A target user state monitoring method, medium and device

Abstract

The present application relates to the technical field of health monitoring and data processing, in particular to a target user state monitoring method, medium and equipment, the method comprising: acquiring morphological changes and physiological quantitative data of the current period; according to the monitoring period stage attribute, generating body shape change characteristics by calculating the difference value of the initial / previous period data and the morphological change data through the first preset model; outputting dynamic body shape parameters combined with the period stage; adjusting the weight of the initial / previous period data comparison result through the second preset model with the parameter as feedback; outputting the associated state dynamic digital evaluation result by fusing the comparison result through the third preset model; and outputting the monitoring prompt by comparing the preset threshold. The method improves the monitoring accuracy and meets the personalized needs.

Description

Technical Field

[0001] This invention relates to the field of health monitoring and data processing technology, and in particular to a method, medium, and device for monitoring the status of a target user. Background Technology

[0002] With the increasing awareness of health management, continuous and accurate monitoring of the status of target users (such as people with special menstrual cycles) has become a demand. Such monitoring requires the collection and analysis of morphological change data (such as weight and body circumference) and physiological quantitative data (such as heart rate and blood pressure), combined with the characteristics of the cycle stage to output assessment results, providing a basis for health management. In some scenarios, exercise guidance is also required to assist in the adjustment of status.

[0003] Patent document (CN119405309A) discloses a method and system for monitoring user health status based on smart wearable devices. This method responds to the current operating mode of the user-selected smart wearable device, determines a data collection strategy, collects target physiological data, and then obtains the target health level through a multi-dimensional health status index grading model, constructing a health status monitoring report. However, in terms of model application, this method relies solely on a single grading model to process data, without constructing a multi-model collaborative mechanism. It lacks a feature extraction model based on time-series data difference analysis, as described in this invention, for accurately analyzing body shape change characteristics; nor does it introduce a dynamic weight allocation model when evaluating related states. It simply uses fixed weights to fuse data comparison results, ignoring the feedback effect of dynamic body shape parameters on the evaluation logic. This results in a significant deviation between the dynamic digital evaluation results of related states and the actual state, making it difficult to meet the stringent requirements of accurate monitoring.

[0004] In terms of patented technologies related to exercise guidance, existing technologies generally have shortcomings. For example, no patent has yet established a complete mapping relationship between "cycle stage and exercise threshold," making it impossible to dynamically generate quantitative parameters of exercise amplitude (such as cadence, limb movement angle thresholds, etc.) based on the target user's current cycle stage and body shape changes. Furthermore, exercise guidance information is often based solely on general standards and does not link to the target user's historical exercise data, resulting in a lack of personalization in exercise guidance. This can easily lead to problems such as unsuitable exercise intensity or missing reminders of exercise contraindications, failing to effectively assist users in adjusting their own state through exercise within a safe range.

[0005] Furthermore, from the perspective of data integration and feedback, although health monitoring devices can collect user medical data and process, analyze, and store it on cloud servers, the data processing flow does not form a tight closed loop. After collecting data, only a single type of parameter is output, without using dynamic body shape parameters as feedback factors to optimize subsequent evaluation weights, nor comparing the dynamic numerical evaluation results of the associated status with preset monitoring thresholds to trigger tiered prompts. Ultimately, this results in a disjointed monitoring process, making it difficult to provide timely warnings of abnormal states or deliver effective health advice to users.

[0006] In summary, existing technologies have significant shortcomings in areas such as data comparison logic, model collaboration, exercise guidance adaptability, and process closure. There is an urgent need for a status monitoring method that can dynamically select comparison benchmarks based on periodic stage attributes, improve evaluation accuracy through multiple preset models, and provide personalized exercise guidance to fill the technological gap and meet the precise health monitoring needs of target users. Summary of the Invention

[0007] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows:

[0008] According to a first aspect of the present invention, a method for monitoring the status of a target user is provided, comprising the following steps:

[0009] Acquire current period data collected by a data acquisition device. The current period data includes the morphological changes and physiological quantitative data of the target user within the current monitoring period.

[0010] Based on the first preset model and the stage attributes of the current monitoring period, the morphological change data in the current period data is selectively compared with the body shape data of the initial period or the previous monitoring period to calculate the difference and generate the current body shape change characteristics.

[0011] Based on the current characteristics of body shape changes and the current monitoring period of the target user, output dynamic body shape parameter numerical results.

[0012] Based on the second preset model, the weights of the first comparison result and the second comparison result are dynamically adjusted using the dynamic body shape parameter numerical results of the current monitoring period as feedback factors. The first comparison result is the comparison result between the initial period data and the current period data, and the second comparison result is the comparison result between the previous monitoring period data and the current period data.

[0013] Based on the third preset model, the first comparison result and the second comparison result are fused and calculated to output the dynamic digital evaluation result of the target user's association status.

[0014] The dynamic digital evaluation result of the associated status is compared with the preset monitoring threshold, and the corresponding status monitoring prompt information is output according to the comparison result.

[0015] According to a second aspect of the present invention, an electronic device is provided, including a processor and a memory; the processor executes the steps of the method described in the first aspect of the present invention by invoking a program or instructions stored in the memory.

[0016] According to a third aspect of the present invention, a computer-readable storage medium is provided that stores a program or instructions that cause a computer to perform the steps of the method described in the first aspect of the present invention.

[0017] The present invention has at least the following beneficial effects:

[0018] 1. Optimize data comparison logic and improve feature extraction accuracy: Based on the first preset model, combined with the selective matching comparison benchmark (initial cycle / previous cycle data) of the monitoring cycle stage attributes, the rigidity of the existing technology comparison mode is solved, and the body shape change characteristics of different stages are accurately captured, providing a reliable data foundation for subsequent evaluation.

[0019] 2. Multi-model collaboration improves assessment accuracy: The second preset model uses dynamic body shape parameters as feedback to adjust the weight of the comparison results, and the third preset model performs fusion calculations, breaking the limitations of a single model and making the dynamic digital assessment results of the associated state more in line with reality, reducing the deviation from the true state.

[0020] 3. Form a complete monitoring closed loop and enhance the timeliness of early warning: From data collection to evaluation result generation, and then to comparison with preset thresholds and output prompts, a complete process is constructed to avoid the monitoring gap problem of existing technologies, and to provide timely early warning of anomalies, thus providing effective support for health management.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a target user status monitoring method provided in an embodiment of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0026] It should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processes, many of these steps can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the steps can be rearranged. A process can be terminated when its operation is complete, but it may also have additional steps not included in the figures. A process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0027] This invention provides a method for monitoring the status of a target user, such as... Figure 1 As shown, the steps may include the following:

[0028] S100, acquire the current cycle data collected by the data acquisition device, wherein the current cycle data is the morphological change data and physiological quantitative data of the target user in the current monitoring cycle.

[0029] In this embodiment of the invention, the target users are specific groups of people who need to undergo periodic health monitoring, such as people in a special physiological cycle. In one illustrative embodiment, the target users are users whose weight increases in stages and whose trunk circumference continuously expands due to the development of a related life form (i.e., fetus) during a preset physiological cycle (i.e., pregnancy), accompanied by regular changes in specific physiological indicators such as heart rate, blood pressure, and fetal heart rate. Specifically, the target users are pregnant women. For this type of user, the data collection frequency of the data acquisition device can be dynamically adjusted according to the stage of pregnancy. For example, data collection is set to once a day in the first trimester (weeks 1-12), twice a day in the second trimester (weeks 13-27), and three times a day in the third trimester (weeks 28 to delivery). The elastic fabric of the adjustable body circumference monitoring belt is made of highly breathable material to avoid skin stuffiness and discomfort during pregnancy. At the same time, all data acquisition devices used for pregnant women must pass medical device safety certification (such as FDA Class I or NMPA Class I medical device certification) to ensure that the use of the device poses no health risks to the pregnant woman and the fetus.

[0030] In this embodiment of the invention, the morphological change data is a set of quantitative data reflecting the dynamic changes in the body shape of the target user, specifically including the target user's weight change (unit: kg, accurate to 0.1 kg), limb morphological changes (including changes in upper arm circumference, forearm circumference, lower thigh circumference, and calf circumference, unit: cm, accurate to 0.1 cm), trunk morphological changes (including changes in trunk anteroposterior diameter and lateral diameter, unit: cm, accurate to 0.1 cm), and body circumference changes (including changes in waist circumference and abdominal circumference, unit: cm); the physiological quantitative data is a set of quantitative data reflecting the target user's physiological functional state, specifically including heart rate (unit: beats / minute, accurate to 1 beat / minute), blood pressure (including systolic and diastolic blood pressure, unit: mmHg, accurate to 1 mmHg), blood oxygen saturation (unit: %, accurate to 1%), and quantitative values ​​of body composition, including body fat percentage, muscle mass, and body water percentage.

[0031] In an illustrative embodiment of the present invention, the data acquisition device is a multi-device collaborative acquisition system, specifically including wearable devices, vital sign monitoring devices, and morphological measurement devices. Each device establishes a data interaction link with the back-end data processing terminal through a wireless communication module (such as Bluetooth, Wi-Fi, LoRa) to achieve real-time transmission or periodic uploading of the acquired data. The wearable devices include, but are not limited to, smart bracelets, smartwatches, retractable limb morphological monitoring bracelets, and adjustable body circumference monitoring straps.

[0032] Smart bracelets / watches collect heart rate and blood oxygen saturation data of target users in real time through built-in optical sensors and pressure sensors, with a sampling frequency of 1Hz-5Hz to ensure the continuity of physiological data;

[0033] Regarding the equipment for collecting systolic blood pressure, diastolic blood pressure, and body composition data: While current mainstream consumer-grade smart bracelets can estimate blood pressure using photoelectric sensors or PPG (photoplethysmography) technology, the measurement error is typically greater than ±10 mmHg due to factors such as wearing tightness and skin condition (e.g., pregnancy edema), which cannot meet the accuracy requirements for medical-grade monitoring (within ±5 mmHg). Basal metabolic rate and respiratory quotient require calculations based on oxygen consumption and carbon dioxide production, relying on gas exchange sensors. Bracelets, limited by size and power consumption, cannot integrate these components. Therefore, dedicated vital sign monitoring equipment (electronic blood pressure monitor, body composition analyzer) is needed to collect the data, ensuring that the data accuracy meets the medical reference requirements for pregnancy health monitoring.

[0034] Extendable limb morphology monitoring wristband: This wristband is made of elastic conductive material (such as conductive silicone) and has a built-in strain resistance sensor and data storage module. When in use, it is worn on the middle of the upper arm, middle of the forearm, middle of the thigh, and middle of the calf of the target user (one wristband for each limb, for a total of four). The wristband detects its own expansion and contraction in real time through the strain resistance sensor. When the limb morphology changes (such as the circumference increases or decreases), the wristband expands and contracts synchronously with the limb circumference, and the resistance value of the strain resistance changes accordingly. The background data processing terminal automatically calculates the circumference data of each part of the limb based on the preset "resistance change - circumference change" calibration formula (this formula is calibrated through a standard phantom, such as a 10Ω change in resistance corresponding to a 0.1cm change in circumference). The amount of limb morphology change is generated by the difference between the current period circumference data and the historical period circumference data. The acquisition accuracy is ±0.2cm, which meets the needs of morphological change monitoring.

[0035] Regarding the correlation between trunk circumference and limb morphological changes: There is no fixed physiological correlation between trunk circumference (such as waist circumference and abdominal circumference) and limb morphological changes. The expansion of trunk circumference during pregnancy is mainly due to the enlargement of the uterus and the accumulation of abdominal fat, while changes in limb circumference may be affected by factors such as edema and muscle mass adjustment. There is no linear correlation between the trends of the two (for example, some pregnant women may only have an increase in abdominal circumference, with no significant change in limb circumference). If trunk data is inferred from changes in limb morphology, the error will exceed ±1cm, which cannot meet the accuracy requirements of trunk circumference for fetal growth and development assessment (within ±0.5cm). Therefore, it is necessary to directly collect trunk data through an adjustable body circumference monitoring belt to ensure data accuracy.

[0036] Adjustable Body Measurement Bands: These bands are made of breathable elastic fabric (such as spandex blends) and are 3cm-5cm wide to enhance wearing comfort. They incorporate flexible strain sensors and a miniature data transmission module. During use, they are wrapped around the waist and abdomen (one band for each measurement location, four in total). The bands have Velcro adjustment at both ends to flexibly adjust the tightness according to changes in body measurement during pregnancy, ensuring a close fit between the sensor and skin without pressure. The flexible strain sensors detect the stretching of the bands and convert it into an electrical signal. The backend data processing terminal uses this signal to transmit data. The "elongation-circumference value" mapping algorithm (which is calibrated using standard rings of different sizes, such as an increase of 0.1cm in circumference for every 1mm increase in elongation) calculates the circumference data of each torso position in real time. The changes in torso shape (including changes in waist circumference, abdominal circumference, and changes in the front-to-back and left-to-right diameters of the torso) are generated by the difference between the current period's circumference data and the historical period's circumference data and a geometric conversion formula. The acquisition accuracy reaches ±0.2cm, and the fabric material meets the skin contact safety standards (such as the EU REACH regulation and China GB / T18885-2020) to avoid causing skin allergies in pregnant women.

[0037] The vital signs monitoring equipment includes an electronic blood pressure monitor and a body composition analyzer. The electronic blood pressure monitor uses the oscillometric method to collect the target user's systolic and diastolic blood pressure data. The collection cycle is synchronized with the current monitoring cycle (e.g., 1-3 times per day, with automatic generation of blood pressure quantification values ​​and a collection timestamp after each collection). The measurement accuracy meets international standards (±3 mmHg). The body composition analyzer uses bioelectrical impedance analysis to detect the target user's body fat percentage, muscle mass, body water percentage, bone mass, and other body composition quantification values. During the collection process, the target user must stand barefoot and fasting in the detection area of ​​the device. The device scans various body tissues with multi-frequency current and outputs body composition data after calculation by the built-in algorithm.

[0038] The morphological measurement device includes a smart body fat scale: the smart body fat scale collects the target user's weight data through bioelectrical impedance analysis, and outputs related data such as body fat percentage and muscle mass. The weight change is automatically calculated by the difference between the current period's weight data and the historical period's weight data.

[0039] S200, based on the first preset model and the stage attributes of the current monitoring period, selectively calculates the difference between the morphological change data in the current period data and the body shape data of the initial period or the previous monitoring period to generate the current body shape change characteristics.

[0040] In this embodiment of the invention, the first preset model is a feature extraction model based on time series data difference analysis. Its core function is to dynamically select appropriate benchmark data (initial cycle data or body shape data of the previous monitoring cycle) according to the stage attributes of the target user's current monitoring cycle, and extract quantitative features that can reflect the target user's body shape change trend through multi-dimensional difference calculation. The model architecture includes a stage attribute judgment module, a benchmark data selection module, and a difference feature calculation module. Each module works together to achieve accurate generation of body shape change features.

[0041] The stage attribute judgment module is used to identify the stage attribute of the target user's current monitoring period. The stage attribute division is determined based on the target user's monitoring scenario and physiological cycle characteristics. Taking pregnant women as an example, the stage attribute is divided into early pregnancy (weeks 1-12), mid-pregnancy (weeks 13-27), and late pregnancy (weeks 28 to delivery) based on gestational week. For patients with chronic diseases (such as diabetic patients), the stage attribute can be divided into blood sugar stabilization period and fluctuation adjustment period based on the disease control stage. For postoperative recovery groups, the stage attribute can be divided into postoperative recovery period (weeks 1-4 postoperatively), functional training period (weeks 5-12 postoperatively), and rehabilitation consolidation period (weeks 13 and beyond postoperatively) based on the rehabilitation process.

[0042] The criteria for determining the stage attribute include: the cumulative number of historical monitoring cycles of the target user, such as the trend of physiological quantitative data changes in the first 12 cycles from the initial monitoring, corresponding to the early pregnancy and pre-pregnancy stages, such as blood glucose fluctuations exceeding 10% for 3 consecutive cycles, which are then determined to be a fluctuation adjustment period; and the scenario tags entered by the user, such as the current gestational week actively entered by the pregnant woman. The stage attribute determination module compares the above information with the preset "cycle-stage" mapping table and outputs the stage attribute classification result of the current monitoring cycle, such as "3rd week of mid-pregnancy" or "blood glucose fluctuation adjustment period".

[0043] The benchmark data selection module is used to filter suitable benchmark data from the backend database based on the output of the stage attribute judgment module. The filtering logic is preset in the model, and the specific rules are as follows:

[0044] When the current monitoring period belongs to the initial stage (e.g., the first 4 weeks of pregnancy for a pregnant woman), the initial period data is selected as the baseline data. The initial period data consists of morphological change data (including initial weight, initial limb circumference, and initial trunk circumference) collected when the target user first begins monitoring. This data is verified by the backend terminal (e.g., outliers are removed, and missing items are filled) and then stored as the baseline dataset. This serves as a reference benchmark for judging body shape changes in the initial stage, avoiding comparison bias caused by insufficient data accumulation in the early stages.

[0045] When the current monitoring period is in a stable change phase (e.g., mid-pregnancy) or a rapid change phase (e.g., late pregnancy), body shape data from the previous monitoring period is selected as the baseline data. The body shape data from the previous monitoring period consists of morphological change data collected within the preceding complete monitoring period adjacent to the current period, and must meet the requirement of "data integrity ≥ 90%" (i.e., the number of times each morphological indicator is collected within that period is not less than 90% of the preset collection frequency). If the data integrity of the previous period does not meet the standard, the data from the two preceding periods with satisfactory data integrity will be automatically backtracked as the baseline, and the data backtracking record will be marked to ensure the reliability of the baseline data.

[0046] The difference feature calculation module is used to perform dimension-by-dimensional difference calculations between the morphological change data in the current period data and the benchmark data determined by the benchmark data selection module, generating multi-dimensional body shape change feature parameters. The specific calculation process is as follows:

[0047] First, perform data alignment processing on the current cycle pattern change data and the benchmark data to ensure that the indicator dimensions and collection time nodes (such as data collected at fixed time periods every day) are consistent. For example, compare the "daily average upper arm circumference" of the current cycle with the "daily average upper arm circumference" in the benchmark data to avoid calculation errors caused by mismatch in data dimensions.

[0048] Secondly, differentiated difference calculation methods are used for different morphological indicators:

[0049] For absolute numerical indicators such as changes in weight, changes in limb circumference, and changes in trunk circumference, the absolute difference between the current period data value and the baseline data value is used for calculation, and the output result is retained to one decimal place. For example, if the current upper arm circumference is 32.5cm and the baseline upper arm circumference is 30.2cm, the difference is +2.3cm.

[0050] For relative change indicators such as body circumference growth rate and weight change rate, the relative difference is calculated as (current period data value - baseline data value) / baseline data value × 100%, and the output is rounded to two decimal places. For example, if the current weight is 65.0 kg and the baseline weight is 60.0 kg, the weight change rate is +8.33%.

[0051] Finally, the difference calculation results of each dimension are integrated into the current body shape change feature. This feature is used to characterize the multi-dimensional quantitative feature set of the target user's dynamic body shape change, which specifically includes absolute change feature, relative change feature and trend change feature.

[0052] Among them, the absolute change feature is the absolute difference between the current cycle morphological change data and the baseline data, which is used to directly reflect the actual increase or decrease in the target user's body shape indicators, and specifically includes the following sub-features:

[0053] Absolute weight change: The difference between the average weight of the current period and the average weight of the baseline period, expressed in kilograms (kg). The data is rounded to one decimal place. The formula is "Absolute weight change = Average weight of the current period - Average weight of the baseline period". If the difference is positive, it means that the weight has increased compared to the baseline period. If the difference is negative, it means that the weight has decreased (e.g., if the average weight of the current period is 62.3 kg and the average weight of the baseline period is 60.1 kg, the absolute weight change is +2.2 kg).

[0054] Absolute changes in limb circumference: including absolute changes in upper arm circumference, forearm circumference, thigh circumference, and calf circumference. Each sub-feature is the difference between the average circumference of the corresponding part in the current period and the average circumference of the corresponding part in the baseline period, in centimeters (cm). The data is kept to one decimal place. The calculation formula is "Absolute change in circumference of a part = Average circumference of that part in the current period - Average circumference of that part in the baseline period" (e.g., if the average upper arm circumference in the current period is 32.5cm and the average upper arm circumference in the baseline period is 30.8cm, the absolute change in upper arm circumference is +1.7cm).

[0055] Absolute change in trunk circumference: including absolute change in waist circumference and absolute change in abdominal circumference. The calculation method for each sub-feature is the same as that for absolute change in limb circumference. The unit is centimeters (cm). The data precision is retained to one decimal place. It is used to reflect the actual increase or decrease in the circumference of key parts of the trunk (e.g., the average abdominal circumference in the current period is 92.4cm, the average abdominal circumference in the baseline period is 88.6cm, and the absolute change in abdominal circumference is +3.8cm).

[0056] Absolute changes in trunk morphology: This includes the absolute changes in the anteroposterior diameter and the absolute changes in the lateral diameter of the trunk. It is calculated by the difference between the measured values ​​of the anteroposterior diameter / lateral diameter of the trunk in the current period and the corresponding measured values ​​in the baseline period. The unit is centimeters (cm), and the data is kept to one decimal place. It is used to characterize the changes in the three-dimensional morphology of the trunk (e.g., the average anteroposterior diameter of the trunk in the current period is 28.3cm, the average anteroposterior diameter of the trunk in the baseline period is 26.5cm, and the absolute change in the anteroposterior diameter of the trunk is +1.8cm).

[0057] The relative change characteristic is the rate of change of the current cycle morphological change data relative to the baseline data. It is used to reflect the relative increase or decrease of the target user's body shape indicators, eliminating the influence of the initial value difference of the baseline data on the judgment of the change magnitude. Specifically, it includes the following sub-features:

[0058] Relative weight change rate: The ratio of the absolute change in weight to the average weight of the baseline period, expressed as a percentage (%). The data is rounded to two decimal places. The formula is "Relative weight change rate = (absolute weight change / average weight of the baseline period) × 100%" (e.g., if the absolute weight change is +2.2kg and the average weight of the baseline period is 60.1kg, the relative weight change rate is +3.66%).

[0059] Relative change rate of limb circumference: including relative change rate of upper arm circumference, relative change rate of forearm circumference, relative change rate of thigh circumference, and relative change rate of calf circumference. Each sub-feature is the ratio of the absolute change in circumference of the corresponding part to the mean circumference of the corresponding part in the baseline period, expressed as a percentage (%). The data is kept to two decimal places. The calculation formula is "relative change rate of circumference of a part = (absolute change in circumference of the part / mean circumference of the part in the baseline period) × 100%" (e.g., if the absolute change in upper arm circumference is +1.7cm, and the mean upper arm circumference in the baseline period is 30.8cm, the relative change rate of upper arm circumference is +5.52%).

[0060] Relative change rate of trunk circumference: including relative change rate of waist circumference and relative change rate of abdominal circumference. The calculation method is the same as that of relative change rate of limb circumference, expressed as a percentage (%). The data accuracy is retained to two decimal places (e.g., absolute change of abdominal circumference +3.8cm, mean abdominal circumference of the baseline period is 88.6cm, and the relative change rate of abdominal circumference is +4.29%).

[0061] Trend change characteristics are generated through statistical analysis based on body shape change data from the current period and several previous consecutive monitoring periods. They reflect the overall trend (e.g., increasing, decreasing, or stable) of the target user's body shape changes and specifically include the following sub-features:

[0062] Continuous period weight change trend value: Take the absolute weight change of the current period and the previous two monitoring periods, calculate the arithmetic mean of the three, in kilograms (kg), and keep one decimal place. The calculation formula is "Continuous period weight change trend value = (absolute weight change in the current period + absolute weight change in the previous period + absolute weight change in the previous two periods) / 3". If the mean value is positive and increases with each period, it means that the weight is increasing at an accelerated rate. If the mean value is close to 0, it means that the weight change is stable (e.g., the absolute weight change in the current period is +2.2kg, the previous period is +1.8kg, the previous two periods are +1.5kg, and the continuous period weight change trend value is +1.8kg).

[0063] Continuous cycle abdominal circumference change trend value: Take the absolute change in abdominal circumference of the current cycle and the previous two monitoring cycles, calculate the arithmetic mean, and the unit is centimeters (cm). The data precision is retained to one decimal place. The calculation method is the same as the continuous cycle weight change trend value. It is used to reflect the change trend of key parts of the trunk in scenarios such as pregnancy (e.g., the absolute change in abdominal circumference in the current cycle is +3.8cm, the previous cycle is +3.2cm, the previous two cycles are +2.9cm, and the continuous cycle abdominal circumference change trend value is +3.3cm).

[0064] Body shape change stability coefficient: Based on the relative change rate of weight and the relative change rate of waist circumference in the current period and the previous two monitoring periods, calculate the coefficient of variation (the ratio of standard deviation to mean) of each indicator, and then take the arithmetic mean of each coefficient of variation. The data precision is retained to 3 decimal places. The calculation formula is "body shape change stability coefficient = (coefficient of variation of relative change rate of weight + coefficient of variation of relative change rate of waist circumference) / 2". The smaller the coefficient, the more stable the body shape change. The coefficient is greater than 0.1, which means that the body shape change fluctuates greatly (e.g., the coefficient of variation of relative change rate of weight is 0.082, the coefficient of variation of relative change rate of waist circumference is 0.065, and the body shape change stability coefficient is 0.074).

[0065] In this embodiment of the invention, the current body shape change characteristics are stored and transmitted in the form of a structured data set of "feature-value-unit", for example: {"absolute change in weight": "+2.2kg", "relative change rate of upper arm circumference": "+5.52%", "continuous cycle abdominal circumference change trend value": "+3.3cm", "body shape change stability coefficient": "0.074"}; all feature values ​​are verified by data (outliers that exceed the reasonable range are removed, such as when the absolute change in weight is greater than ±5kg, they are marked as outliers and recalculated) to ensure the accuracy and validity of the feature data and provide reliable input for the subsequent generation of dynamic body shape parameters.

[0066] To ensure the accuracy of the model's difference calculation and the rationality of the benchmark selection, the first preset model needs to be pre-trained and iteratively optimized using the target user's historical monitoring data:

[0067] The training dataset uses historical morphological change data of target users in the same scenario (such as morphological monitoring data of 1,000 pregnant women during pregnancy and morphological monitoring data of 500 postoperative recovery patients during the recovery period). The data annotation includes the stage attributes of each cycle, the corresponding baseline data, and manually annotated "effective body shape change features".

[0068] During model training, by adjusting the threshold parameters for stage attribute judgment (such as the gestational week division threshold between early and mid-pregnancy and the data integrity judgment threshold) and optimizing the weight coefficients for difference calculation (such as assigning higher calculation weight to the abdominal circumference change in late pregnancy), the matching degree between the body shape change features output by the model and the manually labeled results is greater than or equal to 95%.

[0069] After the model is deployed, it supports online iterative optimization based on newly added monitoring data. For example, when the calculation error of the body shape change characteristics of a certain type of target user (such as overweight pregnant women) is greater than 5% for three consecutive times, the model parameters are automatically fine-tuned, and the "cycle-stage" mapping table and difference calculation rules are updated to ensure that the model always adapts to the monitoring needs of the target user.

[0070] The S300 outputs dynamic body shape parameter numerical results based on the current body shape change characteristics and the cycle stage to which the target user's current monitoring cycle belongs.

[0071] In this embodiment of the invention, the dynamic body shape parameter numerical result is a set of core parameters that quantitatively represent the target user's current body shape adaptability and health risk correlation, generated by integrating the current body shape change characteristics and periodic stage attributes. Its generation process relies on a preset "feature-stage-parameter" mapping algorithm, which is achieved through weighted calculation of the current body shape change characteristics and periodic stage adaptability calibration.

[0072] In this embodiment of the invention, the dynamic body shape parameter numerical results include body shape growth adaptability parameters, trunk morphology coordination parameters, body shape change trend risk parameters, and cyclical stage body shape achievement rate parameters. Each parameter corresponds to a different assessment dimension of body shape change. Among them, the body shape growth adaptability parameter is used to assess the degree of matching between the target user's current body shape growth (or change) and the health standards of the corresponding cyclical stage. The value range is 0-100 points, with higher scores indicating better adaptability. When the score is less than 60 points, it indicates that the body shape change deviates from the health standards, and potential risks need to be considered. The trunk morphology coordination parameter focuses on the coordination of changes in key trunk parts (such as abdominal circumference) and limb morphology. The value range is 0-100 points, with scores greater than or equal to 80 points indicating coordination between trunk and limb morphological changes, and scores less than 60 points indicating a risk of morphological imbalance (such as excessively rapid abdominal circumference growth during pregnancy while limb circumference does not change reasonably). The body shape change trend risk parameter assesses the potential health risks of future body shape changes based on continuous periodic body shape change trends. The value ranges from 0 to 5 (0 for no risk, 5 for extremely high risk). When the risk level is greater than or equal to 3, a risk warning should be triggered and intervention recommendations should be output. The periodic stage body shape achievement rate parameter calculates the percentage of current body shape indicators (such as weight and waist circumference) relative to the target value for the corresponding periodic stage. The value ranges from 0% to 200%. A achievement rate between 80% and 120% indicates compliance with the stage target; a rate greater than 150% or less than 50% suggests the need to adjust the body shape management strategy.

[0073] In this embodiment of the invention, each dynamic body shape parameter is calculated using a feature-weighted summation plus stage calibration logic. The specific formulas and examples are as follows:

[0074] (1) Calculation of body size growth fit parameters

[0075] Calculation formula: Body size growth fit = [(BaseScore - MinBase) / (MaxBase - MinBase)] × 100%;

[0076] Among them, BaseScore is the basic calculated value of body growth adaptation, MinBase is the minimum possible value of BaseScore within the corresponding cycle stage, and MaxBase is the maximum possible value of BaseScore within the corresponding cycle stage. The values ​​of MinBase and MaxBase are based on the statistical analysis of historical monitoring data of 1,000 target users in the same scenario (such as pregnant women and patients with chronic diseases). The data source is the 2022-2023 public dataset of XX Medical Database. For example, MinBase=0 and MaxBase=2.5 in the second trimester, and MinBase=1 and MaxBase=3.0 in the third trimester. The standard score coefficient is set with reference to the health standard values ​​of the corresponding cycle stage in the "Guidelines for Health Management of Chinese Adults (2023 Edition)" and "Guidelines for Health Management of Pregnant Women (2022 Edition)".

[0077] Where, BaseScore=∑ n i=1 (F) i ×W i ×S i ); where F i The value of the i-th body shape change feature is taken from the set of "current body shape change features", such as absolute change in abdominal circumference +3.8cm or relative change in weight +3.66%. The value of i ranges from 1 to n, where n is the total number of body shape change features included in the calculation (dynamically adjusted according to the stage of the pregnancy, such as 3-5 features in the second trimester); W i This is the stage weight coefficient corresponding to the i-th feature (value range 0-1, sum may not be 1), taken from the stage weight coefficient table, such as the weight coefficient for the absolute change in abdominal circumference during mid-pregnancy is 0.3. i is the standard score coefficient corresponding to the i-th feature, with a value range of 0-1. 1 indicates that it fully meets the health standard. It is generated by comparing the current body shape change feature value with the health standard value of the corresponding cycle stage. For example, if the current absolute change in abdominal circumference is +3.8cm and the health standard for abdominal circumference change in the second trimester is +2.0cm-+4.0cm, then the standard score coefficient of this feature is 0.9.

[0078] (2) Calculation of trunk morphological coordination parameters

[0079] Calculation formula: Trunk morphological coordination = [1 - |(Comprehensive change rate of trunk circumference - Comprehensive change rate of limb circumference)|] × 100;

[0080] Among them, the overall change rate of trunk circumference is the mean of the relative change rates of waist circumference and abdominal circumference, and the overall change rate of limb circumference is the mean of the relative change rates of upper arm circumference, forearm circumference, thigh circumference and calf circumference; the smaller the absolute value, the more coordinated the changes of trunk and limbs are.

[0081] (3) Calculation of risk parameters for body shape change trend

[0082] Calculation formula: Risk level of body shape change trend = floor[(risk coefficient of continuous period weight change trend value + risk coefficient of continuous period waist circumference change trend value) / 2];

[0083] Among them, the trend value risk coefficient is generated by comparing the trend value with the stage risk threshold (e.g., if the trend value of the abdominal circumference change in the late pregnancy is > +3.5cm, the risk coefficient is 4; if it is > +3.0cm and ≤ +3.5cm, the risk coefficient is 3); floor[] is the floor function.

[0084] (4) Calculation of body shape achievement rate parameters during the cycle stage

[0085] Calculation formula:

[0086] Body shape compliance rate = (Current actual body shape index value / Target body shape index value for the period) × 100%;

[0087] Among them, the “target value of body shape index in the cycle stage” is a value preset based on medical standards or population benchmark data (such as the target weight gain in the second trimester is 3kg, and the current actual gain is 2.7kg).

[0088] Example: If the current weight gain is 2.7 kg and the target weight gain in the second trimester is 3 kg, then the achievement rate = (2.7 / 3) × 100% = 90%.

[0089] In this embodiment of the invention, the dynamic body shape parameter numerical results are output in the form of structured data messages, including parameter name, value, unit, reference range and status description.

[0090] The output data also supports interface integration with the second preset model and motion threshold mapping module in subsequent steps, providing standardized input for weight adjustment and motion amplitude parameter generation.

[0091] S400, based on the second preset model, uses the dynamic body shape parameter numerical results of the current monitoring period as feedback factors to dynamically adjust the weights of the first comparison result and the second comparison result. The first comparison result is the comparison result between the initial period data and the current period data, and the second comparison result is the comparison result between the previous monitoring period data and the current period data.

[0092] In this embodiment of the invention, the second preset model is a multi-dimensional fusion evaluation model based on dynamic weight allocation. Its core function is to adjust the weight ratio of the first comparison result and the second comparison result in the subsequent fusion evaluation in real time according to the dynamic body shape parameter numerical results of the target user in the current monitoring period (as feedback basis). This solves the problem that fixed weights cannot adapt to the body shape change characteristics of different period stages, and ensures that the weight allocation matches the actual body shape status of the target user. The model architecture includes a comparison result preprocessing module, a feedback factor analysis module, a dynamic weight calculation module, and a weight output verification module. Each module works together to achieve accurate weight adjustment.

[0093] The comparison result preprocessing module is used to standardize the first and second comparison results to ensure that the two types of comparison results are comparable, providing a unified data foundation for subsequent weight adjustment.

[0094] First comparison result calculation: The first comparison result is the quantitative value of the difference between the initial cycle data and the current cycle data. Specifically, it is calculated by "(current cycle data - initial cycle data) / initial cycle data × 100%" to calculate the relative change rate of each morphological / physiological indicator. Then, a weighted average is used (the weights are preset based on the importance of the indicators, such as the weight of waist circumference and weight indicators being higher than that of limb circumference) to generate the comprehensive value of the first comparison result. The value range is [-20%, 50%]. A negative sign indicates that the current data is lower than the initial data, and a positive value indicates that it is higher than the initial data.

[0095] The second comparison result is calculated as follows: The second comparison result is the quantitative value of the difference between the data of the previous monitoring period and the data of the current period. The calculation method is "(current period data - previous period data) / previous period data × 100%". Similarly, the comprehensive value of the second comparison result is generated by weighted average. The value range is [-10%, 20%]. Because the difference between adjacent period data is small, the range is narrower than that of the first comparison result.

[0096] Standardization processing: The combined values ​​of the first and second comparison results are mapped to the interval [0, 1]. The mapping formula is "standardized value = (original combined value - minimum value) / (maximum value - minimum value)", where the minimum value of the first comparison result is equal to -20% and the maximum value is equal to 50%, and the minimum value of the second comparison result is equal to -10% and the maximum value is equal to 20%, so as to avoid the impact of the difference in numerical range on the accuracy of weight adjustment.

[0097] The feedback factor analysis module uses the dynamic body shape parameter numerical results of the current monitoring period as feedback factors, extracts the core parameters that are strongly correlated with weight adjustment, and constructs a feedback factor vector:

[0098] Core feedback parameter selection: Select "body size growth fit parameter" and "body size change trend risk parameter" from the dynamic body size parameter numerical results as core feedback parameters. The body size growth fit parameter reflects the degree of matching between the current body size and the standard of the cycle stage, and the body size change trend risk parameter reflects the risk level of future body size changes. The two together determine the direction of weight adjustment (e.g., when the fit is low and the risk is high, more reliance should be placed on the comparison of recent data).

[0099] Feedback factor quantification: The core feedback parameters are converted into quantifiable values ​​that can be used for calculation. Among them, the body size growth fit parameter (0-100 points) is directly taken as the original score, and the body size change trend risk parameter (0-5 levels) is converted into a quantifiable value of 0-100 according to "risk level × 20" to form a feedback factor vector (e.g., fit 85 points, risk level 2, the feedback factor vector is [85, 40]).

[0100] The dynamic weight calculation module is the core of the second preset model. Based on the feedback factor vector and the preset feedback-weight mapping rule, it calculates the weight of the first comparison result (denoted as W1) and the weight of the second comparison result (denoted as W2), and satisfies W1 + W2 = 1. The specific calculation logic is as follows:

[0101] Weight mapping rules are preset: A "feedback factor-weight" mapping table is generated by training with sample data from the same scenario (such as pregnancy monitoring data from 1000 pregnant women). The core rules include:

[0102] When the body size growth fit parameter is greater than or equal to the first preset score (excellent fit) and the body size change trend risk parameter is less than or equal to the first level (low risk), it indicates that the current body size change meets the cycle stage standard. It is necessary to balance the comparison between the initial data and the recent data and set W1=0.3 and W2=0.7.

[0103] When the body size growth fit parameter is less than the second preset score (insufficient fit) or the body size change trend risk parameter is greater than or equal to the third level (medium to high risk), it indicates that the current body size change deviates from the standard. It is necessary to rely heavily on recent data (previous period) to judge the change trend, and set W1=0.1 and W2=0.9.

[0104] When the body size growth fit parameter is within the preset score range (good fit) and the body size change trend risk parameter is equal to the first level (low risk), set W1=0.2 and W2=0.8;

[0105] The first preset value is 80 points, the second preset value is 60 points, the preset score range is 60-79, the first level is level 2, and the second level is level 3.

[0106] Weight interpolation calculation: If the feedback factor vector is in the middle range of the above rules (e.g., fit score 75, risk level 2), then the weight is calculated using linear interpolation, with the formula: W1 = W1 min +(FA-F down ) / (F up -F down )×(W1 max -W1 min ), of which W1 min W1 represents the minimum weight of the first comparison result in the corresponding interval. max FA represents the maximum weight of the first comparison result in the corresponding interval, where FA is the actual value of the feedback factor. down F is the lower limit of the feedback factor. up This is the upper limit of the feedback factor.

[0107] When the feedback factor vector contains multiple parameters (such as body size growth fit FA1 and body size change trend risk quantification value FA2), first calculate the corresponding W11 and W12 based on each parameter in the formula, and then take the arithmetic mean of the two as the final W1. If a parameter is in a clearly defined interval (not the middle interval), then the fixed W1 value corresponding to that parameter is directly used in the average calculation. For example, if the feedback factor vector is "fit 75 points (middle interval, calculate W11=0.279), risk level 2 (clearly defined interval, corresponding to W12=0.2)," then the final W1=(0.279+0.2) / 2=0.239.

[0108] The weight output verification module is used to verify the reasonableness of the calculated W1 and W2, and to prevent the weights from deviating from the reasonable range due to abnormal feedback factors.

[0109] Range verification: Ensure that W1∈[0.1,0.3] and W2∈[0.7,0.9]. If the range is exceeded (e.g., W1=0.05 is calculated due to abnormal feedback factor), the weights will be automatically corrected to the boundary values ​​of the corresponding interval (e.g., W1=0.1).

[0110] Historical consistency verification: Compare the currently calculated weight with the weight of the previous monitoring period. If the weight change is greater than 0.2 (e.g., W1=0.3 in the previous period and W1=0.1 in the current period), a second calculation is triggered to re-verify the feedback factor analysis and weight calculation process and eliminate the influence of data error.

[0111] After the verification is passed, the final W1 and W2 are output and transmitted to the subsequent S500 step (fusion operation based on the third preset model).

[0112] Assume the relevant data for the target users during the second trimester is as follows:

[0113] Comparison results after preprocessing: Standardized value of the first comparison result = 0.6 (corresponding to the original composite value = 22%, that is, the current data has increased by 22% compared to the initial data), Standardized value of the second comparison result = 0.7 (corresponding to the original composite value = 7%, that is, the current data has increased by 7% compared to the previous period);

[0114] Feedback factor vector: In the dynamic body shape parameters, the body shape growth fit parameter = 75 points, and the body shape change trend risk parameter = level 2 (quantitative value = 40).

[0115] 1. Weight Calculation Process

[0116] Determine the feedback factor's range: fit score 75 (range 60-79), risk level 2, corresponding to the weighting rules.

[0117] The W1 range is 0.2-0.3, and the W2 range is 0.7-0.8.

[0118] Linear interpolation calculation of W1:

[0119] Fit score: lower limit = 60 points, upper limit = 79 points, actual score = 75 points, W1 min =0.2, W1 max =0.3, then: W1==0.2+(79−60) / (75−60)×(0.3−0.2)≈0.2+0.789×0.1≈0.279;

[0120] Calculate W2: W2 = 1 - W1 ≈ 0.721;

[0121] 2. Weight Verification and Output

[0122] Range verification: W1=0.279∈[0.1,0.3], W2=0.721∈[0.7,0.9], which meets the requirements;

[0123] Historical consistency check: Assuming the previous period's W1 = 0.29, and the current weight change magnitude = 0.011 < 0.2, the check passes;

[0124] Final output: W1=0.28, W2=0.72, used for subsequent fusion calculations of the third preset model.

[0125] S500, based on the third preset model, performs a fusion operation on the first comparison result and the second comparison result, and outputs the dynamic digital evaluation result of the target user's association status.

[0126] In this embodiment of the invention, the dynamic digital evaluation result of the associated status refers to a structured digital set that quantitatively represents the health associated status of the target user, generated by weighted fusion calculation of the first comparison result and the second comparison result based on the third preset model. Specifically, it includes: dimensional evaluation data, weight and calculation basis description, and data source and scenario adaptation label.

[0127] The dimensional assessment data consists of quantitative information corresponding to the core health assessment dimensions determined for the target users. Each dimension includes a comprehensive value, a grade, and key indicator values. The comprehensive value is the overall quantitative result (ranging from 0-1 or the corresponding grade range) of the weighted calculation of each key indicator within that dimension, used to intuitively reflect the overall level of health status in that dimension. The grade is a qualitative label based on the comprehensive value range (e.g., "Excellent / Good," "Low Risk / High Risk"), used to quickly interpret the state's quality. Key indicator values ​​are quantitative data broken down to specific assessment directions within that dimension, used to pinpoint specific health advantages or potential problems. The weighting and calculation basis explanation provides key logical information supporting the generation of assessment results, including the weight allocation of the two types of comparison results and the reference standards for indicator calculation, used to clarify the generation logic of the assessment results and ensure traceability and interpretability. The data source and scenario adaptation label explains the original data support and applicable scenarios of the assessment results, including the data source, used to define the scope of application of the assessment results and avoid misuse across scenarios.

[0128] As a special user, the digital assessment results of pregnant women's status cover the relevant data of the pregnant woman's physiological adaptation status that conforms to the standard of pregnancy stage, as well as the relevant data of the fetal growth status that is indirectly inferred from the pregnant woman's physiological data, with the core focus on the collaborative assessment of maternal and infant health.

[0129] Among them, the pregnant woman's physiological adaptation status is used to assess the compatibility of the pregnant woman's current physiological status with the standards for the stage of pregnancy, including:

[0130] Pregnancy morphological fit: Combining the cumulative weight gain (absolute increase in current weight compared to the initial cycle, denoted as △WT) and cumulative abdominal circumference change (increase in current abdominal circumference compared to the initial cycle, denoted as △CT) from the first comparison result, and the short-term weight gain (increase in current weight compared to the previous cycle, denoted as △WV) and short-term abdominal circumference change (increase in current abdominal circumference compared to the previous cycle, denoted as △CV) from the second comparison result, the result is calculated using the following formula:

[0131] F P-S = (△WT / SW×0.25 + △CT / SC×0.25) + (△WT / SWV×0.25 + △CT / SCV×0.25); where, F P-SFor pregnancy morphology fit, SW refers to the cumulative weight gain standard value during pregnancy, which is the reasonable upper limit of weight gain that the target user (pregnant woman) should have during the current monitoring period compared to the initial period (early pregnancy stage), expressed in kilograms (kg). It is used to measure the fit of the cumulative weight gain value. SC refers to the cumulative abdominal circumference gain standard value during pregnancy, which is the reasonable upper limit of abdominal circumference gain that the pregnant woman should have during the current monitoring period compared to the initial period, expressed in centimeters (cm). It is used to measure the fit of the cumulative change in abdominal circumference. SWV is the short-term weight gain standard value during pregnancy, and SCV is the short-term abdominal circumference gain standard value during pregnancy. Weighting rule: weight and abdominal circumference indicators each have a total weight of 0.5, and the first and second comparison results each account for 50% of the same type of indicator.

[0132] Physiological adaptation during pregnancy: Based on the trends in blood pressure changes during pregnancy (the change in current systolic blood pressure compared to the initial cycle, denoted as △BP1) and adaptive changes in heart rate (the increase in current heart rate compared to the initial cycle, denoted as △HP1) in the first comparison results, and the short-term fluctuations in blood pressure (the range of fluctuation in current systolic blood pressure compared to the previous cycle, denoted as △BP2) and short-term stability of heart rate (the amplitude of fluctuation in current heart rate compared to the previous cycle, denoted as △HP2) in the second comparison results, combined with the pregnancy safety standard (systolic blood pressure ≤140mmHg, heart rate increase of 10-15 beats / minute), the formula is: F P-P = (140 - (B0 - △BP1) / (140 - B0)) × 0.25 + △HP1 / 15 × 0.25) + ((5 - △BP2) / 5 × 0.25 + (5 - △HP2) / 5 × 0.25), where B0 is the initial systolic blood pressure during the cycle, and 5 is the safe threshold for short-term fluctuations in blood pressure / heart rate during pregnancy; F P-P The value represents the compatibility of physiological functions during pregnancy; the closer the value is to 1, the better the compatibility.

[0133] Pregnancy body composition fit: Combining the pregnancy body fat percentage change rate (the percentage increase in current body fat percentage compared to the initial cycle, denoted as RBF1), pregnancy muscle mass change rate (the percentage change in current muscle mass compared to the initial cycle, denoted as RMM1), and pregnancy body water percentage change rate (the percentage change in current body water percentage compared to the initial cycle, denoted as RWM1) from the first comparison results, and the short-term body fat percentage change rate (the percentage change in current body fat percentage compared to the previous cycle, denoted as RBF2), short-term muscle mass change rate (the percentage change in current muscle mass compared to the previous cycle, denoted as RMM2), and short-term body water percentage change rate (the percentage change in current body water percentage compared to the previous cycle, denoted as RWM2) from the second comparison results, and combining the pregnancy body composition standards (body fat percentage increase of 5%-10%, muscle mass change ±2%, body water percentage increase of 3%-5%), the formula is:

[0134] F P-B= (RBF1 / 10×0.3+(2-|RMM1|) / 2×0.25+RWM1 / 5×0.2)+((2-|RBF2|) / 2×0.15+(1-|RMM2|) / 1×0.05+(1-|RWM2|) / 1×0.05);

[0135] Among them, F P-B For the body composition fit during pregnancy, the closer the value is to 1, the better the fit; RBF1 / 10 represents the proportion of body fat percentage increase to the upper limit of the standard, (2-|RMM1|) / 2 represents the degree of muscle mass change deviating from 0 (the closer to 0, the higher the score), RWM1 / 5 represents the proportion of body water percentage increase to the upper limit of the standard, and the short-term change rate is "2-|change rate|" and "1-|change rate|" to ensure that the smaller the fluctuation, the higher the score.

[0136] Fetal growth correlation status is indirectly correlated with fetal growth status based on maternal physiological data (not direct ultrasound monitoring, but inferred from maternal indicators). Specifically, it includes fetal growth mismatch risk: It integrates the "cumulative abdominal circumference growth rate" (current cumulative abdominal circumference growth / current gestational week, denoted as VCT) and "cumulative weight gain rate" (current cumulative weight gain / current gestational week, denoted as VWT) from the first comparison result, with the "short-term abdominal circumference growth rate" (current short-term abdominal circumference growth / week interval, denoted as VCV) and "short-term weight gain rate" (current short-term weight gain / week interval, denoted as VWV) from the second comparison result, combined with the standard gestational abdominal circumference growth rate SV (e.g., 1 cm / week in mid-pregnancy) and standard weight gain rate SWV (e.g., 0.3 kg / week in mid-pregnancy), to determine the fetal growth mismatch risk R. F-G The calculation formula is:

[0137] R F-G =(1-(VCT×0.6+VWT×0.4) / SV 综 )×0.5+(1-(VCV×0.6+VWV×0.4) / SV 综 ) × 0.5;

[0138] Among them, SV 综 The comprehensive standard rate is (SV×0.6+SWV×0.4) (e.g., (1×0.6+0.3×0.4)=0.72), with abdominal circumference weighted at 0.6 (more related to fetal growth space) and body weight weighted at 0.4. R F-GThe closer the value is to 0, the lower the risk. In this embodiment of the invention, the third preset model is a multi-dimensional evaluation model based on a weighted fusion algorithm. Its core function is to fuse two types of comparison results (the first comparison result is the comparison result between the initial period and the current period data, and the second comparison result is the comparison result between the previous monitoring period and the current period data) into a structured dynamic digital evaluation result of the associated state through three steps: "preprocessing-weighted calculation-comprehensive value generation".

[0139] In one illustrative embodiment, taking a pregnant woman as an example, the fusion calculation process includes:

[0140] 1. Pre-treatment: Adjusting the standardization range according to the stage of pregnancy.

[0141] Pre-treatment for pregnant women needs to be dynamically adjusted within a reasonable range based on the stage of pregnancy (first trimester 1-12 weeks, second trimester 13-27 weeks, and third trimester 28 weeks to delivery) to ensure it conforms to the physiological changes during pregnancy.

[0142] The reasonable range for short-term weight gain during the second trimester is 0.3 kg to 0.5 kg per week. If the actual value is 0.4 kg per week, the standardized value is 0.5, calculated as "(actual value - lower limit) / (upper limit - lower limit)".

[0143] The reasonable range for the short-term increase rate of abdominal circumference in the second trimester is 0.8cm to 1.0cm per week. The reasonable range for the trend of blood pressure changes during pregnancy is a decrease of 5mmHg to an increase of 15mmHg from the initial value (the upper limit is relaxed compared to general users because a moderate increase in systolic blood pressure is allowed during pregnancy). Other indicators are standardized according to the reasonable range of the corresponding pregnancy stage.

[0144] 2. Weighted Calculation: Rules for Increasing the Weight of Core Indicators

[0145] For pregnant women, the weighting of indicators strongly correlated with maternal and infant health should be increased. The specific rules are as follows:

[0146] In the pregnancy morphology fit assessment, the weight of abdominal circumference-related indicators increased from 0.4 to 0.6 for general users, while the weight of weight-related indicators decreased from 0.6 to 0.4, because changes in abdominal circumference better reflect the fetal growth space.

[0147] In the fetal growth-related status assessment, the weight of fetal growth fit risk was set at 0.5, which is higher than the weight of placental function-related risk (0.3) and pregnancy complication warning risk (0.2), ensuring that core risk indicators are prioritized for assessment.

[0148] The calculation method for the index value is the same as that for general users, which is still "standardized value of the first comparison result × W1 + standardized value of the second comparison result × W2".

[0149] 3. Comprehensive value generation: Combining medical standard assessment and grading.

[0150] The composite value needs to be generated with reference to the medical standards for pregnancy, and the composite values ​​of "maternal physiological fitness status" and "fetal growth-related status" should be calculated separately:

[0151] The comprehensive value of a pregnant woman's physiological adaptation status is the arithmetic mean of three indicators: morphological adaptation during pregnancy, physiological function adaptation during pregnancy, and metabolic adaptation during pregnancy. The classification is based on the "Guidelines for Health Management of Pregnant Women": a comprehensive value of 0.8 to 1.0 is "excellent", 0.6 to 0.8 is "good", 0.4 to 0.6 is "needs attention", and 0 to 0.4 is "needs intervention".

[0152] The composite value of fetal growth-related status is the weighted average of three indicators: fetal growth compatibility risk, placental function-related risk, and pregnancy complication warning risk (with weights of 0.5, 0.3, and 0.2, respectively). The classification rules are as follows: a composite value of 0 to 0.3 is "low risk", 0.3 to 0.5 is "needs monitoring", and 0.5 to 1.0 is "needs medical evaluation".

[0153] 4. Optimized output results

[0154] The dynamic numerical assessment results of the pregnant woman's correlation status are also presented in a structured format, including the pregnant woman's physiological adaptation status, fetal growth correlation status, and data sources, and supplemented with medical reference information:

[0155] Pregnant woman's physiological fit status: comprehensive value 0.82, grade "excellent", key indicators include pregnancy morphological fit 0.85, pregnancy physiological function fit 0.81, pregnancy metabolic fit 0.79, with the weighting explanation "abdominal circumference 0.6, weight 0.4 (adjusted for mid-pregnancy fit)" and supplementary medical reference "meets the health standards of mid-pregnancy (13-27 weeks) of the 'Guidelines for Weight Management of Pregnant Women'".

[0156] Fetal growth-related status: composite value 0.28, level "low risk", key indicators include fetal growth fit risk 0.25, placental function-related risk 0.30, and pregnancy complication warning risk 0.29. The weighting explanation is "fetal growth risk 0.5, placental function risk 0.3, complication risk 0.2". The supplementary medical reference is "abdominal circumference growth rate 0.9cm / week, which is in line with the expected fetal growth in the second trimester".

[0157] Data source: labeled as "generated by fusion of data from 18 weeks of pregnancy (current cycle), 6 weeks of pregnancy (initial cycle), and 16 weeks of pregnancy (previous cycle)".

[0158] S600, compare the dynamic digital evaluation result of the associated status with the preset monitoring threshold, and output the corresponding status monitoring prompt information according to the comparison result.

[0159] In this embodiment of the invention, the preset monitoring threshold is a quantitative benchmark for determining whether a user's health status requires intervention, based on the target user and related status dimensions (such as fetal growth-related status). Its value needs to be determined in conjunction with medical standards, population sample statistical data, and monitoring scenario requirements. The status monitoring prompt information is a structured information generated based on the comparison results, possessing the attributes of "risk classification - intervention suggestion - execution guidance". Its core function is to deliver health status warnings to users or medical staff and assist in formulating appropriate health management strategies.

[0160] The preset monitoring thresholds for pregnant women are set based on two dimensions: the pregnant woman's physiological adaptation status and the correlation between the pregnant woman's physiological adaptation status and the fetal growth status. The values ​​are determined with reference to the "Guidelines for Health Management of Pregnant Women" and clinical monitoring data during pregnancy, and need to be dynamically adjusted according to the stage of pregnancy.

[0161] Physiological adaptation thresholds for pregnant women are divided into three levels based on the overall value and gestational stage: adaptation threshold, attention threshold, and medical intervention threshold. In early pregnancy, the adaptation threshold is an overall value ≥ 0.7, the attention threshold is 0.5 ≤ overall value < 0.7, and the medical intervention threshold is an overall value < 0.5. In mid and late pregnancy, the adaptation threshold is lowered to ≥ 0.6 (the standard is appropriately relaxed due to the increased physiological changes during pregnancy), and the medical intervention threshold remains an overall value < 0.5. Sub-thresholds are set for key indicators (such as metabolic adaptation during pregnancy). For example, if the metabolic adaptation during pregnancy is < 0.5, a medical attention prompt will still be triggered even if the overall value is ≥ 0.6.

[0162] Fetal growth-related status thresholds are divided into three levels based on the comprehensive value: low-risk threshold, monitoring threshold, and medical assessment threshold. The low-risk threshold is a comprehensive value ≤ 0.3 (corresponding to the "low-risk" level), the monitoring threshold is 0.3 < comprehensive value ≤ 0.5 (corresponding to the "monitoring required" level), and the medical assessment threshold is a comprehensive value > 0.5 (corresponding to the "medical assessment required" level). For fetal growth mismatch risk, sub-thresholds are set according to the gestational stage. For example, when the fetal growth mismatch risk value in late pregnancy is > 0.4, a medical assessment prompt is directly triggered (due to the need for rapid intervention due to abnormal fetal growth in late pregnancy).

[0163] In this embodiment of the invention, the comparison process between the correlation status evaluation result and the preset threshold must follow the logic of dimension priority - sub-index verification - level confirmation to ensure that the comparison result is accurate and without omission. The specific steps are as follows:

[0164] Dimension matching: Match each dimension of the dynamic digital evaluation result of the associated status with the corresponding preset monitoring threshold dimension to avoid cross-dimensional comparison.

[0165] Comprehensive value comparison: Calculate the relationship between the comprehensive value of the current dimension and the corresponding threshold to preliminarily determine the warning level; for example, the comprehensive value of the "potential risk warning status" of a general user is 0.32, which is compared with the "medium risk threshold (0.3 < comprehensive value ≤ 0.6)" and preliminarily determined to be "medium risk warning".

[0166] Sub-indicator verification: Check whether the key indicators under the current dimension have triggered the sub-threshold. If they have, the initial warning level will be upgraded or maintained. For example, if the pregnant woman's "fetal growth-related status" composite value is 0.45 (preliminary judgment "monitoring warning"), but the sub-indicator "fetal growth matching risk value" is 0.48 (late pregnancy sub-threshold > 0.4), then it will be upgraded to "medical assessment warning".

[0167] Level Confirmation: Combining the comprehensive value comparison results with the sub-indicator verification results, the final alert level is determined to ensure that there are no cases of "low risk misjudging high risk" or "high risk omitting low risk". For example, if the comprehensive value of "health baseline adaptation status" for a general user is 0.65 (preliminary "normal alert"), but the sub-indicator "physiological function adaptation" is 0.48 (triggering the attention sub-threshold), then it is adjusted to "attention alert".

[0168] Status monitoring prompts should be categorized by prompt level, and the output format should balance "user readability" and "medical professionalism." Specific categorization and examples are as follows:

[0169] 1. Prompt Message Hierarchy Rules

[0170] Normal / Low Risk Warning: The core content is "status confirmation + health advice", which requires no intervention and only provides guidance for daily management; for example, "low risk warning for fetal growth-related status" for pregnant women.

[0171] Attention / Monitoring Tips: The core content consists of "status description + adjustment suggestions + re-examination requirements," requiring users to actively adjust their lifestyles and undergo re-examinations at specified intervals; for example, "physiological adaptation status monitoring tips for pregnant women."

[0172] Intervention / Medical Assessment Tips: The core content is "risk warning + medical advice + emergency treatment guidelines". Users need to seek medical attention or contact medical staff immediately, and the tips must include information such as recommendations for nearby medical institutions and emergency contact numbers; for example, "medical assessment tips related to fetal growth status" for pregnant women.

[0173] 2. Example of prompt message output

[0174] Example of pregnancy alert information (medical assessment alert):

[0175] "

Pregnancy Medical Assessment Notice

[0176] 3. Output format of prompt information

[0177] The notification message needs to be output simultaneously through multiple channels to ensure that users receive it in a timely manner:

[0178] Terminal push notifications: Push pop-up notifications to users via their monitoring devices (such as smart bracelets) and mobile apps. Intervention / medical assessment notifications should include a "read confirmation" button to ensure users see the notifications.

[0179] Report generation: Automatically generates a PDF "Status Monitoring Alert Report" which includes comparison results, alert level, recommendations, data source, and other information. Users can print or share the report with medical staff.

[0180] Synchronization between medical staff and healthcare professionals: If the prompt is for intervention / medical assessment, the system should automatically synchronize the prompt information to the user's linked medical staff terminal (such as doctor's workstation or nurse's APP) so that medical staff can understand the user's condition in advance and make preparations for diagnosis and treatment.

[0181] Furthermore, the method also includes the following steps:

[0182] S700, based on the dynamic body shape parameter digital results, calls the preset periodic stage motion threshold mapping relationship to generate and output motion amplitude quantification parameters that are adapted to the target user's current monitoring period and its corresponding periodic stage.

[0183] S800: Based on the motion amplitude quantization parameters, generate and output corresponding motion guidance information.

[0184] In this embodiment of the invention, the motion amplitude quantification parameters include step frequency threshold, limb movement angle threshold, exercise duration threshold, and exercise intensity level; the periodic stage motion threshold mapping relationship is a preset exercise safety threshold reference table based on the physiological characteristics of the target user at different periodic stages (such as gestational age and fetal development stage), and its values ​​are based on the "Guidelines for Exercise in Pregnant Women" and clinical exercise safety data.

[0185] Among them, pregnant women are divided into gestational stages according to "gestational week + the pregnant woman's physiological adaptation status", for example:

[0186] Early pregnancy (weeks 1-12): When the pregnant woman's physiological fitness is ≥0.7, the step frequency threshold is preset to 80-100 steps / minute, the limb movement angle threshold (such as hip joint movement angle) is preset to 60°-90°, and the exercise duration threshold is ≤30 minutes / time; when the pregnant woman's physiological fitness is <0.7, the step frequency threshold is reduced to 70-90 steps / minute, the exercise duration threshold is ≤20 minutes / time, and limb movement angle >90° is prohibited.

[0187] During the second trimester (13-27 weeks): when the pregnant woman's physiological fitness is ≥0.6, the step frequency threshold can be increased to 90-110 steps / minute, the limb movement angle threshold can be relaxed to 90°-120°, and the exercise duration threshold can be ≤45 minutes / session. During the third trimester (28 weeks and beyond): the step frequency threshold drops back to 80-100 steps / minute, the limb movement angle threshold is limited to 60°-90°, the exercise duration threshold can be ≤30 minutes / session, and the exercise intensity level is set to "low intensity" (heart rate maintained at 50%-60% of maximum heart rate).

[0188] The generation of motion amplitude quantization parameters requires three steps: parameter filtering, threshold adjustment, and anomaly detection, as detailed below:

[0189] Parameter filtering: Based on the target user's current cycle stage (e.g., 18 weeks of pregnancy), extract the initial exercise threshold (e.g., initial cadence threshold of 90-110 steps / minute) from the cycle stage exercise threshold mapping relationship.

[0190] Threshold adjustment: Optimize the initial threshold by combining the numerical results of dynamic body shape parameters, for example:

[0191] If the pregnant woman's metabolic fit during pregnancy is 0.68 (good), but the comprehensive value of the fetal growth-related status is 0.35 (needs monitoring), then the exercise duration threshold should be shortened by 5 minutes from the lower limit of the initial range (e.g., ≤40 minutes / time), and the limb movement angle threshold should be lowered by 10° (e.g., 80°-110°).

[0192] Anomaly Detection: If the adjusted threshold exceeds the "exercise safety limit range" (e.g., pregnant woman's step frequency > 120 steps / minute, general user exercise intensity level > "high intensity"), it will automatically revert to the safety limit value and mark the "threshold adjustment reason" (e.g., "due to the need to monitor fetal growth, the exercise duration threshold has been reverted to 30 minutes / time") to ensure parameter safety.

[0193] Motion amplitude quantization parameters are output in structured data format, including parameter name, adaptation range, and safety basis, as shown in the example below:

[0194] Pregnant woman (mid-pregnancy, 18 weeks, physiological fit 0.82):

[0195] Step frequency threshold: The suitable range is 90-110 steps / minute.

[0196] Limb range of motion thresholds: elbow joint range of motion adaptation range is 90°-120°, hip joint range of motion adaptation range is 60°-90°.

[0197] Exercise duration threshold: The suitable range is 30-45 minutes / session.

[0198] Exercise intensity level: The appropriate level is low to moderate intensity, corresponding to a heart rate range of 100-120 beats per minute.

[0199] The compatibility criteria were determined based on the user's mid-pregnancy (18 weeks) and the pregnant woman's excellent physiological compatibility (0.82), and were adjusted according to the "Guidelines for Exercise in Pregnant Women".

[0200] S800: Based on the motion amplitude quantization parameters, generate and output corresponding motion guidance information.

[0201] In this embodiment of the invention, the exercise guidance information includes recommendations for exercise types suitable for the current cycle stage, suggestions for the duration of a single exercise session, and reminders of exercise contraindications. The exercise guidance information is generated based on a comparison of exercise amplitude quantification parameters and the target user's historical exercise data. Wherein:

[0202] Recommended exercise types: Suitable types are selected based on exercise intensity level and limb movement angle threshold, for example:

[0203] Exercise intensity level is "low intensity" and limb movement angle threshold is ≤90°: walking, prenatal yoga (gentle postures), and seated stretching are recommended. Avoid high-intensity exercises such as running and jumping.

[0204] Exercise intensity level is "moderate intensity" with a limb range of motion threshold of 120°-150°: recommended activities include brisk walking, jogging, swimming (freestyle / breaststroke), and standing strength training (such as bodyweight squats). Exercises that require large bending or twisting (such as sit-ups and high-intensity interval training) are prohibited.

[0205] Single exercise plan: The exercise process is refined by combining cadence thresholds and exercise duration thresholds, including the allocation of time and intensity control for three stages: "warm-up - main exercise - cool-down". For example:

[0206] Pregnant women (step frequency 90-110 steps / minute, exercise duration 30-45 minutes):

[0207] "Warm-up phase (5 minutes): slow walking (70-80 steps / minute) + light upper limb stretching; main exercise phase (20-35 minutes): brisk walking (90-110 steps / minute, rest for 1 minute every 10 minutes); cool-down phase (5 minutes): slow walking (70-80 steps / minute) + gentle lower limb stretching."

[0208] Exercise contraindications: Based on the target user's lifecycle stage and dynamic body shape parameters, clearly define prohibited exercise behaviors and risky scenarios, such as:

[0209] Pregnant women (fetal growth status needs to be monitored): "Contraindications: 1. Avoid abdominal strain during exercise (such as bending over); 2. Avoid exercise in high-temperature environments (>30℃) or enclosed spaces; 3. If abdominal pain or decreased fetal movement occurs during exercise, stop immediately and rest."

[0210] When generating guidance information, it is necessary to combine users' historical exercise preferences (such as prioritizing swimming if they prefer it), exercise duration habits (such as adjusting to "short duration per session, multiple times a day" if they are used to short exercise) and post-exercise reactions (such as lowering the intensity level if recovery is slow after high intensity) to improve user compliance; the output format should adopt "text description + necessary visual illustrations" (such as action diagrams, cadence-heart rate correspondence tables) to ensure that the information is clear and easy to understand.

[0211] In this embodiment of the invention, the "status monitoring prompt information" output in step S600, the "motion amplitude quantification parameters" output in step S700, and the "exercise guidance information" output in step S800 are all health management reference information generated based on the target user's current monitoring cycle data (initial cycle, current cycle, and previous cycle data), cycle stage characteristics, dynamic body shape parameters, and historical exercise data. Their core function is to provide adaptive feedback for the user's daily health monitoring and exercise planning. They do not possess the attributes of medical diagnosis, disease confirmation, clinical treatment recommendations, or medical intervention. The specific declaration is as follows:

[0212] (1) Unified definition of information nature

[0213] The generation logic for all three types of output information is based on publicly available health guidelines (such as the "Guidelines for Health Management of Pregnant Women"), population sample statistical thresholds, and user monitoring data. It does not involve medical examinations necessary for medical diagnosis (such as laboratory tests and imaging examinations), clinical symptom assessment, or in-depth medical history inquiries.

[0214] The status monitoring prompts only reflect the health-related status adaptability or risk tendency at the monitoring data level (such as the risk of abnormal weight changes, fetal growth-related risks) and do not constitute a disease diagnosis conclusion.

[0215] The quantitative parameters of exercise amplitude (step frequency threshold, limb movement angle threshold, etc.) and exercise guidance information (recommended exercise types, contraindications, etc.) are only for daily exercise reference in the absence of clear medical contraindications, and are not intended to develop therapeutic exercise programs for specific diseases (such as hypertension, gestational diabetes).

[0216] (2) Mandatory reminders regarding medical professionalism

[0217] If the target user falls under any of the following circumstances, they must prioritize following the professional diagnoses and advice of formal medical institutions (such as hospitals and community health service centers) and licensed physicians, and must not use the reference information output by this invention as a substitute for medical treatment:

[0218] If you receive an "Intervention / Medical Assessment Prompt" in step S600 (such as a high-risk warning for potential risks, or a need for medical assessment of fetal growth), or if you experience clear symptoms of discomfort (such as persistent dizziness, abdominal pain, abnormal fetal movement, or severe pain after exercise);

[0219] Known chronic diseases (such as heart disease, joint diseases, diabetes), special physiological conditions (such as uterine contractions and bleeding during pregnancy, postoperative recovery period), or a history of sports-related injuries;

[0220] If you experience any discomfort (such as chest tightness, weakness, or nausea) after exercising according to the steps in S700-S800, you should stop exercising immediately and consult a doctor.

[0221] (3) Prerequisites for use and notification of risks and responsibilities

[0222] The use of these three types of output information is subject to the following conditions, and users shall bear all related risks:

[0223] This is only applicable to the health management reference of the target user during the current monitoring period and does not cover special scenarios such as sudden illness, rare diseases, or extreme environments (such as high temperature or high altitude).

[0224] When users adjust their lifestyle (such as diet and sleep) or engage in exercise based on information, they should make flexible adjustments based on their own actual situation (such as allergy history, underlying diseases, and exercise ability) and should not apply the information mechanically.

[0225] The entity implementing this invention shall not be liable for any health risks (such as worsening of condition, sports injury, or delayed treatment) resulting from ignoring individual differences, failing to follow medical advice, or arbitrarily exceeding exercise safety thresholds (such as exceeding the upper limit of cadence or exercise duration).

[0226] This statement must be presented in a prominent form (such as bold font, a separate pop-up window, or a footer on the report's first page) along with the output information of steps S600-S800 to ensure that users are clearly aware of its attribute boundaries and usage prerequisites when obtaining reference information, thus avoiding misuse of information.

[0227] This invention also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being configured to perform the method described in this invention.

[0228] This invention also provides a computer-readable storage medium storing computer-executable instructions for performing the methods described in this invention.

[0229] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0230] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of monitoring the state of a target user, characterized by, The method comprises the following steps: acquiring current period data collected by a data collection device, the current period data being morphological change data and physiological quantitative data of a target user in a current monitoring period; based on a first preset model, based on the stage attribute of the current monitoring period, selectively performing difference calculation on the morphological change data in the current period data and the initial period data or the body shape data of the previous monitoring period to generate current body shape change characteristics; based on the current body shape change characteristics and the period stage to which the target user's current monitoring period belongs, outputting a dynamic body shape parameter digital result; based on a second preset model, taking the dynamic body shape parameter digital result of the current monitoring period as a feedback factor, dynamically adjusting the weights of the first comparison result and the second comparison result, wherein the first comparison result is a comparison result of the initial period data and the current period data, and the second comparison result is a comparison result of the previous monitoring period data and the current period data; based on a third preset model, performing fusion operation on the first comparison result and the second comparison result to output a dynamic digital evaluation result of the associated state of the target user; comparing the associated state dynamic digital evaluation result with a preset monitoring threshold, and outputting corresponding state monitoring prompt information according to the comparison result; The first preset model is a feature extraction model based on time series data difference analysis, the second preset model is a multi-dimensional fusion evaluation model based on dynamic weight distribution, and the third preset model is a multi-dimensional evaluation model based on weighted fusion algorithm.

2. The method of claim 1, wherein, It also comprises the following steps: based on the dynamic body shape parameter digital result, calling a preset period stage exercise threshold mapping relationship to generate and output an exercise amplitude quantitative parameter adapted to the target user's current monitoring period and the period stage to which it belongs; based on the exercise amplitude quantitative parameter, generating and outputting corresponding exercise guidance information.

3. The method of claim 1, wherein, The morphological change data includes the target user's weight change, limb shape change, torso shape change and body circumference change; the physiological quantitative data includes heart rate, blood pressure, blood oxygen saturation and human composition quantitative value.

4. The method of claim 2, wherein, The exercise amplitude quantitative parameter includes step frequency threshold, limb movement angle threshold, exercise duration threshold and exercise intensity level; the period stage exercise threshold mapping relationship is a movement safety threshold reference table preset based on physiological characteristics of different period stages.

5. The method of claim 2, wherein, The exercise guidance information includes exercise type recommendation, single exercise duration suggestion and exercise contraindication prompt adapted to the current period stage, and the exercise guidance information is generated based on the comparison result of the exercise amplitude quantitative parameter and the target user's historical exercise data.

6. The method of claim 1, wherein, The target user is a specific population that needs to be monitored periodically, and the dynamic digital evaluation result of the associated state is a structured digital set that quantitatively represents the health associated state of the target user, which is generated by performing weighted fusion operation on the first comparison result and the second comparison result based on the third preset model.

7. The method of claim 1, wherein, The data collection device includes a wearable device, a physical sign monitoring device and a shape measuring device.

8. An electronic device, comprising: It comprises a processor and a memory; The processor, by calling the program or instruction stored in the memory, is used to execute the steps of the method as claimed in any one of claims 1 to 7. The processor, by calling the program or instruction stored in the memory, is used to execute the steps of the method as claimed in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium is used to store programs or instructions, which make the computer execute the steps of the method according to any one of claims 1 to 7.

Images