A data processing method and system for perinatal depression monitoring

Abstract

The present invention provides a data processing method and system for perinatal depression monitoring. The data processing method for perinatal depression monitoring includes: extracting the current pregnancy stage of a perinatal patient, setting a data collection frequency according to the current pregnancy stage of the perinatal patient, and dynamically adjusting the data collection frequency of the current pregnancy stage of the perinatal patient in real time during the data collection process; collecting data from the perinatal patient according to the data collection frequency, obtaining the behavior data and physiological data of the perinatal patient, and performing data quality assessment and data quality anomaly warning on the behavior data and physiological data; and storing the behavior data and physiological data that meet the data quality requirements of the perinatal patient in groups. The system includes modules corresponding to the method steps.

Description

Technical Field

[0001] The present invention provides a data processing method and system for perinatal depression monitoring, belonging to the technical field of data processing. Background Art

[0002] The perinatal period, that is, the period around childbirth, is a special physiological and psychological change stage in a woman's life. During this stage, a pregnant woman not only has to face many physical changes, but also bears psychological pressure, which may all lead to the occurrence of perinatal depression. Perinatal depression not only affects the physical and mental health of the pregnant woman, but may also have an adverse impact on the health and development of the fetus. Therefore, effective monitoring and intervention of perinatal depression are particularly important. Traditional perinatal depression monitoring methods mainly rely on the observations of clinicians and the self-reports of patients. These methods have problems such as strong subjectivity, unfixed monitoring frequency, and incomplete data collection, and it is difficult to achieve accurate and real-time monitoring of perinatal depression. With the development of information technology and medical technology, using advanced data processing methods to collect, analyze, and monitor the behavioral data and physiological data of perinatal patients has become a new and potential means.

[0003] However, there are still some challenges in applying existing data processing methods to perinatal depression monitoring. On the one hand, the physiological and psychological states of perinatal patients change with different stages of pregnancy, so the frequency and content of data collection also need to be adjusted accordingly to meet the needs of different stages. On the other hand, the quality of the collected data is uneven, and the existence of data anomalies and noise may affect the accuracy of the monitoring results. Summary of the Invention

[0004] The present invention provides a data processing method and system for perinatal depression monitoring to solve the problem of low data management and processing efficiency in the above-mentioned prior art. The technical solutions adopted are as follows:

[0005] A data processing method for perinatal depression monitoring, the data processing method for perinatal depression monitoring includes:

[0006] Extract the stage of the current pregnancy of the perinatal patient, set the data collection frequency according to the stage of the current pregnancy of the perinatal patient, and perform real-time dynamic adjustment of the data collection frequency of the stage of the current pregnancy of the perinatal patient during the data collection process;

[0007] Collect data from the perinatal patient according to the data collection frequency, obtain the behavioral data and physiological data of the perinatal patient, and perform data quality evaluation and data quality anomaly warning on the behavioral data and physiological data;

[0008] Group and store the behavioral data and physiological data that meet the data quality requirements of the perinatal patients.

[0009] Further, extract the current pregnancy stage of the perinatal patient, set the data collection frequency according to the current pregnancy stage of the perinatal patient, and perform real-time dynamic adjustment on the data collection frequency of the current pregnancy stage of the perinatal patient during the data collection process, including:

[0010] Judge the current pregnancy stage of the current perinatal patient according to the preset pregnancy stage division strategy;

[0011] Set the initial data collection frequency according to the current pregnancy stage of the perinatal patient;

[0012] Collect the behavioral data and physiological data of the perinatal patient according to the initial data collection frequency, and dynamically adjust the data collection frequency according to the behavioral data and physiological data.

[0013] Further, the stage cycle of the pregnancy stage division strategy is as follows:

[0014] The early pregnancy stage cycle includes the first early pregnancy stage, the second early pregnancy stage, and the third early pregnancy stage. Among them, the early pregnancy stage is from 0 to 12 weeks of pregnancy, and the first early pregnancy stage is from 0 to 3 weeks of the early pregnancy stage; the second early pregnancy stage is from 4 to 9 weeks of the early pregnancy stage; the third early pregnancy stage is from 10 to 12 weeks of the early pregnancy stage;

[0015] The mid-pregnancy stage cycle includes the first mid-pregnancy stage, the second mid-pregnancy stage, the third mid-pregnancy stage, and the fourth mid-pregnancy stage. Among them, the mid-pregnancy stage is from 13 to 28 weeks of pregnancy, and the first mid-pregnancy stage is from 13 to 16 weeks of the mid-pregnancy stage; the second mid-pregnancy stage is from 17 to 20 weeks of the mid-pregnancy stage; the third mid-pregnancy stage is from 21 to 25 weeks of the mid-pregnancy stage; the fourth mid-pregnancy stage is from 26 to 28 weeks of the mid-pregnancy stage;

[0016] The late pregnancy stage cycle includes the first late pregnancy stage, the second late pregnancy stage, and the third late pregnancy stage. Among them, the late pregnancy stage is from 29 to 40 weeks of pregnancy, and the first late pregnancy stage is from 29 to 31 weeks of the late pregnancy stage; the second late pregnancy stage is from 32 to 36 weeks of the late pregnancy stage; the third late pregnancy stage is from 37 to 40 weeks of the late pregnancy stage;

[0017] The postpartum period cycle includes the first postpartum period and the second postpartum period. Among them, the postpartum period includes 0 to 6 weeks after childbirth; and the first postpartum period is 0 to 4 weeks after childbirth; the second postpartum period is 5 to 6 weeks after childbirth.

[0018] Further, set the initial data collection frequency according to the current pregnancy stage of the perinatal patient, including:

[0019] Extract the time period from the current pregnancy of the perinatal patient to the starting week of the stage where the current pregnancy is located as the first time period;

[0020] Extract the time period from the current pregnancy of the perinatal patient to the ending week of the stage where the current pregnancy is located as the second time period;

[0021] Extract the data collection time interval corresponding to the reference data collection frequency, where the value range of the data collection time interval corresponding to the reference data collection frequency is 1 day - 3 days;

[0022] Use the first time period and the second time period to combine with the data collection time interval corresponding to the reference data collection frequency to obtain the data collection time interval corresponding to the initial data collection frequency; among them, the data collection time interval corresponding to the initial data collection frequency is obtained through the following formula:

[0023]

[0024] Among them, D represents the data collection time interval corresponding to the initial data collection frequency; B represents the data collection time interval corresponding to the reference data collection frequency; W represents the importance weight value corresponding to the pregnancy stage, and the value range of the importance weight value in the first trimester is 0.2 - 0.5, the value range of the importance weight value in the second trimester is 0.4 - 0.6, and the value range of the importance weight value in the third trimester is 0.8 - 1.0; T 01 represents the time length corresponding to the first time period; T 02 represents the time length corresponding to the second time period;

[0025] e represents a constant with a value of 2.71.

[0026] Further, collect the behavioral data and physiological data of the perinatal patient according to the initial data collection frequency, and dynamically adjust the data collection frequency according to the behavioral data and physiological data, including:

[0027] Collect the behavioral data and physiological data of the perinatal patient according to the initial data collection frequency; among them, the behavioral data includes sleep duration, number of sleep interruptions, and deep sleep duration; the physiological data includes heart rate data, blood pressure data, respiratory rate, and blood oxygen saturation;

[0028] Set a first adjustment coefficient by using the sleep duration, the number of sleep interruptions, and the deep sleep duration; wherein, the first adjustment coefficient is obtained through the following formula:

[0029]

[0030] wherein, K 01 represents the first adjustment coefficient; S t represents the total sleep length; S d represents the deep sleep duration; S max represents a preset reference value for the deep sleep duration; I s represents the number of sleep interruptions; I max represents a preset reference value for the number of sleep interruptions; α 01 and β 01 represent the weight values corresponding to the sleep duration data and the sleep interruption data;

[0031] Set a second adjustment coefficient by using the heart rate data, the blood pressure data, the respiratory rate, and the blood oxygen saturation; wherein, the second adjustment coefficient is obtained through the following formula:

[0032]

[0033] wherein, K 02 represents the second adjustment coefficient; H c , R c and S c represent the values corresponding to the heart rate data, the respiratory rate, and the blood oxygen saturation; B c represents the difference between the diastolic blood pressure and the systolic blood pressure; B x represents a preset reference value for the difference between the diastolic blood pressure and the systolic blood pressure; H x , R x and S x represent the preset reference values corresponding to the heart rate data, the respiratory rate, and the blood oxygen saturation;

[0034] Adjust the data collection time interval corresponding to the initial data collection frequency by using the first adjustment coefficient and the second adjustment coefficient, and obtain the data collection time interval corresponding to the adjusted data collection frequency; wherein, the data collection time interval corresponding to the adjusted data collection frequency is obtained through the following formula:

[0035]

[0036] wherein, D t represents the data collection time interval corresponding to the adjusted data collection frequency; D represents the data collection time interval corresponding to the initial data collection frequency; e represents a constant, and the value is 2.71; K 01represents the first adjustment coefficient; K 02 represents the second adjustment coefficient.

[0037] Furthermore, data of the perinatal patients is collected according to the data collection frequency, the behavior data and physiological data of the perinatal patients are obtained, and data quality assessment and data quality anomaly warning are performed on the behavior data and physiological data, including:

[0038] Data of the perinatal patients is collected according to the data collection frequency, and the behavior data and physiological data of the perinatal patients are obtained;

[0039] Data preprocessing is performed on the behavior data and physiological data of the perinatal patients, wherein the data preprocessing includes information extraction processing of garbled data and its corresponding data types and information extraction processing of missing data corresponding data types;

[0040] Data quality anomaly determination and warning are performed according to the data type weight values of the garbled data and its corresponding data types and the missing data corresponding data types.

[0041] Furthermore, data quality anomaly determination and warning are performed according to the data type weight values of the garbled data and its corresponding data types and the missing data corresponding data types, including:

[0042] Extract the data type weight values corresponding to the data types of each garbled data and the data type weight values corresponding to the data types of each missing data;

[0043] Extract the importance weight value corresponding to the current pregnancy stage of the perinatal patient to obtain the data quality anomaly severity coefficient; wherein, the data quality anomaly severity coefficient is obtained through the following formula:

[0044]

[0045] wherein, S q represents the data quality anomaly severity coefficient; W s represents the importance weight value corresponding to the current pregnancy stage; N ci represents the number of garbled data in the i-th data type; N mi represents the number of missing data in the i-th data type; W ti represents the data type weight value of the i-th data type; N t represents the total number of data; n represents the total number of data types;

[0046] When the data quality anomaly severity coefficient exceeds the preset severity coefficient threshold, it is determined that there is a data quality anomaly in the data collection of the current behavior data and physiological data of the perinatal patient, and a data quality anomaly warning is given.

[0047] Further, the behavioral data and physiological data of the perinatal patients that meet the data quality requirements are grouped and stored, including:

[0048] Set a time window according to the current pregnancy stage of the perinatal patient;

[0049] Group the behavioral data and physiological data collected during the current pregnancy stage according to the time window to form multiple groups of behavioral data and physiological data;

[0050] Group and store each group of behavioral data and physiological data.

[0051] Further, the grouping and storage of the behavioral data and physiological data of the perinatal patients that meet the data quality requirements further include:

[0052] Perform data aggregation processing on each group of behavioral data and physiological data to generate a state comprehensive index parameter corresponding to each group of behavioral data and physiological data; wherein, the state comprehensive index parameter is obtained through the following formula:

[0053]

[0054] wherein, E represents the state comprehensive index parameter; S t represents the total sleep length; S tc represents the reference value of the total sleep length; S max represents the preset reference value of the deep sleep duration; S d represents the deep sleep duration; I s represents the number of sleep interruptions; I symax represents the maximum allowable number of sleep interruptions; C max represents the maximum difference between the value of the physiological data type in the physiological data and its standard value; C ymax represents the maximum allowable difference;

[0055] Compare the state comprehensive index parameter corresponding to the perinatal patient with the preset index parameter;

[0056] When the state comprehensive index parameter corresponding to the perinatal patient exceeds the preset index parameter, then mark a group of behavioral data and physiological data whose state comprehensive index parameter exceeds the preset index parameter;

[0057] When the number of groups of marked behavioral data and physiological data exceeds the preset group number threshold, then give a warning prompt.

[0058] A data processing system for perinatal depression monitoring, the data processing system for perinatal depression monitoring includes:

[0059] A data acquisition frequency setting and adjustment module, configured to extract the current pregnancy stage of a perinatal patient, set the data acquisition frequency according to the current pregnancy stage of the perinatal patient, and perform real-time dynamic adjustment on the data acquisition frequency of the current pregnancy stage of the perinatal patient during the data acquisition process;

[0060] A data quality anomaly warning module, configured to perform data acquisition on a perinatal patient according to the data acquisition frequency, obtain the behavioral data and physiological data of the perinatal patient, and perform data quality assessment and data quality anomaly warning on the behavioral data and physiological data;

[0061] A grouped storage module, configured to group and store the behavioral data and physiological data of the perinatal patient that meet the data quality requirements.

[0062] Advantages of the present invention:

[0063] The present invention provides a data processing method and system for perinatal depression monitoring. By dynamically adjusting the data acquisition frequency according to the pregnancy stage, this technical solution can more accurately monitor the physiological and psychological states of perinatal patients. This helps medical staff to timely detect the abnormal conditions of patients and take effective intervention measures. Real-time dynamic adjustment of the data acquisition frequency can ensure that more valuable data is collected during critical periods, while reducing data redundancy during stable periods. This helps to improve the quality and analysis efficiency of data. This technical solution can perform personalized data monitoring according to requirements, avoiding over-collection or omission of important data. This helps to reduce the burden on patients and enhance their overall experience. By real-time dynamically adjusting the data acquisition frequency, this technical solution can ensure the reasonable allocation and utilization of medical resources. During critical periods, the system can automatically increase the data acquisition frequency to more detailedly monitor the patient's condition; while during stable periods, the data acquisition frequency can be reduced to save medical resources. Description of the Drawings

[0064] Figure 1 is a flowchart of the method of the present invention;

[0065] Figure 2 is a system block diagram of the method of the present invention. Detailed Embodiments

[0066] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0067] An embodiment of the present invention provides a data processing method for perinatal depression monitoring, as Figure 1 shown, the data processing method for perinatal depression monitoring includes:

[0068] S1. Extract the current pregnancy stage of the perinatal patient, set the data collection frequency according to the current pregnancy stage of the perinatal patient, and make real-time dynamic adjustment to the data collection frequency of the current pregnancy stage of the perinatal patient during the data collection process;

[0069] S2. Collect data from the perinatal patient according to the data collection frequency, obtain the behavioral data and physiological data of the perinatal patient, and conduct data quality assessment and data quality anomaly warning on the behavioral data and physiological data;

[0070] S3. Group and store the behavioral data and physiological data of the perinatal patient that meet the data quality requirements.

[0071] The working principle of the above technical solution is as follows: With the help of a preset pregnancy stage division strategy, the system can accurately judge the current pregnancy stage of the perinatal patient. This strategy is usually based on medical knowledge and experience, and divides the pregnancy into several key stages, such as the first trimester, the second trimester, and the third trimester.

[0072] Once the pregnancy stage of the patient is determined, the system will set a reasonable initial data collection frequency according to the characteristics and requirements of this stage. For example, in the first trimester and the third trimester, since the physiological and psychological changes of the patient are more significant, a higher data collection frequency may be required.

[0073] During the data collection process according to the initial frequency, the system will analyze the collected behavioral data and physiological data in real time. Based on these data, the system will dynamically adjust the data collection frequency to ensure that important changes in the patient's physiological and psychological states can be captured. For example, if the system detects an abnormal fluctuation in a certain physiological index of the patient, it may automatically increase the data collection frequency to monitor the patient's condition in more detail.

[0074] The effects of the above technical solution are as follows: By dynamically adjusting the data collection frequency according to the pregnancy stage, this technical solution can more accurately monitor the physiological and psychological states of perinatal patients. This helps medical staff to detect the abnormal conditions of patients in time and take effective intervention measures. Real-time dynamic adjustment of the data collection frequency can ensure that more valuable data is collected during critical periods, while reducing data redundancy during stable periods. This helps to improve the quality and analysis efficiency of data. This technical solution can perform personalized data monitoring according to needs, avoiding over-collection or omission of important data. This helps to reduce the burden on patients and enhance their overall experience. By real-time dynamically adjusting the data collection frequency, this technical solution can ensure the reasonable allocation and utilization of medical resources. During critical periods, the system can automatically increase the data collection frequency to monitor the patient's condition in more detail; while during stable periods, the data collection frequency can be reduced to save medical resources.

[0075] In one embodiment of the present invention, the stage of the current pregnancy of a perinatal patient is extracted, the data collection frequency is set according to the stage of the current pregnancy of the perinatal patient, and the data collection frequency of the stage of the current pregnancy of the perinatal patient is dynamically adjusted in real time during the data collection process, including:

[0076] S101. Determine the stage of the current pregnancy of the current perinatal patient according to a preset pregnancy stage division strategy;

[0077] S102. Set the initial data collection frequency according to the stage of the current pregnancy of the perinatal patient;

[0078] S103. Collect the behavior data and physiological data of the perinatal patient according to the initial data collection frequency, and dynamically adjust the data collection frequency according to the behavior data and physiological data.

[0079] The working principle of the above technical solution is as follows: With the help of a preset pregnancy stage division strategy, the system can accurately determine the current pregnancy stage of the perinatal patient. This strategy is usually based on medical knowledge and experience, and divides the pregnancy into several key stages, such as the first trimester, the second trimester, the third trimester, etc. Once the pregnancy stage of the patient is determined, the system will set a reasonable initial data collection frequency according to the characteristics and requirements of this stage. For example, in the first trimester and the third trimester, since the physiological and psychological changes of the patient are more significant, a higher data collection frequency may be required. During the data collection process according to the initial frequency, the system will analyze the collected behavior data and physiological data in real time. Based on these data, the system will dynamically adjust the data collection frequency to ensure that important changes in the physiological and psychological states of the patient can be captured. For example, if the system detects an abnormal fluctuation in a certain physiological index of the patient, it may automatically increase the data collection frequency to monitor the patient's condition in more detail.

[0080] The effects of the above technical solution are as follows: By dynamically adjusting the data collection frequency according to the pregnancy stage, this technical solution can more accurately monitor the physiological and psychological states of perinatal patients. This helps medical staff to promptly detect abnormal conditions of patients and take effective intervention measures. Real-time dynamic adjustment of the data collection frequency can ensure that more valuable data is collected during critical periods, while reducing data redundancy during stable periods. This helps improve the quality and analysis efficiency of data. This technical solution can perform personalized data monitoring according to the actual needs of patients, avoiding over-collection or omission of important data. This helps reduce the burden on patients and enhance their overall experience. By real-time dynamically adjusting the data collection frequency, this technical solution can ensure the reasonable allocation and utilization of medical resources. During critical periods, the system can automatically increase the data collection frequency to more detailedly monitor the patient's condition; while during stable periods, the data collection frequency can be reduced to save medical resources.

[0081] In one embodiment of the present invention, the stage cycle of the pregnancy stage division strategy is as follows:

[0082] The early pregnancy stage cycle includes the first early pregnancy stage, the second early pregnancy stage, and the third early pregnancy stage. Among them, the early pregnancy stage is from 0 to 12 weeks of pregnancy, and the first early pregnancy stage is from 0 to 3 weeks of the early pregnancy stage; the second early pregnancy stage is from 4 to 9 weeks of the early pregnancy stage; the third early pregnancy stage is from 10 to 12 weeks of the early pregnancy stage;

[0083] The mid-pregnancy stage cycle includes the first mid-pregnancy stage, the second mid-pregnancy stage, the third mid-pregnancy stage, and the fourth mid-pregnancy stage. Among them, the mid-pregnancy stage is from 13 to 28 weeks of pregnancy, and the first mid-pregnancy stage is from 13 to 16 weeks of the mid-pregnancy stage; the second mid-pregnancy stage is from 17 to 20 weeks of the mid-pregnancy stage; the third mid-pregnancy stage is from 21 to 25 weeks of the mid-pregnancy stage; the fourth mid-pregnancy stage is from 26 to 28 weeks of the mid-pregnancy stage;

[0084] The late pregnancy stage cycle includes the first late pregnancy stage, the second late pregnancy stage, and the third late pregnancy stage. Among them, the late pregnancy stage is from 29 to 40 weeks of pregnancy, and the first late pregnancy stage is from 29 to 31 weeks of the late pregnancy stage; the second late pregnancy stage is from 32 to 36 weeks of the late pregnancy stage; the third late pregnancy stage is from 37 to 40 weeks of the late pregnancy stage;

[0085] The postpartum stage cycle includes the first postpartum stage and the second postpartum stage. Among them, the postpartum stage includes 0 to 6 weeks after childbirth; and the first postpartum stage is from 0 to 4 weeks after childbirth; the second postpartum stage is from 5 to 6 weeks after childbirth.

[0086] The working principle of the above technical solution is as follows: Through a preset pregnancy stage division strategy, the system can automatically or assist medical staff in accurately identifying the specific stage and cycle that the perinatal patient is currently in. This helps to formulate corresponding data collection and processing plans according to the characteristics of different stages and cycles. Based on the stage and cycle that the patient is currently in, the system can automatically adjust the data collection frequency. For example, in the early and late pregnancy, since the physiological and psychological changes of pregnant women are relatively significant, the system may increase the data collection frequency; while in the relatively stable second trimester, the collection frequency can be appropriately reduced. Through detailed stage division, the system can formulate a personalized monitoring plan for each perinatal patient. This includes the content, time, method, etc. of data collection to ensure the pertinence and effectiveness of monitoring. During the data collection process, the system can also dynamically adjust the collection frequency according to the patient's real-time physiological and behavioral data. If an abnormal fluctuation is detected in a certain index of the patient, the system will immediately increase the collection frequency to obtain more detailed information, so as to timely discover and warn of potential problems.

[0087] The effects of the above technical solution are as follows: Through detailed stage division and personalized monitoring plans, this technical solution can more accurately monitor the physiological and psychological state changes of perinatal patients, improving the accuracy and reliability of monitoring. Dynamically adjusting the data collection frequency according to the actual needs of patients avoids waste of resources and over-collection. This helps to optimize the allocation and utilization efficiency of medical resources. The personalized monitoring plan can reduce the burden and pressure on patients and enhance their overall experience. At the same time, timely warning and intervention measures also help to relieve the anxiety and uneasiness of patients. Real-time and accurate monitoring data provides an important reference basis for medical staff, helping them to more accurately evaluate the health status of patients and formulate effective treatment plans.

[0088] In summary, through detailed stage division and personalized monitoring plans, this technical solution realizes precise monitoring and dynamic adjustment of the physiological and psychological states of perinatal patients, provides strong support for clinical decision-making, and enhances the patient experience.

[0089] In an embodiment of the present invention, setting an initial data collection frequency according to the current pregnancy stage of the perinatal patient includes:

[0090] S1021. Extract the time period from the current pregnancy of the perinatal patient to the starting week of the stage where the current pregnancy is located as the first time period;

[0091] S1022. Extract the time period from the current pregnancy of the perinatal patient to the ending week of the stage where the current pregnancy is located as the second time period;

[0092] S1023. Extract the data acquisition time interval corresponding to the reference data acquisition frequency, where the value range of the data acquisition time interval corresponding to the reference data acquisition frequency is 1 day to 3 days;

[0093] S1024. Use the first time period and the second time period to combine with the data acquisition time interval corresponding to the reference data acquisition frequency to obtain the data acquisition time interval corresponding to the initial data acquisition frequency; where, the data acquisition time interval corresponding to the initial data acquisition frequency is obtained through the following formula:

[0094]

[0095] where, D represents the data acquisition time interval corresponding to the initial data acquisition frequency; B represents the data acquisition time interval corresponding to the reference data acquisition frequency; W represents the importance weight value corresponding to the pregnancy stage, and the value range of the importance weight value in the first trimester is 0.2 - 0.5, the value range of the importance weight value in the second trimester is 0.4 - 0.6, and the value range of the importance weight value in the third trimester is 0.8 - 1.0; T 01 represents the time length corresponding to the first time period; T 02 represents the time length corresponding to the second time period; e represents a constant, and its value is 2.71.

[0096] The working principle of the above technical solution is as follows: The system first extracts the current pregnancy of the perinatal patient and determines the starting week and ending week of the stage to which it belongs, so as to calculate the first time period (the time from the current pregnancy to the starting week of the stage) and the second time period (the remaining time of the stage, that is, the time from the starting week of the stage to the ending week of the stage). The system presets a reference data acquisition frequency, and this frequency corresponds to a data acquisition time interval, and the value range is between 1 day and 3 days. This reference frequency serves as a reference point for subsequent calculations. According to the importance of the pregnancy stage (the first trimester, the second trimester, the third trimester), the system assigns an importance weight value (W) to each stage. The importance in the first trimester is relatively low, and the weight value is between 0.2 and 0.5; the second trimester is moderate, and the weight value is between 0.4 and 0.6; the third trimester is the most critical, and the weight value is between 0.8 and 1.0. Use the formula to calculate the data acquisition time interval (D) corresponding to the initial data acquisition frequency. The formula takes into account the reference data acquisition time interval (B), the length of the first time period (T01), the length of the second time period (T02), and the constant e (the base of the natural logarithm, approximately equal to 2.71). By adjusting these parameters, the system can dynamically calculate the data acquisition frequency suitable for the current stage of pregnancy.

[0097] The effects of the above technical solution are as follows: This technical solution can dynamically adjust the data collection frequency according to the specific pregnancy period and stage of perinatal patients. This personalized data collection method better meets the actual needs of patients and improves the pertinence and effectiveness of monitoring. By reasonably setting the data collection frequency, waste of resources and over-collection are avoided. In relatively stable pregnancy stages, the collection frequency can be appropriately reduced; while in critical or highly variable stages, the collection frequency is increased to obtain more detailed information. The concept of importance weight value is introduced, enabling the system to fully consider the importance of pregnancy stages when calculating the data collection frequency. This is of great significance for timely detecting potential problems and warning of complications, enhancing the accuracy and reliability of monitoring. Real-time and accurate data collection provides important reference basis for medical staff. By continuously monitoring the changes in patients' physical and mental states, medical staff can more accurately evaluate patients' health conditions and formulate effective treatment plans.

[0098] On the other hand, by introducing the importance weight value (W) corresponding to the pregnancy stage, the formula can automatically adjust the initial data collection frequency according to the importance of different pregnancy stages. The importance weight values in the first trimester, second trimester, and third trimester gradually increase, reflecting that as pregnancy progresses, the urgency and importance of monitoring the health status of the mother and baby also increase. At the same time, the formula uses the time lengths of the first time period (T01, the period from the current pregnancy to the starting week of the stage) and the second time period (T02, the period from the current pregnancy to the ending week of the stage). This helps to fine-tune the data collection frequency according to the remaining length of the pregnancy, ensuring the balance and effectiveness of data collection throughout the pregnancy stage. The data collection time interval corresponding to the benchmark data collection frequency (B) ranges from 1 day to 3 days, which provides a basic and adjustable framework for data collection. By adjusting the benchmark frequency, the initial data collection frequency can be flexibly set according to actual situations (such as medical resources, patient needs, etc.). Rationality of the mathematical model: The formula uses the form of natural logarithm (the exponential form of e). This mathematical expression can smoothly adjust the data collection time interval and avoid sudden changes in the data collection frequency during pregnancy stage transitions. At the same time, the introduction of the constant e (approximately equal to 2.71) increases the scientificity and precision of the formula. By dynamically adjusting the data collection frequency, medical resources can be more reasonably allocated. In relatively stable pregnancy stages, the data collection frequency can be appropriately reduced to save medical resources and costs; while in critical pregnancy stages, the data collection frequency is increased to ensure timely monitoring and intervention of the health of the mother and baby.

[0099] In summary, the technical solution calculates the initial data collection frequency by comprehensively considering multiple factors, achieving personalized, efficient, and accurate monitoring of perinatal patients, and providing strong support for clinical decision-making. At the same time, the above formula realizes the dynamic adjustment and optimal configuration of the initial data collection frequency by comprehensively considering factors such as the importance of the pregnancy stage, the time length, and the reference data collection frequency, providing more scientific, reasonable, and effective technical support for the health monitoring of perinatal patients.

[0100] In one embodiment of the present invention, data collection of behavioral data and physiological data is performed on perinatal patients according to the initial data collection frequency, and the data collection frequency is dynamically adjusted according to the behavioral data and physiological data, including:

[0101] S1031. Perform data collection of behavioral data and physiological data on perinatal patients according to the initial data collection frequency; wherein, the behavioral data includes sleep duration, number of sleep interruptions, and deep sleep duration; the physiological data includes heart rate data, blood pressure data, respiratory rate, and blood oxygen saturation;

[0102] S1032. Set a first adjustment coefficient by using the sleep duration, number of sleep interruptions, and deep sleep duration; wherein, the first adjustment coefficient is obtained through the following formula:

[0103]

[0104] wherein, K 01 represents the first adjustment coefficient; S t represents the total sleep length; S d represents the deep sleep duration; S max represents the preset reference value of the deep sleep duration; I s represents the number of sleep interruptions; I max represents the preset reference value of the number of sleep interruptions; α 01 and β 01 represent the weight values corresponding to the sleep duration data and the sleep interruption data;

[0105] S1033. Set a second adjustment coefficient by using the heart rate data, blood pressure data, respiratory rate, and blood oxygen saturation; wherein, the second adjustment coefficient is obtained through the following formula:

[0106]

[0107] wherein, K 02 represents the second adjustment coefficient; H c 、R c and S c represent the values corresponding to the heart rate data, respiratory rate, and blood oxygen saturation; B crepresents the difference corresponding to diastolic blood pressure and systolic blood pressure; B x represents the reference value of the difference between the preset diastolic blood pressure and systolic blood pressure; H x , R x and S x represent the preset reference values corresponding to heart rate data, respiratory rate, and blood oxygen saturation;

[0108] S1034. Adjust the data acquisition time interval corresponding to the initial data acquisition frequency by using the first adjustment coefficient and the second adjustment coefficient to obtain the data acquisition time interval corresponding to the adjusted data acquisition frequency; wherein, the data acquisition time interval corresponding to the adjusted data acquisition frequency is obtained through the following formula:

[0109]

[0110] wherein, D t represents the data acquisition time interval corresponding to the adjusted data acquisition frequency; D represents the data acquisition time interval corresponding to the initial data acquisition frequency; e represents a constant with a value of 2.71; K 01 represents the first adjustment coefficient; K 02 represents the second adjustment coefficient.

[0111] The working principle of the above technical solution is as follows: According to the preset initial data acquisition frequency, the system starts to collect the behavioral data and physiological data of perinatal patients. The behavioral data includes sleep duration, number of sleep interruptions, and deep sleep duration, while the physiological data covers key indicators such as heart rate, blood pressure, respiratory rate, and blood oxygen saturation. The system calculates the first adjustment coefficient (K01) by using the collected behavioral data (sleep duration, number of sleep interruptions, deep sleep duration) through a specific formula. This coefficient reflects the quality of the patient's sleep, and balances the influence of sleep duration and number of sleep interruptions on sleep quality through the weight values (α01 and β01). Similarly, the system calculates the second adjustment coefficient (K02) by using the physiological data (heart rate, blood pressure, respiratory rate, blood oxygen saturation) through another formula. This coefficient comprehensively evaluates the patient's physiological condition, and reflects whether the patient's physiological indicators are within the normal range by comparing the actual measured values with the preset reference values. Based on the first adjustment coefficient and the second adjustment coefficient, the system dynamically adjusts the initial data acquisition frequency. Through a specific formula, the system combines these two adjustment coefficients with the initial data acquisition time interval (D) to calculate the adjusted data acquisition time interval (Dt). This adjustment process ensures that the data acquisition frequency can change in real time according to the actual condition of the patient, so as to increase the monitoring density when necessary to capture important changes.

[0112] The effects of the above technical solution are as follows: In the data collection of perinatal patients, the initial collection frequency may not accurately reflect the actual condition changes of the patients. If the data collection frequency is too low, important emotional or health change signals may be missed; if it is too high, data redundancy and patient burden may be caused. Therefore, a flexible and sensitive mechanism is needed to dynamically adjust the collection frequency according to the real-time data of the patients, so that it can not only capture subtle changes but also avoid over-collection. Dynamically adjusting the data collection frequency enables the system to more accurately capture the physiological and behavioral changes of perinatal patients. The collection frequency is reduced when the patient's condition is stable to save resources; the collection frequency is increased when abnormal conditions occur to obtain more detailed information, thereby improving the accuracy and effectiveness of monitoring. Through the intelligent dynamic adjustment mechanism, this technical solution avoids waste of resources and over-collection. The system can reasonably allocate collection resources according to actual needs to ensure sufficient data support for clinical decision-making during critical periods. The real-time and dynamic monitoring method helps medical staff to detect the abnormal conditions of patients in time and take intervention measures, thereby reducing the pain and uneasiness of patients. At the same time, the reasonable data collection frequency also reduces the monitoring burden of patients and improves their overall experience. High-quality and real-time monitoring data provides an important reference basis for medical staff. By continuously monitoring the changes in the physiological and behavioral conditions of patients, medical staff can more accurately evaluate the health status of patients and formulate personalized treatment plans, thereby improving the scientificity and effectiveness of clinical decision-making.

[0113] On the other hand, according to the initially set data collection frequency, systematically collect the behavioral data (such as sleep duration, number of sleep interruptions, deep sleep duration) and physiological data (such as heart rate, blood pressure, respiratory rate, blood oxygen saturation) of perinatal patients. These data provide a basis for subsequent health assessment and frequency adjustment. Calculate the first adjustment coefficient (K01) through a formula, and this coefficient is based on the patient's sleep quality and sleep interruption situation. When the patient's sleep quality deteriorates (such as a decrease in deep sleep duration and an increase in the number of sleep interruptions), the value of K01 will increase accordingly, indicating that more frequent data collection is needed to monitor the patient's health status. This adjustment mechanism helps to detect and solve potential sleep problems in time. At the same time, calculate the second adjustment coefficient (K02) through a formula, and this coefficient is based on the difference between the patient's physiological indicators (heart rate, respiratory rate, blood oxygen saturation) and blood pressure (the difference between diastolic blood pressure and systolic blood pressure). When these physiological indicators deviate from the normal range, the value of K02 will increase accordingly, indicating that the patient's physiological condition may have problems and closer monitoring is needed. This adjustment mechanism helps to detect and respond to possible health risks in time.

[0114] Adjust the initial data acquisition frequency using the first adjustment coefficient and the second adjustment coefficient to obtain the adjusted data acquisition frequency. This adjustment is based on the patient's current behavior and physiological data, and can ensure that when the patient's health condition changes, the data acquisition frequency can increase or decrease accordingly. Specifically, when the values of K01 and K02 increase, the adjusted data acquisition time interval (Dt) will be shortened, that is, the data acquisition frequency will increase; conversely, when the values of K01 and K02 decrease, Dt will be extended, that is, the data acquisition frequency will decrease. This dynamic adjustment mechanism helps to optimize the allocation of medical resources and improve the efficiency and accuracy of health monitoring. Through the above steps and formulas, this technical solution realizes the dynamic adjustment of the data acquisition frequency for perinatal patients. This adjustment mechanism not only considers the importance of the pregnancy stage, but also combines the patient's actual health condition (reflected by behavior data and physiological data). This personalized data acquisition strategy helps to provide more accurate and timely health monitoring services and provides strong support for the health management of perinatal patients.

[0115] In one embodiment of the present invention, data is collected from perinatal patients according to the data acquisition frequency, the behavior data and physiological data of the perinatal patients are obtained, and data quality assessment and data quality anomaly warning are performed on the behavior data and physiological data, including:

[0116] S201. Collect data from perinatal patients according to the data acquisition frequency, and obtain the behavior data and physiological data of the perinatal patients;

[0117] S202. Perform data preprocessing on the behavior data and physiological data of the perinatal patients, wherein the data preprocessing includes information extraction processing of garbled data and its corresponding data types and information extraction processing of missing data corresponding data types;

[0118] S203. Determine and give an early warning of data quality anomalies according to the data type weight values of the garbled data and its corresponding data types and the missing data corresponding data types.

[0119] The working principle of the above technical solution is as follows: According to the preset data acquisition frequency, the system continuously acquires data from perinatal patients, obtaining their behavioral data and physiological data. These data are the basis for subsequent analysis and are crucial for evaluating the health status of patients. Before the data enters the analysis stage, preprocessing is first performed to ensure the quality of the data. The preprocessing steps include the extraction and processing of garbled data and their corresponding data types, and the extraction and processing of missing data and their corresponding data types. Garbled data may be caused by encoding errors, transmission errors, etc., while missing data may be due to equipment failures, patient non-cooperation, etc. By extracting this information, the system can identify potential data quality problems. Based on the preprocessed data, the system conducts a quality assessment of the garbled data and missing data according to the preset data type weight values. The data type weight values reflect the importance of different types of data in the overall assessment. If the garbled or missing situation of a certain type of data exceeds the preset threshold, the system will trigger an abnormal warning, prompting relevant personnel to pay attention to the data quality problem and possibly take further remedial measures.

[0120] The effects of the above technical solution are as follows: Through the data preprocessing and quality assessment steps, the system can timely detect and handle the garbled and missing problems in the data, thereby improving the quality of the overall data. High-quality data is the basis for subsequent analysis and decision-making, helping to improve the accuracy and reliability of monitoring. The data quality abnormal warning mechanism enables the system to quickly respond to potential data quality problems, enhancing the robustness and stability of the system. Even if some unforeseen problems occur during the data acquisition process, the system can timely detect and solve these problems through the warning mechanism, ensuring the smooth progress of the monitoring work. The data quality assessment results help to optimize resource allocation. For monitoring points or devices with poor data quality, the data acquisition strategy can be adjusted in a timely manner or equipment maintenance can be carried out to reduce resource waste and improve monitoring efficiency. High-quality data provides an important reference basis for medical staff. By continuously monitoring and evaluating the behavioral data and physiological data of perinatal patients, medical staff can more accurately evaluate the health status of patients and develop personalized treatment plans, thereby improving the scientificity and effectiveness of clinical decision-making.

[0121] In summary, through steps such as data acquisition, preprocessing, quality assessment, and abnormal warning, the technical solution realizes the comprehensive management and quality control of perinatal patient data, providing strong support for clinical decision-making.

[0122] In one embodiment of the present invention, data quality abnormal determination and warning are performed according to the garbled data and their corresponding data types and the data type weight values of the missing data and their corresponding data types, including:

[0123] S2031. Extract the data type weight values corresponding to the data types of each garbled data and the data type weight values corresponding to the data types of each missing data;

[0124] S2032. Extract the importance weight value corresponding to the current pregnancy stage of the perinatal patient to obtain the data quality anomaly severity coefficient; wherein, the data quality anomaly severity coefficient is obtained through the following formula:

[0125]

[0126] wherein, S q represents the data quality anomaly severity coefficient; W s represents the importance weight value corresponding to the current pregnancy stage; N ci represents the number of garbled data in the i-th data type; N mi represents the number of missing data in the i-th data type; W ti represents the data type weight value of the i-th data type; N t represents the total number of data; n represents the total number of data types;

[0127] S2033. When the data quality anomaly severity coefficient exceeds the preset severity coefficient threshold, it is determined that there is a data quality anomaly in the data collection of the current behavioral data and physiological data of the perinatal patient, and a data quality anomaly warning is issued.

[0128] The working principle of the above technical solution is as follows: The system first extracts each garbled data and its corresponding data type weight value, and each missing data and its corresponding data type weight value. The data type weight value reflects the importance of different types of data in the overall evaluation and is the basis for calculating the data quality anomaly severity coefficient in the follow-up.

[0129] Next, the system extracts the importance weight value corresponding to the current pregnancy stage of the perinatal patient. This weight value reflects the importance of the current pregnancy stage in the overall monitoring process.

[0130] Then, the system calculates the data quality anomaly severity coefficient (Sq) using a preset formula. This coefficient comprehensively considers the importance of the current pregnancy stage, the number of garbled and missing data in each type of data, and the data type weight values. Through weighted summation, the system can quantitatively evaluate the data quality anomaly situation in the current data collection process.

[0131] Finally, the system compares the calculated data quality anomaly severity coefficient with a preset severity coefficient threshold. If Sq exceeds the threshold, it is determined that there is a data quality anomaly in the data collection of the current behavioral and physiological data of the perinatal patient, and a warning mechanism is triggered. The warning mechanism may include sending alarm messages to medical staff, displaying anomaly prompts on the monitoring interface, etc., so that relevant personnel can take timely measures to solve the problem.

[0132] The effects of the above technical solutions are as follows: In perinatal data collection, the importance of different data types (such as heart rate data, sleep duration, blood oxygen saturation, etc.) for data analysis varies. Some key data (such as heart rate and blood pressure) will have a more serious impact on judging the patient's health status if there are garbled characters or missing values. While some secondary data (such as the frequency of social media use) will have a smaller impact even if there are anomalies. Therefore, data quality assessment needs to consider the weight differences of various data types to accurately reflect the severity of data anomalies. By comprehensively considering the data type weight values, the importance of the current pregnancy stage, and the number of garbled characters and missing data, the system can accurately determine the data quality anomaly situation in the data collection process. This determination method is more scientific and objective, which helps to improve the accuracy of early warning. Once a data quality anomaly is determined, the system can quickly trigger the warning mechanism and provide timely and effective alarm information to relevant personnel. This helps medical staff to discover problems in time, evaluate the impact, and formulate corresponding solutions, thus ensuring the monitoring effect and safety of perinatal patients. The data quality anomaly determination and warning mechanism also helps to optimize resource allocation. Through continuous monitoring and analysis of data quality anomaly situations, the system can discover weak links and potential problems in the data collection process, providing strong support for resource allocation and process optimization. This helps to improve monitoring efficiency, reduce resource waste, and enhance the overall service quality.

[0133] Meanwhile, the above formula comprehensively evaluates the impact of garbled characters and missing data that occur during the data collection process on the overall data quality by calculating the data quality anomaly severity coefficient (Sq). This comprehensive evaluation method is more comprehensive and accurate than simply considering garbled characters or missing data alone. The importance weight value (Ws) corresponding to the current stage of pregnancy is introduced in the formula, which reflects the differences in data quality requirements at different stages of pregnancy. During the more critical stages of pregnancy, the importance of data quality is higher. Therefore, even a small amount of garbled characters or missing data may result in a relatively high data quality anomaly severity coefficient. The formula takes into account the weight values (Wti) of different types of data (such as different indicators in behavioral data and physiological data). This reflects the differences in the importance of different types of data when evaluating data quality. For key indicators (such as heart rate, blood pressure, etc.), their weight values may be higher. Therefore, when garbled characters or missing data occur, the impact on the overall data quality is also greater. The formula quantifies the specific impact of garbled characters and missing data on the overall data quality by calculating the number of garbled data (Nc) and the number of missing data (Nmi) in each data type and combining the data type weight value (Wti). This quantification method makes the evaluation of data quality anomalies more objective and accurate. When the data quality anomaly severity coefficient (Sq) exceeds the preset severity coefficient threshold, the system will determine that there are data quality anomalies in the data collection of the current behavioral data and physiological data of the perinatal patient and trigger an early warning mechanism. This helps to timely detect and handle data quality problems, ensuring the accuracy and reliability of subsequent analysis and decision-making. By regularly evaluating the data quality anomaly severity coefficient and triggering the early warning mechanism, medical institutions can continuously optimize the data collection process and improve the accuracy and integrity of data collection. For example, data verification and completion measures can be strengthened for data types that frequently have garbled characters or missing data, or the data collection frequency and method can be adjusted to meet the requirements of different pregnancy stages.

[0134] In summary, through precise determination of data quality anomalies and a timely early warning mechanism, this technical solution provides strong guarantee for the monitoring of perinatal patients. It can not only improve the accuracy and reliability of monitoring, but also optimize resource allocation, enhance service efficiency, and provide more scientific and effective support for clinical decision-making.

[0135] In one embodiment of the present invention, the behavioral data and physiological data of the perinatal patient that meet the data quality requirements are grouped and stored, including:

[0136] S301. Set a time window according to the current stage of pregnancy of the perinatal patient;

[0137] S302. Group the behavioral data and physiological data collected during the current stage of pregnancy according to the time window to form multiple groups of behavioral data and physiological data;

[0138] S303. Group and store each set of behavioral data and physiological data.

[0139] The working principle of the above technical solution is as follows: According to the current pregnancy stage of the perinatal patient, the system sets a reasonable time window. This time window is determined based on the natural laws of pregnancy development and monitoring requirements, aiming to ensure that the data within each time window can reflect the specific physiological and behavioral characteristics of the patient at that stage. According to the set time window, the system groups the behavioral data and physiological data collected during the current pregnancy stage. This step cuts the continuously collected data stream into multiple time segments, and each segment corresponds to a data set within a time window. Such grouping helps with subsequent data analysis and processing, enabling the data of each stage to be independently evaluated and applied. Group and store the behavioral data and physiological data within each time window. This means that the system will classify and save the relevant data in different storage units according to the time sequence and pregnancy stage. This storage method facilitates the rapid retrieval, access, and analysis of data, and also provides convenience for future data mining and scientific research work.

[0140] The effect of the above technical solution is as follows: By setting a time window according to the pregnancy stage and grouping and storing the data, the system can achieve the orderly management of perinatal patient data. This helps reduce data chaos and redundancy, and improves the efficiency and accuracy of data processing. The grouped and stored data enables the data of each pregnancy stage to be independently evaluated and analyzed. This helps medical staff better understand the physiological and behavioral change trends of patients, providing a scientific basis for clinical decision-making. At the same time, it also provides rich data resources for future scientific research work, helping to promote the research progress in the field of perinatal medicine. Grouping and storing also helps improve the level of data security and privacy protection. By storing the data of different stages in different storage units respectively, the system can more effectively control data access permissions and the security of the data transmission process, reducing the risk of data leakage and abuse.

[0141] In summary, through reasonable setting of the time window and grouping and storing the behavioral data and physiological data of perinatal patients, the technical solution realizes the orderly management and efficient utilization of data, providing strong support for clinical decision-making and scientific research work.

[0142] In an embodiment of the present invention, for the behavioral data and physiological data of the perinatal patient that meet the data quality requirements, the grouping and storage further include:

[0143] Step 1. Perform data aggregation processing on each set of behavioral data and physiological data to generate a state comprehensive index parameter corresponding to each set of behavioral data and physiological data; wherein, the state comprehensive index parameter is obtained through the following formula:

[0144]

[0145] Among them, E represents the comprehensive state index parameter; S t represents the total sleep duration; S tc represents the reference value of the total sleep duration; S max represents the reference value of the preset deep sleep duration; S d represents the deep sleep duration; I s represents the number of sleep interruptions; I symax represents the maximum allowable number of sleep interruptions; C max represents the maximum difference between the value of the physiological parameter type in the physiological data and its standard value; C ymax represents the maximum allowable difference;

[0146] Step 2: Compare the comprehensive state index parameter corresponding to the perinatal patient with the preset index parameter;

[0147] Step 3: When the comprehensive state index parameter corresponding to the perinatal patient exceeds the preset index parameter, mark a set of behavior data and physiological data for which the comprehensive state index parameter exceeds the preset index parameter;

[0148] Step 4: When the number of groups of marked behavior data and physiological data exceeds the preset group number threshold, give a warning prompt.

[0149] The working principle of the above technical solution is as follows: First, the system collects the behavior data and physiological data of perinatal patients, and these data need to meet the data quality requirements to ensure accuracy and integrity. For each group (grouped by time window or pregnancy stage) of behavior data and physiological data, the system performs data aggregation processing. In this step, the comprehensive state index parameter (E) is calculated through a preset formula, which comprehensively considers multiple factors related to the health state, such as sleep duration, deep sleep duration, number of sleep interruptions, and the difference between the physiological value and its standard value, etc. The weights and thresholds of these factors can be set according to clinical experience and research results. The calculated comprehensive state index parameter (E) is then compared with the preset index parameter. The preset index parameter is set based on authoritative sources such as health standards, clinical guidelines, or expert consensus, aiming to reflect the normal or acceptable health state range of perinatal patients. Through comparison, the system can judge whether the health state of the current perinatal patient is within the normal range. If the comprehensive state index parameter exceeds the preset index parameter, it may mean that there are abnormalities or potential risks in the patient's health state.

[0150] When the state comprehensive index parameter exceeds the preset index parameter, the system will mark the corresponding behavior data and physiological data. This marking mechanism helps medical staff quickly identify data groups with abnormalities. The system further determines whether the number of marked data groups exceeds the preset group number threshold. This threshold is set according to clinical actual needs and risk assessment results, aiming to balance the timeliness and accuracy of early warning. If the number of marked data groups exceeds the preset threshold, the system will give an early warning prompt. The early warning prompt may be presented in the form of sound, light signal, pop-up window, etc., aiming to attract the attention of medical staff and prompt them to take measures in time to intervene in the health risks of patients.

[0151] This technical solution generates a state comprehensive index parameter through data aggregation processing, compares and analyzes it with the preset index parameter, and finally gives an early warning prompt according to the comparison result and the early warning threshold judgment. This workflow realizes the real-time monitoring and risk assessment of the health status of perinatal patients, providing timely and accurate decision-making support for medical staff.

[0152] The effect of the above technical solution is as follows: By calculating the state comprehensive index parameter (E), this solution comprehensively considers multiple dimensions of the sleep quality and physiological data of perinatal patients, such as total sleep length, deep sleep duration, number of sleep interruptions, and the difference between physiological values and their standard values, etc., so as to provide a more comprehensive and accurate health status assessment. Comparing the actual data with reference values (such as total sleep length reference value, deep sleep duration reference value, maximum allowable number of sleep interruptions, maximum allowable difference, etc.) helps to eliminate individual differences and makes the assessment results more objective and comparable.

[0153] This solution can calculate the state comprehensive index parameter in real time or regularly, and compare it with the preset index parameter, so as to realize the dynamic monitoring of the health status of perinatal patients. When the state comprehensive index parameter exceeds the preset index parameter, mark the corresponding behavior data and physiological data; when the number of marked data groups exceeds the preset threshold, trigger an early warning prompt. This mechanism helps to detect potential health risks in time and provides a time window for medical staff to take intervention measures. Through the marking and early warning mechanism, medical staff can quickly locate perinatal patients with health risks and carry out precise intervention on them, avoiding waste of resources and ineffective intervention. This solution has a high degree of automation, can reduce the workload of manual evaluation, and improve the utilization efficiency of medical resources. The timeliness of the early warning prompt helps medical staff to pay attention to the health changes of patients in time, give patients more care and support, and thus improve the medical experience of patients. Based on the evaluation results of the state comprehensive index parameter, medical staff can provide more personalized nursing plans for patients to meet the different needs of patients.

[0154] On the other hand, the formula generates a comprehensive status indicator parameter (E) by integrating data from multiple dimensions, such as total sleep duration, deep sleep duration, number of sleep interruptions, and the difference between the physiological data type and the standard value. This comprehensive evaluation method can more comprehensively reflect the patient's health status, rather than just the changes in a single indicator. Reference values (such as the reference value of total sleep duration Sct, the reference value of deep sleep duration Smax, the maximum allowable number of sleep interruptions Isymax, and the maximum allowable difference Cymax) are introduced in the formula to standardize the original data. This processing method makes the data between different patients comparable and can more accurately evaluate the patient's health status. Although the formula itself does not directly show the weight distribution, the positions and calculation methods of different indicators in the formula imply their different impacts on the patient's overall health status. For example, deep sleep duration and the number of sleep interruptions may have an important impact on the patient's sleep quality, so they occupy important positions in the formula. By comparing the calculated comprehensive status indicator parameter with the preset indicator parameter, it can be detected whether the patient's health status is abnormal. When the comprehensive status indicator parameter exceeds the preset value, it indicates that there may be problems with the patient's health and further attention is needed.

[0155] For the behavior data and physiological data groups where the comprehensive status indicator parameter exceeds the preset value, marking processing is performed. When the number of marked data groups exceeds the preset group threshold, the system will give a warning prompt. This mechanism helps to timely detect and handle the patient's health problems and avoid the deterioration of the condition. By regularly calculating and comparing the comprehensive status indicator parameter, medical institutions can more accurately understand the changing trend of the patient's health status, so as to formulate a more personalized health management plan. At the same time, the triggering of the warning mechanism can also prompt medical institutions to take intervention measures in a timely manner to ensure the health and safety of patients.

[0156] In summary, this technical solution realizes the timely discovery and warning of health risks by comprehensively evaluating the behavior data and physiological data of perinatal patients, which helps to optimize the allocation of medical resources, improve the patient experience, and enhance the overall medical quality. At the same time, the above formula in this embodiment generates a comprehensive status indicator parameter by comprehensively evaluating the behavior data and physiological data of the patient, providing an effective means of health monitoring and warning for medical institutions. This technical means helps to improve the quality and efficiency of medical services and provide more comprehensive and accurate health management services for patients.

[0157] An embodiment of the present invention proposes a data processing system for perinatal depression monitoring, as Figure 2 shown, the data processing system for perinatal depression monitoring includes:

[0158] A data acquisition frequency setting and adjustment module, which is used to extract the current pregnancy stage of a perinatal patient, set the data acquisition frequency according to the current pregnancy stage of the perinatal patient, and perform real-time dynamic adjustment of the data acquisition frequency for the data of the current pregnancy stage of the perinatal patient during the data acquisition process;

[0159] A data quality abnormal warning module, which is used to collect data from perinatal patients according to the data acquisition frequency, obtain the behavioral data and physiological data of the perinatal patients, and perform data quality assessment and data quality abnormal warning on the behavioral data and physiological data;

[0160] A grouped storage module, which is used to group and store the behavioral data and physiological data of the perinatal patients that meet the data quality requirements.

[0161] The working principle of the above technical solution is as follows: With the help of a preset pregnancy stage division strategy, the system can accurately judge the current pregnancy stage of a perinatal patient. This strategy is usually based on medical knowledge and experience, and divides pregnancy into several key stages, such as the first trimester, the second trimester, and the third trimester.

[0162] Once the pregnancy stage of the patient is determined, the system will set a reasonable initial data acquisition frequency according to the characteristics and requirements of this stage. For example, in the first trimester and the third trimester, since the physiological and psychological changes of the patient are more significant, a higher data acquisition frequency may be required.

[0163] During the data acquisition process according to the initial frequency, the system will analyze the collected behavioral data and physiological data in real time. Based on these data, the system will dynamically adjust the data acquisition frequency to ensure that important changes in the physiological and psychological states of the patient can be captured. For example, if the system detects an abnormal fluctuation in a certain physiological index of the patient, it may automatically increase the data acquisition frequency to monitor the patient's condition in more detail.

[0164] The effects of the above technical solution are as follows: By dynamically adjusting the data collection frequency according to the pregnancy stage, this technical solution can more accurately monitor the physiological and psychological states of perinatal patients. This helps medical staff to timely detect abnormal conditions of patients and take effective intervention measures. Real-time dynamic adjustment of the data collection frequency can ensure that more valuable data is collected during critical periods, while reducing data redundancy during stable periods. This helps to improve the quality and analysis efficiency of data. This technical solution can perform personalized data monitoring according to needs, avoiding over-collection or omission of important data. This helps to reduce the burden on patients and enhance their overall experience. By real-time dynamically adjusting the data collection frequency, this technical solution can ensure the reasonable allocation and utilization of medical resources. During critical periods, the system can automatically increase the data collection frequency to more detailedly monitor the patient's condition; while during stable periods, the data collection frequency can be reduced to save medical resources.

[0165] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A data processing method for perinatal depression monitoring, characterized in that: The data processing method for perinatal depression monitoring comprises: S1: extracting the current pregnancy stage of the perinatal patient, setting the data collection frequency according to the current pregnancy stage of the perinatal patient, and dynamically adjusting the data collection frequency of the current pregnancy stage of the perinatal patient in real time during the data collection process; S2: collecting data from perinatal patients according to the data collection frequency, obtaining behavioral data and physiological data of the perinatal patients, and performing data quality assessment and data quality abnormality warning on the behavioral data and physiological data; S3: storing the behavioral data and physiological data of the perinatal patients that meet the data quality requirements in groups; wherein step S1 includes: Determining the current pregnancy stage of the perinatal patient according to a preset pregnancy stage classification strategy; Setting an initial frequency of data collection according to the current pregnancy stage of the perinatal patient; Collecting behavioral data and physiological data from perinatal patients according to the initial frequency of data collection, and dynamically adjusting the data collection frequency according to the behavioral data and physiological data; Wherein, setting the initial frequency of data collection according to the current pregnancy stage of the perinatal patient includes: Extracting the period of the current pregnancy of the perinatal patient and the starting week of the stage of the current pregnancy as the first time period; extracting the period of the current pregnancy of the perinatal patient and the ending week of the stage of the current pregnancy as the second time period; Extracting a data collection time interval corresponding to a benchmark data collection frequency, wherein the data collection time interval corresponding to the benchmark data collection frequency ranges from 1 day to 3 days; The data collection time interval corresponding to the initial data collection frequency is obtained by combining the first time period and the second time period with the data collection time interval corresponding to the reference data collection frequency; wherein the data collection time interval corresponding to the initial data collection frequency is obtained by the following formula: in, D Indicates the data collection time interval corresponding to the initial frequency of data collection; B Indicates the data collection time interval corresponding to the benchmark data collection frequency; W Indicates the importance weight value corresponding to the pregnancy stage, and the importance weight value range of the early pregnancy is 0.2-0.5, the importance weight value range of the mid-pregnancy is 0.4-0.6, and the importance weight value range of the late pregnancy is 0.8-1.0; T 01 Indicates the time length corresponding to the first time period; T 02 Indicates the time length corresponding to the second time period; e Represents a constant, and its value is 2.

71.

2. The data processing method for perinatal depression monitoring according to claim 1, characterized in that: The stage cycle of the pregnancy stage division strategy is as follows: The early pregnancy stage cycle includes a first early pregnancy stage, a second early pregnancy stage and a third early pregnancy stage, wherein the early pregnancy stage is from 0 to 12 weeks of pregnancy, and the first early pregnancy stage is from 0 to 3 weeks of the early pregnancy stage; the second early pregnancy stage is from 4 to 9 weeks of the early pregnancy stage; the third early pregnancy stage is from 10 to 12 weeks of the early pregnancy stage; The mid-pregnancy stage cycle includes the first mid-pregnancy stage, the second mid-pregnancy stage, the third mid-pregnancy stage and the fourth mid-pregnancy stage, wherein the mid-pregnancy stage is from 13 weeks to 28 weeks of pregnancy, and the first mid-pregnancy stage is from 13 weeks to 16 weeks of the mid-pregnancy stage; the second mid-pregnancy stage is from 17 weeks to 20 weeks of the mid-pregnancy stage; the third mid-pregnancy stage is from 21 weeks to 25 weeks of the mid-pregnancy stage; the fourth mid-pregnancy stage is from 26 weeks to 28 weeks of the mid-pregnancy stage; The late pregnancy stage cycle includes a first late pregnancy stage, a second late pregnancy stage and a third late pregnancy stage, wherein the late pregnancy stage is from 29 weeks to 40 weeks of pregnancy, and the first late pregnancy stage is from 29 weeks to 31 weeks of the late pregnancy stage; the second late pregnancy stage is from 32 weeks to 36 weeks of the late pregnancy stage; the third late pregnancy stage is from 37 weeks to 40 weeks of the late pregnancy stage; The postpartum period cycle includes a first postpartum period and a second postpartum period, wherein the postpartum period includes 0 to 6 weeks after delivery; and the first postpartum period is 0 to 4 weeks after delivery; and the second postpartum period is 5 to 6 weeks after delivery.

3. The data processing method for perinatal depression monitoring according to claim 1, characterized in that: Collecting behavioral data and physiological data of perinatal patients according to the initial frequency of data collection, and dynamically adjusting the data collection frequency according to the behavioral data and physiological data, including: Collecting behavioral data and physiological data of perinatal patients according to the initial frequency of data collection; wherein the behavioral data includes sleep duration, number of sleep interruptions and deep sleep duration; and the physiological data includes heart rate data, blood pressure data, respiratory rate and blood oxygen saturation; The first adjustment coefficient is set using the sleep duration, the number of sleep interruptions, and the deep sleep duration; wherein the first adjustment coefficient is obtained by the following formula: in, K 01 represents the first adjustment coefficient; S t Indicates the total sleep length; S d Indicates the duration of deep sleep; S max Indicates the preset reference value of deep sleep duration; I s Indicates the number of sleep interruptions; I max Indicates the preset reference value of sleep interruption times; α 01 and β 01 Indicates the weight values ​​corresponding to the sleep duration data and the sleep interruption data; The second adjustment coefficient is set using the heart rate data, blood pressure data, respiratory rate and blood oxygen saturation; wherein the second adjustment coefficient is obtained by the following formula: in, K 02 represents the second adjustment coefficient; H c , R c and S c Indicates the corresponding values ​​of heart rate data, respiratory rate and blood oxygen saturation; B c It represents the difference between diastolic and systolic blood pressure; B x Indicates the preset reference value of the difference between diastolic and systolic blood pressure; H x , R x and S x Indicates the preset reference values ​​corresponding to heart rate data, respiratory rate and blood oxygen saturation; The data collection time interval corresponding to the initial frequency of data collection is adjusted by using the first adjustment coefficient and the second adjustment coefficient to obtain the data collection time interval corresponding to the adjusted data collection frequency; wherein the data collection time interval corresponding to the adjusted data collection frequency is obtained by the following formula: in, D t Indicates the data collection time interval corresponding to the adjusted data collection frequency; D Indicates the data collection time interval corresponding to the initial frequency of data collection; e represents a constant, and its value is 2.71; K 01 represents the first adjustment coefficient; K 02 Represents the second adjustment coefficient.

4. The data processing method for perinatal depression monitoring according to claim 1, characterized in that: Data is collected from perinatal patients according to the data collection frequency to obtain behavioral data and physiological data of the perinatal patients, and data quality assessment and data quality abnormality warning are performed on the behavioral data and physiological data, including: Collecting data from perinatal patients according to the data collection frequency to obtain behavioral data and physiological data of the perinatal patients; Performing data preprocessing on the behavioral data and physiological data of the perinatal patients, wherein the data preprocessing includes information extraction processing of garbled data and its corresponding data type and information extraction processing of the data type corresponding to the missing data; Data quality anomaly determination and warning are performed based on the data type weight values ​​of the garbled data and its corresponding data type and the data type corresponding to the missing data.

5. The data processing method for perinatal depression monitoring according to claim 4, characterized in that: According to the data type weight value of the garbled data and its corresponding data type and the data type corresponding to the missing data, data quality abnormality judgment and warning are performed, including: Extract the data type weight value corresponding to the data type of each garbled data and the data type weight value corresponding to the data type of each missing data; The importance weight value corresponding to the current pregnancy stage of the perinatal patient is extracted to obtain the data quality abnormality severity coefficient; wherein the data quality abnormality severity coefficient is obtained by the following formula: in, S q Indicates the severity coefficient of data quality anomaly; W s Indicates the importance weight value corresponding to the current stage of pregnancy; N ci Indicates i The number of garbled data in each data type; N mi Indicates i The number of missing data in each data type; W ti Indicates i The data type weight value of each data type; N t Indicates the total amount of data; n Indicates the total number of data types; When the data quality abnormality severity coefficient exceeds a preset severity coefficient threshold, it is determined that data quality abnormalities exist in the data collection of the current behavioral data and physiological data of the perinatal patient, and a data quality abnormality warning is issued.

6. The data processing method for perinatal depression monitoring according to claim 1, characterized in that: The behavioral data and physiological data of the perinatal patient that meet the data quality requirements are grouped and stored, including: Setting a time window according to the current pregnancy stage of the perinatal patient; Grouping the behavioral data and physiological data collected during the current pregnancy stage according to the time window to form multiple groups of behavioral data and physiological data; Each set of behavioral data and physiological data is stored in groups.

7. The data processing method for perinatal depression monitoring according to claim 6, characterized in that: The behavioral data and physiological data of the perinatal patients that meet the data quality requirements are grouped and stored, further comprising: Data aggregation processing is performed on each set of behavioral data and physiological data to generate a state comprehensive index parameter corresponding to each set of behavioral data and physiological data; wherein the state comprehensive index parameter is obtained by the following formula: in, E Indicates the comprehensive indicator parameters of the status; S t Indicates the total sleep length; S tc Indicates the total sleep length reference value; S max Indicates the preset reference value of deep sleep duration; S d Indicates the duration of deep sleep; I s Indicates the number of sleep interruptions; I symax Indicates the maximum allowed number of sleep interruptions; C max Indicates the maximum difference between the value of the physiological number type in the physiological data and its standard value; C ymax Indicates the maximum allowable difference; Comparing the comprehensive index parameters of the status corresponding to the perinatal patient with the preset index parameters; When the state comprehensive index parameter corresponding to the perinatal patient exceeds the preset index parameter, a group of behavioral data and physiological data whose state comprehensive index parameter exceeds the preset index parameter is marked; When the number of groups of marked behavioral data and physiological data exceeds the preset group number threshold, an early warning prompt will be issued.

8. A data processing system for monitoring perinatal depression, characterized in that: The data processing system for perinatal depression monitoring comprises: A data collection frequency setting and adjustment module, used to extract the current pregnancy stage of a perinatal patient, set the data collection frequency according to the current pregnancy stage of the perinatal patient, and dynamically adjust the data collection frequency of the current pregnancy stage of the perinatal patient in real time during the data collection process; A data quality abnormality warning module is used to collect data from perinatal patients according to the data collection frequency, obtain behavioral data and physiological data of the perinatal patients, and perform data quality assessment and data quality abnormality warning on the behavioral data and physiological data; A grouping storage module, used for grouping and storing the behavioral data and physiological data of the perinatal patients that meet the data quality requirements; The data acquisition frequency setting and adjustment module includes: Determining the current pregnancy stage of the perinatal patient according to a preset pregnancy stage classification strategy; Setting an initial frequency of data collection according to the current pregnancy stage of the perinatal patient; Collecting behavioral data and physiological data from perinatal patients according to the initial frequency of data collection, and dynamically adjusting the data collection frequency according to the behavioral data and physiological data; Wherein, setting the initial frequency of data collection according to the current pregnancy stage of the perinatal patient includes: Extracting the period of the current pregnancy of the perinatal patient and the starting week of the stage of the current pregnancy as the first time period; extracting the period of the current pregnancy of the perinatal patient and the ending week of the stage of the current pregnancy as the second time period; Extracting a data collection time interval corresponding to a benchmark data collection frequency, wherein the data collection time interval corresponding to the benchmark data collection frequency ranges from 1 day to 3 days; The data collection time interval corresponding to the initial data collection frequency is obtained by combining the first time period and the second time period with the data collection time interval corresponding to the benchmark data collection frequency, wherein the data collection time interval corresponding to the initial data collection frequency is obtained by the following formula: in, D Indicates the data collection time interval corresponding to the initial frequency of data collection; B Indicates the data collection time interval corresponding to the benchmark data collection frequency; W Indicates the importance weight value corresponding to the pregnancy stage, and the importance weight value range of the early pregnancy is 0.2-0.5, the importance weight value range of the mid-pregnancy is 0.4-0.6, and the importance weight value range of the late pregnancy is 0.8-1.0; T 01 Indicates the time length corresponding to the first time period; T 02 Indicates the time length corresponding to the second time period; e Represents a constant, and its value is 2.71.

Images