Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a remote health management service method based on big data.
The first aspect of the invention discloses a remote health management service method based on big data, which comprises the following steps:
S1, tracking and monitoring posture changes of a pregnant woman body in a movement process in real time through a sensor, collecting movement data of different movement types of the pregnant woman, and dynamically adjusting monitoring frequency and monitoring sensitivity of the movement process of the pregnant woman according to the movement data;
S2: analyzing motion parameters in the process of pregnant woman motion according to the motion data acquired by the sensor, evaluating the intensity level of the motion through the motion parameters, and adapting the monitoring scheme of the corresponding level to different intensity levels;
s3: acquiring physical characteristics and basic information of pregnant women, wherein the physical characteristics comprise body weight, abdomen size, spine curvature and pelvic bone position, and the basic information comprises age and health status;
s4: judging health threats existing in the movement process of the pregnant woman according to the bearing range of the gesture deformation and the movement data of the pregnant woman, and informing the pregnant woman of the health threats through mobile application to reduce the intensity level of movement and/or change the movement mode;
S5: assessing physical fitness of the pregnant woman according to the exercise frequency, exercise intensity and exercise state of the pregnant woman, wherein the exercise state comprises heart rate, blood pressure and balance of the pregnant woman;
S6: presetting a physical fitness threshold of a pregnant woman, judging whether the physical fitness evaluation of the pregnant woman is lower than the physical fitness threshold, if yes, mapping and analyzing physical characteristic data of the pregnant woman changing during pregnancy and the physical fitness of the pregnant woman so as to evaluate the correlation of the change of the physical characteristic of the pregnant woman during pregnancy and the physical fitness of the pregnant woman, and determining the influence degree of the change of the physical characteristic of the pregnant woman on the physical fitness of the pregnant woman;
S7: and according to the influence degree evaluation of the change of the physical characteristics of the pregnant woman on the physical adaptability of the pregnant woman, providing personalized remote health management service for the pregnant woman, continuously monitoring real-time data and feedback data of the remote health management service, and periodically evaluating and adjusting the remote health management service of the pregnant woman.
In an optional embodiment, the monitoring the posture change of the pregnant woman body during the exercise process by the sensor in real time, collecting exercise data of different exercise types of the pregnant woman, and dynamically adjusting the monitoring frequency and the monitoring sensitivity of the exercise process of the pregnant woman according to the exercise data comprises:
s101: after the sensor acquires initial motion data and performs preprocessing, identifying specific postures of the pregnant woman in the motion data in the motion process, and setting independent corresponding monitoring parameters for real-time tracking and monitoring of posture changes of the pregnant woman in the motion process for each specific posture;
S102: integrating motion data received by different sensors by adopting a multi-source information fusion technology, carrying out differential classification on the motion types of the motion data through a preset decision tree algorithm, and extracting the change characteristics of the posture of the pregnant woman in the motion data according to the differential classification of the motion types;
s103: determining a change state of the movement type of the pregnant woman in the acquired movement data according to the monitoring parameters and the change characteristics, and automatically adjusting the monitoring frequency of the sensor according to the change state;
s104: the preprocessed movement data, the preprocessed monitoring parameters and the preprocessed change characteristics are transmitted to a central server in real time through a network, and the central server analyzes and outputs analysis results by adopting a random forest algorithm to analyze real-time health information of the pregnant women;
S105: judging whether the pregnant woman has potential abnormal activity behaviors in the movement process according to the analysis result, if so, improving the monitoring sensitivity of the sensor in real time to enhance the sampling rate and the dynamic capture rate of the fine posture change, and if not, continuously analyzing and judging the abnormal activity behaviors.
In an alternative embodiment, the analysis of the exercise parameters during the exercise of the pregnant woman according to the exercise data collected by the sensor, the evaluation of the intensity level of the exercise according to the exercise parameters, and the monitoring scheme of adapting the corresponding level to different intensity levels comprises:
s201: the method comprises the steps that motion data of a pregnant woman are collected through a sensor and converted into motion parameters corresponding to motion actions, wherein the motion parameters comprise motion time, a deformation angle of the limb of the pregnant woman, a deformation speed of the limb of the pregnant woman and deformation acceleration of the limb of the pregnant woman;
S202: obtaining a difficulty score of each exercise action by analyzing the exercise parameters of the exercise process of the pregnant woman, classifying intensity levels of the exercise actions according to the difficulty scores, constructing a mapping relation of the exercise parameters, the difficulty scores of the exercise actions and the intensity level classifications of the exercise actions, and constructing a calibration parameter mapping table of the exercise parameters for calibrating monitoring frequency and monitoring sensitivity;
s203: judging the current movement state of the pregnant woman through the mapping relation, when the movement state of the pregnant woman belongs to low-intensity movement, calibrating the monitoring frequency and the monitoring sensitivity of the sensor through the calibration parameter mapping table by the monitoring system to match the current movement state of the pregnant woman for acquiring movement data, and when the movement state of the pregnant woman belongs to medium-high-intensity movement, calibrating the monitoring frequency and the monitoring sensitivity through the calibration parameter mapping table by the monitoring system for adjusting the data sampling rate for acquiring the movement data;
S204: inputting updated motion data acquired after the monitoring frequency and the monitoring sensitivity are adjusted into a machine learning model, analyzing the correlation between the motion mode of a pregnant woman and the physical response state of the pregnant woman reflected by the motion parameters, identifying the individual difference among the pregnant woman according to the physical response state of the pregnant woman, generating a monitoring scheme corresponding to the individual pregnant woman by combining the motion mode and the individual difference with the updated motion data, and configuring a real-time feedback mechanism for the monitoring scheme by adopting sensing equipment;
S205: and continuously outputting a monitoring result for the pregnant woman through long-term real-time monitoring according to the monitoring scheme by combining the historical movement data and the real-time movement data, generating a personalized movement scheme comprising movement suggestions according to the monitoring result for feedback, and simultaneously storing the personalized movement scheme into a cloud platform library.
In an optional embodiment, the acquiring the physical characteristics and the basic information of the pregnant woman changing during the pregnancy, and determining the bearing range of the posture deformation of the pregnant woman with different ages and health states during the exercise of the pregnant woman at different stages of the pregnancy according to the physical characteristics and the physiological information includes:
S301: collecting weight growth data of a pregnant woman through a weight sensor, recording change of daily weight data of the pregnant woman, analyzing weight growth trend of the pregnant woman according to the daily weight data, comparing the weight growth trend with health states of different stages of the pregnancy, and judging whether the weight of the pregnant woman in a target stage is in a range of the health state;
S302: periodically monitoring the expansion condition of the abdomen size of the pregnant woman through ultrasonic measurement equipment, obtaining change data of the abdomen size, judging the growth state of the fetus according to the change data, and correlating the growth state with the pregnant woman's week to draw a visual abdomen expansion curve;
S303: monitoring the change data of the curvature of the spine of the pregnant woman by adopting a three-dimensional imaging technology, combining the change data with the posture deformation and deformation bearing capacity of the pregnant woman to obtain spine deformation data, analyzing the health state of the spine of the pregnant woman according to the spine deformation data, and predicting the change trend of the spine health;
s304: measuring the adjusting data of the position of the pelvic bone through a displacement sensor, matching the adjusting data with the pregnancy process of the pregnant woman to obtain a reference range for adjusting the position of the pelvic bone, inputting the reference range, the physical characteristics of the pregnant woman and basic information into a machine learning model for analysis and prediction of the bearing range of the posture deformation of the pregnant woman, and storing the bearing range of the posture deformation;
s305: and generating a movement scheme aiming at the change of the physical characteristics of the pregnant woman in different pregnancy stages through the bearing range of the posture deformation and the physical characteristic data of the pregnant woman.
In an optional embodiment, the determining the health threat existing in the exercise process of the pregnant woman according to the bearing range of the posture deformation and the exercise data of the pregnant woman, and notifying the health threat to the pregnant woman through the mobile application to reduce the intensity level of exercise and/or change the exercise mode includes:
S401: capturing motion data containing the motion movement change of the limbs of the pregnant woman through a sensor mounted on the sports equipment, and transmitting the motion data to a data processing center for storage through wireless transmission;
S402: the received motion data is finely analyzed through a real-time analysis program, and compared with the bearing range of the gesture deformation, and the analyzed comparison result is output;
s403: if the limb movement action change exceeds the bearing range of the gesture deformation in the comparison result, the current health state information of the pregnant woman is fused to perform exercise risk assessment, and the potential risk of the current exercise state of the pregnant woman is output;
S404: further analyzing the potential risk and the current exercise scene of the pregnant woman, judging whether the current exercise of the pregnant woman forms a threat to the health of the pregnant woman, if the health threat exists, generating a warning signal by the remote health management system, informing the pregnant woman of the warning signal in a notification and/or warning mode through a mobile application connected with the remote health management system end, and suggesting the pregnant woman to reduce the intensity level of the exercise and/or change the exercise mode so as to adapt to the bearing range of the gesture deformation;
s405: building an early warning model through the potential risks and the health threats, collecting feedback information of the pregnant women after the movement modes of the pregnant women are changed, and performing iterative optimization on the early warning model, wherein the early warning model iterates the movement modes of the pregnant women through a genetic algorithm, and continuously updates a personalized customized movement mode scheme of the pregnant women;
S406: after the pregnant woman changes the movement mode, the latest movement data containing the movement change of the limbs of the pregnant woman are continuously captured through the sensor so as to ensure that the movement process of the pregnant woman is always in the bearing range of the posture deformation.
In an alternative embodiment, the assessing the physical fitness of the pregnant woman according to the movement frequency, the movement intensity and the movement state of the pregnant woman comprises:
S501: collecting movement state data of the pregnant woman through the physiological monitoring equipment, extracting heart rate variability data in the movement state data to perform heart rate level analysis, and monitoring movement frequency and movement intensity of the pregnant woman in real time through the intelligent wearing equipment;
S502: according to the heart rate variability data analyzed by the heart rate level, the motion frequency data and the motion intensity data of the pregnant woman monitored in real time and the pregnancy status record of the pregnant woman, comprehensively analyzing, and evaluating the physical fitness of the pregnant woman by using a support vector machine algorithm;
s503: setting and adjusting the monitoring related parameters of the intelligent wearable equipment according to the physical adaptability result of pregnant woman evaluation, so as to formulate a personalized monitoring scheme of the pregnant woman;
S504: generating customized pregnancy movement advice for the pregnant woman based on the assessment result of the physical fitness of the pregnant woman and the personalized monitoring scheme of the pregnant woman, wherein the pregnancy movement advice comprises movement frequency, movement intensity and movement mode of the pregnant woman meeting the physical fitness, the customized pregnancy movement advice is fed back to the pregnant woman end through mobile application, and meanwhile, a movement reminding function is applied to regularly remind the pregnant woman to execute periodic movement projects;
s505: and collecting exercise feedback information of the pregnant woman executing the exercise project, wherein the exercise feedback information comprises exercise progress, physical feeling feedback and physical feedback, evaluating exercise adaptability of the pregnant woman through the exercise feedback information, and continuously optimizing the exercise project executed by the pregnant woman according to the exercise adaptability of the pregnant woman.
In an optional embodiment, the preset physical fitness threshold of the pregnant woman, determining whether the physical fitness evaluation of the pregnant woman is lower than the physical fitness threshold, if yes, performing mapping analysis on physical characteristic data of the pregnant woman changing during pregnancy and the physical fitness of the pregnant woman to evaluate the correlation between the change of the physical characteristic of the pregnant woman during pregnancy and the physical fitness of the pregnant woman, and determining the influence degree of the change of the physical characteristic of the pregnant woman on the physical fitness of the pregnant woman includes:
S601: extracting continuous change data of abdomen size of pregnant women during pregnancy through the feature changes of the pregnant women recorded by the data processing center, and using the continuous change data for analyzing the influence degree of the abdomen size change on standing stability in the physical adaptability of the pregnant women;
s602: quantifying the relationship between the abdomen size increase and the gravity center deviation by using a statistical model, and confirming the adjustment requirement of the pregnant woman body according to the quantified relationship;
S603: calculating the change trend of the pelvic bone inclination angle according to the abdomen size change through linear regression analysis, generating an adjustment strategy of the pregnant woman sitting posture inclination angle according to the change trend, analyzing historical data of spine curvature change and pregnant woman weight increase by utilizing a decision tree model, and providing an adjustment strategy of seat design parameters for the pregnant woman by predicting the influence of different spine curvatures on the pregnant woman sitting comfort level;
s604: acquiring joint flexibility data of a pregnant woman by adopting a joint flexibility test, acquiring a physical training strategy for improving the walking posture of the pregnant woman by analyzing the relationship between the joint flexibility data and the walking posture of the pregnant woman, and applying the physical training strategy to a virtual reality technology to simulate the walking posture of the pregnant woman so as to ensure that the coordination relationship between physical balance and waistline expansion degree is used for adjusting and optimizing the physical training strategy in real time;
S605: collecting physical state data of a pregnant woman during sleep through a pressure sensing pad, evaluating the influence of different sleep postures of the pregnant woman on physical fitness through the physical state data, so as to provide a regulating strategy of the sleep postures of the pregnant woman, and generating a movement optimizing scheme of the pregnant woman during pregnancy, which aims at balancing movement states and rest states, by combining muscle elasticity change data of the pregnant woman recorded by a muscle elasticity sensor and the waistline expansion degree;
s606: and carrying out diet suggestion analysis by combining the exercise optimization scheme with the daily activity mode of the pregnant woman, adopting an image recognition technology to periodically evaluate the posture equilibrium of the pregnant woman, and carrying out continuous optimization aiming at posture recovery on the exercise optimization scheme by combining the posture equilibrium with the joint flexibility data.
In an alternative embodiment, the evaluating the influence degree of the change of the physical characteristics of the pregnant woman on the physical fitness of the pregnant woman provides personalized remote health management service for the pregnant woman, and the method comprises the following steps:
S701: designing a comprehensive supervision scheme for capturing key data affecting daily life of a pregnant woman based on real-time change of physical characteristics of the pregnant woman, and combining the key indexes of the pregnant woman acquired by the sensor equipment and the key data to form an original data set containing physiological parameters of the pregnant woman;
S702: transmitting the original data set to a remote health management system through a secure encryption technology, and deeply mining the original data set through a data analysis algorithm to obtain a mode of health state change of the pregnant woman and potential risk factors;
S703: constructing a physical adaptability model according to the mode of the health state change and potential risk factors, and evaluating target requirements and health risks of the pregnant woman in different stages of pregnancy through the physical adaptability model;
S704: the life habit and the movement pattern of the pregnant woman in the physiological and psychological state change are fused with the target requirement and the health risk to be analyzed by applying a behavior analysis technology, a personalized movement scheme and a diet scheme of the pregnant woman are proposed by an intelligent algorithm, and meanwhile, the personal preference of the pregnant woman is added into the personalized scheme;
S705: the method comprises the steps of tracking a pregnant woman executing a personalized exercise scheme and a diet scheme through a real-time monitoring mechanism, obtaining a tracking record of the pregnant woman for life style adaptability after the exercise scheme and the diet scheme are adjusted, continuously adjusting the personalized scheme of the pregnant woman through the tracking record, simultaneously integrating an original data set, target requirements, health risks, the personalized scheme and the tracking record into a health file of the pregnant woman to be stored in a remote health management system, and providing long-term health management support for the pregnant woman through the health file.
In an alternative embodiment, the continuous monitoring of real-time data and feedback data of the remote health management service, the periodic evaluation and adjustment of the remote health management service for pregnant women, comprises:
S706: collecting real-time data of the health state of the pregnant woman after receiving the remote health management service by adopting an updated personalized monitoring scheme, quantitatively analyzing the real-time data through statistical analysis and pattern recognition to obtain an evaluation result of the physiological parameters of the pregnant woman after receiving the remote health management service, and formulating a health intervention strategy through the evaluation result;
S707: collecting feedback data of pregnant women through a real-time feedback system and/or questionnaire survey, combining the feedback data with the evaluation result of the physiological parameters, and identifying potential problems in remote health management service and target problems of pregnant women through correlation analysis;
S708: setting an evaluation period of the remote health management service according to the result of the association analysis, carrying out service demand analysis by regular monitoring data examination and service satisfaction examination in the evaluation period, and timely adjusting the remote health management service according to the service demand analysis;
s709: screening risk factors on the basis of adjusting remote management service, predicting potential risks of health of pregnant women and health of fetuses through cross verification and statistical analysis of pre-pregnancy data and pregnancy monitoring data, and optimizing monitoring service for timely providing medical intervention measures according to potential risk prediction results;
S710: and generating a psychological counseling scheme for performing personalized psychological intervention of the pregnant woman through the evaluation result of the physiological parameters and the evaluation of the psychological support service so as to perfect the remote health management service.
Compared with the prior art, the invention has the following advantages:
The invention discloses a remote health management service method based on big data, which is characterized in that a pregnant woman motion monitoring system based on a sensor technology can track tiny activities and posture changes of a pregnant woman body in real time, dynamically adjust monitoring frequency and sensitivity according to data transmitted by different motion states of the pregnant woman, evaluate the intensity level of motion according to the deformation degree and the action difficulty of limbs of the pregnant woman, and adapt to different monitoring schemes according to different intensity levels. Meanwhile, the system can also judge the gesture deformation range which can be born by pregnant women of different ages and health conditions in the movements of different pregnancy stages according to the physical characteristics of the pregnant women, and immediately inform the pregnant women when the movement exceeds the gesture deformation range which can be born, and suggest that the pregnant women reduce the strength or change the movement mode. In addition, the system can also evaluate the physical fitness of the pregnant woman according to the exercise frequency, the exercise intensity and the exercise state of the pregnant woman, and provide corresponding remote health management services for the pregnant woman according to the evaluation result.
Detailed Description
The present application will be described and illustrated with reference to the accompanying drawings and examples in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application. All other embodiments, which can be made by a person of ordinary skill in the art based on the embodiments provided by the present application without making any inventive effort, are intended to fall within the scope of the present application.
It is apparent that the drawings in the following description are only some examples or embodiments of the present application, and it is possible for those of ordinary skill in the art to apply the present application to other similar situations according to these drawings without inventive effort. Moreover, it should be appreciated that while such a development effort might be complex and lengthy, it would nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as having the benefit of this disclosure.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by those of ordinary skill in the art that the described embodiments of the application can be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. The terms "a," "an," "the," and similar referents in the context of the application are not to be construed as limiting the quantity, but rather as singular or plural. The terms "comprising," "including," "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in connection with the present application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein means two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. The terms "first," "second," "third," and the like, as used herein, are merely distinguishing between similar objects and not representing a particular ordering of objects.
Example 1
Referring to fig. 1, the embodiment of the invention discloses a remote health management service method based on big data, which comprises the following steps:
S1, tracking and monitoring posture changes of a pregnant woman body in a movement process in real time through a sensor, collecting movement data of different movement types of the pregnant woman, and dynamically adjusting monitoring frequency and monitoring sensitivity of the movement process of the pregnant woman according to the movement data;
in an optional embodiment, the monitoring the posture change of the pregnant woman body during the exercise process by the sensor in real time, collecting exercise data of different exercise types of the pregnant woman, and dynamically adjusting the monitoring frequency and the monitoring sensitivity of the exercise process of the pregnant woman according to the exercise data comprises:
s101: after the sensor acquires initial motion data and performs preprocessing, identifying specific postures of the pregnant woman in the motion data in the motion process, and setting independent corresponding monitoring parameters for real-time tracking and monitoring of posture changes of the pregnant woman in the motion process for each specific posture;
S102: integrating motion data received by different sensors by adopting a multi-source information fusion technology, carrying out differential classification on the motion types of the motion data through a preset decision tree algorithm, and extracting the change characteristics of the posture of the pregnant woman in the motion data according to the differential classification of the motion types;
s103: determining a change state of the movement type of the pregnant woman in the acquired movement data according to the monitoring parameters and the change characteristics, and automatically adjusting the monitoring frequency of the sensor according to the change state;
s104: the preprocessed movement data, the preprocessed monitoring parameters and the preprocessed change characteristics are transmitted to a central server in real time through a network, and the central server analyzes and outputs analysis results by adopting a random forest algorithm to analyze real-time health information of the pregnant women;
S105: judging whether the pregnant woman has potential abnormal activity behaviors in the movement process according to the analysis result, if so, improving the monitoring sensitivity of the sensor in real time to enhance the sampling rate and the dynamic capture rate of the fine posture change, and if not, continuously analyzing and judging the abnormal activity behaviors.
As an example, in monitoring the health condition of a pregnant woman, a multi-sensor data fusion technique is used, for example, the heartbeat of the pregnant woman is continuously monitored by using a fetal heart monitoring device, and the data can be expressed as hr=bpm/CT, where HR is the heart rate, BPM is the number of beats per minute, and CT is the cycle time. Meanwhile, the blood pressure of the pregnant woman is recorded through the sphygmomanometer, and the blood pressure change is tracked in real time by applying the formula BP= (SP-DP)/TT, wherein BP is the blood pressure change rate, SP is the systolic pressure, DP is the diastolic pressure, and TT is the measurement interval time. These data are sent to a central monitoring system by wireless transmission. The central monitoring system integrates artificial intelligence algorithms, such as analysis of physiological data using random forest algorithms in machine learning, to discover potential risk factors in hundreds of dimensions. The algorithm can accurately predict the risk of pregnancy complications through a model obtained through training a large amount of historical data, and the process can be summarized by the following expression:
Risk=f1 (data_1) +f2 (data_2) +fn (data_n), where f1, f2, fn represents the function obtained by training, data_1, data_2, data_n represents the Data obtained from the respective sensor.
Furthermore, in the operation of the monitoring system, the real-time performance of the data is considered, for example, the data transmission frequency is set to be once every 5 minutes, so that the timeliness of the monitoring data can be ensured, and the rapid response to the emergency situation can be made. In addition, for data storage, a time sequence table is used for storing data acquired each time, and key information can be recorded through the structure: time |hr|bp|, where time represents the time point of the data record, HR is heart rate, and BP is the rate of change of blood pressure.
Furthermore, if the monitoring system finds that a certain index is abnormal, for example, the fetal heart rate is 60 times/min lower than the normal value, the system starts an early warning mechanism and automatically adopts a decision tree algorithm to judge whether medical intervention is needed. This process can be represented by the following logic: ifHR <60th Signal_alert > elseContinue _monitoring. Next, parameters of the monitoring scheme are automatically adjusted according to the predicted risk level, if the risk is high, the monitoring frequency may be reduced from once every 5 minutes to once every 3 minutes. Meanwhile, the cloud platform is connected with a doctor end, so that a doctor can check real-time data at any time, and remote medical consultation or suggestion can be timely carried out according to early warning pushed by the system. Finally, comparing the real-time monitoring result with the historical case by utilizing a data mining technology, searching for a similar mode, and comparing the real-time data with the historical health record of the patient so as to personally recommend medical treatment to promote the health of the pregnant woman. For example, clustering, association rule mining, or anomaly detection techniques may be employed to discover similarities or anomalies between data. By comparison, the current state of the pregnant woman can be estimated more accurately, and more targeted suggestions can be provided. For example, by contrast analysis method Cmp (data_real_time, data_history), wherein Cmp is a comparison function, data_real_time is real-time monitoring Data, and data_history is history health Data, thereby allowing doctors to provide medical services in a targeted manner.
S2: analyzing motion parameters in the process of pregnant woman motion according to the motion data acquired by the sensor, evaluating the intensity level of the motion through the motion parameters, and adapting the monitoring scheme of the corresponding level to different intensity levels;
in an alternative embodiment, the analysis of the exercise parameters during the exercise of the pregnant woman according to the exercise data collected by the sensor, the evaluation of the intensity level of the exercise according to the exercise parameters, and the monitoring scheme of adapting the corresponding level to different intensity levels comprises:
s201: the method comprises the steps that motion data of a pregnant woman are collected through a sensor and converted into motion parameters corresponding to motion actions, wherein the motion parameters comprise motion time, a deformation angle of the limb of the pregnant woman, a deformation speed of the limb of the pregnant woman and deformation acceleration of the limb of the pregnant woman;
S202: obtaining a difficulty score of each exercise action by analyzing the exercise parameters of the exercise process of the pregnant woman, classifying intensity levels of the exercise actions according to the difficulty scores, constructing a mapping relation of the exercise parameters, the difficulty scores of the exercise actions and the intensity level classifications of the exercise actions, and constructing a calibration parameter mapping table of the exercise parameters for calibrating monitoring frequency and monitoring sensitivity;
s203: judging the current movement state of the pregnant woman through the mapping relation, when the movement state of the pregnant woman belongs to low-intensity movement, calibrating the monitoring frequency and the monitoring sensitivity of the sensor through the calibration parameter mapping table by the monitoring system to match the current movement state of the pregnant woman for acquiring movement data, and when the movement state of the pregnant woman belongs to medium-high-intensity movement, calibrating the monitoring frequency and the monitoring sensitivity through the calibration parameter mapping table by the monitoring system for adjusting the data sampling rate for acquiring the movement data;
S204: inputting updated motion data acquired after the monitoring frequency and the monitoring sensitivity are adjusted into a machine learning model, analyzing the correlation between the motion mode of a pregnant woman and the physical response state of the pregnant woman reflected by the motion parameters, identifying the individual difference among the pregnant woman according to the physical response state of the pregnant woman, generating a monitoring scheme corresponding to the individual pregnant woman by combining the motion mode and the individual difference with the updated motion data, and configuring a real-time feedback mechanism for the monitoring scheme by adopting sensing equipment;
S205: and continuously outputting a monitoring result for the pregnant woman through long-term real-time monitoring according to the monitoring scheme by combining the historical movement data and the real-time movement data, generating a personalized movement scheme comprising movement suggestions according to the monitoring result for feedback, and simultaneously storing the personalized movement scheme into a cloud platform library.
As an example, in order to monitor the movement state of pregnant women in real time and give corresponding movement advice, a set of intelligent monitoring systems is developed for monitoring movement parameters. Firstly, the motion parameter data of the limbs of the pregnant woman are captured in real time by using wearable equipment such as an accelerometer, an angle sensor and the like. For example, the sensor may record the angular velocity ω=Δθ/Δt at the time of arm swing, where Δθ is the amount of angular displacement change, and Δt is the amount of time change. These data are input to a pre-designed scoring algorithm, such as using the euclidean distance calculation formula d= v + ((x 2-x 1) 2+ (y 2-y 1) 2), where x2, x1 and y2, y1 are each sensor data measured twice in succession, to calculate the amount of change between the limb movement data, from which the intensity of the movement is estimated.
Further, the exercise intensity scoring algorithm refers to the reference threshold of limb exercise obtained in the previous study, if the calculated exercise intensity is smaller than the low intensity threshold lambda, the system judges the exercise as low risk exercise, and at the moment, the monitoring system reduces the data sampling frequency f to 5 times per minute, reduces the energy consumption and ensures the effective monitoring of the data. For movements exceeding this threshold, the monitoring system will dynamically increase the data sampling frequency, e.g. up to 10 times per second, in order to more accurately capture and analyze the rapid limb deformation resulting from the high intensity movements.
Still further, the system may input the captured data into a machine learning model, such as using a random forest algorithm to analyze the correlation of the movement pattern of the pregnant woman with the physical response. The training set is used to generate the decision tree and the test set is used to verify the accuracy of the model by building the training set and the test set. By analysing a set of limb movement data sets of pregnant women while walking, jogging and fast walking, the model is able to learn features identifying these movements, and in the subsequent monitoring process, the monitoring strategy is automatically adjusted to optimise the accuracy of monitoring for such movement patterns whenever the sensor data exhibits a similar pattern. For each monitored movement pattern, not only is feedback to the real-time state assessment of the pregnant woman, but also personalized movement advice is sent to the device according to the movement intensity. These suggestions are generated by a set of calculation formulas, for example according to the heart rate reserve=hrmax-HRrest, where HRmax is the maximum heart rate and HRrest is the resting heart rate, calculating the appropriate exercise heart rate interval and using this to guide the exercise intensity of the pregnant woman, avoiding the risk of excessive exercise. As the system monitors pregnant women for a long period of time, it accumulates exercise data for each user and updates personal health profiles in a cloud database.
Further, when any possible risk actions are monitored, such as abnormal heart rate jumps, the system may pass algorithms, such as beat variability analysis, immediately: sdnn= v (1/N Σ (NNi-mean (NN i)) -2), where NNi represents a continuous RR interval, mean (NN i) represents an average value of RR intervals, and SDNN represents a standard deviation of NN intervals, to evaluate irregularity of heart rate, if the value of SDNN is abnormal, the system generates an alarm to notify medical personnel. Finally, all collected data are comprehensively analyzed through the cloud computing platform. And classifying the users according to multidimensional factors such as exercise habits, physiological states, seasons and the like of pregnant women by utilizing big data technology such as K-means cluster analysis so as to find common exercise modes and potential risk coefficients of different characteristics in the group. Through such information aggregation and analysis, the monitoring system constantly optimizes individual activity recommendations and adjusts the health management strategy for the entire maternal population.
S3: acquiring physical characteristics and basic information of pregnant women, wherein the physical characteristics comprise body weight, abdomen size, spine curvature and pelvic bone position, and the basic information comprises age and health status;
In an optional embodiment, the acquiring the physical characteristics and the basic information of the pregnant woman changing during the pregnancy, and determining the bearing range of the posture deformation of the pregnant woman with different ages and health states during the exercise of the pregnant woman at different stages of the pregnancy according to the physical characteristics and the physiological information includes:
S301: collecting weight growth data of a pregnant woman through a weight sensor, recording change of daily weight data of the pregnant woman, analyzing weight growth trend of the pregnant woman according to the daily weight data, comparing the weight growth trend with health states of different stages of the pregnancy, and judging whether the weight of the pregnant woman in a target stage is in a range of the health state;
S302: periodically monitoring the expansion condition of the abdomen size of the pregnant woman through ultrasonic measurement equipment, obtaining change data of the abdomen size, judging the growth state of the fetus according to the change data, and correlating the growth state with the pregnant woman's week to draw a visual abdomen expansion curve;
S303: monitoring the change data of the curvature of the spine of the pregnant woman by adopting a three-dimensional imaging technology, combining the change data with the posture deformation and deformation bearing capacity of the pregnant woman to obtain spine deformation data, analyzing the health state of the spine of the pregnant woman according to the spine deformation data, and predicting the change trend of the spine health;
s304: measuring the adjusting data of the position of the pelvic bone through a displacement sensor, matching the adjusting data with the pregnancy process of the pregnant woman to obtain a reference range for adjusting the position of the pelvic bone, inputting the reference range, the physical characteristics of the pregnant woman and basic information into a machine learning model for analysis and prediction of the bearing range of the posture deformation of the pregnant woman, and storing the bearing range of the posture deformation;
s305: and generating a movement scheme aiming at the change of the physical characteristics of the pregnant woman in different pregnancy stages through the bearing range of the posture deformation and the physical characteristic data of the pregnant woman.
As an example, in order to effectively monitor and analyze the physical change of a pregnant woman during pregnancy, first, the weight of the pregnant woman is recorded daily using an intelligent body weight scale having a bluetooth function. Assuming a pregnant woman with an initial weight of 60 kg, the weight gain data can be used to predict future weight trends using a linear regression model, where weight gain of 0.5 kg per week is the desired goal. The calculated weight gain curve can be compared with the medical guideline, and if the calculated weight gain curve deviates from the normal range recommended by the guideline, the system can give a reminder and recommend the pregnant woman to consult with a doctor.
Further, the ultrasound device periodically monitors, for example, once every 4 weeks, measures the circumference of the abdomen of the pregnant woman, tracks changes in the size of the abdomen, and draws a map of the trend of the abdomen expansion using polynomial curve fitting techniques. A quadratic polynomial equation is used, which is approximately of the form 'abdominal circumference = a+b × gestational week + c × gestational week ≡2'. Parameters a, b and c will be adaptively calculated based on the actually measured abdominal circumference and perigestational data in order to most accurately reflect the trend of the change in abdominal dimensions.
Furthermore, the three-dimensional imaging technology can be used for capturing the change of the spine of the pregnant woman, the lordosis of the spine begins to increase in the middle period of pregnancy, the angle change rate is obtained by comparing and calculating the bending angle difference of the front spine and the rear spine, and the pressure distribution situation born by the pregnant woman is analyzed by combining with mechanical simulation software. For example, an increase in lordosis of the spine from normal 12 degrees to 18 degrees indicates a greater deformation, thereby suggesting the need for additional attention and possible intervention. The pelvic position change can be tracked by a displacement sensor arranged on the waistband, the sensor records the forward tilting angle or displacement of the pelvis, and whether the pelvic adjustment of the pregnant woman is in a normal range is analyzed by the data average value and the standard difference. For example, the sensor may find a month rate of increase in pelvic forward angle of 0.1 degrees/month, and if a preset threshold is exceeded, an alarm may be activated. Through the collected data, a machine learning algorithm can be used for analyzing the posture deformation and bearing capacity of the pregnant woman, building a prediction model, such as a decision tree or random forest algorithm, and outputting corresponding posture and motion bearing capacity scores based on factors such as height, weight, spine curvature and the like. The algorithm can guide the physician to give personalized advice by analyzing patterns in the dataset and returning predictions. After the mechanical monitoring data of all pregnant women are fused with the personal background of the pregnant women, the proposed exercise guide can provide safe and effective exercise advice aiming at different pregnancy stages, such as yoga or aerobic exercise in water. Taking into account the weight of pregnant women, the spine bending rate and other factors, the customized exercise scheme is guided by maximizing health benefits and reducing risks.
S4: judging health threats existing in the movement process of the pregnant woman according to the bearing range of the gesture deformation and the movement data of the pregnant woman, and informing the pregnant woman of the health threats through mobile application to reduce the intensity level of movement and/or change the movement mode;
In an optional embodiment, the determining the health threat existing in the exercise process of the pregnant woman according to the bearing range of the posture deformation and the exercise data of the pregnant woman, and notifying the health threat to the pregnant woman through the mobile application to reduce the intensity level of exercise and/or change the exercise mode includes:
S401: capturing motion data containing the motion movement change of the limbs of the pregnant woman through a sensor mounted on the sports equipment, and transmitting the motion data to a data processing center for storage through wireless transmission;
S402: the received motion data is finely analyzed through a real-time analysis program, and compared with the bearing range of the gesture deformation, and the analyzed comparison result is output;
s403: if the limb movement action change exceeds the bearing range of the gesture deformation in the comparison result, the current health state information of the pregnant woman is fused to perform exercise risk assessment, and the potential risk of the current exercise state of the pregnant woman is output;
S404: further analyzing the potential risk and the current exercise scene of the pregnant woman, judging whether the current exercise of the pregnant woman forms a threat to the health of the pregnant woman, if the health threat exists, generating a warning signal by the remote health management system, informing the pregnant woman of the warning signal in a notification and/or warning mode through a mobile application connected with the remote health management system end, and suggesting the pregnant woman to reduce the intensity level of the exercise and/or change the exercise mode so as to adapt to the bearing range of the gesture deformation;
s405: building an early warning model through the potential risks and the health threats, collecting feedback information of the pregnant women after the movement modes of the pregnant women are changed, and performing iterative optimization on the early warning model, wherein the early warning model iterates the movement modes of the pregnant women through a genetic algorithm, and continuously updates a personalized customized movement mode scheme of the pregnant women;
S406: after the pregnant woman changes the movement mode, the latest movement data containing the movement change of the limbs of the pregnant woman are continuously captured through the sensor so as to ensure that the movement process of the pregnant woman is always in the bearing range of the posture deformation.
As an example, first, sensors on sports equipment, such as accelerometers and gyroscopes, can collect motion data at a frequency of 128Hz, which means that they can record 128 motion states per second, obtaining extremely accurate limb motion information. The motion data is transmitted to the central processing unit in real time through the bluetooth low energy (BluetoothLowEnergy, BLE). For example, the angular velocity of a certain joint at the moment of movement exceeds a safety threshold of 45 degrees/second, and the system will immediately mark as a potential risk. The central data processing center processes the real-time data streams using complex event processing (ComplexEventProcessing, CEP) techniques. This technique enables the application of predefined rules immediately after receiving the data, such as comparing the collected limb dynamics to a database of daily activities of healthy pregnant women (containing hundreds to thousands of safe exercise patterns), thereby identifying exercise attitudes that do not meet the criteria. If the analyzed data shows that the biceps brachii muscle stretches more frequently than 30 times per minute, the system may identify that the motion frequency is unsuitable for a certain phase of pregnancy. The system then combines the health profile of the pregnant woman's individual, such as age, weight, week of pregnancy, and past medical history, through machine learning algorithms, and performs multivariate regression analysis in combination with real-time data. If the pregnant woman is 30 years old and weighs 65 kg, the system judges the risk level of high-intensity aerobic exercise by combining exercise data acquired in real time according to the data in the middle of pregnancy.
Further, if the intensity level of the risk of exercise is found to be over medium, an alert may be triggered. After the warning signal is generated, the system sends out a notice through the mobile application program, and the pregnant woman is reminded of making adjustment by vibration and sound. For example, the application displays via a simple push notification: "you have too high exercise intensity, suggest slowing down or stopping to rest. "the prompt is based on real-time data analysis, for example, the heart rate of the pregnant woman when exercising reaches a warning line of 160 beats per minute. To personalize exercise feedback, the system gathers physiological feedback after exercise of the pregnant woman, such as heart rate variability and self-reported fatigue, and trains predictive models using past exercise data and responses. For example, if a pregnant woman reports extreme fatigue after the heart rate reaches 140 beats per minute, the system will adjust his heart rate alert threshold based on this feedback. When designing a personalized exercise program based on the collected data and user feedback, the system may use complex optimization algorithms, such as genetic algorithms, to iteratively find the type and intensity of exercise that best suits the pregnant woman. It may take into account low-impact aerobic exercises such as walking and yoga, keep heart rate 100-120 times per minute, and proper muscle exercise, limited to within 12 times per group, and set rest intervals of at least 1 minute. After the pregnant woman adjusts the movement according to the suggestion of the system, the wearable device tracks the adjustment, continuously monitors the movement posture and strength of the pregnant woman, and ensures that the pregnant woman moves in a safe range. This closed loop feedback ensures that the system provides timely supervision and advice even when the movement state of the pregnant woman changes.
S5: assessing physical fitness of the pregnant woman according to the exercise frequency, exercise intensity and exercise state of the pregnant woman, wherein the exercise state comprises heart rate, blood pressure and balance of the pregnant woman;
In an alternative embodiment, the assessing the physical fitness of the pregnant woman according to the movement frequency, the movement intensity and the movement state of the pregnant woman comprises:
S501: collecting movement state data of the pregnant woman through the physiological monitoring equipment, extracting heart rate variability data in the movement state data to perform heart rate level analysis, and monitoring movement frequency and movement intensity of the pregnant woman in real time through the intelligent wearing equipment;
S502: according to the heart rate variability data analyzed by the heart rate level, the motion frequency data and the motion intensity data of the pregnant woman monitored in real time and the pregnancy status record of the pregnant woman, comprehensively analyzing, and evaluating the physical fitness of the pregnant woman by using a support vector machine algorithm;
s503: setting and adjusting the monitoring related parameters of the intelligent wearable equipment according to the physical adaptability result of pregnant woman evaluation, so as to formulate a personalized monitoring scheme of the pregnant woman;
S504: generating customized pregnancy movement advice for the pregnant woman based on the assessment result of the physical fitness of the pregnant woman and the personalized monitoring scheme of the pregnant woman, wherein the pregnancy movement advice comprises movement frequency, movement intensity and movement mode of the pregnant woman meeting the physical fitness, the customized pregnancy movement advice is fed back to the pregnant woman end through mobile application, and meanwhile, a movement reminding function is applied to regularly remind the pregnant woman to execute periodic movement projects;
s505: and collecting exercise feedback information of the pregnant woman executing the exercise project, wherein the exercise feedback information comprises exercise progress, physical feeling feedback and physical feedback, evaluating exercise adaptability of the pregnant woman through the exercise feedback information, and continuously optimizing the exercise project executed by the pregnant woman according to the exercise adaptability of the pregnant woman.
As an example, for a comprehensive assessment of the physical fitness of a pregnant woman, first a monitoring of Heart Rate Variability (HRV) is performed, for example measuring standard deviation NN (SDNN) values using a physiological monitoring device, which is the standard deviation of the interval between two successive beats of heart rate. For example, 24-hour monitoring data of a pregnant woman shows that SDNN is 140 milliseconds, which indicates that the pregnant woman has better heart health and low stress level. Inputting these data into heart rate level analysis formulas, such as LF/HF ratio (low frequency/high frequency), may provide insight into autonomic nervous system balance. A low LF/HF ratio may mean that parasympathetic nervous system activity dominates, which is more common during pregnancy.
Further, the movement frequency and intensity are then monitored in real time by means of a smart wearable device, such as a smart watch. These devices can use built-in acceleration sensors and GPS positioning to estimate activity and exercise intensity, such as measuring energy expenditure with METs (metabolic equivalent). If the pregnant woman consumes 3METs of energy while walking and more than 6METs of running, the average energy consumption per day can be tracked by the equipment, and the approximate physical level can be calculated. Further, the application program records key data such as week of pregnancy and weight gain through a special mobile application program, and complex algorithms such as linear regression analysis are embedded in the application program to predict the adaptability and health risk of the pregnant woman. If a pregnant woman gains more than 0.5 kg per week, the application may give a prompt advising the referring physician, which may also be integrated into the overall fitness assessment.
Furthermore, the integrated analysis stage can adopt an artificial intelligence algorithm, such as a method based on a support vector machine, and combines heart rate variability data and daily activity data, as well as week of pregnancy and weight information, and the training model predicts the physical strength level and potential health risk of the pregnant woman. The models can continuously optimize own parameters according to the received new data so as to improve the prediction accuracy. After initial physical evaluation is obtained, parameters of the intelligent equipment can be finely adjusted, for example, a specific activity recognition algorithm threshold is set, and data is ensured to be more fit with actual conditions. Such personalized settings promote accuracy of the data and allow the system to better understand and adapt to the unique needs of each pregnant woman. Next, based on the evaluation results, the AI system may generate a personalized pregnancy exercise program, including exercise type and intensity advice. For example, a pregnant woman whose physical strength level is estimated to be medium, the application program may recommend that the exercise be performed 5 times per week for 20 minutes of aerobic exercise with an intensity not exceeding 60% of the maximum heart rate of the pregnant woman. By means of mobile application, the customized sport advice is transmitted to the pregnant woman and reminds the pregnant woman to regularly carry out the recommended sport, and meanwhile, the sport safety of the pregnant woman is ensured to the greatest extent. These recommendations and reminders will be presented in an interactive manner, such as by personalized notification and motivational information to promote engagement by the pregnant woman. After completion of the prescribed exercise program, feedback is collected from the pregnant woman, such as heart rate, fatigue level, and perceived exercise intensity recorded by punching a card on the mobile application (RPEscale). These data are used to adjust future exercise recommendations to ensure that they are always appropriate for the actual experience and physical fitness of the pregnant woman. Finally, by comparing the data changes before and after the movement, it is assessed whether there is a significant increase in muscle fitness, for example using a paired t-test. If statistical significance P <0.05, it is shown that the provided training effectively improves the muscle fitness of the pregnant woman. These data are then used to refine the algorithm, continuously optimizing the overall system. In this way, the monitoring and exercise advice system is continuously self-perfecting, thereby realizing personalized self-adaption and providing optimal health support for each pregnant woman.
S6: presetting a physical fitness threshold of a pregnant woman, judging whether the physical fitness evaluation of the pregnant woman is lower than the physical fitness threshold, if yes, mapping and analyzing physical characteristic data of the pregnant woman changing during pregnancy and the physical fitness of the pregnant woman so as to evaluate the correlation of the change of the physical characteristic of the pregnant woman during pregnancy and the physical fitness of the pregnant woman, and determining the influence degree of the change of the physical characteristic of the pregnant woman on the physical fitness of the pregnant woman;
In an optional embodiment, the preset physical fitness threshold of the pregnant woman, determining whether the physical fitness evaluation of the pregnant woman is lower than the physical fitness threshold, if yes, performing mapping analysis on physical characteristic data of the pregnant woman changing during pregnancy and the physical fitness of the pregnant woman to evaluate the correlation between the change of the physical characteristic of the pregnant woman during pregnancy and the physical fitness of the pregnant woman, and determining the influence degree of the change of the physical characteristic of the pregnant woman on the physical fitness of the pregnant woman includes:
S601: extracting continuous change data of abdomen size of pregnant women during pregnancy through the feature changes of the pregnant women recorded by the data processing center, and using the continuous change data for analyzing the influence degree of the abdomen size change on standing stability in the physical adaptability of the pregnant women;
s602: quantifying the relationship between the abdomen size increase and the gravity center deviation by using a statistical model, and confirming the adjustment requirement of the pregnant woman body according to the quantified relationship;
S603: calculating the change trend of the pelvic bone inclination angle according to the abdomen size change through linear regression analysis, generating an adjustment strategy of the pregnant woman sitting posture inclination angle according to the change trend, analyzing historical data of spine curvature change and pregnant woman weight increase by utilizing a decision tree model, and providing an adjustment strategy of seat design parameters for the pregnant woman by predicting the influence of different spine curvatures on the pregnant woman sitting comfort level;
s604: acquiring joint flexibility data of a pregnant woman by adopting a joint flexibility test, acquiring a physical training strategy for improving the walking posture of the pregnant woman by analyzing the relationship between the joint flexibility data and the walking posture of the pregnant woman, and applying the physical training strategy to a virtual reality technology to simulate the walking posture of the pregnant woman so as to ensure that the coordination relationship between physical balance and waistline expansion degree is used for adjusting and optimizing the physical training strategy in real time;
S605: collecting physical state data of a pregnant woman during sleep through a pressure sensing pad, evaluating the influence of different sleep postures of the pregnant woman on physical fitness through the physical state data, so as to provide a regulating strategy of the sleep postures of the pregnant woman, and generating a movement optimizing scheme of the pregnant woman during pregnancy, which aims at balancing movement states and rest states, by combining muscle elasticity change data of the pregnant woman recorded by a muscle elasticity sensor and the waistline expansion degree;
s606: and carrying out diet suggestion analysis by combining the exercise optimization scheme with the daily activity mode of the pregnant woman, adopting an image recognition technology to periodically evaluate the posture equilibrium of the pregnant woman, and carrying out continuous optimization aiming at posture recovery on the exercise optimization scheme by combining the posture equilibrium with the joint flexibility data.
As an example, to analyze the effect of increased abdominal circumference on the standing stability of a pregnant woman, it is possible to first set a baseline abdominal circumference size, such as 60 cm, and an initial center of gravity shift, 0 cm, and then collect continuous monitoring data. Through statistical analysis, it was possible to find that when the abdominal circumference increased to 90 cm, the center of gravity shift was 4 cm in mean and 0.5 in variance. Based on this set of data, a linear regression model is applied, which can yield the following formula: (text { center of gravity shift (cm) } = a\ t imes \text { circumference (cm) } +b), and the values of the coefficients a, b are obtained by the least square method. By this formula, the expected values of center of gravity shifts under different abdominal circumferences can be predicted.
Further, by linear regression analysis, the initial inclination angle of the pelvis was set to 10 degrees, and the actual angle change as the abdominal circumference increased from 60 cm to 90cm was measured. If the abdomen circumference is increased by 5 cm, the pelvis inclination angle is increased by 0.5 degrees, so that another relation model can be constructed: (text { pelvic tilt angle (degree) } = c\ t imes \text { abdominal circumference (cm) } +d), and after the values of c, d are obtained, a suitable pelvic tilt adjustment strategy can be calculated based on this. And analyzing a back curve and a pregnancy weight increase historical data set by using a decision tree model, constructing a decision tree by selecting a feature segmentation data set with the maximum information gain, and predicting the relation between different back curves and sedentary comfort. In the historical data, 80% of pregnant women have a 20% decrease in comfort when the back curve increases by 10%, and this law is captured by the node division and used to guide the corresponding seat design optimization.
Further, joint flexibility test data of the pregnant woman is correlated with video analysis data of walking posture. By calculating the maximum range of motion of the joint, e.g., the knee joint may be flexed to 120 degrees, a targeted physical training recommendation may be implemented upon finding an abnormal gait, e.g., a reduced stride, when the knee joint is at 90 degrees of flexibility. The pressure sensing pad is adopted to continuously collect sleep posture data, if pressure distribution is uneven under a certain posture, if the pressure value of the right shoulder is higher than that of the left shoulder by 30%, the best sleep posture suggestion can be given by combining subjective feedback of sleep quality, and comfort and safety are guaranteed. The data recorded by the muscle elasticity sensor is processed in a linkage way with the abdominal circumference increasing data, for example, when the elasticity of the muscle is reduced by 5%, the abdominal circumference is increased to have larger influence on the muscle, so that the exercise scheme of the pregnant woman can be timely adjusted, for example, certain exercise with high influence is reduced or the rest time is increased, and the proper activity and rest balance is conveniently maintained. Finally, the data of meal intake and consumption are analyzed in combination with the daily activity pattern of the pregnant woman, for example, 2000 kcal daily activity is found, and when 2200 kcal daily intake is recommended, the weight gain is kept in the recommended range, for example, 1-1.5 kg monthly increase, and the dietary advice is given to help maintain healthy weight.
S7: and according to the influence degree evaluation of the change of the physical characteristics of the pregnant woman on the physical adaptability of the pregnant woman, providing personalized remote health management service for the pregnant woman, continuously monitoring real-time data and feedback data of the remote health management service, and periodically evaluating and adjusting the remote health management service of the pregnant woman.
In an alternative embodiment, the evaluating the influence degree of the change of the physical characteristics of the pregnant woman on the physical fitness of the pregnant woman provides personalized remote health management service for the pregnant woman, and the method comprises the following steps:
S701: designing a comprehensive supervision scheme for capturing key data affecting daily life of a pregnant woman based on real-time change of physical characteristics of the pregnant woman, and combining the key indexes of the pregnant woman acquired by the sensor equipment and the key data to form an original data set containing physiological parameters of the pregnant woman;
S702: transmitting the original data set to a remote health management system through a secure encryption technology, and deeply mining the original data set through a data analysis algorithm to obtain a mode of health state change of the pregnant woman and potential risk factors;
S703: constructing a physical adaptability model according to the mode of the health state change and potential risk factors, and evaluating target requirements and health risks of the pregnant woman in different stages of pregnancy through the physical adaptability model;
S704: the life habit and the movement pattern of the pregnant woman in the physiological and psychological state change are fused with the target requirement and the health risk to be analyzed by applying a behavior analysis technology, a personalized movement scheme and a diet scheme of the pregnant woman are proposed by an intelligent algorithm, and meanwhile, the personal preference of the pregnant woman is added into the personalized scheme;
S705: the method comprises the steps of tracking a pregnant woman executing a personalized exercise scheme and a diet scheme through a real-time monitoring mechanism, obtaining a tracking record of the pregnant woman for life style adaptability after the exercise scheme and the diet scheme are adjusted, continuously adjusting the personalized scheme of the pregnant woman through the tracking record, simultaneously integrating an original data set, target requirements, health risks, the personalized scheme and the tracking record into a health file of the pregnant woman to be stored in a remote health management system, and providing long-term health management support for the pregnant woman through the health file.
As an example, in order to accurately monitor the physical form change of a pregnant woman, an intelligent wearable device, such as an intelligent abdominal girth measuring belt, is used in combination with a pressure sensor and an accelerometer, so as to continuously capture key indexes such as the weight, the abdominal girth and the like of an individual. These devices can record data periodically, such as once per hour, and calculate Body Mass Index (BMI) by the formula BMI = body weight (kg)/height (m)/(2), and month rate of increase by changes in girth and width, etc. The collected data is secured for confidentiality and integrity prior to transmission to the remote health management system via advanced encryption techniques such as TLS/SSL protocols via I nternet. Once the encrypted data reach the cloud end, a preset big data analysis tool is started immediately for processing. For example, by adopting time series analysis, it is explored whether the abdominal circumference change of the pregnant woman has statistical correlation with the expected date, eating habit and the like, and then a supervised learning algorithm, such as a random forest algorithm, is used for analyzing the relationship between the abdominal circumference increase and the potential health risk, which needs to collect a large amount of historical abdominal circumference data as training data to accurately find the mode of the change of the health condition.
Further, after the change mode of the health condition is mined, the body type change trend of the pregnant woman in the whole pregnancy is predicted by means of an artificial intelligence algorithm, such as a body shape adaptability model based on logistic regression, and the specific personal needs and health risks of the pregnant woman are estimated accordingly. The model may output a risk score, e.g. 0 to 10 points, representing the probability of the pregnant woman developing gestational diabetes, so that the doctor may intervene in advance. Further analyzing life habits and movement patterns of pregnant women, combining the collected activity level data with abdominal circumference growth data by means of movement monitoring sensors such as pedometers or accelerometers, adopting a clustering analysis technology in machine learning such as a K-means clustering algorithm, formulating targeted movement and diet improvement suggestions, and fine-tuning according to personal preference of the pregnant women. Next, an adaptive system is introduced, using a real-time feedback mechanism to track lifestyle adjustments of the pregnant woman. For example, when the system monitors that the daily activities of the pregnant woman decrease resulting in abnormal girth growth rate, the adaptive system will immediately adjust the exercise regimen, possibly by changing the type or intensity of exercise, the system will issue a recommendation notification, and predict whether the pregnant woman can follow the new exercise regimen by a Hidden Markov Model (HMM) like. Finally, all analysis data, risk assessment, personalized advice and tracking records are integrated into the electronic health record of the pregnant woman, a data visualization technology, such as a linear graph, is used for representing the abdominal circumference growth trend, a color coding graph is used for displaying the activity level, and the health risk level is clearly converted into a level system which is easy to understand, so that a comprehensive and long-term health management reference view is provided for doctors.
In an alternative embodiment, the continuous monitoring of real-time data and feedback data of the remote health management service, the periodic evaluation and adjustment of the remote health management service for pregnant women, comprises:
S706: collecting real-time data of the health state of the pregnant woman after receiving the remote health management service by adopting an updated personalized monitoring scheme, quantitatively analyzing the real-time data through statistical analysis and pattern recognition to obtain an evaluation result of the physiological parameters of the pregnant woman after receiving the remote health management service, and formulating a health intervention strategy through the evaluation result;
S707: collecting feedback data of pregnant women through a real-time feedback system and/or questionnaire survey, combining the feedback data with the evaluation result of the physiological parameters, and identifying potential problems in remote health management service and target problems of pregnant women through correlation analysis;
S708: setting an evaluation period of the remote health management service according to the result of the association analysis, carrying out service demand analysis by regular monitoring data examination and service satisfaction examination in the evaluation period, and timely adjusting the remote health management service according to the service demand analysis;
s709: screening risk factors on the basis of adjusting remote management service, predicting potential risks of health of pregnant women and health of fetuses through cross verification and statistical analysis of pre-pregnancy data and pregnancy monitoring data, and optimizing monitoring service for timely providing medical intervention measures according to potential risk prediction results;
S710: and generating a psychological counseling scheme for performing personalized psychological intervention of the pregnant woman through the evaluation result of the physiological parameters and the evaluation of the psychological support service so as to perfect the remote health management service.
As an example, when designing a remote monitoring system, first, by evaluating key physiological parameters of a pregnant woman, such as heart rate, blood pressure, etc., and recording the physiological parameters into monitoring software, the physiological data is collected in real time using a heart rate algorithm, such as average heart rate=total heart rate number/measurement time. Then, the data are subjected to deep analysis by using a statistical analysis method, such as Z score compiling, and a pattern recognition technology, such as a Support Vector Machine (SVM), so that specific physiological patterns can be recognized according to the data of different individuals. For example, the system may identify patterns of heart rate variability in the pregnant woman by an SVM algorithm to determine whether there is potential cardiovascular stress. In the process, the system can display analysis results in real time, collect user feedback information through questionnaire investigation, and simultaneously encode and analyze open feedback of users by utilizing an NLP natural language processing technology to find out problems in services. For example, by text emotion analysis to find the level of need for sleep quality monitoring for pregnant women, keyword can be mined using LDA latent dirichlet allocation topic modeling to identify a priority improvement range. In combination with user feedback and quantitatively assessed physiological parameters, correlation analysis, such as Apriori algorithm, is utilized to identify the most interesting problems for pregnant women.
Further, periodic service evaluations are performed according to the analysis results, including data review and user satisfaction, such as scoring surveys using a 5-point scale, to ensure timely response and adjustment of service requirements. Meanwhile, the system uses risk factor screening tools, for example, logistic regression analysis, combines pre-pregnancy data with real-time monitoring data, establishes a risk assessment model, such as risk score = β0+β1x1+β2x2+.+ βnxn, where β represents a coefficient and X represents an influencing factor, to predict potential health risk of pregnant women and fetuses, and adjusts the monitoring strategy accordingly. For risk prediction, the system optimizes monitoring parameters, such as dynamically adjusting blood glucose monitoring frequency, ensures parameter accuracy, and provides timely adjustment. Based on the monitored data, the medical team may provide personalized nutritional recommendations, such as recommendations based on the Caroli intake (recommended intake = 660+ (9.6 x body weight kg) + (1.8 x height cm) - (4.7 x age)) and nutrient proportioning. In addition, based on the real-time monitoring data and the personal habits of the pregnant woman, the intelligent system can automatically adjust a personalized exercise program, such as based on the current activity level and heart rate monitoring, and establish a proper heart rate interval, such as maintaining 50% -70% of the maximum heart rate, to guide exercise. At the same time, the system monitors psychological states in real time, combines physiological data, such as calculating stress indexes through galvanic skin response, adjusts psychological counseling schemes, provides personalized psychological intervention suggestions, analyzes psychological questionnaires through classification regression trees, and adapts counseling strategies according to the results.
The pregnant woman movement monitoring system based on the sensor technology can track tiny movements and posture changes of the pregnant woman in real time, dynamically adjust monitoring frequency and sensitivity according to data transmitted by different movement states of the pregnant woman, evaluate the intensity level of movement according to the deformation degree and the movement difficulty of limbs of the pregnant woman, and adapt different monitoring schemes according to different intensity levels. Meanwhile, the system can also judge the gesture deformation range which can be born by pregnant women of different ages and health conditions in the movements of different pregnancy stages according to the physical characteristics of the pregnant women, and immediately inform the pregnant women when the movement exceeds the gesture deformation range which can be born, and suggest that the pregnant women reduce the strength or change the movement mode. In addition, the system can also evaluate the physical fitness of the pregnant woman according to the exercise frequency, the exercise intensity and the exercise state of the pregnant woman, and provide corresponding remote health management services for the pregnant woman according to the evaluation result so as to meet the personalized and real-time health monitoring requirements of the pregnant woman.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.