Pregnancy exercise safety monitoring system based on physiological monitoring

Abstract

The invention relates to the field of maternal and infant health monitoring, in particular to a pregnancy exercise safety monitoring system based on physiological monitoring, which comprises an individual parameter acquisition module, a personalized exercise adaptation module, an early warning and dynamic adjustment module and an interactive guidance management module, wherein the individual parameter acquisition module acquires physiological parameters, a pregnant woman motion state, an equipment state and pregnant woman individual characteristic data; the individual exercise adaptation module establishes an individual physiological parameter reference, analyzes the adaptation degree and generates an exclusive safety threshold value; the early warning and dynamic adjustment module divides risk levels, gives out early warning and emergency suggestions, provides personalized exercise guidance, adjusts an exercise plan and optimizes a long-term exercise scheme; and the interactive guidance management module displays the monitoring data, the risk early warning information and the long-term exercise scheme, remotely transmits the data and performs doctor-patient collaborative management. Therefore, the problems of single monitoring dimension, insufficient evaluation accuracy, lack of personalized guidance and the like in the prior art are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of maternal and child health monitoring, in particular to a pregnancy exercise safety monitoring system based on physiological monitoring. BACKGROUND

[0002] As a sensitive stage of weight gain for women, pregnancy is prone to excessive weight gain due to changes in hormones and metabolism and increased energy requirements, which in turn increases the risk of adverse pregnancy outcomes such as gestational diabetes and hypertension. Although exercise during pregnancy can effectively control weight and improve pregnancy outcomes, it is still unclear whether exercise can induce uterine contractions and affect physical reserves during labor. Therefore, monitoring uterine contractions is crucial. However, traditional methods of monitoring uterine contractions have obvious limitations, such as the fact that a delivery pressure meter is affected by various factors, an intrauterine pressure catheter is invasive and prone to infection, and a doctor's palpation is highly subjective, all of which make it difficult to meet the monitoring needs of pregnant women during exercise.

[0003] Current exercise monitoring during pregnancy has many shortcomings, such as the lack of personalized guidance for pregnant women in different situations, the inability to comprehensively and real-time monitor key indicators such as uterine contractions, fetal heart rate, and fetal movement to determine the impact of exercise on the fetus, and the complexity of existing devices and the inconvenience of wearing them, making it difficult to synchronize and correlate exercise types with uterine contraction signals. Although uterine electromyography has the advantages of non-invasiveness, high sensitivity, and accuracy, it can distinguish between abdominal muscle exercise and uterine contractions and is not easily affected by factors such as exercise. However, the application of uterine contraction detection during exercise is still a blank, and there is an urgent need for a system that can achieve multi-parameter synchronous monitoring and real-time assessment of exercise safety. SUMMARY

[0004] The present application provides a pregnancy exercise safety monitoring system based on physiological monitoring to solve the problems of single monitoring dimension, insufficient evaluation accuracy, and lack of personalized guidance in the prior art.

[0005] The first aspect of the present application provides a pregnancy exercise safety monitoring system based on physiological monitoring, comprising: an individual parameter acquisition module, a personalized exercise adaptation module, a warning and dynamic adjustment module, and an interactive guidance management module; wherein the individual parameter acquisition module is used to collect physiological parameters, pregnant women's exercise state, device state, and pregnant women's individual characteristic data; the personalized exercise adaptation module is used to establish a personal physiological parameter benchmark, analyze the exercise and physiological state adaptation degree, and generate a dedicated safety threshold based on historical data; the warning and dynamic adjustment module is used to divide risk levels and issue warnings and emergency recommendations in abnormal situations, while providing personalized exercise guidance based on risk levels, dynamically adjusting exercise plans, and summarizing daily data to optimize long-term exercise programs; the interactive guidance management module is used to display individualized monitoring data, risk warning information, and long-term exercise programs, and remotely transmit data for doctor-patient collaborative management.

[0006] Preferably, the individual parameter acquisition module comprises an integrated probe unit, a motion sensing unit, a device monitoring unit, and an individual information input unit, wherein the integrated probe unit is used to acquire uterine myoelectric signals, maternal electrocardiogram, and fetal electrocardiogram physiological signals; the motion sensing unit is used to acquire the motion type, motion intensity, and body position change data of the pregnant woman; the device monitoring unit is used to acquire electrode contact impedance change information, probe tilt and sliding position state data; and the individual information input unit is used to manually input individual characteristic data of the pregnant woman.

[0007] Preferably, the individual motion adaptation module comprises an individual baseline calibration unit, an individual threshold adaptation unit, and a multi-parameter correlation analysis unit, wherein the individual baseline calibration unit is used to integrate physiological parameters, pregnant woman motion state, device state, and pregnant woman individual characteristic data to establish an individual physiological parameter baseline; the individual threshold adaptation unit is used to generate an exclusive individualized safety threshold based on the individual physiological parameter baseline and in combination with historical data of the pregnant woman in different motion scenarios, using an adaptive threshold algorithm; and the multi-parameter correlation analysis unit is used to remove motion interference in real-time physiological signals through an NLMS algorithm, and analyze the adaptation degree of the current motion and physiological state using a LightGBM algorithm.

[0008] Preferably, the NLMS algorithm formula is:

[0009]

[0010]

[0011] wherein, represents the estimated value of motion interference; represents the filter weight vector; represents the transpose of the vector; represents the input signal vector; represents the pure physiological signal after removing motion interference; represents the expected signal; represents the step factor; represents the regularization parameter; represents the interference intensity.

[0012] Preferably, the early warning and dynamic adjustment module comprises a risk monitoring and early warning unit, a personalized adjustment unit and a trend iteration unit, wherein the risk monitoring and early warning unit divides the risk level through a random forest algorithm by monitoring parameters and preset individualized safety thresholds in real time, combining the fitness analysis of the current motion and physiological state, and issuing early warning and emergency suggestions in abnormal cases; the personalized adjustment unit provides personalized motion guidance and dynamically adjusts the motion plan based on the risk level; and the trend iteration unit is used for automatically summarizing daily motion data and corresponding physiological parameter trend data, updating and optimizing the long-term motion scheme and the individualized safety threshold.

[0013] Preferably, the interaction guidance management module comprises a user interaction display unit, an AR action guidance unit and a remote collaboration unit, wherein the user interaction display unit is used for real-time display of individualized monitoring data, risk warning information, motion suggestions and long-term motion scheme, and receives feedback from the pregnant woman; the AR action guidance unit is used for providing standardized action guidance through AR to help the pregnant woman maintain correct posture during exercise; and the remote collaboration unit is used for transmitting real-time data to a cloud server or a doctor terminal for data sharing and remote medical care.

[0014] The second aspect embodiment of the present application provides a pregnancy exercise safety monitoring method based on physiological monitoring, comprising: acquiring physiological parameters, pregnant woman motion state, device state and pregnant woman individual characteristic data; establishing a personal physiological parameter benchmark according to the physiological parameters, pregnant woman motion state, device state and pregnant woman individual characteristic data, combining the historical data of the pregnant woman in different motion scenarios, and generating an exclusive individualized safety threshold using an adaptive threshold algorithm; in the pregnant woman's exercise process, removing additional interference signals generated by exercise through an NLMS algorithm, analyzing the fitness of the current motion and physiological state using a LightGBM algorithm, combining device real-time monitoring data and the individualized safety threshold, and dividing the risk level using a random forest algorithm; providing personalized motion guidance and dynamically adjusting the motion plan according to the risk level, while automatically summarizing daily motion data and corresponding physiological parameter trend data, updating and optimizing the long-term motion scheme and the individualized safety threshold, and transmitting the data to a cloud server for remote medical guidance.

[0015] The third aspect embodiment of the present application provides an electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement a pregnancy exercise safety monitoring method based on physiological monitoring as described in the above embodiments.

[0016] The fourth aspect embodiment of the present application provides a computer readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement a pregnancy exercise safety monitoring method based on physiological monitoring as described in the above embodiments.

[0017] The fifth aspect of the present application provides a computer program product comprising computer programs or instructions for implementing a physiological monitoring based pregnancy exercise safety monitoring method according to the above embodiments.

[0018] Therefore, the present application includes the following beneficial effects: The embodiments of the present application collect multi-dimensional data through the individual parameter acquisition module, use the integrated probe unit to obtain uterine myoelectricity, maternal and fetal electrocardiogram physiological signals, the exercise perception unit captures exercise type, intensity and body position change data, the device monitoring unit obtains electrode contact state information, and the individual information input unit collects pregnant woman individual characteristic data, so as to improve the data integrity of pregnancy exercise monitoring; with the help of the individual exercise adaptation module, the individual physiological parameter benchmark is established, the exercise and physiological state adaptation degree is analyzed by combining the LightGBM algorithm, the adaptive threshold algorithm is used to generate exclusive safety threshold combined with historical data, and the individuality and accuracy of exercise risk assessment are improved; through the early warning and dynamic adjustment module, the risk level is divided based on the random forest algorithm and early warning is issued, individualized exercise guidance and dynamic adjustment scheme are provided according to the risk level, long-term exercise scheme is optimized by summarizing data, and the pertinence and adaptability of individualized guidance are enhanced; the monitoring data, early warning information and exercise scheme are displayed by the interactive guidance management module, and doctor-patient collaborative management is realized through remote data transmission, so as to improve the information intercommunication and collaborative efficiency. Therefore, the problems of single monitoring dimension, insufficient evaluation accuracy and lack of individualized guidance in the prior art are solved.

[0019] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0020] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the accompanying drawings, in which: Figure 1 FIG. 1 is a structural schematic diagram of a physiological monitoring based pregnancy exercise safety monitoring system according to an embodiment of the present application; Figure 2 FIG. 2 is a schematic diagram of an individual parameter acquisition module according to an embodiment of the present application; Figure 3 FIG. 3 is a schematic diagram of monitoring a pregnant woman performing slow walking exercise according to an embodiment of the present application; Figure 4 FIG. 4 is a schematic diagram of an individual exercise adaptation module according to an embodiment of the present application; Figure 5 FIG. 5 is a schematic diagram of monitoring a pregnant woman performing pregnancy gymnastics according to an embodiment of the present application; Figure 6 a schematic diagram of a pre-warning and dynamic adjustment module according to an embodiment of the present application; Figure 7 a schematic diagram of monitoring a pregnant woman to perform water walking according to an embodiment of the present application; Figure 8 a schematic diagram of an interactive guidance management module according to an embodiment of the present application; Figure 9 a schematic diagram of monitoring a pregnant woman to perform Pilates training according to an embodiment of the present application; Figure 10 a schematic diagram of a physiological monitoring based pregnancy exercise safety monitoring system according to an embodiment of the present application; Figure 11 a flowchart of a physiological monitoring based pregnancy exercise safety monitoring method according to an embodiment of the present application; Figure 12 a schematic diagram of monitoring a pregnant woman to perform bodybuilding exercises according to an embodiment of the present application; Figure 13 a schematic diagram of a physiological monitoring based pregnancy exercise safety monitoring method according to an embodiment of the present application; Figure 14 a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0022] A physiological monitoring-based pregnancy exercise safety monitoring system is described below with reference to the accompanying drawings. In view of the lack of personalized guidance mentioned in the background art, the present application provides a physiological monitoring-based pregnancy exercise safety monitoring system. In the physiological monitoring-based pregnancy exercise safety monitoring system, the individual parameter acquisition module is used to obtain uterine myoelectricity, maternal and fetal electrocardiogram physiological signals by using the integrated probe unit, the exercise perception unit captures exercise type, intensity and body position change data, the device monitoring unit obtains electrode contact state information, and the individual information input unit collects pregnant woman individual characteristic data to comprehensively collect multi-dimensional data and improve the data integrity of pregnancy exercise monitoring. With the help of the individual exercise adaptation module, the personal physiological parameter benchmark is established, the LightGBM algorithm is used to analyze the exercise and physiological state adaptation degree, the adaptive threshold algorithm is used to generate exclusive safety threshold combined with historical data, and the individualization and accuracy of exercise risk assessment are improved. Through the early warning and dynamic adjustment module, the risk level is divided based on the random forest algorithm and early warning is issued, personalized exercise guidance and dynamic adjustment scheme are provided according to the risk level, long-term exercise scheme is optimized by summarizing data, and the pertinence and adaptability of personalized guidance are enhanced. The interactive guidance management module displays monitoring data, early warning information and exercise scheme, and realizes doctor-patient collaborative management through remote data transmission to improve information intercommunication and collaborative efficiency. Thus, the problems of single monitoring dimension, insufficient evaluation accuracy and lack of personalized guidance in the prior art are solved.

[0023] Figure 1 A structure diagram of a physiological monitoring-based pregnancy exercise safety monitoring system provided by the embodiment of the present application.

[0024] The embodiment of the present application provides a physiological monitoring-based pregnancy exercise safety monitoring system, which comprises an individual parameter acquisition module 100, an individual exercise adaptation module 200, an early warning and dynamic adjustment module 300 and an interactive guidance management module 400.

[0025] The individual parameter acquisition module 100 is used to collect physiological parameters, pregnant woman exercise state, device state and pregnant woman individual characteristic data; the individual exercise adaptation module 200 is used to establish a personal physiological parameter benchmark, analyze exercise and physiological state adaptation degree, and generate exclusive safety threshold combined with historical data; the early warning and dynamic adjustment module 300 is used to divide risk level and issue early warning and emergency suggestion in abnormal condition, provide personalized exercise guidance based on risk level, dynamically adjust exercise plan, and optimize long-term exercise scheme by summarizing daily data; and the interactive guidance management module 400 is used to display individualized monitoring data, risk early warning information and long-term exercise scheme, and remotely transmit data for doctor-patient collaborative management.

[0026] It can be understood that, in the embodiments of the present application, the individual parameter acquisition module is used to obtain uterine myoelectricity, maternal and fetal electrocardiogram and other physiological signals by using the integrated probe unit, the motion sensing unit captures motion type, intensity and body position change data, the device monitoring unit obtains electrode contact state information, and the individual information input unit collects pregnant woman individual characteristic data, so as to comprehensively collect multi-dimensional data, and improve the data integrity of the monitoring of the pregnant women's exercise; with the aid of the individual exercise adaptation module, the individual physiological parameter benchmark is established, the exercise and physiological state adaptation degree is analyzed by combining the LightGBM algorithm, the adaptive threshold algorithm is used to generate exclusive safety threshold combined with historical data, and the individuality and accuracy of the exercise risk assessment are improved; through the early warning and dynamic adjustment module, the risk level is divided based on the random forest algorithm and early warning is issued, personalized exercise guidance and dynamic adjustment scheme are provided according to the risk level, long-term exercise scheme is optimized by summarizing data, and the pertinence and adaptability of personalized guidance are enhanced; the interactive guidance management module displays monitoring data, early warning information and exercise scheme, and realizes doctor-patient collaborative management through remote data transmission, and improves the information intercommunication and collaborative efficiency. Thus, the problems of single monitoring dimension, insufficient assessment accuracy and lack of personalized guidance in the prior art are solved.

[0027] In the embodiments of the present application, the individual parameter acquisition module 100 includes: as shown in Figure 2 The integrated probe unit, the motion sensing unit, the device monitoring unit and the individual information input unit.

[0028] Among them, the integrated probe unit is used to obtain uterine myoelectricity signal, maternal electrocardiogram, fetal electrocardiogram physiological signal; the motion sensing unit is used to obtain the motion type, motion intensity and body position change data of the pregnant woman; the device monitoring unit is used to obtain electrode contact impedance change information, probe tilt and sliding position state data; the individual information input unit is used for individual characteristic data manually input by the pregnant woman.

[0029] It can be understood that, in the embodiments of the present application, the integrated probe unit obtains uterine myoelectricity signal, maternal electrocardiogram, fetal electrocardiogram physiological signal, provides key data for maternal and infant core physiological state monitoring, and supports the basis of safety assessment; the motion sensing unit obtains the motion type, motion intensity and body position change data of the pregnant woman, and records the exercise state in detail, which provides the basis for the exercise and physiological state adaptation degree analysis; the device monitoring unit obtains electrode contact impedance change information, probe tilt and sliding position state data, improves the reliability of the collected data, and avoids the evaluation misjudgment caused by device problems; the individual information input unit receives the individual characteristic data manually input by the pregnant woman, supplements the individual basic information, and provides support for establishing exclusive physiological parameter benchmark and safety threshold.

[0030] For example, as shown in Figure 3As shown, Ms. Zhang, 25 weeks pregnant, walked slowly along the plastic circular path in the early morning. The integrated probe unit obtained her uterine myoelectric signal without abnormal contraction amplitude, maternal ECG at 68 times / minute at rest and 92 times / minute during walking, and fetal ECG at baseline 142 times / minute and occasional 150 times / minute transient fluctuations; the motion sensing unit captured her step frequency of 90 steps / minute, exercise intensity of 3.0 METs, hip joint angle change of 15° when turning from flat ground to uphill, and stride length reduced from 65 cm to 58 cm; the device monitoring unit showed that the electrode contact impedance was stable at 3.5 kΩ, the probe tilted 0.2° due to clothing friction but did not slide and did not affect signal acquisition; the individual information input unit recorded her age of 29, pre-pregnancy BMI of 22, no pregnancy complications, and the habit of walking 3 times a week before pregnancy. These data covering exercise environment, real-time physiological indicators, action details and individual background provide comprehensive basis for subsequent establishment of personalized physiological parameter benchmark, generation of exclusive safety threshold and analysis of exercise and physiological state adaptation, ensuring accurate assessment of exercise safety and giving appropriate guidance.

[0031] In the embodiments of the present application, the individual exercise adaptation module 200 comprises: Figure 4 As shown, the individual baseline calibration unit, the individual threshold adaptation unit and the multi-parameter correlation analysis unit.

[0032] Among them, the individual baseline calibration unit is used to integrate physiological parameters, pregnant women's exercise state, device state and pregnant women's individual characteristic data to establish individual physiological parameter benchmark; the individual threshold adaptation unit generates exclusive individualized safety threshold based on individual physiological parameter benchmark, combined with pregnant women's historical data in different exercise scenarios, using adaptive threshold algorithm; the multi-parameter correlation analysis unit is used to remove exercise interference in real-time physiological signals through NLMS algorithm, and analyzes the adaptation degree of current exercise and physiological state combined with LightGBM algorithm.

[0033] It should be noted that the adaptive threshold algorithm formula is:

[0034] Among them, is the adaptive threshold value of time ; is the basic threshold value; is a function based on features, historical data and time.

[0035] The LightGBM formula is:

[0036]

[0037]

[0038]

[0039] wherein, is the predicted motion and physiological state fitness; is the initial base fitness reference function; is the weight of the fitness evaluation of the th feature; is the base function corresponding to the th feature; is the total number of physiological parameters and motion-related parameters considered; is the loss function of fitness prediction; is the actual fitness of the pregnant woman's motion and physiological state; is the weight of the fitness evaluation of the th feature in the th iteration; is the partial derivative symbol; is the fitness of the th sample; is the predicted value of the fitness of the th pregnant woman sample at the th iteration; is the number of pregnant woman samples; is the parameter of the minimum value.

[0040] It can be understood that the individual baseline calibration unit of the embodiments of the present application establishes an individual physiological parameter reference by integrating physiological parameters, pregnant woman motion states, device states and pregnant woman individual feature data, providing personalized reference for subsequent analysis; the individual threshold fitness unit generates exclusive individualized safety threshold based on the reference, in combination with historical data of different motion scenarios of pregnant women, using an adaptive threshold algorithm to clearly define the motion safety boundary; the multi-parameter correlation analysis unit eliminates motion interference in real-time physiological signals through the NLMS algorithm, analyzes the fitness of the current motion and physiological state using the LightGBM algorithm, and judges whether the motion is suitable for the current physiological state of the pregnant woman. Together, they provide reference, safety limits and fitness judgments for personalized motion safety evaluation during pregnancy, supporting the system to conduct scientific evaluation and guidance.

[0041] For example, as Figure 5As shown, Ms. Zhou, 24 weeks pregnant, starts the system while doing pregnancy exercise in her living room. The individual parameter acquisition module acquires her uterine electromyography signal normal, maternal resting heart rate 71 beats per minute, fetal heart rate 140 beats per minute, exercise type is hand exercise (intensity 2.3 METs), device state is stable, personal information is 28 years old, BMI 20, no pregnancy abnormalities, and the individual baseline calibration unit integrates these multi-dimensional data to establish her personalized physiological parameter benchmark, for example, the resting heart rate benchmark interval is set to 68-74 beats per minute, and the fetal heart rate benchmark range is 138-145 beats per minute. The individual threshold adaptation unit generates exclusive safety thresholds based on the benchmark and in combination with the historical data of her 6 hand exercise practices in the past two weeks through an adaptive threshold algorithm: the upper limit of exercise heart rate is 122 beats per minute, the continuous exercise duration is not more than 15 minutes, and the joint activity angle is not more than 40°. After 8 minutes of exercise, the multi-parameter correlation analysis unit first starts the NLMS algorithm to accurately exclude signal interference caused by limb swinging to obtain pure physiological signals: maternal heart rate rises to 115 beats per minute, fetal heart rate is 143 beats per minute, and uterine electromyography signal remains stable. Subsequently, the system calls the LightGBM algorithm to comprehensively analyze the correlation between real-time exercise intensity, body position changes and physiological indicators, and finally obtains the adaptation degree of the current exercise and physiological state as 91%, indicating that the exercise state is safe and suitable for Ms. Zhou.

[0042] In the embodiments of the present application, the NLMS algorithm formula is:

[0043]

[0044]

[0045] wherein, represents the estimated value of exercise interference; represents the filter weight vector; represents the transpose of the vector; represents the input signal vector; represents the pure physiological signal after removing exercise interference; represents the expected signal; represents the step factor; represents the regularization parameter; represents the interference intensity.

[0046] It can be understood that the embodiments of the present application continuously update the filter weight vector through iteration, dynamically adapt to the interference changes in different exercise scenarios, ensure that the uterine electromyography signal, maternal and fetal electrocardiogram and other physiological signals are not affected by the additional interference brought by exercise when the pregnant woman exercises, and guarantee the authenticity and reliability of the signals, providing accurate data basis for subsequent analysis.

[0047] For example, when Ms. Lin, who was 29 weeks pregnant, was doing low-intensity training on a stationary bike at a community gym, the NLMS algorithm was activated to process her real-time physiological signals. At this time, the maternal electrocardiogram (ECG) signal collected by the integrated probe unit was mixed with interference from the vibration of the bike. The input signal vector was x(0)=[0.3,0.4], the expected signal was d(0)=1.5 (the original ECG signal containing interference), the initial weight vector of the filter was W(0)=[0,0], the step size factor was μ=0.12, and the regularization parameter was δ=0.02. The NLMS algorithm quickly processed the signal: first, it calculated the estimated value of motion interference, then obtained the pure ECG signal after removing the interference, and dynamically updated the filter weights. When the ride entered the 3rd minute (n=1), the slight shaking of the bike caused the interference to increase. The input signal vector was x(1)=[0.35,0.45], the expected signal was d(1)=1.6, and the pure signal output after the algorithm processing was e(1)=1.42, which more clearly reflected the changes in the maternal heart rate than the original signal. Continuing to ride until the 5th minute (n=2), x(2)=[0.32,0.41], d(2)=1.55, and the processed e(2)=1.38, effectively filtering out the periodic interference caused by pedaling alternation. This provides a reliable basis for safety assessment.

[0048] In this embodiment, the early warning and dynamic adjustment module 300 includes: Figure 6 As shown, there are risk monitoring and early warning units, personalized adjustment units, and trend iteration units.

[0049] The risk monitoring and early warning unit uses real-time monitoring parameters and preset individualized safety thresholds, combined with the adaptability analysis of the current exercise and physiological state, to classify risk levels using a random forest algorithm, and issues early warnings and emergency suggestions in abnormal situations; the personalized adjustment unit provides personalized exercise guidance based on risk levels and dynamically adjusts exercise plans; the trend iteration unit is used to automatically summarize daily exercise data and corresponding physiological parameter trend data, update and optimize long-term exercise plans and individualized safety thresholds.

[0050] It should be noted that the formula for the Random Forest algorithm is:

[0051]

[0052] in, The dataset is composed of real-time monitoring parameters, preset individualized safety thresholds, and the degree of adaptation between exercise and physiological state. The Gini index; The number of risk level categories; It is the first in the dataset The proportion of samples of each class; The final predicted risk level; The number of decision trees; For the first The predicted risk level of each decision tree; For indicator functions; To solve for the function.

[0053] It is understood that the risk monitoring and early warning unit in this application embodiment, through real-time monitoring parameters and preset individualized safety thresholds, combined with the adaptability analysis of the current exercise and physiological state, uses a random forest algorithm to classify risk levels, issues early warnings and provides emergency suggestions when abnormal situations occur, providing timely risk assessment for exercise safety during pregnancy. The personalized adjustment unit provides personalized exercise guidance based on the risk level, dynamically adjusting the exercise plan to better suit the pregnant woman's real-time condition. The trend iteration unit automatically summarizes daily exercise data and corresponding physiological parameter trend data, updates and optimizes long-term exercise plans and individualized safety thresholds, enabling the assessment system to continuously adapt to the pregnant woman's physiological changes, improving the accuracy and safety of exercise guidance.

[0054] For example, such as Figure 7 As shown, Ms. Zhao, 27 weeks pregnant, was walking in an indoor heated pool. The individual parameter acquisition module had already obtained stable uterine electromyography signals, a maternal resting heart rate of 70 beats / minute, and a fetal heart rate of 142 beats / minute. The exercise type was water walking (intensity 2.2 METs), and the equipment was functioning normally. Simultaneously, it directly retrieved the individualized safety thresholds generated by the personalized exercise adaptation module: an upper limit of 125 beats / minute for heart rate during exercise, a water temperature adaptation range of 28-30℃, and an 88% fit between the current exercise and her physiological state obtained from the multi-parameter correlation analysis unit. After 12 minutes of exercise, Ms. Zhao increased her pace. The exercise sensing unit detected that the intensity had increased to 2.6 METs, and the integrated probe unit showed that the maternal heart rate had increased to 128 beats / minute. The risk monitoring and early warning unit immediately compared the real-time parameters with the safety thresholds, combined with the change in fit, and classified the risk level as Level 2 using a random forest algorithm, simultaneously issuing an early warning: "Heart rate slightly high, it is recommended to slow down." Based on this level, the personalized adjustment unit pushed a guidance plan: "Adjust the cadence to 30 steps / minute, and you can switch to 1 minute of static stretching in the water." Three minutes after the adjustment, the mother's heart rate dropped to 118 beats / minute, and the fit increased to 86%. After the exercise ended that day, the trend iteration unit automatically summarized the data and found that Ms. Zhao's fit was higher at a water temperature of 29℃. Therefore, the water temperature recommendation in the long-term exercise plan was refined to 29±0.5℃, and the upper limit of the safe heart rate for walking in the water was slightly adjusted to 126 beats / minute, making the plan more suitable for her physical condition.

[0055] In this embodiment of the application, the interactive guidance management module 400 includes, as follows: Figure 8The user interaction display unit, the AR action guidance unit, and the remote collaboration unit are shown.

[0056] The user interaction display unit is configured to display individualized monitoring data, risk warning information, exercise suggestions, and long-term exercise programs in real time, and receive feedback from the pregnant woman. The AR action guidance unit is configured to provide standardized action guidance through AR to help the pregnant woman maintain correct posture during exercise. The remote collaboration unit is configured to transmit real-time data to a cloud server or a doctor terminal for data sharing and remote medical monitoring.

[0057] It can be understood that the user interaction display unit of the embodiment of the present application displays various monitoring information and programs in real time and receives feedback, allowing the pregnant woman to intuitively grasp her own exercise and physiological conditions and adjust her exercise behavior in a timely manner. The AR action guidance unit provides standardized action guidance to help the pregnant woman maintain correct exercise posture and reduce risks caused by improper actions. The remote collaboration unit realizes real-time data transmission and sharing, facilitating remote monitoring by doctors, allowing the pregnant woman to obtain timely professional guidance, improving the safety and scientific nature of exercise during pregnancy, and providing comprehensive support for personalized exercise during pregnancy.

[0058] For example, as shown in Figure 9 When Ms. Zheng, who is 28 weeks pregnant, is doing a prenatal Pilates exercise at home, the user interaction display unit displays her various data in real time on the screen: maternal heart rate 112 beats per minute, fetal heart rate 146 beats per minute, current exercise intensity 2.3 METs, and pops up risk warning information "left lateral turning action amplitude is too large" and exercise suggestion "adjust the turning angle of the torso to within 15°". Ms. Zheng clicks the screen to feedback "has been adjusted". At this time, the AR action guidance unit captures her action through the front camera and projects a standardized action virtual image on the wall to prompt her "right hand should extend along the mat surface to avoid hunching the shoulders", helping her quickly correct her posture. The remote collaboration unit encrypts the real-time monitoring data and transmits it to the cloud server, and the doctor terminal receives it synchronously. The doctor observes that her uterine muscle electrical signal is stable, and remarks "current exercise state is appropriate, can maintain for 10 minutes and then rest" in the system, and the information is immediately transmitted back to Ms. Zheng's device terminal.

[0059] This application proposes a pregnancy exercise safety monitoring system based on physiological monitoring. Through an individual parameter acquisition module, an integrated probe unit acquires physiological signals such as uterine electromyography and maternal and fetal electrocardiograms. A motion sensing unit captures data on exercise type, intensity, and positional changes. An equipment monitoring unit acquires electrode contact status information. An individual information entry unit collects individual characteristic data of the pregnant woman, enabling comprehensive multi-dimensional data acquisition and improving the data integrity of pregnancy exercise monitoring. A personalized exercise adaptation module establishes personal physiological parameter benchmarks and analyzes the fit between exercise and physiological state using the LightGBM algorithm. An adaptive threshold algorithm, combined with historical data, generates a unique safety threshold, improving the personalization and accuracy of exercise risk assessment. An early warning and dynamic adjustment module classifies risk levels based on a random forest algorithm and issues early warnings. Personalized exercise guidance and dynamic adjustment plans are provided according to the risk level, and data is aggregated to optimize long-term exercise plans, enhancing the relevance and adaptability of personalized guidance. An interactive guidance management module displays monitoring data, early warning information, and exercise plans. Remote data transmission enables collaborative management between doctors and patients, improving information exchange and collaboration efficiency. This solves the problems of single monitoring dimensions, insufficient assessment accuracy, and lack of personalized guidance in existing technologies.

[0060] The following will illustrate a pregnancy exercise safety monitoring system based on physiological monitoring through a specific embodiment, such as... Figure 10 As shown, it includes: When Ms. Zhao, who was 26 weeks pregnant, was briskly walking in the city forest park in the morning, the individual parameter acquisition module was activated first, and its various units operated synchronously: the integrated probe unit accurately captured the uterine electromyography signal (no abnormal uterine contraction waves, amplitude stable at 3μV) within 3 seconds, the maternal resting heart rate of 69 beats / minute, and the fetal baseline heart rate of 142 beats / minute; the motion sensing unit recorded the exercise type as brisk walking, the initial step frequency of 88 steps / minute, the exercise intensity of 2.9 METs, and the body forward lean angle of 6° through the accelerometer; the device monitoring unit displayed the electrode contact impedance in real time as 3.7kΩ (within the normal range of 2-5kΩ), the probe did not slip when attached to the abdomen, and the tilt angle was <1°; the individual information entry unit retrieved Ms. Zhao's preset data: 30 years old, mid-pregnancy, pre-pregnancy BMI of 21.5, no pregnancy complications, and an average exercise duration of 22 minutes in the last 12 sessions.

[0061] These data are transmitted in real time to the individual motion adaptation module, which has various units working in coordination: the individual baseline calibration unit immediately integrates multidimensional information such as physiological parameters, motion state, device state, and individual characteristics, and establishes a physiological parameter benchmark - the maternal resting heart rate benchmark interval 66-72 beats per minute, the fetal heart rate benchmark interval 139-145 beats per minute, and the normal fluctuation threshold of uterine electromyography <6 μV; the individual threshold adaptation unit, based on the benchmark, calls the historical data of Ms. Zhao's last 12 times of fast walking (average exercise heart rate 116 beats per minute, maximum 120 beats per minute), and generates exclusive safety thresholds through an adaptive threshold algorithm: , the upper limit of exercise heart rate 124 beats per minute, continuous fast walking not more than 16 minutes, and uterine contraction frequency ≤1 time per 30 minutes; the multi-parameter correlation analysis unit is started simultaneously, first through the NLMS algorithm formula: 、 、 , after eliminating signal interference and obtaining pure physiological signals, combining the LightGBM algorithm formula: 、 、 、 , the adaptation degree of the current exercise and physiological state is analyzed, with an initial value of 89%.

[0062] When the exercise has been going on for 10 minutes, Ms. Zhao walks on a gentle slope with a slope of 7°. The exercise perception unit monitors that the step frequency rises to 92 steps per minute, the exercise intensity increases to 3.3 METs, and the maternal heart rate rises to 123 beats per minute. The multi-parameter correlation analysis unit again processes the signal through the NLMS algorithm, showing that the fetal heart rate is 146 beats per minute (still within the benchmark interval), and the adaptation degree decreases to 85%. At this time, the units of the early warning and dynamic adjustment module begin to operate: the risk monitoring and early warning unit compares the real-time parameters with the preset individualized safety thresholds, combines the changes in the adaptation degree, and through the random forest algorithm formula: 、 , the risk level is divided into level one, and the user interaction display unit of the interactive guidance management module pops up the early warning information: "heart rate close to the upper limit, suggest slowing down the step frequency to 85 steps per minute". The individualized adjustment unit provides an adjustment scheme simultaneously: "can change to slow walking for 1 minute and then restore the original speed", and dynamically adjusts the current exercise plan.

[0063] After Ms. Zhao adjusted her posture as suggested, the AR motion guidance unit captured her gait through her phone's camera and projected a standardized brisk walking posture image onto the screen, prompting her to "reduce stride length by 2cm to reduce knee pressure" and helping her maintain the correct posture. Three minutes later, the individual parameter acquisition module showed that the mother's heart rate had dropped to 118 beats per minute, the fetal heart rate was 144 beats per minute, and the compatibility had recovered to 87%. The remote collaboration unit encrypted and transmitted the real-time data to the cloud server. After reviewing the data on the terminal, Ms. Zhao's attending physician provided feedback through the system: "Current condition is good; you can continue exercising for 5 minutes before resting."

[0064] After the exercise, the trend iteration unit of the early warning and dynamic adjustment module automatically summarizes the exercise data of the day (including the total brisk walking time of 15 minutes, the step frequency range of 88-92-85 steps / minute, the exercise intensity fluctuation of 2.9-3.3-3.0 METs) and the corresponding physiological parameter trends (maternal heart rate from 69→123→118 beats / minute, fetal heart rate stable at 142-146-144 beats / minute, uterine electromyography always <3μV). This data is then integrated with Ms. Zhao's historical exercise data from the past 12 times to update and optimize her long-term exercise plan, while fine-tuning the individualized safety threshold to make it more in line with the physiological state of 26 weeks of pregnancy.

[0065] In summary, this application embodiment constructs a system comprising an individual parameter acquisition module, a personalized exercise adaptation module, an early warning and dynamic adjustment module, and an interactive guidance management module to comprehensively assess the safety of personalized exercise during pregnancy. The individual parameter acquisition module collects data from multiple dimensions, providing a foundation for the assessment; the personalized exercise adaptation module establishes physiological benchmarks, generates safety thresholds, and analyzes the degree of adaptation, ensuring the personalization of the assessment; the early warning and dynamic adjustment module classifies risk levels, issues warnings, and adjusts exercise plans to ensure exercise safety; the interactive guidance management module displays information, provides movement guidance, and enables doctor-patient collaboration, improving management efficiency. The collaborative work of these modules enhances the safety of exercise during pregnancy and the accuracy of personalized guidance, providing a scientific guarantee for exercise during pregnancy.

[0066] Next, referring to the accompanying drawings, a method for monitoring the safety of exercise during pregnancy based on physiological monitoring, according to an embodiment of this application, is described.

[0067] like Figure 11 As shown, this method for monitoring the safety of exercise during pregnancy based on physiological monitoring includes the following steps: In step S101, physiological parameters, the pregnant woman's exercise status, equipment status, and the pregnant woman's individual characteristics data are acquired.

[0068] It can be understood that the embodiments of the present application comprehensively capture the information related to the exercise during pregnancy by acquiring physiological parameters, pregnant woman exercise state, device state and pregnant woman individual characteristic data, provide multi-dimensional original basis for establishing individual physiological parameter benchmark, guarantee the generation of exclusive individualized safety threshold; support the analysis of the adaptation degree of exercise and physiological state, help to divide the risk level and issue early warning, and promote the implementation of personalized exercise safety evaluation during pregnancy.

[0069] In step S102, according to the physiological parameters, the pregnant woman exercise state, the device state and the pregnant woman individual characteristic data, the individual physiological parameter benchmark is established, and the exclusive individualized safety threshold is generated by using the adaptive threshold algorithm in combination with the historical data of the pregnant woman in different exercise scenes.

[0070] The individual physiological parameter benchmark is a standard value or normal range that reflects whether it is safe or exceeds the individual tolerance limit, which is established by integrating physiological parameters, pregnant woman exercise state, device state and pregnant woman individual characteristic data.

[0071] It can be understood that the embodiments of the present application integrate multi-dimensional data, make the setting of safety threshold more suitable for the physiological characteristics of pregnant women, provide a benchmark for analyzing the adaptation degree of exercise and physiological state, improve the pertinence and accuracy of the adaptation degree analysis, and guarantee the scientificity and individualization of the whole exercise safety evaluation during pregnancy.

[0072] For example, when Ms. Liu, who is 24 weeks pregnant, exercises yoga during pregnancy, the individual exercise adaptation module obtains the uterine electromyographic signal amplitude 4μV, the maternal resting heart rate 68 times / minute, the fetal heart rate 140 times / minute, the exercise intensity 2.1 METs, the electrode impedance 3.2kΩ, the age 29 years old, the BMI 20, and no record of abnormal pregnancy by integrating the individual parameter acquisition module, establishes the individual physiological parameter benchmark: the maternal resting heart rate benchmark interval 65-71 times / minute, the fetal heart rate benchmark 138-142 times / minute, and the normal amplitude of uterine electromyography <6μV, and provides individualized reference standards for subsequent generation of exclusive individualized safety threshold and analysis of the adaptation degree of exercise and physiological state.

[0073] In step S103, during the exercise of the pregnant woman, the NLMS algorithm is used to eliminate the additional interference signals generated by the exercise, the LightGBM algorithm is used to analyze the adaptation degree of the current exercise and physiological state, the device real-time monitoring data and the individualized safety threshold are combined, and the random forest algorithm is used to divide the risk level.

[0074] The risk level refers to the classification of the safety risk that may be caused by the mismatch between the exercise state and the physiological state of the pregnant woman during exercise.

[0075] It should be noted that when the risk is low, the real-time monitoring data is less than 80% of the upper limit of the individual safety threshold, and the fitness of the exercise and physiological state is 80% or more, at this time, the continuous monitoring data, the pregnant woman can continue to perform according to the long-term exercise scheme, when the risk is medium, the real-time monitoring data is more than 80% but less than 100% of the upper limit of the individual safety threshold, and the fitness of the exercise and physiological state is between 60% and 79%, it is recommended to appropriately reduce the exercise intensity or shorten the exercise time, adjust the exercise type to a more gentle project, when the risk is high, the real-time monitoring data is more than 100% of the upper limit of the individual safety threshold, and the fitness of the exercise and physiological state is less than 60%, an early warning is immediately issued and emergency suggestions are provided, the data is synchronized to the doctor end, and further professional guidance is waited.

[0076] It can be understood that the embodiments of the present application provide targeted guidance for pregnant women's exercise by dividing the risk level, warning and providing emergency suggestions for abnormal conditions, dynamically adjusting the exercise plan, and at the same time, the auxiliary trend iteration unit optimizes the long-term exercise scheme, ensures the safety of the exercise during pregnancy, and improves the adaptability and effectiveness of the exercise scheme.

[0077] For example, Ms. Zhang, who is 24 weeks pregnant, after walking for 30 minutes, the real-time monitoring of her uterine myoelectric signal rises to 0.45mV, the maternal heart rate is 90 beats per minute, the fetal heart rate is 155 beats per minute, and the exercise state is still fast walking (step frequency 100 steps per minute). The multi-parameter correlation analysis unit calculates that the fitness of the exercise and physiological state is 70%. The risk monitoring and early warning unit determines that the risk is secondary (medium risk) by combining the real-time parameters and the safety threshold through the random forest algorithm. Then, the system issues a warning and suggests reducing the step frequency to 80 steps per minute, and continues to monitor. After adjusting for 10 minutes, the parameters fall back to uterine myoelectric signal 0.35mV, maternal heart rate 80 beats per minute, fetal heart rate 145 beats per minute, and the fitness increases to 85%, which ensures the safety of the exercise.

[0078] In step S104, according to the risk level, individualized exercise guidance is performed, the exercise plan is dynamically adjusted, at the same time, daily exercise data and corresponding physiological parameter trend data are automatically summarized, the long-term exercise scheme and the individualized safety threshold are updated and optimized, and the data is transmitted to the cloud server for remote medical guidance.

[0079] It can be understood that the embodiments of the present application ensure the safety of the exercise during pregnancy by individualized guidance and plan adjustment, use data summarization and optimization to make the exercise scheme continuously adapt to the physiological changes of the pregnant woman, improve the scientificity and effectiveness of the long-term exercise, realize doctor-patient collaborative management through remote data transmission, enhance the timeliness and professionalism of the exercise monitoring during pregnancy, and ensure the safety and health of the pregnant woman.

[0080] For example, as Figure 12As shown, Ms. Li, 25 weeks pregnant, is doing bodybuilding exercises for 18 minutes, and the system classifies her current exercise risk as level two (medium risk), and then guides her to reduce the action frequency to 25 beats per measure, reduce jumping actions, and increase the proportion of stretching actions. After adjusting, the parameters change to uterine myoelectric signal 0.37 mV, maternal heart rate 85 beats per minute, and fetal heart rate 146 beats per minute after 12 minutes, and the fitness degree increases to 84%. After the exercise is completed, the system automatically summarizes the data: 30 minutes of bodybuilding exercises (including 12 minutes after adjustment) in a day, the peak uterine myoelectric signal is 0.43 mV, and the average maternal heart rate is 89 beats per minute. Combined with the data trend in the past 10 days, the upper limit of the single duration of bodybuilding exercises in the long-term exercise plan is adjusted from 20 minutes to 18 minutes, and the data is transmitted to the cloud server. The doctor feedbacks that "the current adjustment is good, and it is suggested to add 5 minutes of pelvic floor muscle contraction action to the bodybuilding exercise tomorrow.

[0081] According to the embodiment of the present application, a physiological monitoring-based exercise safety monitoring method for pregnant women is provided. The individual parameter acquisition module is used to obtain uterine myoelectricity, maternal and fetal electrocardiogram physiological signals by using an integrated probe unit, the exercise perception unit is used to capture exercise type, intensity and body position change data, the device monitoring unit is used to obtain electrode contact state information, and the individual information input unit is used to collect pregnant woman individual characteristic data. The multi-dimensional data is comprehensively collected to improve the data integrity of the exercise monitoring during pregnancy. With the help of the individual exercise adaptation module, the individual physiological parameter benchmark is established, the exercise and physiological state fitness degree is analyzed by using the LightGBM algorithm, and the exclusive safety threshold is generated by using the adaptive threshold algorithm combined with historical data to improve the individuality and accuracy of exercise risk assessment. Through the early warning and dynamic adjustment module, the risk level is divided based on the random forest algorithm and early warning is issued, individualized exercise guidance and dynamic adjustment scheme are provided according to the risk level, data is summarized to optimize the long-term exercise plan, and the pertinence and adaptability of individualized guidance are enhanced. The interactive guidance management module displays monitoring data, early warning information and exercise scheme, and realizes doctor-patient collaborative management through remote data transmission to improve information intercommunication and collaborative efficiency. Thus, the problems of single monitoring dimension, insufficient assessment accuracy and lack of individualized guidance in the prior art are solved.

[0082] A physiological monitoring-based exercise safety monitoring method for pregnant women will be described below through a specific embodiment, such as Figure 13 As shown, it comprises: Ms. Chen, 28 weeks pregnant, is doing a pregnant woman's yoga exercise. First, the relevant data is obtained: the physiological parameters are maternal resting heart rate 70 beats per minute, uterine myoelectric signal 0.2 mV, and fetal heart rate 130 beats per minute; the exercise state is to practice 30 minutes of gentle yoga, and the initial action is mountain standing; the device state shows that the electrode contact is good and there is no abnormality; the individual characteristics include no pregnancy complications, height 160 cm, and weight 58 kg.

[0083] Then, according to these data, the individual physiological parameter baseline is established, and combined with Ms. Chen's historical data of the past 3 times of yoga exercise, the adaptive threshold algorithm formula is used: The exclusive safety threshold is generated: the upper limit of maternal heart rate is 90 beats / min, the upper limit of uterine myoelectric signal is 0.4 mV, the normal range of fetal heart rate is 120-160 beats / min, and the single action holding time is not more than 20 seconds.

[0084] After the start of the exercise, during the cat-cow action at the 8th minute, the NLMS algorithm formula is used: 、 、 The signal interference caused by body fluctuation is removed to obtain pure physiological data: maternal heart rate 82 beats / min, uterine myoelectric signal 0.3 mV, fetal heart rate 138 beats / min. Using the LightGBM algorithm formula: 、 、 、 , it is concluded that the current exercise and physiological state adaptation degree is 80%. Continue to exercise to the 15th minute to perform baby style, real-time monitoring of maternal heart rate 88 beats / min, uterine myoelectric signal 0.38 mV, combined with safety threshold, through the random forest algorithm formula: 、 The risk level is divided into level one (low risk).

[0085] According to the risk level, Ms. Chen is guided to maintain the current action rhythm. When switching to butterfly style at the 25th minute of exercise, the maternal heart rate rises to 92 beats / min, exceeding the safety threshold, and the risk level is adjusted to level two (medium risk), and it is immediately suggested to shorten the action holding time to 10 seconds. After 5 minutes of adjustment, the data falls back to maternal heart rate 85 beats / min, uterine myoelectric signal 0.32 mV, and the adaptation degree rises to 85%. After the end of the exercise, the data of the day is automatically summarized: total duration 30 minutes, peak maternal heart rate 92 beats / min, peak uterine myoelectric signal 0.38 mV, combined with the trend in the past week, the upper limit of single holding time of butterfly style in the long-term exercise program is adjusted from 15 seconds to 12 seconds, the upper limit of maternal heart rate in the safety threshold is adjusted to 88 beats / min, and the data is transmitted to the cloud. After the doctor checks, it is feedback to continue to maintain the current exercise intensity, and add 5 minutes of breathing exercise the next day. This process completes the whole process safety control of pregnancy yoga exercise, improves the dynamic adaptation of exercise program and physiological state of pregnant women, and guarantees the scientificity and safety of pregnancy exercise.

[0086] In summary, the embodiment of the present application obtains physiological parameters, a pregnant woman's exercise state, device state and individual characteristic data of the pregnant woman, establishes a personal benchmark and generates an exclusive safety threshold, eliminates interference signals during exercise, analyzes fitness and divides a risk level, guides exercise and adjusts a plan, simultaneously summarizes data and optimizes a scheme and transmits the scheme to the cloud for remote guidance. The embodiment dynamically adapts to physiological changes of the pregnant woman, avoids exercise risks in a timely manner, guarantees safety and scientific nature of the exercise during pregnancy, improves precision and effectiveness of the exercise scheme through doctor-patient collaborative management, and provides reliable evaluation and personalized exercise guidance for the exercise during pregnancy.

[0087] Figure 14 A structural schematic diagram of an electronic device provided by the embodiment of the present application is provided. The electronic device can include: The memory 1401, the processor 1402 and the computer program stored in the memory 1401 and executable on the processor 1402.

[0088] The processor 1402 implements the method for monitoring safety of exercise during pregnancy based on physiological monitoring provided in the above embodiment when executing the program.

[0089] Further, the electronic device further includes: The communication interface 1403 is used for communication between the memory 1401 and the processor 1402.

[0090] The memory 1401 is used for storing the computer program executable on the processor 1402.

[0091] The memory 1401 can include a high-speed RAM (Random Access Memory, random access memory) memory, and can also include a non-volatile memory, for example, at least one disk memory.

[0092] If the memory 1401, the processor 1402 and the communication interface 1403 are independently implemented, the communication interface 1403, the memory 1401 and the processor 1402 can be connected to each other through a bus and complete communication between each other. The bus can be an ISA (Industry Standard Architecture, industry standard architecture) bus, a PCI (Peripheral Component, peripheral component interconnect) bus or an EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 14 Only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0093] Optionally, in a specific implementation, if the memory 1401, the processor 1402 and the communication interface 1403 are integrated on a chip, the memory 1401, the processor 1402 and the communication interface 1403 can complete the communication among each other through an internal interface.

[0094] The processor 1402 can be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to perform the embodiments of the present application.

[0095] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the physiological monitoring based pregnancy exercise safety monitoring method.

[0096] In addition, the embodiments of the present application also provide a computer program product, which includes a computer program or instructions, and the computer program or instructions are executed to implement the physiological monitoring based pregnancy exercise safety monitoring method.

[0097] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms is not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0098] In addition, the terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0099] Any processes or methods described in the flow charts or otherwise described herein can be understood as representing code modules, segments, or portions of code which include one or more executable instructions for implementing specific logic functions (or steps) of the application, and alternate implementations are possible. In this description and in the claims, steps or functions can be described or claimed in a manner that can sometimes alter the order of the steps or functions, including steps that are described, discussed or illustrated in a serial fashion in this description and in the claims. No additional limitations are intended or should be implied from the order of steps or functions as described, discussed or illustrated in this description and in the claims.

[0100] It should be understood that portions of the application can be implemented in hardware, software, firmware, or combinations thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. As such, if implemented in hardware, and in another embodiment, any of the following technologies, or combinations thereof, can be used: discrete logic circuitry having logic gates for implementing logic functions upon an application of data signals, application-specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field-programmable gate arrays (FPGA), and the like.

[0101] Those of ordinary skill in the art can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing relevant hardware, and the programs can be stored in a computer-readable storage medium. When the programs are executed, they include one or a combination of the steps of the method embodiments.

[0102] Although the embodiments of the application have been shown and described above, it should be understood that the above embodiments are exemplary and are not to be construed as limiting the application, and those of ordinary skill in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the application.

Claims

1. A pregnancy exercise safety monitoring system based on physiological monitoring, characterized in that, include: The module includes an individual parameter acquisition module, a personalized exercise adaptation module, an early warning and dynamic adjustment module, and an interactive guidance and management module; among them, The individual parameter acquisition module is used to collect physiological parameters, pregnant woman's exercise status, equipment status, and pregnant woman's individual characteristics data. The personalized exercise adaptation module is used to establish personal physiological parameter benchmarks, analyze the degree of adaptation between exercise and physiological state, and generate exclusive safety thresholds by combining historical data. The early warning and dynamic adjustment module is used to classify risk levels and issue early warnings and emergency suggestions in abnormal situations. At the same time, based on the risk level, it provides personalized exercise guidance, dynamically adjusts exercise plans, and summarizes daily data to optimize long-term exercise programs. The interactive guidance management module is used to display individualized monitoring data, risk warning information and long-term exercise plans, and remotely transmit data for collaborative management between doctors and patients.

2. The pregnancy exercise safety monitoring system based on physiological monitoring according to claim 1, characterized in that, The individual parameter acquisition module includes an integrated probe unit, a motion sensing unit, a device monitoring unit, and an individual information input unit. The integrated probe unit is used to acquire uterine electromyography signals, maternal electrocardiogram (ECG), and fetal ECG physiological signals. The motion sensing unit is used to acquire data on the pregnant woman's movement type, movement intensity, and body position changes. The device monitoring unit is used to acquire information on changes in electrode contact impedance, probe tilt, and sliding position status. The individual information input unit is used for the pregnant woman to manually input individual characteristic data.

3. The pregnancy exercise safety monitoring system based on physiological monitoring according to claim 1, characterized in that, The personalized exercise adaptation module includes an individual baseline calibration unit, an individual threshold adaptation unit, and a multi-parameter correlation analysis unit. The individual baseline calibration unit integrates physiological parameters, the pregnant woman's exercise status, device status, and the pregnant woman's individual characteristics to establish an individual physiological parameter baseline. The individual threshold adaptation unit, based on the individual physiological parameter baseline and combined with the pregnant woman's historical data in different exercise scenarios, uses an adaptive threshold algorithm to generate a unique, personalized safety threshold. The multi-parameter correlation analysis unit uses the NLMS algorithm to remove motion interference from real-time physiological signals and combines it with the LightGBM algorithm to analyze the fit between the current exercise and physiological status.

4. The pregnancy exercise safety monitoring system based on physiological monitoring according to claim 1, characterized in that, The NLMS algorithm formula is as follows: in, Represents the estimated value of motion disturbance; Represents the filter weight vector; Represents the transpose of a vector; Represents the input signal vector; This indicates the pure physiological signal after removing motion interference; Indicates the desired signal; Indicates the step size factor; Represents the regularization parameter; Indicates the intensity of interference.

5. A pregnancy exercise safety monitoring system based on physiological monitoring according to claim 1, characterized in that, The early warning and dynamic adjustment module includes a risk monitoring and early warning unit, a personalized adjustment unit, and a trend iteration unit. The risk monitoring and early warning unit, through real-time monitoring of parameters and preset individualized safety thresholds, combined with an analysis of the fit between current exercise and physiological state, classifies risk levels using a random forest algorithm and issues early warnings and emergency suggestions in abnormal situations. The personalized adjustment unit provides personalized exercise guidance based on the risk level and dynamically adjusts the exercise plan. The trend iteration unit automatically summarizes daily exercise data and corresponding physiological parameter trend data to update and optimize the long-term exercise plan and the individualized safety thresholds.

6. A pregnancy exercise safety monitoring system based on physiological monitoring according to claim 1, characterized in that, The interactive guidance management module includes a user interaction display unit, an AR motion guidance unit, and a remote collaboration unit. The user interaction display unit is used to display individualized monitoring data, risk warning information, exercise suggestions, and long-term exercise plans in real time, and to receive feedback from pregnant women. The AR motion guidance unit is used to provide standardized motion guidance through AR to help pregnant women maintain the correct posture during exercise. The remote collaboration unit is used to transmit real-time data to a cloud server or doctor's terminal for data sharing and remote medical monitoring.

7. A method for monitoring the safety of exercise during pregnancy based on physiological monitoring, characterized in that, include: Acquire physiological parameters, pregnant woman's exercise status, equipment status, and individual characteristics of the pregnant woman; Based on the physiological parameters, the pregnant woman's exercise status, the equipment status, and the pregnant woman's individual characteristics, a personal physiological parameter benchmark is established. Combined with the pregnant woman's historical data in different exercise scenarios, an adaptive threshold algorithm is used to generate a unique individual safety threshold. During exercise by pregnant women, the NLMS algorithm is used to remove additional interference signals generated by exercise, the LightGBM algorithm is used to analyze the fit between the current exercise and physiological state, and the risk level is classified by combining real-time monitoring data from the device with the individualized safety threshold. Based on the risk level, personalized exercise guidance is provided, and the exercise plan is dynamically adjusted. At the same time, daily exercise data and corresponding physiological parameter trend data are automatically summarized, the long-term exercise plan and the individualized safety threshold are updated and optimized, and the data is transmitted to the cloud server for remote medical guidance.

8. An electronic device, characterized in that, include: The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for monitoring the safety of exercise during pregnancy based on physiological monitoring as described in claim 7.

9. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed, they implement the method for monitoring the safety of exercise during pregnancy based on physiological monitoring as described in claim 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed, they implement the method for monitoring the safety of exercise during pregnancy based on physiological monitoring as described in claim 7.

Images