updates to the intervention program. This results in poor adherence to intervention measures, a lack of continuity in management, and an inability to achieve dynamic and precise control throughout the entire pregnancy. Summary of the Invention

[0004] This application provides an intelligent management system for pregnancy weight assessment and intervention tracking to solve the problems in existing technologies, such as difficulty in adapting to the differentiated needs of different pregnant women and difficulty in responding to emergencies during pregnancy.

[0005] The first aspect of this application provides an intelligent management system for pregnancy weight assessment and intervention tracking, comprising: a full pregnancy cycle data collection module, a record-keeping module, an intelligent weight assessment and intervention plan generation module, a real-time intervention tracking and risk warning module, and a compliance management and plan iteration optimization module; wherein, the full pregnancy cycle data collection module is used to collect data on the pregnant woman's weight and body composition, dietary and exercise behaviors, and maternal and infant health indicators throughout the entire pregnancy cycle; the record-keeping module is used to construct a structured individual health record through pregnancy-specific data association verification rules and generate a standardized weight management monitoring dataset; the intelligent weight assessment and intervention plan generation module is used to assess the pregnant woman's gestational age-appropriate weight gain trend, weight management risk classification, and maternal and infant health-related impact assessment, and calls a preset pregnancy weight intervention plan library, through gestational age adaptive... The meta-learning algorithm generates personalized weight intervention plans for gestational weeks and daily periods. The real-time intervention tracking and risk warning module uses a comparative learning algorithm to evaluate the effectiveness of weight management during the implementation of the intervention plan. When the evaluation results exceed the appropriate range, it generates visual tracking and correction prompts. It also combines dynamic safety thresholds during pregnancy to analyze the pregnant woman's weight gain fluctuations, body composition changes, pregnancy complication indicators, and fetal development data to adjust the intervention intensity in stages. The compliance management and plan iteration optimization module breaks down the daily implementation time of the intervention plan according to the pregnant woman's daily routine, generates multi-scenario reminders, and receives daily implementation feedback and subjective feeling scores from the pregnant woman. It combines implementation feedback and weight change data to complete a review and evaluation of the periodic weight management effect, and iteratively updates the basic framework of the plan generated the next day based on the evaluation results.

[0006] Preferably, the whole pregnancy cycle data acquisition module includes a weight and body composition data acquisition unit, a diet and exercise behavior data acquisition unit, and a maternal and infant health indicator data acquisition unit. The weight and body composition data acquisition unit is used to collect weight, body fat percentage, muscle mass, water percentage, and visceral fat level data of the pregnant woman throughout the entire pregnancy cycle. The diet and exercise behavior data acquisition unit is used to collect daily dietary nutrient intake, exercise type and duration, and sleep-wake cycle data of the pregnant woman throughout the entire pregnancy cycle. The maternal and infant health indicator data acquisition unit is used to collect gestational age, fetal development indicators, pregnancy complication-related indicators, and maternal physiological baseline data of the pregnant woman throughout the entire pregnancy cycle.

[0007] Preferably, the filing module includes a pregnancy-specific data verification unit, a full-dimensional individual profile construction unit, and a monitoring dataset generation unit. The pregnancy-specific data verification unit verifies the physiological correlation fit of various data collected by the full pregnancy cycle data acquisition module based on pre-built physiological correlation rules during pregnancy, and generates correction prompts for abnormal data. The full-dimensional individual profile construction unit stores the verified full data by category, generating a structured individual health profile including a weight gain baseline, body composition baseline, fetal development baseline, and pregnancy complication risk baseline. The monitoring dataset generation unit integrates the verified full data collection to establish a standardized weight management monitoring dataset with timestamp alignment.

[0008] Preferably, the intelligent weight assessment and intervention program generation module includes a weight grading assessment unit, an algorithm calculation unit, and an intervention program output unit. The weight grading assessment unit determines the appropriate weight gain range for the pregnant woman's gestational age based on her individual health record, and, in conjunction with the monitoring dataset, assesses the deviation of the weight gain trend, the associated risk of pregnancy complications, and the tolerance to intervention, outputting a weight management risk level. The algorithm calculation unit adjusts the dietary nutrient ratio, exercise program parameters, and monitoring frequency using a gestational age adaptive meta-learning algorithm, prioritizing intervention types with high historical compliance and good weight management effects for the pregnant woman. The intervention program output unit, based on the dietary, exercise, and monitoring parameters, and combined with a pre-built gestational weight intervention program library and historical behavioral energy consumption data, generates a daily intervention program including a customized daily menu, personalized exercise guidance, a weight monitoring plan, and key risk management points, simultaneously outputting a gestational age weight gain trend prediction curve.

[0009] Preferably, the real-time intervention tracking and risk warning module includes an execution deviation and effect evaluation unit, a visual tracking correction unit, a risk grading warning unit, and an intervention intensity adjustment unit. The execution deviation and effect evaluation unit uses a comparative learning algorithm to calculate the deviation between the pregnant woman's daily weight gain, dietary nutrient intake, exercise execution data, and the intervention plan template, quantifying the degree of matching between the executed behavior and the plan requirements, and conducting real-time weight management execution effect evaluation. The visual tracking correction unit displays weight gain deviation, nutrient intake deficit, exercise execution completion rate, and real-time evaluation results on the pregnant woman's mobile device through dynamic trend charts, simultaneously outputting voice prompts and text correction guidance. The risk grading warning unit dynamically sets safe ranges for weight gain, body composition changes, and blood sugar and blood pressure indicators based on dynamic safety thresholds during pregnancy, combined with the pregnant woman's individual weight gain baseline, fetal development indicators, gestational age, and complication risk level. Exceeding these ranges triggers a corresponding weight management risk level warning. The intervention intensity adjustment unit adjusts the strictness of dietary control, exercise intensity and duration, and monitoring frequency according to the risk level, or activates a complication-specific intervention plan.

[0010] Preferably, the compliance management and program iteration optimization module includes a time-segmentation unit, a multi-scenario reminder execution unit, a feedback receiving unit, and an evaluation and program iteration unit. The time-segmentation unit is used to divide the daily intervention program into multiple time periods—diet, exercise, and weight monitoring—based on the pregnant woman's recorded daily routine, with each time period matching a corresponding execution task. The multi-scenario reminder execution unit generates vibration and pop-up reminders according to set time periods, triggering ringtone and SMS reminders when there is no response. The feedback receiving unit provides a scoring interface, including four dimensions: program execution completion rate, diet suitability, exercise fatigue, and physical discomfort feedback, for receiving text notes and data supplements. The evaluation and program iteration unit combines execution feedback data and weight change monitoring results to complete a review and evaluation of the periodic weight management effect, analyze the correlation between execution compliance, evaluation results, and intervention measures, identify core factors affecting the effectiveness and safety of weight management, iteratively update the basic framework for generating intervention programs for the next day and subsequent gestational weeks, and archive historical programs, evaluation data, and weight data for retrospective querying.

[0011] The second aspect of this application provides a method for intelligent management of pregnancy weight assessment and intervention tracking, comprising: acquiring the pregnant woman's weight and body composition data, dietary and exercise behavior data, and maternal and infant health indicator data throughout the entire pregnancy cycle; constructing a structured individual health profile based on the pregnant woman's weight and body composition data, dietary and exercise behavior data, and maternal and infant health indicator data throughout the entire pregnancy cycle through pregnancy-specific data association verification rules, and generating a standardized weight management monitoring dataset; conducting a multi-dimensional weight health assessment adapted to gestational week based on the standardized weight management monitoring dataset, generating a weight gain trend prediction curve and identifying pregnancy weight management risks in real time, and obtaining a personalized weight intervention plan; tracking the implementation progress of the pregnant woman's personalized weight intervention plan, synchronously collecting weight change feedback data and maternal and infant health dynamic data during the implementation process, dynamically adjusting the intervention intensity and implementation requirements of pregnancy weight management according to the personalized weight intervention plan and the feedback data and dynamic data, training the optimization model of the plan based on the feedback data and dynamic data, generating an implementation effect evaluation report, and updating the parameter weights of the multi-dimensional weight health assessment.

[0012] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement a method for intelligent management of pregnancy weight assessment and intervention tracking as described in the above embodiments.

[0013] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement a method for intelligent management of pregnancy weight assessment and intervention tracking as described in the above embodiments.

[0014] The fifth aspect of this application provides a computer program product, including a computer program or instructions, for implementing a prenatal weight assessment and intervention tracking intelligent management method as described in the above embodiments.

[0015] Therefore, this application has the following beneficial effects: This application's embodiments utilize a full-pregnancy-cycle data collection and standardized record-keeping module to achieve multi-dimensional data collection of pregnant women's weight and body composition, diet and exercise, and maternal and infant health indicators throughout the entire pregnancy cycle. Based on pregnancy-specific verification rules, it constructs structured health records and standardized monitoring datasets, addressing the pain points of fragmented and insufficiently standardized data in traditional pregnancy weight management, thus laying a data foundation for precise intervention. Through an intelligent weight assessment and intervention plan generation module, it completes the assessment of gestational week-appropriate weight gain trends, risk classification, and the correlation impact on maternal and infant health. Combined with a gestational week-adaptive meta-learning algorithm, it generates phased and daily personalized intervention plans, overcoming the limitations of traditional plan homogenization and gestational week-appropriateness. Overcoming the limitations of poor adaptability, this technology utilizes a real-time intervention tracking and risk warning module. Leveraging comparative learning algorithms, it achieves real-time evaluation and visual correction of intervention effectiveness. Combined with dynamic safety thresholds during pregnancy, it performs multi-dimensional dynamic data analysis, adjusting intervention intensity in stages and providing early warnings of maternal and infant health risks. This effectively prevents pregnancy complications and adverse fetal development problems caused by abnormal weight. Furthermore, through a compliance management and program optimization module, it breaks down intervention program execution periods, generating multi-scenario reminders to improve compliance. By combining pregnant women's feedback and weight change data, it performs periodic effect reviews and program iterations, achieving refined and personalized management of pregnancy weight throughout the entire cycle, effectively ensuring the health and safety of both mother and baby. This solves the problems of existing technologies, such as difficulty in adapting to the differentiated needs of different pregnant women and difficulty in responding to emergencies during pregnancy.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a schematic diagram of the structure of an intelligent management system for pregnancy weight assessment and intervention tracking provided according to an embodiment of this application; Figure 2 This is a schematic diagram of a full pregnancy cycle data acquisition module provided according to an embodiment of this application; Figure 3 This is a schematic diagram of a filing module provided according to an embodiment of this application; Figure 4 This is a schematic diagram of an intelligent weight assessment and intervention scheme generation module provided according to an embodiment of this application; Figure 5 This is a schematic diagram of a real-time intervention tracking and risk warning module provided according to an embodiment of this application; Figure 6 This is a schematic diagram of a compliance management and scheme iteration optimization module according to an embodiment of this application; Figure 7 This is a graph showing the trend of weight change during pregnancy in pregnant women, provided according to an embodiment of this application. Figure 8 This is a flowchart of a smart management method for pregnancy weight assessment and intervention tracking according to an embodiment of this application; Figure 9 This is a schematic diagram of an intelligent management method for pregnancy weight assessment and intervention tracking according to an embodiment of this application; Figure 10 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] The following description, with reference to the accompanying drawings, illustrates an intelligent management system for pregnancy weight assessment and intervention tracking, based on an embodiment of this application. Addressing the issue mentioned in the background art of difficulty in adapting to the diverse needs of different pregnant women, this application provides an intelligent management system for pregnancy weight assessment and intervention tracking. In this system, a full-pregnancy-cycle data collection and standardized record-keeping module enables multi-dimensional collection of the pregnant woman's weight, body composition, diet, exercise, and maternal and infant health indicators throughout the entire pregnancy cycle. Based on pregnancy-specific verification rules, a structured health record and standardized monitoring dataset are constructed, solving the pain points of fragmented and insufficiently standardized traditional pregnancy weight management data, laying a data foundation for precise intervention. Through an intelligent weight assessment and intervention plan generation module, the system completes the assessment of gestational week-appropriate weight gain trends, risk classification, and maternal and infant health-related impacts, combined with a gestational week adaptive meta-learning algorithm to generate... This segmented and daily personalized intervention program overcomes the limitations of traditional programs, such as homogeneity and poor gestational week adaptability. Through a real-time intervention tracking and risk warning module, it utilizes comparative learning algorithms to achieve real-time evaluation and visual correction of intervention effectiveness. Combined with dynamic safety thresholds during pregnancy, it performs multi-dimensional dynamic data analysis, adjusting intervention intensity in stages and providing early warnings of maternal and infant health risks, effectively preventing pregnancy complications and adverse fetal development problems caused by abnormal weight. Through a compliance management and program optimization module, it breaks down the intervention program into different time periods, generating multi-scenario reminders to improve compliance. Combining pregnant women's feedback and weight change data, it performs periodic effect reviews and program iterations, achieving refined and personalized management of pregnancy weight throughout the entire pregnancy cycle, effectively ensuring the health and safety of both mother and baby. This solves the problems of existing technologies, such as difficulty in adapting to the differentiated needs of different pregnant women and difficulty in responding to unexpected situations during pregnancy.

[0020] Figure 1 This is a schematic diagram of the structure of an intelligent management system for pregnancy weight assessment and intervention tracking provided in an embodiment of this application.

[0021] This application provides an intelligent management system for pregnancy weight assessment and intervention tracking, the system 10 including: The system includes a whole pregnancy cycle data collection module (100 modules), a record-keeping module (200 modules), an intelligent weight assessment and intervention plan generation module (300 modules), a real-time intervention tracking and risk warning module (400 modules), and a compliance management and plan iteration optimization module (500 modules).

[0022] The system includes: a full pregnancy cycle data collection module 100 for collecting data on pregnant women's weight and body composition, dietary and exercise behaviors, and maternal and infant health indicators throughout the entire pregnancy cycle; a record-keeping module 200 for constructing structured individual health records and generating standardized weight management monitoring datasets based on pregnancy-specific data association verification rules; an intelligent weight assessment and intervention plan generation module 300 for assessing the pregnant woman's gestational age-appropriate weight gain trend, weight management risk grading, and maternal and infant health-related impact assessment, calling upon a pre-set pregnancy weight intervention plan library, and generating personalized weight intervention plans for different gestational stages and daily through a gestational age-adaptive meta-learning algorithm; and a real-time intervention tracking and risk warning module 400 for... The comparative learning algorithm evaluates the effectiveness of weight management in pregnant women during the implementation of the intervention program in real time. When the evaluation results exceed the appropriate range, it generates visual tracking and correction prompts. At the same time, it combines dynamic safety threshold analysis during pregnancy to analyze the pregnant woman's weight gain fluctuations, body composition changes, pregnancy complication indicators, and fetal development data to adjust the intervention intensity in a graded manner. The compliance management and program iteration optimization module 500 is used to break down the daily intervention program into execution periods according to the pregnant woman's daily routine, generate multi-scenario reminders, and receive daily execution feedback and subjective feeling scores from the pregnant woman. It combines execution feedback and weight change data to complete the periodic weight management effectiveness review and evaluation, and iteratively updates the basic framework of the program generated the next day based on the evaluation results.

[0023] It is understandable that, through the whole pregnancy cycle data collection and standardized filing module, this application achieves multi-dimensional collection of pregnant women's weight and body composition, diet and exercise, and maternal and infant health indicators throughout the entire pregnancy cycle. Based on pregnancy-specific verification rules, it constructs structured health records and standardized monitoring datasets, solving the pain points of fragmented and insufficiently standardized traditional pregnancy weight management data, laying a data foundation for precise intervention. Through the intelligent weight assessment and intervention plan generation module, it completes the assessment of gestational week-appropriate weight gain trends, risk classification, and maternal and infant health-related impacts. Combined with the gestational week adaptive meta-learning algorithm, it generates phased and daily personalized intervention plans, breaking through the homogenization of traditional plans. This approach overcomes the limitations of poor gestational age adaptability. Through a real-time intervention tracking and risk warning module, it utilizes a comparative learning algorithm to achieve real-time evaluation and visual correction of intervention effectiveness. Combined with dynamic safety thresholds during pregnancy, it performs multi-dimensional dynamic data analysis, adjusting intervention intensity in stages and providing early warnings of maternal and infant health risks. This effectively prevents pregnancy complications and adverse fetal development problems caused by abnormal weight gain. Furthermore, through a compliance management and program optimization module, it breaks down the intervention program into different time periods, generating multi-scenario reminders to improve compliance. By combining pregnant women's feedback and weight change data, it performs periodic effect reviews and program iterations, achieving refined and personalized management of pregnancy weight throughout the entire pregnancy cycle, effectively ensuring the health and safety of both mother and baby. This addresses the problems of existing technologies, such as difficulty in adapting to the differentiated needs of different pregnant women and difficulty in responding to unexpected situations during pregnancy.

[0024] In this embodiment of the application, the whole pregnancy cycle data acquisition module 100 includes: Figure 2 As shown, there are three data collection units: body weight and body composition data collection unit, diet and exercise behavior data collection unit, and maternal and infant health indicator data collection unit.

[0025] The weight and body composition data collection unit is used to collect weight, body fat percentage, muscle mass, water percentage, and visceral fat level data of pregnant women throughout the entire pregnancy cycle; the diet and exercise behavior data collection unit is used to collect daily dietary nutrition intake, exercise type and duration, and daily routine data of pregnant women throughout the entire pregnancy cycle; and the maternal and infant health indicator data collection unit is used to collect gestational age, fetal development indicators, pregnancy complication-related indicators, and maternal physiological baseline maternal and infant health indicator data of pregnant women throughout the entire pregnancy cycle.

[0026] It is understood that the weight and body composition data acquisition unit in this application embodiment can collect data such as the pregnant woman's weight, body fat percentage, muscle mass, water percentage, and visceral fat level throughout the entire pregnancy cycle, providing a core basis for intelligent weight assessment and weight management target setting, and helping to identify the risk of abnormal body composition; the diet and exercise behavior data acquisition unit can collect data such as the pregnant woman's daily dietary nutrition intake, exercise type and duration, and work-rest patterns, providing accurate reference for personalized dietary nutrition ratios and exercise plan formulation, while supporting real-time tracking and deviation analysis of intervention program implementation; the maternal and infant health indicator data acquisition unit can collect data such as the pregnant woman's gestational age, fetal development indicators, pregnancy complication-related indicators, and maternal physiological baseline, providing key support for weight management risk classification and real-time health early warning. The three work together to provide accurate and complete dynamic data support for pregnancy weight assessment, intervention program generation, risk management, and program iteration, helping to improve the scientificity and safety of pregnancy weight management and protect the health of the mother and fetus.

[0027] In this embodiment of the application, the filing module 200 includes: Figure 3 As shown, there are pregnancy-specific data verification unit, full-dimensional individual profile construction unit, and monitoring dataset generation unit.

[0028] The pregnancy-specific data verification unit verifies the physiological correlation fit of various data collected by the full pregnancy cycle data acquisition module based on pre-built pregnancy physiological correlation rules, and generates correction prompts for abnormal data; the full-dimensional individual profile construction unit is used to store the verified full data by category and generate a structured individual health profile including weight gain baseline, body composition baseline, fetal development baseline, and pregnancy complication risk baseline; the monitoring dataset generation unit is used to integrate the verified full data and establish a standardized weight management monitoring dataset with timestamp alignment.

[0029] It is understood that the pregnancy-specific data verification unit in this application embodiment verifies the physiological correlation adaptability of the data collected by the full pregnancy cycle data acquisition module based on pre-constructed physiological correlation rules during pregnancy and generates correction prompts for abnormal data. This effectively ensures the authenticity, accuracy, and standardization of the collected data and avoids abnormal data interfering with subsequent management processes. The full-dimensional individual profile construction unit classifies and stores the verified full data, generating a structured individual health profile that includes a weight gain baseline, body composition baseline, fetal development baseline, and pregnancy complication risk baseline. This provides a personalized basis for subsequent weight assessment and intervention plan generation, accurately adapting to individual differences among pregnant women. The monitoring dataset generation unit integrates the verified full data collection to establish a standardized weight management monitoring dataset with timestamp alignment. This allows for the orderly integration and traceability of data, providing standardized and unified data support for subsequent real-time intervention tracking, risk warning, and plan iteration optimization, ensuring the scientific, accurate, and efficient operation of the entire system.

[0030] It should be noted that the physiological correlation fit of various data collected by the full pregnancy cycle data collection module is verified based on pre-constructed pregnancy physiological correlation rules, and correction prompts are generated for abnormal data. The pre-constructed pregnancy physiological correlation rules cover the fit between gestational age and weight gain range, body composition, body fat percentage, muscle mass and the maternal physiological baseline, as well as the intrinsic correlation and normal fluctuation range between maternal and infant health indicators, fetal development indicators and pregnancy complication-related indicators. The pregnancy-specific data verification unit calls these rules to cross-compare various data such as weight, body composition, diet, exercise behavior and maternal and infant health indicators collected by the full pregnancy cycle data collection module, and verifies the physiological logical consistency and numerical fit between the data. If logical contradictions are found in the data, such as serious discrepancies between gestational age and weight gain values, abnormal fluctuations in body fat percentage and water percentage that exceed the normal range for pregnancy, conflicts between maternal and infant health indicators or values ​​that exceed the reasonable threshold for the corresponding gestational age, targeted correction prompts are generated, clearly marking the abnormal data items, the abnormality type and the initial correction direction, guiding pregnant women to supplement or re-collect data, and ensuring the accuracy and usability of the collected data.

[0031] The verified full data is stored by category, generating a structured individual health profile containing baseline weight gain, baseline body composition, baseline fetal development, and baseline pregnancy complication risk. First, the verified full data is categorized and stored according to the type of data: weight, body composition, diet, exercise, behavior, and maternal and infant health indicators. This ensures clear and orderly association of each data type. Then, combining pre-constructed physiological standards for pregnancy with the individual pregnant woman's baseline data, the following baselines are calculated and determined: weight gain, body composition, fetal development, and pregnancy complication risk. The weight gain baseline defines a reasonable range based on gestational age and the individual's baseline weight. The body composition baseline determines the individual's normal baseline based on verified body fat percentage, muscle mass, water percentage, and visceral fat level data. The fetal development baseline defines the individual's appropriate range by referring to the corresponding gestational age fetal development standards and collected fetal development indicators. The pregnancy complication risk baseline sets a risk reference threshold by combining the maternal physiological baseline and pregnancy complication-related indicators. Finally, the categorized full data is linked and integrated with the four baseline data, archived according to a standardized structure, and the data classification hierarchy, baseline reference standards, and individual-specific data tags are clearly defined, generating a structured individual health profile containing various baseline information, categorized data, and individual basic information.

[0032] By integrating and verifying the full collection data, a standardized weight management monitoring dataset with timestamp alignment is established. First, the full collection data that has passed the verification of the pregnancy-specific data verification unit is summarized, covering weight, body composition data, diet, exercise behavior data, and maternal and infant health index data. The formats of various data are standardized, and the data recording specifications and units of measurement are unified to eliminate data format differences and redundant information from different collection channels. Then, the original collection time information corresponding to each data item is extracted, and the timestamps of all data are uniformly calibrated to the same time precision to ensure that the relevant data such as weight, body composition, diet, exercise, and maternal and infant health at the same time point correspond one-to-one. Subsequently, the standardized data with aligned timestamps is classified and organized according to the preset weight management monitoring data classification standards, and the data collection source and verification status are marked to construct a standardized weight management monitoring dataset with complete data structure and time alignment.

[0033] For example, the pregnancy-specific data verification unit verifies the pregnant woman's data collected by the full pregnancy cycle data acquisition module based on pre-built pregnancy physiological association rules. This pregnant woman is 22 weeks gestation, and her measurements are: weight 63.2 kg, body fat percentage 29.5%, muscle mass 22.8 kg, water percentage 53.1%, daily dietary intake of carbohydrates 280 g, protein 88 g, and fat 52 g. The fetal biparietal diameter is 5.5 cm, femur length 3.4 cm, maternal fasting blood glucose 4.9 mmol / L, and blood pressure 120 / 78 mmHg. Verification reveals that her daily carbohydrate intake exceeds the appropriate range for her gestational age, and the carbohydrate intake needs to be adjusted to 220 g / L. -250g / day correction prompt; The full-dimensional individual profile construction unit stores the verified full data by category, generating a structured individual health profile including a weight gain baseline of 61-65kg, a body fat percentage baseline of 27%-30%, a fetal development baseline of biparietal diameter of 5.2-5.8cm, and a pregnancy complication risk baseline of fasting blood glucose ≤5.1mmol / L; The monitoring dataset generation unit integrates the verified full collection data to establish a standardized weight management monitoring dataset with timestamp alignment, clearly recording the weight and body composition data collected at 8:00 AM, the dietary intake data collected at 12:00 PM, and the exercise and maternal and infant health indicator data collected at 7:00 PM daily.

[0034] In this embodiment, the intelligent weight assessment and intervention plan generation module 300 includes: Figure 4 As shown, there are a weight grading assessment unit, an algorithm calculation unit, and an intervention plan output unit.

[0035] The weight grading assessment unit is used to determine the reasonable range of weight gain appropriate for the gestational week of a pregnant woman based on her individual health record. It combines the monitoring dataset to complete the assessment of deviation of weight gain trend, risk assessment of pregnancy complications, and intervention tolerance, and outputs the weight management risk level. The algorithm calculation unit adjusts the dietary nutrition ratio, exercise program parameters, and monitoring frequency through the gestational week adaptive meta-learning algorithm, and prioritizes the intervention type with high historical compliance and good weight management effect for the pregnant woman. The intervention program output unit generates a daily intervention program based on diet, exercise, and monitoring parameters, combined with a pre-built pregnancy weight intervention program library and historical behavioral energy consumption data. The program includes a daily customized diet, personalized exercise guidance, weight monitoring plan, and risk management points, and simultaneously outputs the gestational week weight gain trend prediction curve.

[0036] It is understood that the weight grading assessment unit in this application embodiment can determine the reasonable range of weight gain appropriate for the gestational week based on the individual health record of the pregnant woman, and complete multi-dimensional assessment and output the weight management risk level in combination with monitoring data, providing accurate assessment basis for personalized intervention; the algorithm operation unit dynamically adjusts diet, exercise and monitoring-related parameters through the gestational week adaptive meta-learning algorithm, and prioritizes intervention methods with high compliance and good management effect of pregnant women, improving the rationality and suitability of the plan; the intervention plan output unit can combine the intervention plan library and historical behavioral data to generate a daily personalized plan including customized diet, exercise guidance, monitoring plan and risk points, and simultaneously output the weight gain prediction curve, realizing the precision, personalization and visualization of weight intervention during pregnancy, and providing pregnant women with scientific and feasible full-process weight management guidance.

[0037] It should be noted that, based on individual health records, a reasonable weight gain range appropriate for the pregnant woman's gestational week is determined. This is combined with monitoring datasets to assess weight gain trend deviation, pregnancy complication risk, and intervention tolerance, ultimately outputting a weight management risk level. The structured individual health records of the pregnant woman are retrieved, and corresponding gestational weight gain standards are matched to determine the reasonable weight gain range appropriate for the corresponding gestational week. A standardized weight management monitoring dataset with timestamp alignment is retrieved, and the pregnant woman's actual weight gain data is compared stage by stage with the determined reasonable range, calculating the weight gain rate and data fluctuation amplitude to complete the weight gain trend deviation assessment. Combining maternal physiological indicators, fetal development indicators, and pregnancy complication-related indicators from the monitoring dataset, the positive correlation between the current weight gain status and various pregnancy complications is analyzed to complete the pregnancy complication risk assessment. Combining the pregnant woman's historical physiological baseline, dietary and exercise records, and physical condition data, the acceptance and physical tolerance of the pregnant woman to intervention measures such as dietary control, exercise implementation, and weight monitoring are assessed to complete the intervention tolerance assessment. Based on the combined results of these three assessments and according to pre-set risk judgment rules, quantitative analysis and hierarchical classification are performed, ultimately outputting the pregnant woman's corresponding weight management risk level.

[0038] The gestational week adaptive meta-learning algorithm adjusts dietary nutrient ratios, exercise program parameters, and monitoring frequency, prioritizing intervention types with high historical compliance and good weight management results for the pregnant woman. Using gestational week as the dynamic adaptation basis, and combining individual health records, standardized weight management monitoring datasets, and the pregnant woman's historical intervention execution records and weight management effect data, the algorithm iterates and optimizes parameters to dynamically match the maternal physiological characteristics and weight management requirements of the corresponding gestational week. Targeted adjustments are made to dietary nutrient ratios, exercise program type, intensity, duration, and weight monitoring frequency. Simultaneously, the execution status and weight improvement effects of all previous intervention programs for the pregnant woman are quantitatively analyzed to identify intervention types and implementation modes with high compliance and excellent weight management results. These more adaptable intervention forms are prioritized in parameter configuration and program construction, resulting in an intervention parameter program tailored to the pregnant woman's individual characteristics and gestational stage.

[0039] By combining a pre-built library of pregnancy weight intervention programs with historical behavioral energy consumption data, a daily intervention program is generated, including customized daily meal plans, personalized exercise guidance, weight monitoring plans, and risk management points. A gestational weight gain trend prediction curve is simultaneously output. Based on intervention parameters determined by a gestational week adaptive meta-learning algorithm, a program template suitable for the corresponding gestational week, weight management risk level, and individual physical condition is matched to the pre-built library of pregnancy weight intervention programs. This is further refined by integrating the pregnant woman's historical behavioral energy consumption data, daily dietary and exercise habits, and intervention tolerance, resulting in a complete daily personalized weight intervention program consisting of customized daily meal plans, personalized exercise guidance, weight monitoring plans, and risk management points. Simultaneously, based on the individual's historical weight data, current gestational week development pattern, set intervention parameters, and expected implementation effects, a gestational weight gain trend prediction curve for the entire pregnancy cycle is generated through data fitting and trend extrapolation.

[0040] Formula for the gestational age adaptive meta-learning algorithm: in, The gestational age adaptive weighting coefficient; This refers to the current gestational week; The standardized baseline gestational age for the entire pregnancy; This is a correction factor for the pregnancy stage; The overall preference score for the intervention program; For compliance weight hyperparameters; For the first Historical adherence score to the intervention program; As a weighted hyperparameter for effect; For the first Historical weight management effectiveness scores for similar intervention programs; This is the general loss function for the meta-model; The symbol for mathematical expectation; Each pregnant woman is assigned an individual ID; The probability distribution of pregnant women; For the first Individual loss function for each pregnant woman; Initial parameters for a meta-learning general pregnancy model; For the gradient operator with respect to; This refers to the current gestational week; For the first Personalized fitting parameters for each pregnant woman; The learning rate of the algorithm; This represents the deviation between actual weight gain and the baseline gestational age. This refers to standardized weight gain reference values ​​for gestational weeks. Parameters for adaptive dietary nutrition during gestational weeks; These are baseline dietary parameters for pregnancy. Parameters for the gestational week adaptive exercise program; These are baseline exercise parameters during pregnancy; Adjust the frequency of weight monitoring according to gestational age; This serves as the baseline monitoring frequency parameter during pregnancy.

[0041] For example, the weight grading assessment unit determines the appropriate weight gain range for a pregnant woman at 25 weeks of gestation to be 62-66 kg based on her individual health record. Combining this with the monitoring dataset, the unit finds the pregnant woman's current weight is 65 kg, with an average daily weight gain of 0.3 kg over the past week. The weight gain trend deviation assessment shows a deviation of 0.1 kg. The pregnancy complication risk assessment shows normal fasting blood glucose (4.8 mmol / L) and blood pressure (122 / 79 mmHg). The intervention tolerance assessment shows she can tolerate moderate-intensity exercise, resulting in a low-risk weight management level. The algorithm processing unit adjusts the dietary nutrient ratio using a gestational week adaptive meta-learning algorithm, setting daily protein intake to 90g, carbohydrates to 240g, and fat to 50g. The exercise program parameters are set to 35 minutes of brisk walking daily, and the monitoring frequency is adjusted to daily morning fasting weight and body composition monitoring, and weekly fetal development indicators monitoring, prioritizing... The pregnant woman had a 90% historical compliance rate and good weight control, so brisk walking was chosen as the main intervention type. The intervention program output unit generated a daily intervention plan based on the above-mentioned dietary and exercise monitoring parameters, combined with a pre-constructed pregnancy weight intervention program library and historical behavioral energy consumption data. The plan included: breakfast 50g whole wheat bread, 1 egg, 250ml milk; lunch 100g mixed grain rice, 100g lean meat, 200g green vegetables; dinner 80g millet porridge, 120g steamed fish, 150g cucumber salad. The personalized exercise guidance was to walk briskly for 35 minutes at 5 pm every day at a speed of 60 steps per minute. The weight monitoring plan was to monitor weight and body fat percentage on an empty stomach at 7 am every day. The risk management points were to avoid exercising on an empty stomach and to drink at least 1500ml of water every day. The gestational weight gain trend prediction curve was output simultaneously, predicting that the weight would reach 67.5kg by 30 weeks, which is within a reasonable growth range.

[0042] In this embodiment, the real-time intervention tracking and risk warning module 400 includes, as follows: Figure 5 As shown, there are units for performance deviation and effect evaluation, visualization tracking and correction, risk classification and early warning, and intervention intensity adjustment.

[0043] The implementation deviation and effectiveness evaluation unit uses a comparative learning algorithm to calculate the deviation values ​​between the pregnant woman's daily weight gain, dietary nutrient intake, exercise execution data, and intervention plan template, quantifying the degree of matching between the execution behavior and the plan requirements, and conducting real-time weight management execution effectiveness evaluation. The visualization tracking and correction unit displays weight gain deviation, nutrient intake deficit, exercise execution completion rate, and real-time evaluation results on the pregnant woman's mobile device through dynamic trend charts, and simultaneously outputs voice prompts and text correction guidance. The risk classification and early warning unit dynamically sets safe ranges for weight gain, body composition changes, blood sugar and blood pressure indicators based on the pregnant woman's individual weight gain baseline, fetal development indicators, gestational age, and complication risk level, and triggers corresponding weight management risk level warnings when the range is exceeded. The intervention intensity adjustment unit adjusts the strictness of dietary control, exercise intensity and duration, monitoring frequency, or activates complication-specific intervention plans according to the risk level classification.

[0044] It is understood that the deviation and effect evaluation unit of this application embodiment uses a comparative learning algorithm to quantify the deviation between the pregnant woman's actual data and the intervention plan, which can evaluate the weight management effect in real time and objectively, ensuring that the intervention process is monitorable and measurable; the visualization tracking and correction unit uses dynamic charts, voice and text guidance to intuitively display the implementation status on the mobile terminal and provide correction guidance, which makes it easy for pregnant women to understand intuitively and adjust their behavior in a timely manner; the risk classification and early warning unit combines the dynamic safety threshold during pregnancy and individual maternal and infant health data to set a safety range, which can identify abnormal weight and pregnancy risks in advance, and achieve graded and accurate health warnings; the intervention intensity adjustment unit can dynamically adjust the intensity of diet, exercise and monitoring and activate special plans according to the risk level, so that the intervention strategy can be flexibly adapted to the pregnancy status, ensuring the effectiveness of weight management while maximizing the safety and pertinence of the intervention during pregnancy.

[0045] It should be noted that, in order to quantify the degree of matching between the implemented behavior and the requirements of the plan, and to conduct real-time evaluation of the effectiveness of weight management, data on the actual weight gain, dietary and nutritional intake, and exercise implementation of pregnant women are collected. Each actual data point is compared with the reasonable range of the target values ​​set in the intervention plan, and the deviation value and completion rate of each data point from the plan requirements are calculated. Through multi-dimensional data verification, the quantitative matching degree between the implemented behavior and the plan requirements is obtained. Combined with the gestational age and individual health baseline data, the real-time evaluation of the effectiveness of weight management is completed.

[0046] The system uses dynamic trend charts to display weight gain deviation, nutritional intake deficit, exercise completion rate, and real-time assessment results on pregnant women's mobile devices. It also provides voice prompts and text correction guidance. The system visualizes the real-time calculated weight gain deviation, nutritional intake deficit, exercise completion rate, and real-time management effectiveness assessment results, and displays them in the form of dynamic trend charts on the pregnant women's mobile devices. The system generates corresponding voice prompts based on the deviation of each data point and the assessment conclusions, and simultaneously outputs clear and concise text correction guidance. It provides targeted adjustment guidance for diet, exercise, and weight monitoring-related behaviors, making it easy for pregnant women to intuitively view and promptly optimize their own behavior.

[0047] By using dynamic safety thresholds during pregnancy, combined with the pregnant woman's individual weight gain baseline, fetal development indicators, gestational age, and complication risk level, safe ranges for weight gain, body composition changes, and blood sugar and blood pressure indicators are dynamically set. When these ranges are exceeded, a warning for the corresponding weight management risk level is triggered. Based on the dynamic safety thresholds during pregnancy, combined with the pregnant woman's individual weight gain baseline, fetal development indicators, gestational age, and complication risk level, dynamic settings are made for weight gain, body composition changes, and blood sugar and blood pressure indicators to form safe ranges adapted to the pregnant woman's individual condition. The system continuously collects actual monitoring data for the corresponding indicators and synchronously compares the real-time data with the corresponding safe ranges. Once the monitoring data exceeds the set safe range, a warning message consistent with the current weight management risk level is directly triggered according to the preset warning rules.

[0048] Adjust the strictness of dietary control, exercise intensity and duration, and monitoring frequency according to the risk level classification, or activate the special intervention plan for complications. Based on the determined weight control risk level, adjust the strictness of dietary control, exercise intensity and duration in stages, and adjust the monitoring frequency of weight and health indicators accordingly. The higher the risk level, the stricter the dietary control requirements, the safer and gentler the exercise plan, and the higher the monitoring frequency of indicators. When the risk level reaches the preset critical condition and the related pregnancy complication indicators are abnormal, directly activate the special intervention plan for complications matching the current risk type and implement targeted special intervention measures.

[0049] Contrastive learning algorithm formula: in, is the real-time deviation value of the i-th indicator on day t; i is the core assessment indicator number: i=1 (weight gain), i=2 (dietary nutrition intake), i=3 (exercise execution); t is the assessment date; This represents the actual value of the i-th indicator on day t, and is the real data of the pregnant woman. The intervention plan template is the target value of the i-th indicator on day t. This represents the combined performance deviation value of multiple indicators on day t. The dynamic weight of the i-th indicator at gestational week g; g represents the current gestational week; The matching degree is executed in real time on day t; The deviation from the safety threshold on day t; This represents the lower limit of the dynamic safety threshold for indicators at gestational week g. This represents the upper limit of the dynamic safety threshold for indicators at the g-week of gestation.

[0050] For example, the execution deviation and effectiveness evaluation unit uses a comparative learning algorithm to calculate the deviation values ​​between the pregnant woman's daily weight gain, dietary nutrient intake, exercise execution data, and the intervention plan template. This pregnant woman is 30 weeks pregnant. The intervention plan template sets a daily weight gain of no more than 0.2 kg, a daily protein intake of 95g, a carbohydrate intake of 230g, and a fat intake of 48g, with exercise consisting of 40 minutes of slow walking daily. On that day, her actual weight gain was 0.3 kg, her protein intake was 80g, her carbohydrate intake was 250g, and her fat intake was 45g. She only exercised for 25 minutes. The calculation shows a weight gain deviation of 0.1 kg, a protein intake deficit of 15g, a carbohydrate excess of 20g, and an exercise execution time deviation of 15 minutes. The quantified matching degree between the execution behavior and the plan requirements is 78%, and the real-time weight management execution effectiveness evaluation is judged as average. The visualization tracking and correction unit displays the weight gain deviation of 0.1 kg, the protein intake deficit of 15g, the exercise execution completion rate of 62.5%, and the real-time evaluation results on the pregnant woman's mobile device through dynamic trend charts, simultaneously outputting... Audio prompts remind participants to adjust their diet and exercise promptly, while textual corrections clearly indicate the need to increase high-quality protein intake, reduce carbohydrate intake, and make up for the remaining 15 minutes with slow walking. The risk grading and early warning unit uses dynamic safety thresholds during pregnancy, combined with the pregnant woman's baseline weight gain of 64-68kg, fetal biparietal diameter of 7.8cm, gestational age of 30 weeks, and low-risk weight management level, to dynamically set a safe range for daily weight gain of 0.1-0.2kg, a safe range for body fat percentage of 28%-31%, a safe range for fasting blood glucose of 3.9-5.1mmol / L, and a safe range for blood pressure of 110-130 / 70-85mmHg. On that day, the pregnant woman's weight gain of 0.3kg exceeded the safe range, triggering a low-risk weight management warning. The intervention intensity adjustment unit adjusts the strictness of dietary control based on the low-risk warning, adjusting the daily carbohydrate intake to 220g, increasing protein intake to 100g, keeping the exercise intensity unchanged, adjusting the duration to 30 minutes, and increasing the monitoring frequency from once a day to twice a day, monitoring weight and body composition in the morning on an empty stomach and before bedtime.

[0051] In this embodiment, the compliance management and solution iteration optimization module 500 includes, as follows: Figure 6 As shown, there are time period segmentation unit, multi-scenario reminder execution unit, feedback receiving unit, and evaluation and solution iteration unit.

[0052] The system comprises several modules: a time-segmentation unit, which breaks down the daily intervention plan into multiple time periods based on the pregnant woman's recorded daily routine, including diet, exercise, and weight monitoring, with each time period corresponding to specific tasks; a multi-scenario reminder unit, which generates vibration and pop-up reminders according to set time periods, triggering ringtones and SMS alerts when no response is received; a feedback receiving unit, which provides a scoring interface including four dimensions: plan completion rate, diet suitability, exercise fatigue, and feedback on physical discomfort, for receiving text notes and data supplements; and an evaluation and plan iteration unit, which combines execution feedback data with weight change monitoring results to conduct a review and evaluation of the periodic weight management effect, analyze the correlation between execution compliance, evaluation results, and intervention measures, identify the core factors affecting the effectiveness and safety of weight management, iteratively update the basic framework for generating intervention plans for the next day and subsequent gestational weeks, and archive historical plans, evaluation data, and weight data for retrospective querying.

[0053] It is understood that the time-segmentation unit in this application embodiment can segment the daily intervention plan into time periods and match tasks according to the pregnant woman's daily routine, making the intervention content fit the pregnant woman's lifestyle and significantly improving the feasibility of the plan; the multi-scenario reminder execution unit can effectively urge the pregnant woman to complete the intervention tasks in a timely manner through multi-level linkage reminders such as vibration, pop-up window, ringtone and SMS, and improve weight management compliance; the feedback receiving unit collects the pregnant woman's execution feedback, subjective feelings and physical status information from multiple dimensions, which can comprehensively obtain the plan's adaptability and provide a real basis for subsequent optimization; the evaluation and plan iteration unit combines execution feedback and weight change data to conduct periodic review and evaluation, analyze the intrinsic relationship between compliance and intervention effect, continuously iterate and optimize the subsequent intervention plan framework, and archive and retain relevant data for optimization and traceable management of pregnancy weight management.

[0054] It should be noted that, based on the daily routines entered by pregnant women, the daily intervention plan is broken down into multiple time periods, including diet, exercise, and weight monitoring. Each time period is matched with a corresponding task. By obtaining the daily routine information entered by pregnant women and combining the pregnant women's daily living time, meal times, and free time arrangements, the complete daily intervention plan is decomposed into a time sequence. According to the plan content, the three core contents of diet implementation, exercise implementation, and weight monitoring are classified and divided. Based on the daily routine, each type of implementation content is assigned to the appropriate corresponding time period. Each divided time period is bound with exclusive and directly executable tasks, forming a segmented execution arrangement that is highly consistent with the pregnant women's daily routines, with clear time period divisions and clear task orientations.

[0055] Vibration and pop-up alerts are generated according to the set time period. If there is no response, a ringtone and SMS reminder are triggered. According to the preset execution time period, vibration and pop-up alerts are sent to the pregnant woman's mobile device at the corresponding time node. The confirmation and response status of the pregnant woman to the reminders is monitored in real time. If no valid response is obtained within the preset time limit, the reminder mode is automatically switched and a ringtone and SMS reminder are activated simultaneously. The pregnant woman is reminded in a multi-form and multi-channel linkage to ensure that she is informed of the intervention tasks to be performed in a timely manner.

[0056] The system provides a scoring interface with four dimensions: plan completion rate, dietary suitability, exercise fatigue, and feedback on physical discomfort. This interface is used to receive text notes and data supplements. The system provides pregnant women with a dedicated scoring interface with four independent scoring dimensions: plan completion rate, dietary suitability, exercise fatigue, and feedback on physical discomfort. Pregnant women can complete the corresponding scoring for each dimension. The interface also has a data entry portal, allowing pregnant women to fill in text notes during the implementation process and upload relevant actual data. The system receives and retains all scoring results, text notes, and supplementary data in real time, providing original evidence for subsequent cycle reviews and plan iterations.

[0057] By combining implementation feedback data and weight change monitoring results, a post-hoc evaluation of the effectiveness of cyclical weight management was conducted. The correlation between implementation compliance, evaluation results, and intervention measures was analyzed to identify core factors affecting the effectiveness and safety of weight management. The basic framework for generating intervention plans for the next day and subsequent gestational weeks was iteratively updated, and historical plans, evaluation data, and weight data were archived for retrospective retrieval. The implementation feedback data and weight change monitoring results within the cycle were integrated to conduct a comprehensive post-hoc evaluation of the overall weight management effectiveness. The inherent relationship between implementation compliance, phase evaluation results, and various intervention measures was clarified. Through data comparison and logical analysis, core factors affecting the effectiveness of gestational weight management and maternal and infant safety were identified. Based on the post-hoc conclusions and core influencing factors, the plan generation logic and parameters were optimized and adjusted, and the basic framework of intervention plans for the next day and subsequent gestational weeks was iteratively updated. Simultaneously, historical intervention plans, cyclical evaluation data, and weight monitoring data were uniformly categorized and archived to form a historical data archive that can be accessed at any time, meeting the needs of subsequent data retrospective and retrieval.

[0058] For example, the time-segmentation unit, based on the pregnant woman's daily routine at 27 weeks of gestation (7:00 AM wake-up, 12:00 PM lunch, 6:00 PM dinner, 8:00 PM exercise, 7:00 PM bedtime monitoring), breaks down the daily intervention plan into tasks: breakfast at 7:30 AM, lunch at 12:30 PM, dinner at 6:30 PM, exercise at 8:30 PM, and bedtime weight and body composition monitoring. Each time segment is precisely matched with corresponding execution requirements. The multi-scenario reminder execution unit triggers reminders according to the set time segments. At 7:25 AM, a vibration and pop-up reminder for the breakfast task is pushed to the pregnant woman's mobile device. If there is no response, a ringtone and SMS reminder are sent again at 7:28 AM. Reminders for the corresponding tasks are pushed sequentially at 12:25 PM, 6:30 PM, and 8:25 PM according to the same rules. A pre-sleep monitoring task warm-up reminder is sent at 7:20 AM. The feedback receiving unit provides a rating interface including a plan completion rate of 88%, dietary suitability of 92%, exercise fatigue of 70%, and feedback on physical discomfort such as mild lower limb soreness. The pregnant woman can supplement her feedback. The text notes indicate that the breakfast of mixed grain rice was palatable, the lunch vegetable intake was insufficient, and there was no significant discomfort after 25 minutes of exercise. Additional data shows that the patient's weight was 65.1 kg, body fat percentage was 30.5%, muscle mass was 24.2 kg, fetal biparietal diameter was 6.8 cm, and fasting blood glucose was 4.7 mmol / L. The assessment and program iteration unit combined two weeks of implementation feedback data with weight change monitoring results to complete a cycle review. Overall compliance was 85%. Analysis revealed that the low exercise fatigue level was primarily due to the fixed 25-minute exercise duration lacking flexibility, while dietary suitability was high. However, the persistently insufficient vegetable intake at lunch was a secondary factor affecting weight management effectiveness. The basic framework of the intervention program for the following day and subsequent gestational weeks was iterated and updated, adjusting the exercise duration to a flexible range of 20 to 30 minutes, adding a lower limb relaxation component, and increasing lunch vegetable intake to 220g. Simultaneously, 14 implementation feedback data sets and 28 weight and body composition monitoring data sets from the two-week historical program were archived for future retrospective reference.

[0059] This application proposes an intelligent management system for pregnancy weight assessment and intervention tracking. Through a full-pregnancy data collection and standardized record-keeping module, it achieves multi-dimensional data collection of pregnant women's weight, body composition, diet, exercise, and maternal and infant health indicators throughout the entire pregnancy cycle. Based on pregnancy-specific verification rules, it constructs structured health records and standardized monitoring datasets, addressing the pain points of fragmented and insufficiently standardized data in traditional pregnancy weight management, thus laying a data foundation for precise intervention. Through an intelligent weight assessment and intervention plan generation module, it completes the assessment of gestational week-appropriate weight gain trends, risk classification, and the correlation impact on maternal and infant health. Combined with a gestational week-adaptive meta-learning algorithm, it generates phased and daily personalized intervention plans, breaking through the limitations of traditional methods. Traditional intervention methods suffer from limitations such as homogeneity and poor gestational age adaptability. This approach overcomes these limitations by employing a real-time intervention tracking and risk warning module. Utilizing comparative learning algorithms, it achieves real-time evaluation of intervention effectiveness and provides visual correction prompts. Combined with dynamic safety thresholds during pregnancy, it performs multi-dimensional dynamic data analysis, allowing for tiered adjustments to intervention intensity and early warnings of maternal and infant health risks. This effectively prevents pregnancy complications and adverse fetal development problems caused by abnormal weight gain. Furthermore, the adherence management and program optimization module breaks down the intervention program's execution timeframes, generating multi-scenario reminders to improve adherence. By combining pregnant women's feedback and weight change data, it enables periodic effect reviews and program iterations, achieving refined and personalized management of pregnancy weight throughout the entire pregnancy cycle, effectively ensuring the health and safety of both mother and child. This addresses the shortcomings of existing technologies, such as difficulty in adapting to the diverse needs of different pregnant women and the inability to promptly respond to unexpected situations during pregnancy.

[0060] The following will illustrate a specific embodiment of an intelligent management system for pregnancy weight assessment and intervention tracking, such as... Figure 7 As shown, it includes: A pregnant woman registered for the Pregnancy Weight Assessment and Intervention Tracking Intelligent Management System after confirming her pregnancy at 4 weeks. The system utilizes five modules to complete 40 weeks of weight assessment, intervention implementation, real-time tracking, and program optimization. The pregnant woman's pre-pregnancy height was 162 cm and weight was 78.5 kg, with a calculated body mass index (BMI) of 29.9 kg / m². Based on the recommended weight gain standards for pregnant women, she is considered obese. The recommended total weight gain during pregnancy is 5.0 to 9.0 kg, with a total gain of 0 to 2.0 kg in the first trimester (before 13 weeks) and a weekly gain of 0.15 to 0.30 kg in the second and third trimesters. The system uses this as its core benchmark for intelligent management throughout the entire process. The full pregnancy cycle data collection module serves as the system's data foundation. Through automatic collection, manual supplementation, and intelligent synchronization, it acquires three types of data: the pregnant woman's weight and body composition, dietary and exercise behaviors, and maternal and infant health indicators, ensuring comprehensiveness, real-time performance, and accuracy. Weight and body composition data were collected using a calibrated electronic scale and body composition analyzer. Pregnant women were required to measure their weight every morning on an empty stomach, after urination, barefoot, wearing only thin underwear, at a room temperature of around 25 degrees Celsius. Weight was measured once a day, with detailed body composition analysis added on Wednesdays and Sundays.

[0061] At 4 weeks of pregnancy, the first measurement showed a weight of 78.5 kg, body fat percentage of 32.1%, muscle mass of 42.3 kg, water percentage of 45.2%, and a basal metabolic rate of 1385 kcal. At 12 weeks of pregnancy, the weight was 79.8 kg, body fat percentage of 32.5%, muscle mass of 42.1 kg, water percentage of 45.0%, and a basal metabolic rate of 1410 kcal. At 27 weeks of pregnancy, the weight was 83.2 kg, body fat percentage of 33.0%, muscle mass of 42.5 kg, water percentage of 44.8%, and a basal metabolic rate of 1485 kcal. At 40 weeks of pregnancy, the weight was 86.3 kg, body fat percentage of 33.2%, muscle mass of 42.7 kg, water percentage of 44.6%, and a basal metabolic rate of 1520 kcal. A total of 258 weight data points and 74 body composition data points were collected throughout the pregnancy, with a data completeness rate of 99.8%. Dietary and exercise behavior data were collected using a combination of intelligent recording and manual supplementation. The system's built-in dietary database contains the calorie and nutrient content of over 10,000 ingredients and common dishes. Pregnant women can record their three meals and snacks daily by scanning codes, searching, or taking photos, including the type of ingredients, quantity, and cooking method. The system automatically calculates the total daily calorie intake and the content of protein, carbohydrates, fat, calcium, iron, and folic acid. Exercise data is collected via a smart bracelet, automatically recording the type, duration, intensity, and calories burned. Pregnant women can manually add any unrecognized exercises and record their physical sensations. In the first trimester (weeks 4-13), the average daily intake is 2150 kcal, 65g protein, 280g carbohydrates, 78g fat, 850mg calcium, 18mg iron, and 800mcg folic acid, indicating a high calorie intake and insufficient calcium and iron intake. In the second trimester (weeks 14-27), the average daily intake is 2050 kcal, 75g protein, 260g carbohydrates, 72g fat, 1000mg calcium, 24mg iron, and 800mcg folic acid, which is generally within the recommended range. During the late pregnancy period (28 to 40 weeks), the average daily intake was 2100 kcal, 85g protein, 270g carbohydrates, 75g fat, 1200mg calcium, 29mg iron, and 800mcg folic acid, which met the requirements. Regarding exercise data, in the early pregnancy period, the average daily exercise was 22 minutes, mainly low-intensity, burning 185 kcal; in the mid-pregnancy period, the average daily exercise was 30 minutes, moderate to low-intensity, burning 250 kcal; and in the late pregnancy period, the average daily exercise was 28 minutes, low-intensity, burning 220 kcal. A total of 257 dietary and exercise data points were collected, with a data accuracy rate of 99.2%.

[0062] Maternal and infant health data are collected synchronously through home health monitoring devices and hospital prenatal checkup data. Home devices measure systolic blood pressure, diastolic blood pressure, and fasting blood glucose daily upon waking, and monitor fetal heart rate twice a week. Hospital prenatal checkup data is manually uploaded, including complete blood count, urinalysis, liver function, kidney function, fetal ultrasound, etc., and the system automatically categorizes and archives the data. First prenatal checkup at 4 weeks of gestation: Systolic blood pressure 132 mmHg, diastolic blood pressure 85 mmHg, fasting blood glucose 5.1 mmol / L, hemoglobin 112 g / L; this is very early pregnancy, the embryo has just completed implantation, and ultrasound has not yet measured the gestational sac or fetal structure. Prenatal checkup at 12 weeks of gestation: Systolic blood pressure 130 mmHg, diastolic blood pressure 82 mmHg, fasting blood glucose 5.0 mmol / L, hemoglobin 110 g / L, fetal biparietal diameter 2.8 cm, femur length 1.5 cm, amniotic fluid index 8.2 cm. Prenatal checkup at 20 weeks of gestation: Systolic blood pressure 128 mmHg, diastolic blood pressure 80 mmHg, fasting blood glucose 4.9 mmol / L, hemoglobin 115 g / L, fetal biparietal diameter 4.8 cm, femur length 3.2 cm, amniotic fluid index 12.5 cm. Prenatal checkup at 30 weeks of gestation: Systolic blood pressure 135 mmHg, diastolic blood pressure 86 mmHg, fasting blood glucose 5.2 mmol / L, hemoglobin 113 g / L, fetal biparietal diameter 7.8 cm, femur length 5.6 cm, amniotic fluid index 13.0 cm. Prenatal checkup at 40 weeks of gestation: Systolic blood pressure 138 mmHg, diastolic blood pressure 88 mmHg, fasting blood glucose 5.3 mmol / L, hemoglobin 114 g / L, fetal biparietal diameter 9.3 cm, femur length 7.5 cm, amniotic fluid index 11.8 cm. A total of 583 home monitoring data points and 12 hospital prenatal checkup data points were collected throughout the process, with a data synchronization timeliness rate of 98.5%. After receiving all data from the data collection module, the file creation module cleaned, verified, and correlated the data according to pregnancy-specific data association and verification rules, eliminating abnormal data and correcting errors. Based on pre-pregnancy basic information, gestational cycle data, health indicator data, and diet and exercise data, an individualized structured health record for pregnant women was constructed, generating a standardized weight management monitoring dataset. During verification, it was found that a weight gain of 81.2 kg at 8 weeks of pregnancy deviated by 2.2 kg from the previous day's 79.0 kg, exceeding the normal fluctuation range. This data was identified as abnormal, removed, and a remeasurement was requested. At 10 weeks of pregnancy, the weekly weight gain was 0.4 kg. Considering the weight management requirements for obese pregnant women in early pregnancy, the weight gain fluctuation was too large, indicating a potential risk of exceeding the target later. This data was promptly marked and associated with the subsequent assessment module.

[0063] The standardized monitoring dataset contains 28 core indicators, grouped and archived weekly, generating 37 standardized monitoring reports for easy viewing of changes throughout the entire pregnancy cycle. The intelligent weight assessment and intervention plan generation module, based on the standardized monitoring dataset and combined with a pregnancy weight management knowledge base and intervention plan library, employs a gestational week adaptive meta-learning algorithm to conduct phased assessments of weight gain trends, weight management risk grading, and maternal and infant health impacts, generating personalized intervention plans for each gestational week and each day. The weight gain trend assessment uses a linear regression algorithm to predict weight changes over the next four weeks. At week 12 of pregnancy, based on data from weeks 4 to 12, a weight gain of 1.3 kg over 8 weeks (an average of 0.16 kg per week) is predicted, with a predicted gain of 0.72 kg from weeks 13 to 16 (0.18 kg per week), within the recommended range. However, a weekly weight gain of 0.4 kg at week 10 indicates significant fluctuations in weight gain. At 27 weeks of pregnancy, based on data from weeks 13 to 27, the baby gained 3.4 kg in 14 weeks, averaging 0.24 kg per week. The predicted gain from weeks 28 to 31 is 0.96 kg, or 0.24 kg per week, indicating a stabilizing growth trend. At 37 weeks of pregnancy, based on data from weeks 28 to 37, the baby gained 2.6 kg in 9 weeks, averaging 0.29 kg per week. The predicted gain from weeks 38 to 40 is 0.81 kg, or 0.27 kg per week, approaching the recommended upper limit for weekly weight gain, requiring closer monitoring.

[0064] Weight management risk assessment uses a multi-dimensional scoring method, evaluating four dimensions: weight gain deviation, changes in body composition, maternal and infant health indicators, and adherence to diet and exercise. The total score is 100 points, categorized as low risk (80-100 points), medium risk (60-79 points), and high risk (below 60 points). At 12 weeks of pregnancy, a score of 82 points is low risk (10 points deducted for large weekly weight gain fluctuations, 3 points for a slight increase in body fat percentage, and 5 points for poor adherence), requiring close monitoring. At 20 weeks of pregnancy, all indicators are within the target range, resulting in a score of 98 points, also indicating low risk. At 30 weeks of pregnancy, a score of 87 points is low risk (5 points deducted for weekly weight gain approaching the recommended upper limit, and 8 points for slightly elevated fasting blood glucose reaching the gestational threshold), requiring close monitoring of blood glucose levels. At 38 weeks of pregnancy, a score of 6 points is deducted for weekly weight gain approaching the recommended upper limit, and 7 points are deducted for slightly elevated blood pressure approaching the safe threshold, resulting in a low risk (87 points), requiring enhanced blood pressure and weight management. The assessment of the impact of weight gain on maternal and infant health focuses on analyzing the potential effects of weight gain on maternal and infant health. It clarifies that rapid weight gain in obese pregnant women significantly increases the risk of gestational diabetes, gestational hypertension, and macrosomia. The assessment at 12 weeks of gestation showed that the pregnant woman's weekly weight gain fluctuated significantly. Combined with her pre-pregnancy obesity, the associated risks of gestational diabetes, gestational hypertension, and macrosomia were 2.3 times, 1.8 times, and 2.1 times higher, respectively, compared to pregnant women of normal weight. Simultaneously, the borderline fasting blood glucose level at 4 weeks of gestation also indicated a risk of abnormal glucose metabolism. The assessment at 27 weeks of gestation showed stable and within acceptable limits for weight gain, with the aforementioned risks decreasing by 35%, 28%, and 32%, respectively, compared to 12 weeks of gestation. At 40 weeks of gestation, the total weight gain was 7.8 kg, within the recommended range. Maternal and infant indicators were basically normal, the associated risks decreased to normal or near-normal levels, and fetal development was normal.

[0065] Based on the results of the three assessments, the system calls upon the intervention program library and, through a gestational week adaptive meta-learning algorithm combined with the pregnant woman's personalized data, generates gestational week-specific and daily personalized intervention programs. Early Pregnancy Stage Program: Target total weight gain of 0 to 2.0 kg, daily calorie intake of 1900 to 2000 kcal, protein 60 to 70 g, calcium 800 to 1000 mg, iron 20 to 22 mg, folic acid 800 mcg, 20 to 25 minutes of low-intensity exercise daily, daily monitoring of weight, blood pressure, and blood sugar, and body composition testing twice a week. Mid-Pregnancy Program: Target total weight gain of 3.0 to 5.0 kg, daily calorie intake of 2000 to 2100 kcal, protein 70 to 80 g, calcium 1000 mg, iron 24 mg, folic acid 800 mcg, 25 to 30 minutes of moderate-intensity exercise daily, daily monitoring of baseline indicators, and body composition testing twice a week. Late Pregnancy Plan: Target total weight gain of 2.0 to 3.0 kg, daily calorie intake of 2050 to 2150 kcal, protein 80 to 85 g, calcium 1200 mg, iron 29 mg, folic acid 800 mcg, 25 to 30 minutes of low-intensity exercise daily, and daily monitoring of basic indicators and fetal heart rate. The daily personalized plan is broken down into time slots according to the pregnant woman's daily routine, clearly defining the intervention content for each time slot. For example, at 8 weeks of pregnancy: morning measurement, breakfast, morning snack, lunch, afternoon snack, dinner, and pre-sleep stretching, etc., clearly defining implementation details to ensure feasibility. A real-time intervention tracking and risk warning module, relying on real-time data collection, uses a comparative learning algorithm to evaluate the daily intervention implementation effect, and combines dynamic safety thresholds during pregnancy to analyze weight gain fluctuations, body composition changes, pregnancy complication-related indicators, and fetal development data. For situations exceeding the appropriate range, visual tracking and correction prompts are generated, and the intervention intensity is adjusted according to levels. Daily assessments cover weight target achievement rate, dietary target achievement rate, and exercise target achievement rate, comprehensively calculating the overall implementation success rate.

[0066] At 10 weeks of pregnancy, the pregnant woman's actual calorie intake was 2350 kcal, exceeding the recommended intake. She exercised for 15 minutes that day, failing to meet her exercise goals. Her weekly weight gain was 0.4 kg, showing significant fluctuations. The system determined the implementation effect to be poor and sent targeted corrective prompts, suggesting adjustments to her diet and exercise plan. Regarding risk warnings, dynamic safety thresholds were set for pregnancy: daily weight fluctuation ≤0.5 kg, weekly weight gain in the mid-to-late stages of pregnancy ≤0.30 kg, weekly body fat percentage fluctuation ≤0.5%, systolic blood pressure ≤140 mmHg, diastolic blood pressure ≤90 mmHg, fasting blood glucose ≤5.1 mmol / L, fetal heart rate 110-160 beats / minute, and amniotic fluid index 5-25 cm. At 30 weeks of pregnancy, her fasting blood glucose reached 5.2 mmol / L, exceeding the warning threshold and was classified as a medium-risk warning. A dietary adjustment plan was sent, the frequency of blood glucose monitoring was increased, and the intervention intensity was adjusted in stages, appropriately reducing calorie intake and increasing the duration of low-intensity exercise. At 38 weeks of pregnancy, blood pressure approached the safe threshold, triggering a low-risk warning and fine-tuning the intervention plan. A total of 48 corrective prompts and 12 risk warnings were generated throughout the process, all of which were addressed promptly, and related data gradually returned to a safe range. The compliance management and plan iteration optimization module, as the core of management, focused on resolving intervention adherence issues. Combining daily implementation feedback and weight change data, it completed periodic review assessments and iteratively updated the next day's plan framework. The system segmented intervention periods according to the pregnant woman's schedule, providing at least 5 reminders daily across multiple scenarios, and included a daily implementation feedback entry point where pregnant women could fill in completion status and subjective feeling scores. Overall statistics showed: the average daily compliance rate was 78.5% in early pregnancy, 89.2% in mid-pregnancy, and 92.3% in late pregnancy, with the subjective feeling score increasing from 3.8 in early pregnancy to 4.6 in late pregnancy. The system conducted weekly periodic weight management effectiveness reviews and assessments, optimizing the intervention plan based on weekly data and pregnant woman feedback.

[0067] A review at 12 weeks of pregnancy revealed poor exercise tolerance and a monotonous diet. The plan for weeks 13-16 was optimized by increasing daily exercise time to 22 minutes and enriching the diet with improved nutrient ratios. A review at 27 weeks of pregnancy showed post-dinner bloating. The plan for weeks 28-31 was optimized by delaying post-meal exercise and reducing gas-producing foods. A review at 37 weeks of pregnancy revealed bedtime hunger. The plan for weeks 38-40 was optimized by adding a low-calorie, high-nutrient bedtime snack and gentle stretching exercises. Throughout the process, 37 daily plan iterations and 12 weekly reviews were conducted, ensuring the intervention plan consistently met the individual needs of the pregnant woman. By week 40, the pregnant woman's weight was 86.3 kg, an increase of 7.8 kg from pre-pregnancy, well within the recommended weight gain range of 5.0-9.0 kg for obese pregnant women, achieving a 97.5% target weight gain rate. Her body fat percentage was 33.2%, only 1.1 percentage points higher than pre-pregnancy, indicating reasonable fluctuations. The mother and baby's health indicators were basically normal: systolic blood pressure was 138 mmHg, diastolic blood pressure was 88 mmHg, and fasting blood glucose was 5.3 mmol / L, all close to the safe threshold but not exceeding the standard; hemoglobin was 114 g / L, meeting the standards for pregnancy; the fetal biparietal diameter was 9.3 cm, femur length was 7.5 cm, and the newborn's birth weight was 3.6 kg, all within the normal range. No pregnancy complications or fetal abnormalities occurred throughout the entire pregnancy. Throughout the pregnancy, the system's five modules worked collaboratively to achieve precise assessment, personalized intervention, real-time tracking, and dynamic optimization, effectively solving the core challenge of weight management during pregnancy for obese pregnant women. This provided full-cycle intelligent protection for maternal and infant health, fully demonstrating the system's practicality and scientific rigor.

[0068] In summary, this application's embodiments utilize multi-dimensional standardized data collection, intelligent algorithm evaluation, dynamic personalized intervention, real-time risk warning, and compliance optimization. With complete data and precise monitoring throughout the process, it can strictly control weight gain within the medically recommended range, steadily manage core indicators such as body fat, blood pressure, blood sugar, and fetal development, significantly reduce the risks of adverse pregnancies such as gestational diabetes, hypertension, and macrosomia, continuously improve pregnant women's management compliance, and completely solve the pain points of traditional management being extensive, intervention lagging, monitoring fragmented, and programs homogenized. It not only safeguards maternal and infant safety and improves pregnancy outcomes throughout the process but also verifies the system's scientific validity, practicality, and scalability. It can provide a replicable intelligent model for home-based pregnancy self-monitoring and hospital maternal and child health clinical management, significantly improving the refinement, intelligence, and standardization of perinatal health management.

[0069] Next, referring to the accompanying drawings, a method for intelligent management of pregnancy weight assessment and intervention tracking based on an embodiment of this application is described.

[0070] like Figure 8 As shown, the steps of this intelligent management method for pregnancy weight assessment and intervention tracking are as follows: In step S101, the pregnant woman's weight and body composition data, dietary and exercise behavior data, and maternal and infant health index data throughout the entire pregnancy are obtained.

[0071] It is understood that the embodiments of this application comprehensively acquire the weight and body composition data, dietary and exercise behavior data, and maternal and infant health indicator data of pregnant women throughout the entire pregnancy cycle. This enables a complete, continuous, and multi-dimensional understanding of the pregnant woman's basic physical condition, lifestyle habits, and core information on maternal and infant health during pregnancy. It accurately depicts the patterns of changes in the pregnant woman's weight and body composition, as well as the characteristics of her dietary and exercise behaviors. Simultaneously, it anchors the baseline indicators of maternal and infant health, providing real and comprehensive raw data support for the subsequent construction of structured individual health records and the formation of standardized weight management monitoring datasets. This is the premise and foundation for scientific assessment of pregnancy weight, accurate risk identification, and the formulation of personalized intervention plans. It also provides key data assurance for the dynamic adjustment of subsequent intervention plans, model optimization and iteration, and quantitative evaluation of management effects, ensuring that the entire process of pregnancy weight management is based on evidence and accurately adapted.

[0072] In step S102, a structured individual health profile is constructed based on the pregnant woman's weight and body composition data, dietary and exercise behavior data, and maternal and infant health index data throughout the entire pregnancy cycle, using pregnancy-specific data association verification rules, and a standardized weight management monitoring dataset is generated.

[0073] Among them, the pregnancy-specific data association verification rules refer to a series of standardized conditions set up to verify the consistency, accuracy and rationality of pregnancy-specific data and its logical relationship with related clinical information.

[0074] It is understood that the pregnancy-specific data association verification rules in this application can combine the physiological characteristics of different gestational weeks, the pattern of weight change, and the logic of maternal and infant health association to conduct targeted verification, logical verification, and rationality screening of multi-source data such as body weight, body composition, diet, exercise, and maternal and infant health. This effectively eliminates abnormal, distorted, and contradictory data, ensuring that the data is true, accurate, and appropriate for the gestational stage. At the same time, it achieves standardized association and structured integration of multi-dimensional data, providing data quality assurance for building accurate individual health records and generating high-quality standardized weight management monitoring datasets. This avoids invalid data interfering with subsequent weight assessment, risk identification, and intervention plan formulation, thereby improving the scientificity and reliability of intelligent weight management throughout pregnancy.

[0075] In step S103, based on the standardized weight management monitoring dataset, a multi-dimensional weight health assessment adapted to the gestational week is carried out. Combined with the stage of the pregnancy cycle, a weight gain trend prediction curve is generated, and the risk of weight management during pregnancy is identified in real time, resulting in a personalized weight intervention plan.

[0076] Personalized weight intervention programs refer to comprehensive weight management plans that are tailored to an individual's physical condition, lifestyle, metabolic characteristics, and health goals, covering aspects such as diet, exercise, and behavioral adjustments.

[0077] It is understood that the personalized weight intervention program in this application can be tailored to the pregnant woman's gestational age, body weight and composition, dietary and exercise habits, and maternal and infant health indicators. This breaks the limitations of traditional uniform management and provides precise and individualized guidance for weight management during pregnancy. It can scientifically regulate the pace of weight gain in pregnant women, effectively avoid pregnancy risks caused by excessive or insufficient weight gain, and reduce the possibility of pregnancy complications while meeting the nutritional needs of the mother and the normal development of the fetus. At the same time, the program is tailored to the actual situation of pregnant women, highly feasible, and can significantly improve the compliance of pregnant women. It provides a clear and feasible basis for subsequent intervention tracking, dynamic adjustment, and effect evaluation, and truly achieves safe, efficient, and individualized full-process weight management during pregnancy, helping to optimize maternal and infant health outcomes.

[0078] It should be noted that conducting a multi-dimensional weight health assessment appropriate to the gestational week involves considering the stage of pregnancy, the physiological development characteristics of the pregnant woman in the early, middle, and late stages of pregnancy, official gestational weight gain standards, and individualized basic health status. This involves matching the corresponding gestational week's weight gain reference range and assessment dimensions with a standardized weight management monitoring dataset. The assessment considers multiple dimensions such as weight gain rate, changes in body composition, dietary energy intake, exercise energy expenditure, and the interrelationship between maternal and infant health indicators. This results in a stratified weight health assessment appropriate to the current gestational week, taking into account the key points of weight management and physiological changes during this stage of pregnancy, and completing a targeted and individualized comprehensive assessment of gestational weight health.

[0079] This system generates a predictive curve for weight gain trends and identifies real-time risks in weight management during pregnancy, resulting in personalized weight intervention plans. Supported by a standardized weight management monitoring dataset, and combined with the pregnant woman's pre-pregnancy BMI, gestational age, pregnancy stage, basic health status, and clinical weight gain guidelines, a personalized predictive curve for weight gain trends is generated by fitting a mathematical model of weight gain corresponding to the gestational age. Real-time data on weight, body composition, diet, exercise, and maternal and infant health are compared and analyzed against the predictive curve, the normal growth range for the same gestational age, and risk thresholds. The system intelligently identifies risks in weight management during pregnancy, such as excessively rapid weight gain, insufficient weight gain, abnormal growth rate, and body composition imbalance, and traces the corresponding dietary, exercise, or physiological triggers. Based on this, and considering risk level, gestational age characteristics, individual lifestyle habits, and maternal and infant health status, differentiated and executable personalized weight intervention plans are developed from dimensions such as dietary energy management, exercise prescriptions, monitoring frequency, lifestyle guidance, and medical early warning interventions.

[0080] For example, a pregnant woman carrying a singleton pregnancy at 22 weeks gestation had a pre-pregnancy BMI of 22.8 kg / m², which is within the normal weight range. By week 22, she had gained a total of 8.2 kg. Her daily calorie intake was 2400 kcal, with carbohydrates accounting for 63% of her energy, and dietary fiber 10g / day. She walked an average of 3000 steps daily and had no regular exercise during pregnancy. Her prenatal checkup showed blood pressure of 125 / 80 mmHg and fasting blood glucose of 4.8 mmol / L. Through a multi-dimensional weight health assessment, it was predicted that if this pregnant woman maintained her current lifestyle, her total weight gain at full term would exceed the upper limit recommended by guidelines, posing a risk of excessively rapid weight gain during pregnancy. Based on this, a personalized weight intervention plan was developed: daily total calorie intake controlled at 1900–2000 kcal, carbohydrate intake reduced to 48%, increased intake of high-quality protein and vegetables, dietary fiber increased to over 25g / day, daily walking at least 8500 steps, and 20 minutes of gentle prenatal exercise three times a week, with weekly weight gain controlled at 0.35–0.45 kg. The implementation progress of this personalized weight intervention program will be continuously tracked, and data on pregnant women's weight changes, diet and exercise implementation, and maternal and infant health dynamic indicators will be collected simultaneously. The intensity and implementation requirements of the intervention for weight management during pregnancy will be dynamically adjusted based on actual feedback. The collected data will be used to train the program to optimize the model, update the parameter weights of the multi-dimensional weight health assessment, and generate an intervention effect evaluation report.

[0081] In step S104, the implementation progress of the personalized weight intervention program for pregnant women is tracked, and feedback data on weight changes and dynamic data on maternal and infant health are collected synchronously during the implementation process. Based on the personalized weight intervention program and the feedback and dynamic data, the intervention intensity and implementation requirements for weight management during pregnancy are dynamically adjusted. The program optimization model is trained based on the feedback and dynamic data, an implementation effect evaluation report is generated, and the parameter weights of the multi-dimensional weight health assessment are updated.

[0082] Among them, the scheme optimization model refers to the method or process of finding the best solution under given constraints by establishing a mathematical model.

[0083] The formula is: in, The intensity of intervention in the current cycle; The intervention intensity will be dynamically adjusted for the next cycle; Weight deviation (weight deviation = (actual weight gain - standard gestational week weight gain) / standard gestational week weight gain); To measure the adherence rate to the intervention program; This is a maternal and infant health risk correction coefficient, with a value ranging from 0 to 1. This is the normalized adjustment coefficient; This is the normalized adjustment coefficient; The normalized adjustment coefficient satisfies the following conditions: ; To score the overall intervention effect; Assess the weights for each dimension; For the rate of achieving the target weight gain; Assess the weights for each dimension; Assess the weights for each dimension; This represents the risk value for weight management. For the first The first evaluation dimension Weighting of rounds; For the first The first evaluation dimension Weights after round update; The learning rate is η, and its value ranges from 0 to 1. The loss function is used to predict the effect. This represents the true value of the actual monitoring results; The effective sample size; The predicted performance value of the model; This represents the true value of the actual monitoring results; The sample number; The loss function is used to predict the effect.

[0084] It is understood that the optimization model of the embodiments of this application can continuously learn from the feedback of intervention execution, dynamic changes in weight, and data related to maternal and infant health, and continuously iterate and update the weight assessment parameters and intervention decision logic. It can adaptively optimize the intervention strategy according to the individual physiological changes of pregnant women and the actual implementation situation, effectively improving the accuracy of weight risk identification, intervention intensity control, and management effect evaluation. This makes the weight intervention during pregnancy more in line with individual differences and pregnancy changes, significantly improving the pertinence, scientificity, and practicality of weight management, and providing continuously optimized intelligent decision support for achieving safe and efficient intelligent control of pregnancy weight and ensuring maternal and infant health.

[0085] It should be noted that tracking the implementation progress of personalized weight intervention programs for pregnant women involves simultaneously collecting feedback data on weight changes and dynamic data on maternal and infant health during the implementation process. By establishing a tracking mechanism for the implementation of weight intervention during pregnancy, the entire process of dietary control, exercise implementation, weight monitoring, and lifestyle adherence in the personalized weight intervention program for pregnant women is tracked and recorded at each stage. The completion rate, adherence rate, and progress of each stage of the program are statistically analyzed in real time. Simultaneously, relying on smart wearable devices, mobile self-reporting, prenatal checkup data integration, and clinical data entry, the system continuously collects feedback data on weight changes, such as weight values, body composition changes, and weight gain rates, as well as dynamic data on maternal and infant health, including blood pressure, blood sugar, fundal height, abdominal circumference, and fetal development indicators. The above data is aggregated in real time, standardized, cleaned, and archived synchronously to form a continuous data stream for intervention implementation and health monitoring.

[0086] The intensity and implementation requirements of weight management interventions during pregnancy are dynamically adjusted. This involves combining personalized weight intervention plans, real-time weight change feedback data, and dynamic data on maternal and infant health. Based on the pregnant woman's current gestational week, the degree of weight gain deviation, the risk level of weight management, and the adherence to the intervention plan, adjustments are made according to the weight management adjustment guidelines corresponding to different stages of pregnancy. This involves tiered and adaptive adjustments to dietary intake control standards, exercise load, weight monitoring frequency, and health behavior implementation standards. While ensuring maternal and infant safety, the intensity of weight management interventions during pregnancy is increased or decreased accordingly, and the corresponding implementation requirements are refined or simplified. This ensures that the intensity and implementation requirements always align with the pregnant woman's real-time physical condition, actual ability to implement the intervention, and phased weight management goals.

[0087] Based on feedback data and dynamic data, the training scheme optimization model is used to generate an implementation effect evaluation report and update the parameter weights of the multi-dimensional weight health assessment. The collected weight change feedback data and maternal and infant health dynamic data are used as iterative learning samples, which are imported into the scheme optimization model to carry out data fitting, feature association, and reverse verification of intervention effects. Through multiple rounds of sample learning, the model's judgment rules and fitting ability are continuously trained and optimized. Quantitative analysis and comprehensive evaluation are carried out based on the achievement of weight control goals, the degree of intervention implementation compliance, and the magnitude of changes in maternal and infant health indicators, forming an implementation effect evaluation report that includes the intervention process, implementation results, problem analysis, and improvement directions. Combining the contribution of each influencing factor obtained from model training and the actual intervention effect, the parameter weights of each dimension involved in the multi-dimensional weight health assessment are calibrated and updated one by one to improve the individualization and accuracy of subsequent weight health assessments.

[0088] For example, the maternal and infant health indicators of multiple pregnant women, such as gestational weight changes, dietary intake, exercise adherence, blood glucose, and blood pressure, were input into the optimization model for iterative training. A typical sample of pregnant women aged 21-28 weeks with a pre-pregnancy BMI of 22.6 kg / m² was selected. Before intervention, these pregnant women had an average daily calorie intake of 2410 kcal and an average weekly weight gain of 0.61 kg. After implementing standardized intervention, their average daily calorie intake was controlled at 1920 kcal, and their average weekly weight gain stabilized at 0.40 kg. The model, through deep learning, quantifies the correlation between diet, exercise, weight, and health indicators. The weight of dietary calorie parameters was increased by 7.6%, and the weight of exercise adherence parameters was increased by 5.2%. The model also optimized the weight gain fitting logic by combining gestational age, body fat percentage, and blood glucose data, reducing the weight gain prediction error from 4.3% to 1.7%. The intervention threshold was adjusted for pregnant women with different adherence levels and gestational ages, and the parameter adaptation rules corresponding to body type and gestational age were refined, directly providing accurate algorithmic support for subsequent gestational weight intervention and risk prediction.

[0089] The intelligent management method for pregnancy weight assessment and intervention tracking proposed in this application, through a whole-pregnancy cycle data collection and standardized record-keeping module, achieves multi-dimensional collection of pregnant women's weight, body composition, diet, exercise, and maternal and infant health indicators throughout the entire pregnancy cycle. Based on pregnancy-specific verification rules, it constructs structured health records and standardized monitoring datasets, solving the pain points of fragmented and insufficiently standardized data in traditional pregnancy weight management, laying a data foundation for precise intervention. Through an intelligent weight assessment and intervention plan generation module, it completes the assessment of gestational week-appropriate weight gain trends, risk classification, and maternal and infant health-related impacts. Combined with a gestational week-adaptive meta-learning algorithm, it generates phased and daily personalized intervention plans, breaking through... This approach overcomes the limitations of traditional methods, such as homogeneity and poor gestational age adaptability. Through a real-time intervention tracking and risk warning module, it utilizes a comparative learning algorithm to achieve real-time evaluation and visual correction of intervention effectiveness. Combined with dynamic safety thresholds during pregnancy, it performs multi-dimensional dynamic data analysis, adjusting intervention intensity in stages and providing early warnings of maternal and infant health risks. This effectively prevents pregnancy complications and adverse fetal development problems caused by abnormal weight. Furthermore, through a compliance management and plan optimization module, it breaks down the intervention plan into different time periods, generating multi-scenario reminders to improve compliance. By combining pregnant women's feedback and weight change data, it performs periodic effect reviews and plan iterations, achieving refined and personalized management of pregnancy weight throughout the entire pregnancy cycle, effectively ensuring the health and safety of both mother and baby. This solves the problems of existing technologies, such as difficulty in adapting to the differentiated needs of different pregnant women and difficulty in responding to unexpected situations during pregnancy.

[0090] The following will illustrate a specific example of an intelligent management method for pregnancy weight assessment and intervention tracking, such as... Figure 9 As shown, it includes: The pregnant woman is 28 years old, a primiparous woman, 165cm tall, and weighed 58kg before pregnancy with a body mass index (BMI) of 21.3kg / m², which is within the normal range for pre-pregnancy weight. According to pregnancy weight management standards, a weight gain of 11.5-16kg is recommended throughout the entire pregnancy, with a recommended gain of 0.5-2kg in the first trimester (weeks 1-12) and a weight gain of 13-27kg in the second trimester. 6 The recommended weight gain is 0.3-0.5 kg per week during the first trimester (from week 28 of pregnancy to delivery). The pregnant woman should have no history of hypertension, diabetes, thyroid disease, or other pre-existing conditions, no family history of genetic diseases, regular menstrual cycles, a last menstrual period on March 10, 2025, and an expected delivery date of December 17, 2025. From the time of registration at 6 weeks of pregnancy, a comprehensive intelligent management method for pregnancy weight assessment and intervention will be used to achieve precise weight control throughout the entire pregnancy, ultimately leading to a smooth natural delivery and a safe delivery for both mother and baby.

[0091] The first step is to obtain the pregnant woman's weight and body composition data, dietary and exercise behavior data, and maternal and infant health indicator data throughout the entire pregnancy as the foundation for management. Intelligent management tools collect data through multi-terminal linkage. Weight and body composition data are collected once daily in the morning after emptying the bowels and bladder on an empty stomach using a smart body fat scale, simultaneously recording weight, body fat percentage, muscle mass, water content, and basal metabolic rate. Dietary and exercise behavior data are collected through a smart diet tracking app and a fitness tracker. The pregnant woman enters the types and amounts of food for her three meals and snacks in real time each day; the app automatically calculates calories and nutrient content. Exercise is automatically recorded by the fitness tracker, including type, duration, intensity, and calories burned. Maternal and infant health indicator data is supplemented by data imported from hospital prenatal checkups and home monitoring data.

[0092] The core data collected throughout the entire pregnancy cycle are as follows: At 6 weeks of pregnancy, weight was 58.2 kg, body fat percentage was 23.5%, muscle mass was 26.8 kg, basal metabolic rate was 1280 kcal / day, total daily calorie intake was 1510 kcal, 20 minutes of walking burned 85 kcal, blood pressure was 115 / 75 mmHg, fasting blood glucose was 4.8 mmol / L, blood routine was normal, progesterone was 28 ng / mL, hCG was 85000 mIU / mL, and ultrasound showed the gestational sac size was consistent with the gestational age. At 12 weeks of pregnancy, weight was 59.5 kg, a weight gain of 1.5 kg, body fat percentage was 24.1%, muscle mass was 26.7 kg, basal metabolic rate was 1300 kcal / day, average daily calorie intake in early pregnancy was 1550 kcal, average daily exercise was 22 minutes, and all prenatal checkup indicators were normal. At 20 weeks of pregnancy, the patient weighed 63.8 kg, with a cumulative weight gain of 5.8 kg, averaging 0.54 kg per week, slightly exceeding the recommended range for mid-pregnancy. Body fat percentage increased by 2.2 percentage points to 26.3%. Daily total calorie intake of 2100 kcal far exceeded the recommendation. Exercise was lacking. Fasting blood glucose was 5.3 mmol / L, slightly above the upper limit of normal for pregnancy, while 2-hour postprandial blood glucose was 7.8 mmol / L, within the normal range for pregnancy. Hemoglobin was 120 g / L, within the normal range for pregnancy. At 28 weeks of pregnancy, the patient weighed 67.5 kg, with a cumulative weight gain of 9.5 kg, averaging 0.46 kg per week, a slower rate of increase than before intervention. Body fat percentage was 27.8%. Fasting blood glucose of 5.6 mmol / L met the diagnostic criteria for gestational diabetes, while 2-hour postprandial blood glucose was 8.2 mmol / L, within the normal range. Gestational diabetes was diagnosed. Hemoglobin was 118 g / L, within the normal range for pregnancy. At 36 weeks of pregnancy, the patient weighed 71.2 kg, with a cumulative weight gain of 13.2 kg, averaging 0.46 kg per week, returning to the reasonable range for late pregnancy. Body fat percentage was 26.5%, a decrease of 1.3 percentage points. Blood sugar was well controlled, and hemoglobin was 122 g / L, remaining within the ideal range for pregnancy. At 40 weeks of pregnancy, the patient weighed 72.5 kg, with a cumulative weight gain of 14.5 kg, within the controllable range of the recommended weight gain for the entire pregnancy. Body fat percentage was 26.2%, and the fetal weight of 3300g met the conditions for natural delivery.

[0093] The second step involves constructing structured individual health records and generating standardized weight management monitoring datasets using pregnancy-specific data association verification rules. These verification rules cover three dimensions: data completeness, logical rationality, and gestational week suitability. Data completeness ensures a daily data collection rate of ≥95%. Logical rationality is assessed through algorithms to determine data correlation, such as the match between weight gain and calorie intake. Gestational week suitability is determined by comparing the data to normal reference ranges for different gestational weeks to assess whether the data aligns with physiological characteristics. The individual health records constructed based on these verification rules consist of a basic information module, a full-cycle data module, and a risk warning module. The basic information module clarifies gestational weight gain goals and required weight gain rates at each stage. The full-cycle data module categorizes data by gestational week to create a visualized data ledger. The risk warning module marks potential risks in real time. Simultaneously, a standardized dataset containing 6 core dimensions and 32 specific indicators is generated. Abnormal data is arranged chronologically by gestational week, with specific outliers and their causes annotated. The data completeness rate is 98.2%, and the accuracy rate is 99.5%.

[0094] The third step involves conducting a multi-dimensional weight and health assessment tailored to gestational weeks based on a standardized dataset. A weighted composite score is calculated across four dimensions: reasonableness of weight gain, balanced body composition, suitability of diet and exercise, and correlation with maternal and infant health. At 12 weeks of gestation, the assessment score was 88.7, indicating a good level with no risk of weight management issues. At 20 weeks of gestation, the score was 65, indicating a satisfactory level, but also identifying a moderate risk of excessively rapid weight gain and a mild risk of abnormal blood sugar levels. Without intervention, the cumulative weight gain by the due date would reach 16.6 kg, far exceeding the recommended upper limit. A personalized intervention plan was developed based on the 20-week assessment results, specifying that cumulative weight gain from 20 to 28 weeks of gestation (the remaining period of the second trimester) should be controlled within 4.0 kg, averaging ≤0.5 kg per week, fasting blood glucose should be controlled between 3.9 and 5.1 mmol / L, body fat percentage should be controlled below 27%, and hemoglobin should be maintained above 110 g / L. Dietary intervention quantifies the total daily calorie intake per meal to be controlled at 1550-1600 kcal, protein 80g, carbohydrates 150-180g, and fat 50-60g. High-sugar, high-oil, and high-salt foods are prohibited, and low-GI foods and high-quality protein are preferred. Exercise intervention includes 30 minutes daily, 7 times a week, mainly walking and prenatal yoga, with heart rate controlled at 120-140 beats / minute. Monitoring requires daily recording of weight, body composition, blood pressure, blood sugar, and fetal movement, with data synchronized every 4 weeks during prenatal checkups. At 28 weeks of gestation, the assessment score was 82 points, indicating a good condition. The cumulative weight gain from 20 to 28 weeks of gestation was 3.7 kg, averaging 0.46 kg per week, a significantly slower growth rate compared to before the intervention. Blood sugar levels decreased significantly, and hemoglobin remained within the normal range. For the intervention plan in late pregnancy, the cumulative weight gain during weeks 29-40 of pregnancy (the entire late pregnancy cycle) should be controlled within 5.0 kg, with an average of ≤0.42 kg per week, fasting blood glucose ≤5.1 mmol / L, daily total calories slightly adjusted to 1600-1650 kcal, DHA intake increased, exercise time 35 minutes, 7 times a week, Pilates added, and blood pressure monitoring increased to 3 times a day after week 36 of pregnancy.

[0095] The fourth step involves tracking the progress of the intervention plan, collecting feedback data synchronously, and dynamically adjusting the intensity of the intervention. At weeks 20-21 of pregnancy, the dietary adherence rate was only 75%, and the exercise adherence rate was 70%. The dietary plan was adjusted through app reminders and communication, changing the afternoon snack to unsweetened yogurt with blueberries, replacing rice with mixed grain rice for dinner, and splitting exercise into two 15-minute sessions. At weeks 22-23 of pregnancy, the adherence rates improved to 88% and 82%, respectively. Weight gain slowed, and blood sugar levels showed initial improvement. Carbohydrate intake was slightly adjusted to 160-170g, iron supplementation was increased, and exercise duration was increased to 35 minutes. At weeks 26-27 of pregnancy, the adherence rates reached 93% and 86%, respectively. Weight gain was close to the target, blood sugar was controlled within the normal range, and hemoglobin remained stable. Calorie intake was slightly adjusted, and the frequency of prenatal yoga was increased. Continued monitoring continued from weeks 29-40 of pregnancy. At weeks 33-34 of pregnancy, mild edema and slightly elevated blood pressure appeared. Salt intake was adjusted to 4g, and diuretic foods and leg massage were added, which alleviated the edema. During weeks 37-38 of pregnancy, the mother gained a cumulative weight of 0.7 kg, totaling 13.9 kg, which is within the reasonable range of the overall weight gain target for the entire pregnancy. Calorie intake was controlled below 1600 kcal, exercise was increased to 40 minutes, and the frequency of fetal heart rate monitoring was increased. Based on all feedback data, the model was optimized through training, and the correlation between intervention measures and indicators was analyzed. For example, when daily exercise was ≥30 minutes and carbohydrate intake was ≤170g, the fasting blood glucose control rate reached 92%. At 40 weeks of pregnancy, the mother successfully delivered a male infant naturally, weighing 3300g, with an Apgar score of 10. Blood pressure and blood glucose were normal 24 hours postpartum, with no complications. The generated implementation effect evaluation report showed that the overall diet adherence rate was 91.5%, the exercise adherence rate was 86.2%, the intervention plan was adjusted 4 times, the cumulative weight gain was 14.5 kg, the increase in body fat percentage was reasonable, gestational diabetes was well controlled through diet and exercise, and hemoglobin remained within the normal range throughout the pregnancy. Based on feedback data, the weights of multi-dimensional assessment parameters were updated, increasing the weight of diet adherence rate from 15% to 18%, exercise adherence rate from 10% to 12%, and blood glucose index from 8% to 10%, making the assessment model more in line with clinical practice.

[0096] In summary, the embodiments of this application, through real-time data collection from multiple terminals, structured record-keeping, multi-dimensional risk assessment, and dynamic iterative intervention, can identify high-risk pregnancy issues such as rapid weight gain, gestational diabetes, and anemia at an early stage. This allows for timely correction of health risks arising from improper diet and exercise, controlling gestational weight gain within a safe and manageable range, successfully reversing the risk of complications, ensuring maternal and infant safety, and achieving a smooth natural delivery. Simultaneously, a high-quality, standardized pregnancy health dataset is generated, and the assessment model is continuously optimized based on clinical feedback. This provides clinicians with a quantifiable, replicable, and implementable refined pregnancy weight management plan, which has significant practical and promotional value for improving the quality of prenatal care, preventing pregnancy complications, and optimizing delivery outcomes.

[0097] Figure 10A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 1001, the processor 1002, and the computer program stored on the memory 1001 and capable of running on the processor 1002.

[0098] When the processor 1002 executes the program, it implements the intelligent management method for pregnancy weight assessment and intervention tracking provided in the above embodiments.

[0099] Furthermore, electronic devices also include: Communication interface 1003 is used for communication between memory 1001 and processor 1002.

[0100] The memory 1001 is used to store computer programs that can run on the processor 1002.

[0101] The memory 1001 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0102] If the memory 1001, processor 1002, and communication interface 1003 are implemented independently, then the communication interface 1003, memory 1001, and processor 1002 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0103] Optionally, in a specific implementation, if the memory 1001, processor 1002, and communication interface 1003 are integrated on a single chip, then the memory 1001, processor 1002, and communication interface 1003 can communicate with each other through an internal interface.

[0104] The processor 1002 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of this application.

[0105] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent management method for pregnancy weight assessment and intervention tracking.

[0106] Furthermore, this application also provides a computer program product, including a computer program or instructions, which, when executed, implement the aforementioned intelligent management method for pregnancy weight assessment and intervention tracking.

[0107] In the description of this specification, the references to the terms "an embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0108] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of those features. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0109] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0110] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0111] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0112] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A smart management system for pregnancy weight assessment and intervention tracking, characterized in that, include: The system includes modules for collecting data throughout the entire pregnancy, establishing medical records, intelligent weight assessment and intervention plan generation, real-time intervention tracking and risk warning, and adherence management and iterative optimization of the plan. The whole pregnancy cycle data acquisition module is used to collect data on the pregnant woman's weight and body composition, diet and exercise behavior, and maternal and infant health indicators throughout the whole pregnancy cycle. The filing module is used to construct structured individual health records and generate standardized weight management monitoring datasets by using pregnancy-specific data association and verification rules. The intelligent weight assessment and intervention plan generation module is used to assess the weight gain trend of pregnant women according to gestational week, assess the risk classification of weight management, and assess the impact on maternal and infant health. It calls the preset pregnancy weight intervention plan library and generates personalized weight intervention plans for each gestational week and each day through the gestational week adaptive meta-learning algorithm. The real-time intervention tracking and risk warning module is used to evaluate the weight control effect of pregnant women in the process of implementing the intervention plan in real time through comparative learning algorithms. When the evaluation results exceed the appropriate range, a visual tracking and correction prompt is generated. At the same time, the module combines the dynamic safety threshold analysis of pregnancy to analyze the fluctuation of pregnant women's weight gain, changes in body composition, pregnancy complication indicators and fetal development data, and adjusts the intensity of intervention in a graded manner. The compliance management and program iteration optimization module is used to break down the daily execution time of the intervention program according to the pregnant woman's daily routine, generate multi-scenario reminders, and receive daily execution feedback and subjective feeling scores from the pregnant woman. It combines execution feedback and weight change data to complete the review and evaluation of the periodic weight control effect, and iteratively updates the basic framework of the program generated the next day based on the evaluation results.

2. The intelligent management system for pregnancy weight assessment and intervention tracking according to claim 1, characterized in that, The whole pregnancy cycle data acquisition module includes a weight and body composition data acquisition unit, a diet and exercise behavior data acquisition unit, and a maternal and infant health indicator data acquisition unit. Specifically, the weight and body composition data acquisition unit collects weight, body fat percentage, muscle mass, water percentage, and visceral fat level data for the pregnant woman throughout the entire pregnancy cycle; the diet and exercise behavior data acquisition unit collects daily nutritional intake, exercise type and duration, and sleep-wake cycle data for the pregnant woman throughout the entire pregnancy cycle; and the maternal and infant health indicator data acquisition unit collects gestational age, fetal development indicators, pregnancy complication-related indicators, and maternal physiological baseline maternal and infant health indicator data for the pregnant woman throughout the entire pregnancy cycle.

3. The intelligent management system for pregnancy weight assessment and intervention tracking according to claim 1, characterized in that, The filing module includes a pregnancy-specific data verification unit, a full-dimensional individual profile construction unit, and a monitoring dataset generation unit. The pregnancy-specific data verification unit verifies the physiological correlation fit of various data collected by the full pregnancy cycle data acquisition module based on pre-built physiological correlation rules during pregnancy, and generates correction prompts for abnormal data. The full-dimensional individual profile construction unit stores the verified full data by category, generating a structured individual health profile including baseline weight gain, baseline body composition, baseline fetal development, and baseline risk of pregnancy complications. The monitoring dataset generation unit integrates the verified full data collection to establish a standardized weight management monitoring dataset with timestamp alignment.

4. The intelligent management system for pregnancy weight assessment and intervention tracking according to claim 1, characterized in that, The intelligent weight assessment and intervention program generation module includes a weight grading assessment unit, an algorithm calculation unit, and an intervention program output unit. The weight grading assessment unit determines the appropriate weight gain range for the pregnant woman's gestational age based on her individual health record, and, in conjunction with the monitoring dataset, assesses the deviation of the weight gain trend, the associated risk of pregnancy complications, and the intervention tolerance, outputting a weight management risk level. The algorithm calculation unit adjusts the dietary nutrient ratio, exercise program parameters, and monitoring frequency using a gestational age adaptive meta-learning algorithm, prioritizing intervention types with high historical compliance and good weight management effects for the pregnant woman. The intervention program output unit, based on the dietary, exercise, and monitoring parameters, and combined with a pre-built gestational weight intervention program library and historical behavioral energy consumption data, generates a daily intervention program including customized daily meal plans, personalized exercise guidance, a weight monitoring plan, and key risk management points, simultaneously outputting a gestational age weight gain trend prediction curve.

5. The intelligent management system for pregnancy weight assessment and intervention tracking according to claim 1, characterized in that, The real-time intervention tracking and risk warning module includes an execution deviation and effect evaluation unit, a visual tracking and correction unit, a risk grading and warning unit, and an intervention intensity adjustment unit. The execution deviation and effect evaluation unit uses a comparative learning algorithm to calculate the deviation between the pregnant woman's daily weight gain, dietary nutrient intake, exercise execution data, and the intervention plan template, quantifying the degree of matching between the executed behavior and the plan requirements, and conducting real-time weight management execution effect evaluation. The visual tracking and correction unit displays weight gain deviation, nutrient intake deficit, exercise execution completion rate, and real-time evaluation results on the pregnant woman's mobile device through dynamic trend charts, simultaneously outputting voice prompts and text correction guidance. The risk grading and warning unit dynamically sets safe ranges for weight gain, body composition changes, and blood sugar and blood pressure indicators based on dynamic safety thresholds during pregnancy, combined with the pregnant woman's individual weight gain baseline, fetal development indicators, gestational age, and complication risk level. Exceeding these ranges triggers a corresponding weight management risk level warning. The intervention intensity adjustment unit adjusts the strictness of dietary control, exercise intensity and duration, monitoring frequency, or activates a complication-specific intervention plan based on the risk level.

6. The intelligent management system for pregnancy weight assessment and intervention tracking according to claim 1, characterized in that, The compliance management and program iteration optimization module includes a time-segmentation unit, a multi-scenario reminder execution unit, a feedback receiving unit, and an evaluation and program iteration unit. The time-segmentation unit divides the daily intervention plan into multiple time periods—diet, exercise, and weight monitoring—based on the pregnant woman's recorded daily routine, with each time period corresponding to a specific task. The multi-scenario reminder execution unit generates vibration and pop-up reminders according to set time periods, triggering ringtones and SMS alerts if no response is received. The feedback receiving unit provides a scoring interface, including four dimensions: program completion rate, diet suitability, exercise fatigue, and feedback on physical discomfort, for receiving text notes and data supplements. The evaluation and program iteration unit combines execution feedback data with weight change monitoring results to conduct a periodic weight management effectiveness review and evaluation, analyze the correlation between execution compliance, evaluation results, and intervention measures, identify core factors affecting the effectiveness and safety of weight management, iteratively update the basic framework for generating intervention plans for the next day and subsequent gestational weeks, and archive historical plans, evaluation data, and weight data for retrospective querying.

7. A method for intelligent management of gestational weight assessment and intervention tracking applied to any one of claims 1-6, characterized in that, The method includes: Obtain pregnant women's weight and body composition data, dietary and exercise behavior data, and maternal and infant health index data throughout the entire pregnancy cycle; By using pregnancy-specific data association and verification rules, a structured individual health profile is constructed based on the pregnant woman's weight and body composition data, dietary and exercise behavior data, and maternal and infant health indicator data throughout the entire pregnancy cycle, and a standardized weight management monitoring dataset is generated. Based on the standardized weight management monitoring dataset, a multi-dimensional weight health assessment adapted to gestational week is carried out. Combined with the stage of the pregnancy cycle, a weight gain trend prediction curve is generated, and the risk of weight management during pregnancy is identified in real time, resulting in a personalized weight intervention plan. The implementation progress of the personalized weight intervention program for pregnant women is tracked, and feedback data on weight changes and dynamic data on maternal and infant health are collected synchronously during the implementation process. Based on the personalized weight intervention program and the feedback and dynamic data, the intensity and implementation requirements of the weight management intervention during pregnancy are dynamically adjusted. The program optimization model is trained based on the feedback and dynamic data, an implementation effect evaluation report is generated, and the parameter weights of the multi-dimensional weight health assessment are updated.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the intelligent management method for pregnancy weight assessment and intervention tracking as claimed in claim 7.

9. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When a computer program or instruction is executed, it implements the intelligent management method for pregnancy weight assessment and intervention tracking as claimed in claim 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, When a computer program or instruction is executed, it implements the intelligent management method for pregnancy weight assessment and intervention tracking as claimed in claim 7.

Images