Gynecological and obstetric information processing method and system based on Internet

Abstract

The invention discloses a gynaecology and obstetrics information processing method and system based on the Internet, relates to the technical field of the Internet, and enables a nursing scheme to be more personalized and dynamic by performing extraction and data processing on a data set D and integrating to form a feature data set F. By establishing a time sequence analysis algorithm, the system can calculate an adjustment index C reflecting the fluctuation of the health state of the puerpera, and the adjustment index C is matched with a health fluctuation evaluation threshold TZ to generate a nursing regulation and control suggestion and a nursing scheme which are consistent with the health state of the puerpera, so that the defect that the nursing scheme cannot follow the health change of the puerpera in real time is overcome. Besides, by introducing an effect monitoring mechanism, calculating and adjusting the change trend of an index C, generating an effect execution index R and continuously evaluating the execution effect of the nursing scheme, the effect of the nursing scheme is ensured to always meet the health requirement of the puerpera. The nursing plan is matched with the actual recovery state of the puerpera, so that the recovery effect of the puerpera is improved.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to an Internet-based obstetrics and gynecology information processing method and system. Background Art

[0002] Medical data and patient health information are processed and managed through information technology to improve the efficiency and accuracy of medical services. With the development of the Internet and mobile communication technologies, telemedicine and online health management have become important sub-fields in medical informatization. These technologies are particularly suitable for the field of obstetrics and gynecology, because pregnant women and postpartum women usually need continuous and dynamic health monitoring and nursing guidance.

[0003] Although the application of Internet technology in medical informationization in the field of obstetrics and gynecology has made certain progress, there are still many shortcomings in the field of obstetrics and gynecology nursing. At present, most traditional nursing plans are still based on fixed nursing plans, which are usually formulated after the mother is discharged from the hospital and are rarely adjusted in real time according to the actual situation of the patient. The disadvantage of this static nursing plan is that it cannot fully respond to the dynamic health changes of the mother during the recovery process. For example, the mood swings, sleep quality and physical recovery speed of the mother vary from person to person, and it is difficult for a fixed nursing plan to meet the individual needs of each mother. In addition, although modern medical equipment can collect physiological data of the mother, such as heart rate and blood pressure, most of these data are only used for doctors' diagnosis, and are not fully utilized to dynamically adjust the nursing plan. This leads to insufficient response speed and personalization of the nursing plan, and it is impossible to accurately follow the health changes of the mother and make timely adjustments. Summary of the invention

[0004] In view of the deficiencies of the prior art, the present invention provides an Internet-based obstetrics and gynecology information processing method and system, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an Internet-based obstetrics and gynecology information processing method, comprising the following steps:

[0006] S1, collect physiological parameters of parturients through smart watches, mobile phones and other wearable devices, form a collection data set D, and upload it to the cloud server through the Internet;

[0007] S2, extracting and processing the acquired data set D, and integrating it into a feature data set F;

[0008] S3, by establishing a time series analysis algorithm, substituting the acquired feature data set F into the calculation, and obtaining an adjustment index C reflecting the fluctuation of the maternal health status;

[0009] S4, matching the obtained adjustment index C with the preset health fluctuation assessment threshold TZ, obtaining the maternal health regulation generation suggestion result, and generating a suggested nursing plan according to the maternal health regulation generation suggestion result;

[0010] S5. Generate recommendations based on maternal health regulation results to trigger the effect monitoring mechanism of the recommended nursing plan, and obtain the effect execution index R by calculating the change trend of the adjustment index C;

[0011] S6. By matching the effect execution index R with the preset recommended nursing execution effect threshold ZZ, a nursing effectiveness evaluation strategy is obtained, and relevant personnel are notified and prompted according to the nursing effectiveness evaluation strategy.

[0012] Preferably, said S1 includes S11 and S12;

[0013] S11, collecting physiological parameters of the parturient in real time through smart watches, mobile phones and other wearable devices, including heart rate time series data HRp, sleep time series data SP, emotion time series data PS and exercise time series data St;

[0014] Among them, the heart rate time series data HRp includes the average heart rate HRm, the peak heart rate HRmax and the heart rate fluctuation amplitude HRv; the sleep time series data SP includes the sleep duration SPc, the deep sleep duration SPd, the light sleep duration SPl, the number of deep sleep times Dc and the number of light sleep times Qc; the emotion time series data PS includes the average pressure PSm, the peak pressure PSmax and the pressure fluctuation amplitude PSv; the exercise time series data St includes the total walking time Stc, the number of walking times Stn and the walking distance Std;

[0015] The heart rate time series data HRp is specifically HRp={HRm, HRmax, HRv};

[0016] The sleep time series data SP is specifically SP={SPc, SPd, SP1, Dc, Qc};

[0017] The emotional time series data PS is specifically PS={PSm, PSmax, PSv};

[0018] The motion time series data St is specifically St={Stc, Stn, Std}.

[0019] Preferably, S12, integrating the acquired heart rate time series data HRp, sleep time series data SP, emotion time series data PS and exercise time series data St to form a collection data set D, and connecting to the Internet after a fixed period N to upload the collection data set D to a cloud server;

[0020] The collected data set D is specifically D={HRp, SP, PS, St}.

[0021] Preferably, S2 includes S21 and S22;

[0022] S21, normalizing the acquired data set D including the heart rate time series data HRp, the sleep time series data SP, the emotion time series data PS, and the exercise time series data St, to obtain the heart rate load index HRint, the sleep quality index SPint, the emotion stress index PSint, and the exercise recovery index Stint, wherein the normalization includes using min-max normalization;

[0023] The heart rate load index HRint is Obtain calculation formula;

[0024] The sleep quality index SPint is Obtain calculation formula;

[0025] The emotional stress index PSint is Obtain calculation formula;

[0026] The exercise recovery index Stint is Obtain calculation formula;

[0027] S22. Integrate the obtained heart rate load index HRint, sleep quality index SPint, emotional stress index PSint and exercise recovery index Stint to form a feature data set F = {HRint, SPint, PSint, Stint}.

[0028] Preferably, said S3 includes S31 and S32;

[0029] S31, by establishing a time series analysis algorithm, substituting the obtained feature data set F into calculation, obtaining the heart rate load index difference △HRint, the sleep quality index difference △SPint, the emotional stress index difference △PSint and the exercise recovery index difference △Stint;

[0030] The heart rate load index difference △HRint is obtained by the following calculation formula:

[0031]

[0032] Wherein, HRint(t) and HRint(t-1) represent the heart rate load index HRint at time t and time t-1 respectively, and log represents the natural logarithm function;

[0033] The sleep quality index difference ΔSPint is obtained by the following calculation formula:

[0034]

[0035] Wherein, SPint(t) and SPint(t-1) represent the sleep quality index SPint at time t and time t-1 respectively;

[0036] The emotional stress index difference △PSint is obtained by the following calculation formula:

[0037]

[0038] Where PSint(t) and PSint(t-1) represent the emotional stress index PSint at time t and time t-1, respectively;

[0039] The motion recovery index difference ΔStint is obtained by the following calculation formula:

[0040]

[0041] Wherein, Stint(t) and Stint(t-1) represent the motion recovery index Stint at time t and time t-1, respectively.

[0042] Preferably, S32, performing fitting processing according to the obtained heart rate load index difference △HRint, sleep quality index difference △SPint, emotional stress index difference △PSint and exercise recovery index difference △Stint, to obtain an adjustment index C reflecting the fluctuation of the health status of the parturient;

[0043] The adjustment index C is obtained by the following calculation formula:

[0044]

[0045] Wherein, C(N) represents the adjustment index C within the fixed period N, N represents the fixed period, specifically represents the total number of collected data samples obtained within the fixed period, and t represents time, specifically represents the data samples collected at time t within the fixed period.

[0046] Preferably, the maternal health regulation generation suggestion result is obtained by the following matching method:

[0047] When the adjustment index C is less than the health fluctuation assessment threshold TZ, the maternal health regulation generation recommendation result is a qualified result;

[0048] When the adjustment index C ≥ the health fluctuation assessment threshold TZ, the result of obtaining the maternal health regulation generation recommendation is an unqualified result;

[0049] When the adjustment index C ≥ twice the health fluctuation assessment threshold TZ, the result of obtaining the maternal health regulation generation recommendation is an abnormal result;

[0050] The recommended nursing plan is obtained by the following generation method:

[0051] When the maternal health regulation generates a recommendation result that the result is unqualified, a nursing plan with recommendations for increasing psychological counseling, adjusting diet, and improving sleep is generated;

[0052] When the maternal health regulation generates abnormal recommendations, a doctor's intervention examination and nursing plan are generated.

[0053] Preferably, said S5 includes S51 and S52;

[0054] S51. Generate recommendations based on maternal health regulation to trigger the effectiveness monitoring mechanism of the recommended nursing plan;

[0055] When the maternal health regulation generates a recommendation that is unqualified, the mechanism of doubling the frequency of monitoring the effectiveness of the recommended nursing plan is triggered. Specifically, the sample data volume of time t within the fixed period N is multiplied by 2, and the total number of collected data samples within the fixed period N is adjusted, and a new fixed period XN is marked;

[0056] When the maternal health regulation generates a recommendation that is unqualified, the mechanism of quadrupling the frequency of monitoring the effectiveness of the recommended nursing plan is triggered. Specifically, the sample data volume of time t within the fixed period N is multiplied by 4, and the total number of collected data samples within the fixed period N is adjusted, and a new fixed period XN is marked;

[0057] S52, calculating and adjusting the change trend of the index C according to the acquisition effect monitoring mechanism to obtain the effect execution index R;

[0058] The change trend acquisition effect execution index R is obtained by the following calculation formula:

[0059]

[0060] Wherein, XN represents the new fixed period, specifically represents the total number of new data samples after adjusting the sample data amount within the fixed period N.

[0061] Preferably, the nursing effectiveness evaluation strategy is established by the following matching method:

[0062] When the effect execution index R ≥ the recommended nursing execution effect threshold ZZ, the invalid evaluation result of the nursing recommendation plan is obtained, and the recommended nursing plan is adjusted at the same time, and a record of invalid recommended nursing plans is generated to notify relevant staff and preset emergency contacts;

[0063] When the effect execution index R is less than the recommended nursing execution effect threshold ZZ, the effective evaluation result of the nursing suggestion plan execution is obtained, and the recommended nursing plan is continued to be executed to generate a valid recommended nursing plan record.

[0064] The Internet-based obstetrics and gynecology information processing system includes a physiological data acquisition module, a data processing module, a fluctuation analysis module, a suggestion generation module, a trend analysis module, and an iterative optimization module;

[0065] The physiological data collection module collects the physiological parameters of the parturient through smart watches, mobile phones and other wearable devices to form a collection data set D, and uploads it to the cloud server through the Internet;

[0066] The data processing module extracts and processes the acquired data set D and integrates it into a feature data set F;

[0067] The fluctuation analysis module establishes a time series analysis algorithm, substitutes the acquired feature data set F into calculation, and obtains an adjustment index C reflecting the fluctuation of the maternal health status;

[0068] The suggestion generation module matches the obtained adjustment index C with the preset health fluctuation assessment threshold TZ, obtains the maternal health regulation and generation suggestion result, and generates a suggested nursing plan according to the maternal health regulation and generation suggestion result;

[0069] The trend analysis module generates a suggestion result based on maternal health regulation to trigger the effect monitoring mechanism of the suggested nursing plan, and obtains the effect execution index R by calculating the change trend of the adjustment index C;

[0070] The iterative optimization module matches the effect execution index R with the preset recommended nursing execution effect threshold ZZ, obtains a nursing effectiveness evaluation strategy plan, and notifies and prompts relevant personnel according to the nursing effectiveness evaluation strategy plan.

[0071] The present invention provides an Internet-based obstetrics and gynecology information processing method and system, which has the following beneficial effects:

[0072] (1) By extracting and processing the data set D, the feature data set F is integrated to make the nursing plan more personalized and dynamic. By establishing a time series analysis algorithm, the system can calculate the adjustment index C that reflects the fluctuation of the maternal health status, and match it with the health fluctuation assessment threshold TZ to generate nursing regulation suggestions and nursing plans that are consistent with the maternal health status, thereby avoiding the disadvantage that the nursing plan cannot follow up the changes in maternal health in real time. In addition, by introducing an effect monitoring mechanism, the effect execution index R is generated by calculating the change trend of the adjustment index C, and the execution effect of the nursing plan is continuously evaluated. By matching it with the recommended nursing execution effect threshold ZZ, an effectiveness evaluation strategy is generated to ensure that the effect of the nursing plan always meets the health needs of the mother. Compared with the traditional static nursing model, this dynamic adjustment mechanism can adjust the nursing plan according to real-time health data, respond to factors such as heart rate fluctuations and pressure fluctuations in a timely manner, and ensure that the nursing plan matches the actual recovery status of the mother, thereby improving the recovery effect of the mother and reducing potential health risks.

[0073] (2) The collected data set D of the parturient is uploaded to the cloud server regularly. Thus, a more standardized heart rate load index HRint, sleep quality index SPint, emotional stress index PSint and exercise recovery index Stint are obtained. The normalization process enables the accurate comparison and analysis of these physiological parameters from different sources, which makes the adjustment of the nursing plan more objective and accurate. At the same time, by integrating these data to generate a feature data set F, the nursing plan can not only make decisions based on standardized data, but also better capture the dynamic health changes of the parturient.

[0074] (3) By establishing a time series analysis algorithm, subtle changes in the health status of the mother can be captured. Not only can the health fluctuation trend of the mother be reflected through the data differences at multiple time points, but also the adjustment index C reflecting the overall health status fluctuation can be generated by fitting these difference values. Covering the total number of data samples N within a fixed period, the system can comprehensively evaluate health status changes over a longer time frame. The accuracy of capturing health fluctuations is improved, and the recovery progress of the mother and the adaptability of the current care plan can be fully reflected through the adjustment index C, avoiding the situation where the care plan blindly follows short-term data changes, thereby providing a more stable and scientific basis for care adjustment for the mother over a long period of time.

[0075] (4) By accurately matching the adjustment index C with the health fluctuation assessment threshold TZ, the health status of the mother can be assessed in a timely manner and corresponding nursing recommendations can be generated. In particular, when the adjustment index C exceeds twice the health fluctuation assessment threshold TZ, the system will quickly generate a nursing recommendation plan for the doctor's intervention examination, thereby avoiding the risks caused by the failure of the nursing plan or delayed adjustment. In addition, dynamic adjustments are made through the effect monitoring mechanism. When the maternal health regulation generates a recommendation result that is unqualified or abnormal, the monitoring frequency is automatically doubled or quadrupled to ensure that changes in health status are captured in real time under higher-density data collection, and a new fixed cycle XN is generated to accurately evaluate the nursing effect. The responsiveness and execution effect of the nursing plan are significantly improved, and continuous monitoring of health fluctuations is maintained. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 This is a schematic diagram of the steps of the Internet-based obstetrics and gynecology information processing method of the present invention;

[0077] Figure 2 This is a schematic diagram of the block diagram of the Internet-based obstetrics and gynecology information processing system of the present invention. DETAILED DESCRIPTION

[0078] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0079] Example 1

[0080] The present invention provides an Internet-based obstetrics and gynecology information processing method, please refer to Figure 1 , including the following steps:

[0081] S1, collect physiological parameters of parturients through smart watches, mobile phones and other wearable devices, form a collection data set D, and upload it to the cloud server through the Internet;

[0082] S2, extracting and processing the acquired data set D, and integrating it into a feature data set F;

[0083] S3, by establishing a time series analysis algorithm, substituting the acquired feature data set F into the calculation, and obtaining an adjustment index C reflecting the fluctuation of the maternal health status;

[0084] S4, matching the obtained adjustment index C with the preset health fluctuation assessment threshold TZ, obtaining the maternal health regulation generation suggestion result, and generating a suggested nursing plan according to the maternal health regulation generation suggestion result;

[0085] S5. Generate recommendations based on maternal health regulation results to trigger the effect monitoring mechanism of the recommended nursing plan, and obtain the effect execution index R by calculating the change trend of the adjustment index C;

[0086] S6. By matching the effect execution index R with the preset recommended nursing execution effect threshold ZZ, a nursing effectiveness evaluation strategy is obtained, and relevant personnel are notified and prompted according to the nursing effectiveness evaluation strategy.

[0087] In this embodiment, by extracting and processing the data set D, the feature data set F is integrated to make the nursing plan more personalized and dynamic. By establishing a time series analysis algorithm, the system can calculate the adjustment index C that reflects the fluctuation of the health status of the parturient, and match it with the health fluctuation assessment threshold TZ to generate nursing regulation suggestions and nursing plans that are consistent with the health status of the parturient, thereby avoiding the disadvantage that the nursing plan cannot follow up the changes in the health of the parturient in real time. In addition, by introducing an effect monitoring mechanism, by calculating the change trend of the adjustment index C, the effect execution index R is generated, the execution effect of the nursing plan is continuously evaluated, and by matching with the recommended nursing execution effect threshold ZZ, an effectiveness evaluation strategy is generated to ensure that the effect of the nursing plan always meets the health needs of the parturient. Compared with the traditional static nursing model, the dynamic adjustment mechanism can adjust the nursing plan according to real-time health data, respond to factors such as heart rate fluctuations and pressure fluctuations in a timely manner, and ensure that the nursing plan matches the actual recovery state of the parturient, thereby improving the recovery effect of the parturient and reducing potential health risks.

[0088] Example 2

[0089] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: the S1 includes S11 and S12;

[0090] S11, collecting physiological parameters of the parturient in real time through smart watches, mobile phones and other wearable devices, including heart rate time series data HRp, sleep time series data SP, emotion time series data PS and exercise time series data St;

[0091] Among them, the heart rate time series data HRp includes the average heart rate HRm, the peak heart rate HRmax and the heart rate fluctuation amplitude HRv; the sleep time series data SP includes the sleep duration SPc, the deep sleep duration SPd, the light sleep duration SPl, the number of deep sleep times Dc and the number of light sleep times Qc; the emotion time series data PS includes the average pressure PSm, the peak pressure PSmax and the pressure fluctuation amplitude PSv; the exercise time series data St includes the total walking time Stc, the number of walking times Stn and the walking distance Std;

[0092] The heart rate time series data HRp is specifically HRp={HRm, HRmax, HRv};

[0093] The sleep time series data SP is specifically SP={SPc, SPd, SP1, Dc, Qc};

[0094] The emotional time series data PS is specifically PS={PSm, PSmax, PSv};

[0095] The motion time series data St is specifically St={Stc, Stn, Std}.

[0096] S12, integrating the acquired heart rate time series data HRp, sleep time series data SP, emotion time series data PS and exercise time series data St to form a collection data set D, and connecting to the Internet after a fixed period N to upload the collection data set D to a cloud server;

[0097] The collected data set D is specifically D={HRp, SP, PS, St}.

[0098] The S2 includes S21 and S22;

[0099] S21, normalizing the acquired data set D including the heart rate time series data HRp, the sleep time series data SP, the emotion time series data PS, and the exercise time series data St, to obtain the heart rate load index HRint, the sleep quality index SPint, the emotion stress index PSint, and the exercise recovery index Stint, wherein the normalization includes using min-max normalization;

[0100] The heart rate load index HRint is Obtain calculation formula;

[0101] The sleep quality index SPint is Obtain calculation formula;

[0102] The emotional stress index PSint is Obtain calculation formula;

[0103] The exercise recovery index Stint is Obtain calculation formula;

[0104] S22. Integrate the obtained heart rate load index HRint, sleep quality index SPint, emotional stress index PSint and exercise recovery index Stint to form a feature data set F = {HRint, SPint, PSint, Stint}.

[0105] In this embodiment, the heart rate time series data HRp, sleep time series data SP, emotional time series data PS and exercise time series data St of the parturient are collected and integrated into a collection data set D and then uploaded to the cloud server regularly. By performing min-max normalization processing on the collection data set D, the magnitude differences between different physiological parameters can be effectively eliminated, thereby obtaining a more standardized heart rate load index HRint, sleep quality index SPint, emotional stress index PSint and exercise recovery index Stint. The normalization process ensures that the physiological parameters from these different sources can be accurately compared and analyzed, which makes the adjustment of the nursing plan more objective and accurate. At the same time, by integrating these data to generate a feature data set F, the nursing plan can not only make decisions based on standardized data, but also better capture the dynamic health changes of the parturient.

[0106] Example 3

[0107] This embodiment is explained in Example 2. Please refer to Figure 1 , specifically: S3 includes S31 and S32;

[0108] S31, by establishing a time series analysis algorithm, substituting the obtained feature data set F into calculation, obtaining the heart rate load index difference △HRint, the sleep quality index difference △SPint, the emotional stress index difference △PSint and the exercise recovery index difference △Stint;

[0109] The heart rate load index difference △HRint is obtained by the following calculation formula:

[0110]

[0111] Wherein, HRint(t) and HRint(t-1) represent the heart rate load index HRint at time t and time t-1 respectively, and log represents the natural logarithm function;

[0112] The sleep quality index difference ΔSPint is obtained by the following calculation formula:

[0113]

[0114] Wherein, SPint(t) and SPint(t-1) represent the sleep quality index SPint at time t and time t-1 respectively;

[0115] The emotional stress index difference △PSint is obtained by the following calculation formula:

[0116]

[0117] Where PSint(t) and PSint(t-1) represent the emotional stress index PSint at time t and time t-1, respectively;

[0118] The motion recovery index difference ΔStint is obtained by the following calculation formula:

[0119]

[0120] Wherein, Stint(t) and Stint(t-1) represent the motion recovery index Stint at time t and time t-1, respectively.

[0121] S32, performing fitting processing according to the obtained heart rate load index difference △HRint, sleep quality index difference △SPint, emotional stress index difference △PSint and exercise recovery index difference △Stint, to obtain an adjustment index C reflecting the fluctuation of the health status of the parturient;

[0122] The adjustment index C is obtained by the following calculation formula:

[0123]

[0124] Wherein, C(N) represents the adjustment index C within the fixed period N, N represents the fixed period, specifically represents the total number of collected data samples obtained within the fixed period, and t represents time, specifically represents the data samples collected at time t within the fixed period.

[0125] In this embodiment, by establishing a time series analysis algorithm, the heart rate load index difference △HRint, the sleep quality index difference △SPint, the emotional stress index difference △PSint and the exercise recovery index difference △Stint are obtained, so as to capture the subtle changes in the health status of the parturient. Unlike the traditional static care plan, this system can not only reflect the health fluctuation trend of the parturient through the data differences at multiple time points, but also generate an adjustment index C reflecting the overall health status fluctuation by fitting these difference values. The calculation of the adjustment index C covers the total number of data samples N within a fixed period, and can comprehensively evaluate the changes in health status over a longer time range. The accuracy of capturing health fluctuations is improved, and the recovery progress of the parturient and the adaptability of the current care plan can be fully reflected by adjusting the index C, avoiding the situation where the care plan blindly follows the changes in short-term data, thereby providing a more stable and scientific basis for care adjustment for the parturient over a long period of time.

[0126] Example 4

[0127] This embodiment is explained in Example 3, please refer to Figure 1 Specifically: the maternal health regulation recommendation result is obtained by the following matching method:

[0128] When the adjustment index C is less than the health fluctuation assessment threshold TZ, the maternal health regulation generation recommendation result is a qualified result;

[0129] When the adjustment index C ≥ the health fluctuation assessment threshold TZ, the result of obtaining the maternal health regulation generation recommendation is an unqualified result;

[0130] When the adjustment index C ≥ twice the health fluctuation assessment threshold TZ, the result of obtaining the maternal health regulation generation recommendation is an abnormal result;

[0131] The recommended nursing plan is obtained by the following generation method:

[0132] When the maternal health regulation generates a recommendation result that the result is unqualified, a nursing plan with recommendations for increasing psychological counseling, adjusting diet, and improving sleep is generated;

[0133] When the maternal health regulation generates abnormal recommendations, a doctor's intervention examination and nursing plan are generated.

[0134] The S5 includes S51 and S52;

[0135] S51. Generate recommendations based on maternal health regulation to trigger the effectiveness monitoring mechanism of the recommended nursing plan;

[0136] When the maternal health regulation generates a recommendation that is unqualified, the mechanism of doubling the frequency of monitoring the effectiveness of the recommended nursing plan is triggered. Specifically, the sample data volume of time t within the fixed period N is multiplied by 2, and the total number of collected data samples within the fixed period N is adjusted, and a new fixed period XN is marked;

[0137] When the maternal health regulation generates a recommendation that is unqualified, the mechanism of quadrupling the frequency of monitoring the effectiveness of the recommended nursing plan is triggered. Specifically, the sample data volume of time t within the fixed period N is multiplied by 4, and the total number of collected data samples within the fixed period N is adjusted, and a new fixed period XN is marked;

[0138] S52, calculating and adjusting the change trend of the index C according to the acquisition effect monitoring mechanism to obtain the effect execution index R;

[0139] The change trend acquisition effect execution index R is obtained by the following calculation formula:

[0140]

[0141] Wherein, XN represents the new fixed period, specifically represents the total number of new data samples after adjusting the sample data amount within the fixed period N.

[0142] The strategy for establishing nursing effectiveness evaluation is obtained by the following matching method:

[0143] When the effect execution index R ≥ the recommended nursing execution effect threshold ZZ, the invalid evaluation result of the nursing recommendation plan is obtained, and the recommended nursing plan is adjusted at the same time, and a record of invalid recommended nursing plans is generated to notify relevant staff and preset emergency contacts;

[0144] When the effect execution index R is less than the recommended nursing execution effect threshold ZZ, the effective evaluation result of the nursing suggestion plan execution is obtained, and the recommended nursing plan is continued to be executed to generate a valid recommended nursing plan record.

[0145] In this embodiment, by accurately matching the adjustment index C with the health fluctuation assessment threshold TZ, the health status of the parturient can be evaluated in time and the corresponding nursing plan recommendations can be generated. In particular, when the adjustment index C exceeds twice the health fluctuation assessment threshold TZ, the system will quickly generate a nursing recommendation plan for the doctor's intervention examination, thereby avoiding the risk caused by the failure of the nursing plan or delayed adjustment. In addition, dynamic adjustment is performed through the effect monitoring mechanism. When the result of the recommendation generated by the maternal health regulation is unqualified or abnormal, the monitoring frequency is automatically doubled or quadrupled to ensure that the changes in health status are captured in real time under higher density data collection, and a new fixed cycle XN is generated to accurately evaluate the nursing effect. By calculating the effect execution index R, the effectiveness of the nursing plan can be judged according to its execution effect. If the effect execution index R does not reach the recommended nursing execution effect threshold ZZ, an invalid recommended nursing plan record will be automatically generated, and the relevant staff and emergency contacts will be notified to ensure that the parturient receives more rapid nursing adjustments and necessary medical interventions. This continuous evaluation and monitoring mechanism significantly improves the responsiveness and execution effect of the nursing plan and maintains continuous monitoring of health fluctuations.

[0146] Example 5

[0147] For Internet-based obstetrics and gynecology information processing system, please refer to Figure 2 ,Specifically: it includes physiological data acquisition module, data processing module, fluctuation analysis module, ,suggestion generation module, trend analysis module and iterative optimization module;

[0148] The physiological data collection module collects the physiological parameters of the parturient through smart watches, mobile phones and other wearable devices to form a collection data set D, and uploads it to the cloud server through the Internet;

[0149] The data processing module extracts and processes the acquired data set D and integrates it into a feature data set F;

[0150] The fluctuation analysis module establishes a time series analysis algorithm, substitutes the acquired feature data set F into calculation, and obtains an adjustment index C reflecting the fluctuation of the maternal health status;

[0151] The suggestion generation module matches the obtained adjustment index C with the preset health fluctuation assessment threshold TZ, obtains the maternal health regulation and generation suggestion result, and generates a suggested nursing plan according to the maternal health regulation and generation suggestion result;

[0152] The trend analysis module generates a suggestion result based on maternal health regulation to trigger the effect monitoring mechanism of the suggested nursing plan, and obtains the effect execution index R by calculating the change trend of the adjustment index C;

[0153] The iterative optimization module matches the effect execution index R with the preset recommended nursing execution effect threshold ZZ, obtains a nursing effectiveness evaluation strategy plan, and notifies and prompts relevant personnel according to the nursing effectiveness evaluation strategy plan.

[0154] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An Internet-based obstetrics and gynecology information processing method and system, characterized by: The following steps are involved: S1, collect physiological parameters of parturients through smart watches, mobile phones and other wearable devices, form a collection data set D, and upload it to the cloud server through the Internet; S2, extracting and processing the acquired data set D, and integrating it into a feature data set F; S3, by establishing a time series analysis algorithm, substituting the acquired feature data set F into the calculation, and obtaining an adjustment index C reflecting the fluctuation of the maternal health status; S4, matching the obtained adjustment index C with the preset health fluctuation assessment threshold TZ, obtaining the maternal health regulation generation suggestion result, and generating a suggested nursing plan according to the maternal health regulation generation suggestion result; S5. Generate recommendations based on maternal health regulation results to trigger the effect monitoring mechanism of the recommended nursing plan, and obtain the effect execution index R by calculating the change trend of the adjustment index C; S6. By matching the effect execution index R with the preset recommended nursing execution effect threshold ZZ, a nursing effectiveness evaluation strategy is obtained, and relevant personnel are notified and prompted according to the nursing effectiveness evaluation strategy.

2. The Internet-based obstetrics and gynecology information processing method and system according to claim 1, characterized in that: Said S1 includes S11 and S12; S11, collecting physiological parameters of the parturient in real time through smart watches, mobile phones and other wearable devices, including heart rate time series data HRp, sleep time series data SP, emotion time series data PS and exercise time series data St; Among them, the heart rate time series data HRp includes the average heart rate HRm, the peak heart rate HRmax and the heart rate fluctuation amplitude HRv; the sleep time series data SP includes the sleep duration SPc, the deep sleep duration SPd, the light sleep duration SPl, the number of deep sleep times Dc and the number of light sleep times Qc; the emotion time series data PS includes the average pressure PSm, the peak pressure PSmax and the pressure fluctuation amplitude PSv; the exercise time series data St includes the total walking time Stc, the number of walking times Stn and the walking distance Std; The heart rate time series data HRp is specifically HRp={HRm, HRmax, HRv}; The sleep time series data SP is specifically SP={SPc, SPd, SP1, Dc, Qc}; The emotional time series data PS is specifically PS={PSm, PSmax, PSv}; The motion time series data St is specifically St={Stc, Stn, Std}.

3. The Internet-based obstetrics and gynecology information processing method and system according to claim 2, characterized in that: S12, integrating the acquired heart rate time series data HRp, sleep time series data SP, emotion time series data PS and exercise time series data St to form a collection data set D, and connecting to the Internet after a fixed period N to upload the collection data set D to a cloud server; The collected data set D is specifically D={HRp, SP, PS, St}.

4. The Internet-based obstetrics and gynecology information processing method and system according to claim 3, characterized in that: The S2 includes S21 and S22; S21, normalizing the acquired data set D including the heart rate time series data HRp, the sleep time series data SP, the emotion time series data PS, and the exercise time series data St, to obtain the heart rate load index HRint, the sleep quality index SPint, the emotion stress index PSint, and the exercise recovery index Stint, wherein the normalization includes using min-max normalization; The heart rate load index HRint is Obtain calculation formula; The sleep quality index SPint is Obtain calculation formula; The emotional stress index PSint is Obtain calculation formula; The exercise recovery index Stint is Obtain calculation formula; S22, integrating the heart rate load index HRint, sleep quality index SPint, emotional stress index PSint and exercise recovery index Stint obtained by processing, The feature data set F = {HRint, SPint, PSint, Stint}.

5. The Internet-based obstetrics and gynecology information processing method and system according to claim 4, characterized in that: The S3 includes S31 and S32; S31, by establishing a time series analysis algorithm, substituting the obtained feature data set F into calculation, obtaining the heart rate load index difference △HRint, the sleep quality index difference △SPint, the emotional stress index difference △PSint and the exercise recovery index difference △Stint; The heart rate load index difference △HRint is obtained by the following calculation formula: Wherein, HRint(t) and HRint(t-1) represent the heart rate load index HRint at time t and time t-1 respectively, and log represents the natural logarithm function; The sleep quality index difference ΔSPint is obtained by the following calculation formula: Wherein, SPint(t) and SPint(t-1) represent the sleep quality index SPint at time t and time t-1 respectively; The emotional stress index difference △PSint is obtained by the following calculation formula: Where PSint(t) and PSint(t-1) represent the emotional stress index PSint at time t and time t-1, respectively; The motion recovery index difference ΔStint is obtained by the following calculation formula: Wherein, Stint(t) and Stint(t-1) represent the motion recovery index Stint at time t and time t-1, respectively.

6. The Internet-based obstetrics and gynecology information processing method and system according to claim 5, characterized in that: S32, performing fitting processing according to the obtained heart rate load index difference △HRint, sleep quality index difference △SPint, emotional stress index difference △PSint and exercise recovery index difference △Stint, to obtain an adjustment index C reflecting the fluctuation of the health status of the parturient; The adjustment index C is obtained by the following calculation formula: Wherein, C(N) represents the adjustment index C within the fixed period N, N represents the fixed period, specifically represents the total number of collected data samples obtained within the fixed period, and t represents time, specifically represents the data samples collected at time t within the fixed period.

7. The Internet-based obstetrics and gynecology information processing method and system according to claim 6, characterized in that: The maternal health regulation generation suggestion result is obtained by the following matching method: When the adjustment index C is less than the health fluctuation assessment threshold TZ, the maternal health regulation generation recommendation result is a qualified result; When the adjustment index C ≥ the health fluctuation assessment threshold TZ, the result of obtaining the maternal health regulation generation recommendation is an unqualified result; When the adjustment index C ≥ twice the health fluctuation assessment threshold TZ, the result of obtaining the maternal health regulation generation recommendation is an abnormal result; The recommended nursing plan is obtained by the following generation method: When the maternal health regulation generates a recommendation result that the result is unqualified, a nursing plan with recommendations for increasing psychological counseling, adjusting diet, and improving sleep is generated; When the maternal health regulation generates abnormal recommendations, a doctor's intervention examination and nursing plan are generated.

8. The Internet-based obstetrics and gynecology information processing method and system according to claim 1, characterized in that: The S5 includes S51 and S52; S51. Generate recommendations based on maternal health regulation to trigger the effectiveness monitoring mechanism of the recommended nursing plan; When the maternal health regulation generates a recommendation that is unqualified, the mechanism of doubling the frequency of monitoring the effectiveness of the recommended nursing plan is triggered. Specifically, the sample data volume of time t within the fixed period N is multiplied by 2, and the total number of collected data samples within the fixed period N is adjusted, and a new fixed period XN is marked; When the maternal health regulation generates a recommendation that is unqualified, the mechanism of quadrupling the frequency of monitoring the effectiveness of the recommended nursing plan is triggered. Specifically, the sample data volume of time t within the fixed period N is multiplied by 4, and the total number of collected data samples within the fixed period N is adjusted, and a new fixed period XN is marked; S52, calculating and adjusting the change trend of the index C according to the acquisition effect monitoring mechanism to obtain the effect execution index R; The change trend acquisition effect execution index R is obtained by the following calculation formula: Wherein, XN represents the new fixed period, specifically represents the total number of new data samples after adjusting the sample data amount within the fixed period N.

9. The Internet-based obstetrics and gynecology information processing method and system according to claim 7, characterized in that: The strategy for establishing nursing effectiveness evaluation is obtained by the following matching method: When the effect execution index R ≥ the recommended nursing execution effect threshold ZZ, the invalid evaluation result of the nursing recommendation plan is obtained, and the recommended nursing plan is adjusted at the same time, and a record of invalid recommended nursing plans is generated to notify relevant staff and preset emergency contacts; When the effect execution index R is less than the recommended nursing execution effect threshold ZZ, the effective evaluation result of the nursing suggestion plan execution is obtained, and the recommended nursing plan is continued to be executed to generate a valid recommended nursing plan record.

10. An Internet-based obstetrics and gynecology information processing method and system, applied to the Internet-based obstetrics and gynecology information processing method and system as claimed in any one of claims 1 to 9, characterized in that: It includes physiological data acquisition module, data processing module, fluctuation analysis module, suggestion generation module, trend analysis module and iterative optimization module; The physiological data collection module collects the physiological parameters of the parturient through smart watches, mobile phones and other wearable devices to form a collection data set D, and uploads it to the cloud server through the Internet; The data processing module extracts and processes the acquired data set D and integrates it into a feature data set F; The fluctuation analysis module establishes a time series analysis algorithm, substitutes the acquired feature data set F into calculation, and obtains an adjustment index C reflecting the fluctuation of the maternal health status; The suggestion generation module matches the obtained adjustment index C with the preset health fluctuation assessment threshold TZ, obtains the maternal health regulation and generation suggestion result, and generates a suggested nursing plan according to the maternal health regulation and generation suggestion result; The trend analysis module generates a suggestion result based on maternal health regulation to trigger the effect monitoring mechanism of the suggested nursing plan, and obtains the effect execution index R by calculating the change trend of the adjustment index C; The iterative optimization module matches the effect execution index R with the preset recommended nursing execution effect threshold ZZ, obtains a nursing effectiveness evaluation strategy plan, and notifies and prompts relevant personnel according to the nursing effectiveness evaluation strategy plan.

Images