Obstetrical real-time nursing optimization method and system based on big data

Abstract

The invention relates to an obstetrical real-time nursing optimization method and system based on big data, and relates to the field of medical nursing, and the method comprises the steps: taking a static index of an obstetrical nursing object as a constant, taking a dynamic index as a variable, and retrieving a plurality of abnormal nursing logs; based on the abnormal dynamic index set, performing statistics on a central dynamic index of which the occurrence number of the dynamic indexes in the abnormal nursing logs is greater than or equal to a threshold number and an edge dynamic index of which the occurrence number is smaller than the threshold number; counting a deviation vector of the center dynamic index monitoring value and a deviation index number proportion of the edge dynamic index monitoring value; predicting an abnormal nursing probability which simultaneously meets the static index, the deviation vector and the deviation index number proportion; and when the probability is greater than or equal to a probability threshold value, reminding the nursing end to perform nursing optimization, thereby solving the technical problem that the accuracy and efficiency of real-time nursing are insufficient because individual differences between pregnant women are neglected during real-time nursing in the obstetrical department.

Description

Technical Field

[0001] The present invention relates to the field of medical care, and in particular to a real-time obstetric care optimization method and system based on big data. Background Art

[0002] In the traditional obstetric real-time care model, big data statistics are widely used to predict and judge the abnormal care risks of pregnant women in different states. However, this traditional data statistical method has a significant problem of insufficient individualization. It usually directly collects the real-time status of all indicators of pregnant women and evaluates them based on the probability of abnormalities in these states in historical data. However, this method ignores the differences between individual pregnant women. Different pregnant women have different tolerance levels for different physiological indicators. Specifically, the physiological state of pregnant women is affected by many factors, including age, weight, pregnancy stage, health status, etc. These factors lead to different sensitivity and reaction levels of pregnant women to different indicators. The traditional data statistical method does not fully take these individual differences into account, but uses a unified standard and threshold to evaluate all pregnant women, which is obviously not accurate and individualized. In addition, the traditional data statistical method also has certain limitations in judging abnormal situations. It usually only focuses on whether the indicators are beyond the normal range and lacks in-depth analysis of the indicator change trend and abnormal situations. This simple binary classification judgment method is prone to false positives and false negatives, affecting the accuracy and efficiency of obstetric real-time care. Summary of the invention

[0003] The present invention aims to solve the technical problem that the prior art ignores the individual differences between pregnant women during real-time obstetric care, resulting in insufficient accuracy and efficiency of real-time care, and provides a big data-based obstetric real-time care optimization method and system to solve the problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: In the first aspect, the present invention provides a real-time obstetric care optimization method based on big data, comprising: taking the static indicators of obstetric care objects as constants and the dynamic indicators as variables, retrieving multiple abnormal care logs, wherein any abnormal care log includes a set of abnormal dynamic indicators; based on the set of abnormal dynamic indicators, counting the central dynamic indicators whose number of log entries in the multiple abnormal care logs is greater than or equal to a threshold of the number of log entries, and the edge dynamic indicators whose number of log entries is less than the threshold of the number of log entries; counting the deviation vector of the central dynamic indicator monitoring value of the obstetric care object, and the proportion of the number of deviation indicators of the edge dynamic indicator monitoring value; predicting the probability of abnormal care that simultaneously satisfies the static indicators, the deviation vector and the proportion of the number of deviation indicators; when the probability of abnormal care is greater than or equal to the abnormal probability threshold, reminding the nursing end to perform care optimization.

[0005] In a second aspect, the present invention provides a real-time obstetric care optimization system based on big data, comprising: an information retrieval module, used to retrieve multiple abnormal care logs using static indicators of obstetric care objects as constants and dynamic indicators as variables, wherein any abnormal care log includes a set of abnormal dynamic indicators; a statistical screening module, used to count the central dynamic indicators whose number of log entries is greater than or equal to a threshold of the number of log entries, and the edge dynamic indicators whose number of log entries is less than the threshold of the number of log entries, based on the set of abnormal dynamic indicators; a deviation statistics module, used to count the deviation vector of the central dynamic indicator monitoring value of the obstetric care object, and the proportion of the number of deviation indicators of the edge dynamic indicator monitoring value; an abnormal prediction module, used to predict the probability of abnormal care that simultaneously satisfies the static indicators, the deviation vector and the proportion of the number of deviation indicators; a nursing optimization module, used to remind the nursing end to perform nursing optimization when the probability of abnormal care is greater than or equal to the abnormal probability threshold.

[0006] The beneficial effect of the present invention is that by distinguishing the static indicators and dynamic indicators of obstetric care objects, and based on the statistical analysis of the central dynamic indicators and the marginal dynamic indicators of the abnormal care log, as well as their deviations, the probability of abnormal care can be predicted more accurately, so as to timely remind the nursing end to optimize care when necessary, thereby effectively improving the pertinence and efficiency of real-time obstetric care. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 A flowchart of a real-time obstetric care optimization method based on big data provided by the present invention.

[0008] Figure 2 A structural schematic diagram of a big data-based obstetric real-time nursing optimization system provided by the present invention.

[0009] Explanation of the reference numerals: information retrieval module 11 , statistical screening module 12 , deviation statistics module 13 , abnormality prediction module 14 , nursing optimization module 15 . DETAILED DESCRIPTION

[0010] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0011] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0012] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0013] Embodiment 1:

[0014] like Figure 1 As shown, an embodiment of the present invention provides a real-time obstetric nursing optimization method based on big data, which is characterized by comprising: S10: Taking the static index of the obstetric care object as a constant and the dynamic index as a variable, a plurality of abnormal care logs are retrieved, wherein any abnormal care log includes an abnormal dynamic index set.

[0015] S20: Based on the abnormal dynamic indicator set, statistically analyze dynamic indicators of the central dynamic indicator whose number of log entries in the multiple abnormal nursing logs is greater than or equal to the log entry threshold, and the edge dynamic indicator whose number of log entries is less than the log entry threshold.

[0016] S30: Count the deviation vectors of the central dynamic indicator monitoring values ​​of obstetric care objects, and the proportion of the number of deviation indicators of the marginal dynamic indicator monitoring values.

[0017] S40: Predicting the probability of abnormal care that satisfies the static index, the deviation vector, and the ratio of the number of deviation indexes at the same time.

[0018] S50: When the abnormal nursing probability is greater than or equal to the abnormal probability threshold, the nursing end is reminded to perform nursing optimization.

[0019] For example, in obstetric nursing work, the health status of the nursing object is usually monitored and evaluated based on its specific indicators. These indicators can be divided into two categories: static indicators and dynamic indicators. Among them, static indicators refer to those indicators that are relatively stable in the short term and not prone to significant changes. These indicators provide a basic health portrait for the nursing object and help to initially understand its overall condition. Static indicators usually include age range, physical condition, pregnancy status, emotional state number, and psychological tolerance rating. The pregnancy status includes gestational age, number of fetuses, fetal position, and placental position. Dynamic indicators refer to those indicators that change over time, environment, or treatment intervention. These indicators are important bases for monitoring changes in maternal health status, such as vital signs (including body temperature, pulse, respiration, blood pressure), postpartum hemorrhage, lochia, pain level, environmental status, etc. In obstetric nursing practice, the static and dynamic indicators of the parturient are usually recorded regularly and nursing logs are generated. When dynamic indicators are abnormal, these logs will become an important basis for identifying and dealing with potential problems. Through the database or electronic medical record system, a specific group of parturients can be screened out according to static indicators (such as age, pregnancy status, etc.), and then further search for abnormal values ​​in their dynamic indicators. For any abnormal nursing log, all abnormal dynamic indicators are sorted out to form a set, namely the abnormal dynamic indicator set, which can quickly locate the problem and formulate a corresponding nursing plan. For example, if a parturient's static indicators show that she is an elderly parturient with multiple pregnancies, and her dynamic indicators show abnormal conditions such as increased body temperature, accelerated pulse, and decreased blood pressure, then these abnormal dynamic indicators will indicate that the parturient may have potential risks such as infection and heart failure, and further evaluation and intervention are needed immediately. In summary, through the classification and monitoring of static and dynamic indicators, the health status of obstetric care objects can be understood more comprehensively and accurately, and potential problems can be discovered and dealt with in a timely manner, thereby ensuring the safety of mothers and babies.

[0020] Furthermore, the abnormal dynamic indicators are deeply counted and analyzed to determine which indicators are central dynamic indicators with frequent abnormalities and which are marginal dynamic indicators with occasional abnormalities and relatively small impacts. Before starting the statistics, a log number threshold needs to be set. This threshold is determined according to the research purpose, sample size, and the prevalence of abnormalities. It is used to distinguish central dynamic indicators (frequent abnormalities) from marginal dynamic indicators (occasionally abnormalities). For each abnormal dynamic indicator in an abnormal nursing log, statistics will be performed in the entire data set to record the number of times each indicator appears in all abnormal nursing logs. This step is to understand the frequency of occurrence of each abnormal dynamic indicator. Afterwards, the dynamic indicators are divided into two categories according to the statistical results, namely central dynamic indicators and marginal dynamic indicators. The number of occurrences of central dynamic indicators in multiple abnormal nursing logs is greater than or equal to the previously set log number threshold. They indicate that the abnormalities of these indicators in a specific group are relatively common and may be key factors leading to adverse pregnancy outcomes or requiring special attention. The number of occurrences of marginal dynamic indicators in abnormal nursing logs is less than the log number threshold. They may only be abnormal in individual cases, or the association between their abnormalities and adverse pregnancy outcomes is weak. In summary, through the statistics and analysis of abnormal dynamic indicator sets, we can have a deeper understanding of the health status of obstetric care recipients and provide strong support for the formulation of personalized care plans and clinical decisions.

[0021] In order to more carefully assess the health status of the nursing object, it is necessary to pay attention not only to the frequent abnormalities of dynamic indicators (central dynamic indicators), but also to the degree to which the monitoring values ​​of these indicators deviate from the normal range, as well as marginal dynamic indicators that occasionally appear abnormal but may be equally important. First, a normal range needs to be set for each central dynamic indicator (usually based on clinical guidelines, historical data or expert consensus). The deviation standard can be the degree to which the monitoring value exceeds the normal range, such as standard deviation, percentage, etc. For each abnormal nursing log containing a central dynamic indicator, the degree of deviation of the monitoring value of the indicator relative to the normal range is calculated. This is usually a vector that contains the direction of the deviation (higher or lower than the normal range) and the magnitude (specific value of the deviation). Subsequently, the deviation vector of each central dynamic indicator is recorded and summarized and analyzed as needed. For example, statistics such as the average deviation degree and the maximum deviation degree can be calculated to understand the overall deviation trend of these indicators under abnormal conditions. For marginal dynamic indicators, check and record which indicators have monitoring values ​​that deviate from the normal range. The deviation here can be any form of abnormality, such as higher, lower or not within a specific interval. Summarize the deviation of marginal dynamic indicators in all abnormal nursing logs, and calculate the proportion of the number of deviating indicators to the total number of all marginal dynamic indicators. This ratio reflects the overall degree of deviation of marginal dynamic indicators under abnormal conditions. In summary, by analyzing the deviation vectors of central dynamic indicators, we can understand the general trend of these indicators deviating from the normal range under abnormal conditions, which is crucial for formulating targeted nursing plans and clinical interventions. Although the number of deviation indicators of marginal dynamic indicators accounts for a low proportion, it may reveal some uncommon abnormalities or potential risks. These indicators also need attention because they may indicate specific health problems or complications. Combining the deviation vectors of central dynamic indicators and the number of deviation indicators of marginal dynamic indicators can obtain a more comprehensive assessment of the health status of obstetric care recipients, which helps to formulate personalized care plans, optimize clinical decisions, and ultimately improve care quality and patient satisfaction.

[0022] After that, static indicators, deviation vectors, and the proportion of deviation indicators are collected, and advanced algorithms or models (such as machine learning models) are used to predict the probability of abnormal nursing events for patients. This probability value reflects the possibility of poor nursing outcomes for patients under the current nursing status. An abnormal probability threshold is preset to determine whether the patient's nursing status needs to be optimized. If the predicted abnormal nursing probability is greater than or equal to this threshold, the system will trigger the reminder function and send an alert to the nursing end. After receiving the reminder, the nursing end can immediately view the patient's detailed information and adjust the nursing plan or take other optimization measures as needed. In summary, the entire process comprehensively evaluates static indicators, deviation vectors, and the proportion of deviation indicators, uses algorithms to predict the probability of abnormal nursing, and reminds the nursing end to optimize when necessary, thereby achieving real-time monitoring and dynamic adjustment of the patient's nursing status, which helps to improve the quality of nursing and ensure the safety of patients.

[0023] In a preferred embodiment, based on the abnormal dynamic indicator set, the dynamic indicators are statistically analyzed as the central dynamic indicators of the plurality of abnormal nursing logs where the number of log entries is greater than or equal to the log entry threshold, and the edge dynamic indicators where the number of log entries is less than the log entry threshold, including: Extract the first abnormal dynamic indicator set of the first abnormal nursing log of the multiple abnormal nursing logs, wherein the first abnormal dynamic indicator set is counted in a preset length time zone before the abnormality of the nursing object occurs; count the deviation frequency of the first abnormal dynamic indicator of the first abnormal dynamic indicator of the first abnormal dynamic indicator set in the preset length time zone; when the deviation frequency of the first abnormal dynamic indicator is greater than or equal to the deviation frequency threshold, it is regarded as the number of logs appearing for the first abnormal dynamic indicator plus one; traverse the dynamic indicators, perform statistics based on the multiple abnormal nursing logs, and obtain the central dynamic indicator whose number of logs appearing is greater than or equal to the log number threshold, and the edge dynamic indicator whose number of logs appearing is less than the log number threshold.

[0024] Optionally, the first one is selected from multiple abnormal nursing logs for analysis, and this log records the changes in dynamic indicators of a nursing object within a preset length time zone (for example, the past 24 hours or 48 hours) before the abnormality occurs. All abnormal dynamic indicators in this time zone are extracted to form a first abnormal dynamic indicator set. Among them, the preset length time zone refers to the time range selected when analyzing the abnormal nursing log, which is used to observe the changes in dynamic indicators. The first abnormal dynamic indicator set refers to the set of all abnormal dynamic indicators extracted from the first abnormal nursing log within the preset length time zone. Subsequently, the deviation frequency of each indicator in the first abnormal dynamic indicator set within the preset length time zone is counted. The deviation frequency refers to the number of times a dynamic indicator deviates from the normal range (or threshold) within the preset time zone, which is used to measure the abnormal degree of the indicator. For each first abnormal dynamic indicator, its deviation frequency is compared with the preset deviation frequency threshold. If the deviation frequency of a certain indicator is greater than or equal to the threshold, it is considered that this indicator plays an important role in the abnormal nursing event, so the number of log entries where it appears is increased by one. This means that as long as the deviation frequency of this indicator in any abnormal nursing log reaches or exceeds the threshold, it is considered to have appeared once in the log. Finally, traverse all dynamic indicators and repeat the above steps (extract, count deviation frequency, judge and count) until all abnormal nursing logs are processed. In this process, the number of occurrences of each dynamic indicator in all logs is recorded. After the statistics are completed, the central dynamic indicators and edge dynamic indicators are identified according to the number of occurrences of the dynamic indicators. Specifically, indicators with a number of occurrences greater than or equal to the threshold of the number of logs are regarded as central dynamic indicators. They frequently appear in multiple abnormal nursing logs and are closely related to abnormal nursing events. Indicators with a number of occurrences less than the threshold of the number of logs are regarded as edge dynamic indicators, and their frequency of occurrence in abnormal nursing logs is relatively low. Through this process, dynamic indicators closely related to abnormal nursing events can be effectively extracted from a large number of abnormal nursing logs, providing strong data support for subsequent abnormal nursing probability prediction.

[0025] In a preferred embodiment, predicting the probability of abnormal nursing that satisfies the static index, the deviation vector, and the ratio of the number of deviation indexes simultaneously includes: According to the static indicators, a strict consistency constraint condition is constructed, and according to the deviation vector and the ratio of the deviation indicators, a fault-tolerant consistency constraint condition is constructed, wherein the strictly consistent representation state must be exactly the same, and the fault-tolerant consistency representation state deviation must be less than or equal to the deviation threshold; based on the strict consistency constraint condition and the fault-tolerant consistency constraint condition, the obstetric nursing record data stored on the blockchain is retrieved online; the abnormal nursing trigger frequency ratio of the obstetric nursing record data is counted and set as the abnormal nursing probability.

[0026] Specifically, strict consistency constraints are constructed based on static indicators. These static indicators are usually fixed and immutable, such as basic information such as the age, gender, and gestational period of the nursing object. Strict consistency constraints require that the state to be predicted must be exactly the same as the state described by these static indicators. Fault-tolerant consistency constraints are constructed based on the deviation vector and the proportion of the number of deviation indicators. The deviation vector reflects the direction and degree of deviation of the dynamic indicator relative to the normal range, while the proportion of the number of deviation indicators refers to the proportion of dynamic indicators that deviate from the normal range in all dynamic indicators. Fault-tolerant consistency constraints allow a certain deviation in the state, but the deviation must be less than or equal to the preset deviation threshold. This means that as long as the degree of deviation and the proportion of deviation of the dynamic indicator are within an acceptable range, we consider the state to be consistent. After the constraints are constructed, these conditions are used to retrieve the obstetric nursing record data stored on the blockchain. Blockchain technology ensures the authenticity and immutability of the data and ensures the accuracy of the data. Through retrieval, obstetric nursing record data matching the state to be predicted can be obtained. After obtaining the matching obstetric nursing record data, the triggering frequency of abnormal nursing events in these records is counted. Specifically, the ratio of the number of records that trigger abnormal nursing events to the total number of records is calculated. This ratio is the abnormal nursing trigger frequency ratio. Finally, the abnormal nursing trigger frequency ratio is set as the abnormal nursing probability. This probability value reflects the possibility of abnormal nursing events under given conditions. By comparing this probability value with the preset threshold, it can be determined whether preventive measures or further inspections are needed. In summary, by constructing strict consistency constraints and fault-tolerant consistency constraints, retrieving obstetric nursing record data stored on the blockchain online, and calculating the abnormal nursing trigger frequency ratio, the probability of abnormal nursing can be effectively predicted, providing strong support for obstetric nursing decision-making.

[0027] For a more intuitive explanation, the following example is given: Here, the static indicators are set as "age of pregnant woman = 30 years old" and "gestational period = 32 weeks". The strict consistency constraint requires that the age of the pregnant woman to be predicted must be 30 years old and the gestational period must be 32 weeks, and these two conditions must be met at the same time. Assume that there are 5 dynamic indicators (such as blood pressure, heart rate, blood sugar, urine protein, fetal heart rate), each of which has a normal range. The deviation vector refers to the degree of deviation of the actual monitoring values ​​of these indicators from the normal range, which can be expressed as a numerical value or percentage. Assume that the number of dynamic indicators that deviate from the normal range does not exceed 2 (that is, no more than 40% of the total number of indicators). The fault-tolerant consistency constraint allows the deviation of dynamic indicators to be within a certain range (such as ±10%), and the number of indicators that deviate from the normal range does not exceed 40%. After setting the requirements, search is performed. Assume that there is a blockchain database containing 1,000 obstetric care records, each of which contains the basic information of the pregnant woman, the dynamic indicator monitoring value, and whether an abnormal care event is triggered. Obstetric care records that meet these conditions are retrieved according to the strict consistency constraint and the fault-tolerant consistency constraint. Assume that 200 obstetric nursing records that meet the conditions are retrieved, and 30 of these 200 records trigger abnormal nursing events. Then the abnormal nursing trigger frequency ratio = the number of records that trigger abnormal nursing events / the total number of records = 30 / 200 = 15%. Finally, the abnormal nursing probability is set to 15% based on the calculation results. This means that under given conditions, there is a 15% probability that an abnormal nursing event will occur.

[0028] In a preferred embodiment, based on the strict consistency constraint and the fault-tolerant consistency constraint, online retrieval of obstetric nursing record data stored in blockchain includes: Based on the strict consistency constraint and the fault-tolerant consistency constraint, the first-level obstetric nursing record data stored on the blockchain is retrieved online; when the data volume of the first-level obstetric nursing record data is less than or equal to the data volume threshold, the first-level deviation vector and the first-level deviation indicator quantity ratio are calculated, wherein the data volume threshold is greater than or equal to 5000; according to the first-level deviation vector and the first-level deviation indicator quantity ratio, the fault-tolerant consistency constraint is updated to obtain the first-level fault-tolerant consistency constraint, and combined with the strict consistency constraint, the second-level obstetric nursing record data stored on the blockchain is retrieved online; until the data volume of the first-level obstetric nursing record data to the N-level obstetric nursing record data is greater than or equal to the data volume threshold, or N is equal to 5, the first-level obstetric nursing record data to the N-level obstetric nursing record data are added to the obstetric nursing record data, and N is an integer.

[0029] Furthermore, in the process of predicting the probability of abnormal care, based on the strict consistency constraint and the fault-tolerant consistency constraint, the obstetric nursing record data stored in the blockchain is retrieved online. In order to avoid inaccurate prediction results caused by insufficient data volume, a step-by-step retrieval strategy is adopted. First, according to the strict consistency constraint and the initially set fault-tolerant consistency constraint, the first-level obstetric nursing record data stored in the blockchain is retrieved online. These data are the records that best match the state to be predicted under the strict consistency and fault-tolerant consistency conditions. Next, it is determined whether the data volume of the retrieved first-level obstetric nursing record data is greater than or equal to the preset data volume threshold (for example, 5000). If the data volume is sufficient, these data are directly used as the final obstetric nursing record data for subsequent analysis. If the data volume of the first-level obstetric nursing record data is insufficient, the first-level deviation vector and the first-level deviation index quantity ratio are calculated. These two indicators reflect the degree of deviation between the retrieved data and the state to be predicted in the dynamic indicators. Then, the fault-tolerant consistency constraint is updated according to these deviation information to obtain the first-level fault-tolerant consistency constraint to expand the search scope. Subsequently, combined with the updated strict consistency constraints and the first-level fault-tolerant consistency constraints, the second-level obstetric care record data stored on the blockchain is retrieved online. If the amount of second-level data is still insufficient, repeat the above steps, continue to calculate the deviation vector and the proportion of the number of deviation indicators, update the fault-tolerant consistency constraints, and retrieve the next level of data. Continue to search step by step until the amount of obstetric care record data at a certain level (for example, level N) is greater than or equal to the data volume threshold, or when N is equal to 5 (that is, five levels of data have been retrieved, but the data volume threshold has not been reached), the retrieval process is terminated. Finally, all obstetric care record data from level one to level N are integrated together as the final obstetric care record data for subsequent analysis.

[0030] In a preferred embodiment, counting the abnormal nursing trigger frequency ratio of the obstetric nursing record data and setting it as the abnormal nursing probability includes: Calculate the proportion of the N-level deviation vector and the N-level deviation index number of the N-level obstetric nursing record data, and set the deviation distance from the deviation vector and the proportion of the deviation index number as the N-level distribution distance; until the N-level deviation vector and the N-level deviation index number proportion of the first-level obstetric nursing record data are calculated, and the deviation distance from the deviation vector and the proportion of the deviation index number is set as the first-level distribution distance; calculate the sum of the distribution distances from the first-level distribution distance to the N-level distribution distance; calculate the ratio of the first-level distribution distance to the sum of the distribution distances, use 1 to subtract the ratio to generate a first-level distribution weight, until the N-level distribution weight is obtained; according to the first-level distribution weight up to the N-level distribution weight, weighted fusion of the abnormal care trigger frequency ratio of each level, obtain the abnormal care probability.

[0031] Specifically, in the process of calculating the abnormal nursing trigger frequency ratio to set the abnormal nursing probability, a weighted fusion method of multi-level obstetric nursing record data was adopted. This method considers the deviation distance (i.e., distribution distance) of the data at different levels from the initial conditions in terms of deviation vectors and deviation indicator quantity ratios, and allocates fusion weights according to the distance of the distribution distance. First, the deviation vector and deviation indicator quantity ratio of the obstetric nursing record data at each level (from level 1 to level N) are calculated, and compared with the initial deviation vector and deviation indicator quantity ratio to calculate the deviation distance, which is called the distribution distance. The distribution distance reflects the degree of deviation of the data at that level from the initial conditions in terms of dynamic indicators. Then, the distribution distances from level 1 to level N are accumulated to obtain the sum of the distribution distances, which represents the overall degree of deviation of the data at all levels from the initial conditions in terms of dynamic indicators. Then, the ratio of the distribution distance of each level to the sum of the distribution distances is calculated, and the distribution weight of the level is generated by subtracting this ratio from 1. The purpose of this step is to allocate fusion weights according to the distance of the distribution distance. The farther the distribution distance, the smaller the weight of the data in the fusion process. Finally, the calculated distribution weights of each level are used to weight the fusion of the abnormal nursing trigger frequency ratio of each level. Specifically, the abnormal nursing trigger frequency ratio of each level is multiplied by the corresponding distribution weight, and then all weighted frequency ratios are added to obtain the final abnormal nursing probability. In this process, the distribution distance plays a vital role. It is not only an important indicator to measure the degree of deviation of data at each level from the initial conditions, but also an important basis for allocating fusion weights. By calculating the distribution distance, it is possible to identify which levels of data are closer to the initial conditions, so that higher weights are given in the fusion process; and which levels of data deviate far from the initial conditions are given lower weights in the fusion process. This weighted fusion method based on distribution distance can more accurately reflect the contribution of data at each level to the final abnormal nursing probability, thereby improving the accuracy and reliability of the prediction. In summary, by calculating the distribution distance, the sum of distribution distances and the distribution weights at each level, and weighted fusion of the abnormal nursing trigger frequency ratios at each level, a more accurate abnormal nursing probability can be obtained. This method not only takes into account the quantity and quality of data, but also the degree of deviation of data from the initial conditions. It is a more comprehensive and accurate prediction method.

[0032] For a clearer understanding, the following example is given: Assuming there are three levels of obstetric care record data (level 1, level 2, and level 3), the deviation vector and the percentage of deviation indicators for each level of data have been calculated. For simplicity, as shown in Table 1, it is assumed that the deviation vector and the percentage of deviation indicators can be expressed by a comprehensive indicator, called "deviation degree".

[0033] Table 1: Comparison of deviation and distribution distance of data in the third-level obstetric nursing records

[0034]

[0035] Add the distribution distances of each level to get the total distribution distance. Total distribution distance = 0.05 (level 1) + 0.05 (level 2) + 0.2 (level 3) = 0.3. According to the ratio of the distribution distance of each level to the total distribution distance, calculate the distribution weight of each level, and use 1 minus the ratio to generate the weight, as shown in Table 2 (for simplicity, the weight result of 1 minus the ratio is directly given here): Table 2: Simplified calculation of the weight distribution of the data of the third-level obstetric nursing records

[0036] Note: In actual applications, since the total distribution distance is fixed, the sum of the weights of each level should be 1. The calculation method here is for simplification. In practice, it should be normalized according to the ratio of the distribution distance to the total to ensure that the sum of the weights is 1. As shown in Table 3, the correct weight calculation method is as follows: Table 3: Correctly calculated data distribution weights of the third-level obstetric care records

[0037] Assume that the abnormal nursing trigger frequency ratios of each level are: 0.1 for level 1, 0.15 for level 2, and 0.2 for level 3. Weighted fusion is performed according to the distribution weights of each level: abnormal nursing probability = 0.25 (level 1 weight) × 0.1 (level 1 frequency ratio) + 0.25 (level 2 weight) × 0.15 (level 2 frequency ratio) + 0.5 (level 3 weight) × 0.2 (level 3 frequency ratio) = 0.025 + 0.0375 + 0.1 = 0.1625. Therefore, the final abnormal nursing probability is 0.1625.

[0038] Please note that the data in actual applications will vary depending on the specific situation. In addition, when calculating the distribution weight, you should ensure that the sum of the weights at all levels is 1 to avoid inaccurate weight distribution.

[0039] In a preferred embodiment, calculating the N-level deviation vector and the N-level deviation index quantity ratio of the N-level obstetric nursing record data, and the deviation distance from the deviation vector and the deviation index quantity ratio is set as the N-level distribution distance, including: Calculate the first Euclidean distance between the N-level deviation vector and the deviation vector, wherein the first Euclidean distance has a first weight identifier; calculate the first proportion deviation between the proportion of the number of N-level deviation indicators and the proportion of the number of deviation indicators, wherein the first proportion deviation has a second weight identifier; perform weighted summation of the first Euclidean distance and the first proportion deviation according to the first weight identifier and the second weight identifier to obtain the N-level distribution distance.

[0040] Exemplarily, when processing obstetric nursing record data, in order to evaluate the degree of deviation between data of different levels (set as N levels) and the overall data, the "N-level distribution distance" can be calculated. This distance is a comprehensive indicator that combines the deviation between the deviation vector of the N-level data and the proportion of the number of deviation indicators and the corresponding value of the overall data. First, it is necessary to obtain N-level obstetric nursing record data, which contains the values ​​of multiple nursing indicators. At the same time, it is also necessary to obtain the overall obstetric nursing record data as a comparison benchmark. For the N-level data and the overall data, their deviation vectors are calculated respectively. The deviation vector refers to the vector composed of the difference between each indicator value and its average value (or a certain benchmark value). The N-level deviation vector here specifically refers to the deviation vector of the N-level data, while the deviation vector refers to the deviation vector of the overall data. It is also necessary to calculate the number of deviation indicators (i.e., those indicators that have significant deviations from the average value) in the N-level data and the overall data. Next, the first Euclidean distance between the N-level deviation vector and the deviation vector is calculated. Euclidean distance is a commonly used distance measurement method used to measure the straight-line distance between two vectors. This first Euclidean distance reflects the degree of deviation between the N-level data and the overall data in the deviation vector. In order to emphasize the importance of this distance, a first weight mark is assigned to it, which indicates the weight of this distance when calculating the N-level distribution distance. The proportion of the number of deviation indicators refers to the proportion of the number of deviation indicators to the total number of indicators. It is also necessary to calculate the first proportion deviation between the proportion of the number of deviation indicators at level N and the proportion of the number of deviation indicators. This deviation reflects the degree of deviation between the N-level data and the overall data in the proportion of the number of deviation indicators. Similarly, in order to emphasize the importance of this deviation, a second weight mark is assigned to it. Finally, according to the first weight mark and the second weight mark, the first Euclidean distance and the first proportion deviation are weighted and summed to obtain the N-level distribution distance. This N-level distribution distance is a comprehensive indicator that simultaneously considers the degree of deviation between the N-level data and the overall data in the deviation vector and the proportion of the number of deviation indicators, and is weighted according to the importance (i.e., weight) of these two deviations. Through the above process, a quantitative indicator, the N-level distribution distance, can be obtained to evaluate the degree of deviation between the N-level obstetric nursing record data and the overall data. This indicator is of great significance for understanding the differences between data at different levels, optimizing nursing records, and improving nursing quality.

[0041] In a preferred embodiment, a strict consistency constraint condition is constructed according to the static indicator, and a fault-tolerant consistency constraint condition is constructed according to the deviation vector and the ratio of the deviation indicator quantity, including: Based on the static indicators, strictly consistent benchmark parameters are constructed. When the input indicators are exactly the same as the strictly consistent benchmark parameters, the strictly consistent constraint conditions are deemed to be met. Based on the deviation vector and the vector distance threshold, a first fault-tolerant consistent benchmark parameter is constructed. Based on the deviation indicator quantity ratio and the ratio deviation threshold, a second fault-tolerant consistent benchmark parameter is constructed. When the deviation distance between the input deviation vector and the first fault-tolerant consistent benchmark parameter is less than or equal to the vector distance threshold, and the ratio deviation between the input deviation indicator quantity ratio and the second fault-tolerant consistent benchmark parameter is less than or equal to the ratio deviation threshold, the fault-tolerant consistent constraint conditions are deemed to be met.

[0042] Specifically, when processing a set of static indicators, in order to ensure the accuracy and consistency of the data, two types of constraints can be constructed: strict consistency constraints and fault-tolerant consistency constraints. The static indicators that need to be evaluated are clearly defined, and these indicators are the benchmarks for data accuracy and consistency. Based on these static indicators, a strictly consistent benchmark parameter set is constructed, which contains the ideal value or standard value of each static indicator. When the input indicator data is exactly the same as the strictly consistent benchmark parameters, the data is considered to meet the strict consistency constraints. This means that the data is completely consistent with the benchmark parameters in all aspects without any deviation. For the input data, first calculate its deviation vector, that is, the vector composed of the difference between each indicator and the benchmark value. At the same time, the proportion of the number of deviation indicators is also calculated, that is, the proportion of the number of indicators that deviate from the benchmark value to the total number of indicators. In order to construct the fault-tolerant consistency constraint, two thresholds need to be set: the vector distance threshold and the proportion deviation threshold. These two thresholds are used to measure the tolerance range of the deviation vector and the proportion of the number of deviation indicators, respectively. Based on the deviation vector and the vector distance threshold, the first fault-tolerant consistent benchmark parameter is constructed. This parameter is a benchmark that allows the deviation vector to fluctuate within a certain range. Similarly, based on the proportion of the number of deviation indicators and the proportion deviation threshold, a second fault-tolerant consistent benchmark parameter is constructed. This parameter is a benchmark that allows the proportion of the number of deviation indicators to fluctuate within a certain range. When the deviation distance between the input deviation vector and the first fault-tolerant consistent benchmark parameter is less than or equal to the vector distance threshold, and the proportion deviation between the input deviation indicator proportion and the second fault-tolerant consistent benchmark parameter is less than or equal to the proportion deviation threshold, the data are considered to meet the fault-tolerant consistent constraint. This means that although the data has a certain deviation from the benchmark parameter, the deviation is within an acceptable range, so it is still considered to be consistent. By constructing these two constraints, a more detailed and comprehensive evaluation of the consistency and accuracy of the data can be performed. Strict consistency constraints ensure the complete consistency of the data, while fault-tolerant consistency constraints allow deviations within a certain range, thereby improving the flexibility and practicality of the evaluation.

[0043] The embodiment of the present invention provides a real-time obstetric nursing optimization method based on big data, which has at least the following technical effects: 1. By counting the dynamic indicators in the abnormal nursing log, distinguish the central dynamic indicators and the edge dynamic indicators, and calculate their deviation vectors and the proportion of the number of deviation indicators. Combined with static indicators, it can accurately predict the probability of abnormal nursing that meets these conditions at the same time, so as to timely remind the nursing end to optimize nursing. This big data-based analysis method improves the accuracy and efficiency of identifying abnormal nursing risks.

[0044] 2. A multi-level retrieval strategy was adopted, starting from the first-level obstetric care record data, and gradually deepening according to conditions such as data volume threshold and distribution distance until sufficient data volume was obtained or the highest level (N level) was reached. The deviation vector and deviation index ratio of each level of data were calculated, and the abnormal care trigger frequency ratio of each level was weighted and fused to finally obtain the abnormal care probability. This multi-level retrieval and fusion method effectively improved the accuracy and reliability of the prediction.

[0045] 3. When predicting the probability of abnormal care, strict consistency constraints and fault-tolerant consistency constraints are constructed. Strict consistency constraints ensure that the input indicators are exactly the same as the benchmark parameters, while fault-tolerant consistency constraints allow the input indicators to deviate from the benchmark parameters within a certain range. The combination of these two constraints not only ensures the strict consistency of the data, but also improves the fault tolerance of the system, making the prediction results more in line with the actual situation.

[0046] Embodiment 2:

[0047] like Figure 2 As shown, based on the same inventive concept as the obstetric real-time nursing optimization method based on big data provided in Embodiment 1, the embodiment of the present invention further provides an obstetric real-time nursing optimization system based on big data, including: The information retrieval module 11 is used to retrieve multiple abnormal nursing logs using the static indicators of obstetric nursing objects as constants and the dynamic indicators as variables, wherein any abnormal nursing log includes an abnormal dynamic indicator set.

[0048] The statistical screening module 12 is used to, based on the abnormal dynamic indicator set, calculate the central dynamic indicator of the number of log entries in the multiple abnormal nursing logs that is greater than or equal to the log entry threshold, and the edge dynamic indicator of the number of log entries that is less than the log entry threshold.

[0049] The deviation statistics module 13 is used to count the deviation vectors of the central dynamic index monitoring values ​​of the obstetric care objects and the number ratio of deviation indicators of the marginal dynamic index monitoring values.

[0050] The abnormal prediction module 14 is used to predict the probability of abnormal nursing that satisfies the static index, the deviation vector and the ratio of the number of deviation indexes at the same time.

[0051] The nursing optimization module 15 is used to remind the nursing end to perform nursing optimization when the abnormal nursing probability is greater than or equal to the abnormal probability threshold.

[0052] Furthermore, the statistical screening module 12 is further configured to perform the following steps: Extract the first abnormal dynamic indicator set of the first abnormal nursing log of the multiple abnormal nursing logs, wherein the first abnormal dynamic indicator set is counted in a preset length time zone before the abnormality of the nursing object occurs; count the deviation frequency of the first abnormal dynamic indicator of the first abnormal dynamic indicator of the first abnormal dynamic indicator set in the preset length time zone; when the deviation frequency of the first abnormal dynamic indicator is greater than or equal to the deviation frequency threshold, it is regarded as the number of logs appearing for the first abnormal dynamic indicator plus one; traverse the dynamic indicators, perform statistics based on the multiple abnormal nursing logs, and obtain the central dynamic indicator whose number of logs appearing is greater than or equal to the log number threshold, and the edge dynamic indicator whose number of logs appearing is less than the log number threshold.

[0053] Furthermore, the abnormality prediction module 14 is further configured to perform the following steps: According to the static indicators, a strict consistency constraint condition is constructed, and according to the deviation vector and the ratio of the deviation indicators, a fault-tolerant consistency constraint condition is constructed, wherein the strictly consistent representation state must be exactly the same, and the fault-tolerant consistency representation state deviation must be less than or equal to the deviation threshold; based on the strict consistency constraint condition and the fault-tolerant consistency constraint condition, the obstetric nursing record data stored on the blockchain is retrieved online; the abnormal nursing trigger frequency ratio of the obstetric nursing record data is counted and set as the abnormal nursing probability.

[0054] Furthermore, the abnormality prediction module 14 is further configured to perform the following steps: Based on the strict consistency constraint and the fault-tolerant consistency constraint, the first-level obstetric nursing record data stored on the blockchain is retrieved online; when the data volume of the first-level obstetric nursing record data is less than or equal to the data volume threshold, the first-level deviation vector and the first-level deviation indicator quantity ratio are calculated, wherein the data volume threshold is greater than or equal to 5000; according to the first-level deviation vector and the first-level deviation indicator quantity ratio, the fault-tolerant consistency constraint is updated to obtain the first-level fault-tolerant consistency constraint, and combined with the strict consistency constraint, the second-level obstetric nursing record data stored on the blockchain is retrieved online; until the data volume of the first-level obstetric nursing record data to the N-level obstetric nursing record data is greater than or equal to the data volume threshold, or N is equal to 5, the first-level obstetric nursing record data to the N-level obstetric nursing record data are added to the obstetric nursing record data, and N is an integer.

[0055] Furthermore, the abnormality prediction module 14 is further configured to perform the following steps: Calculate the proportion of the N-level deviation vector and the N-level deviation index number of the N-level obstetric nursing record data, and set the deviation distance from the deviation vector and the proportion of the deviation index number as the N-level distribution distance; until the N-level deviation vector and the N-level deviation index number proportion of the first-level obstetric nursing record data are calculated, and the deviation distance from the deviation vector and the proportion of the deviation index number is set as the first-level distribution distance; calculate the sum of the distribution distances from the first-level distribution distance to the N-level distribution distance; calculate the ratio of the first-level distribution distance to the sum of the distribution distances, use 1 to subtract the ratio to generate a first-level distribution weight, until the N-level distribution weight is obtained; according to the first-level distribution weight up to the N-level distribution weight, weighted fusion of the abnormal care trigger frequency ratio of each level, obtain the abnormal care probability.

[0056] Furthermore, the abnormality prediction module 14 is further configured to perform the following steps: Calculate the first Euclidean distance between the N-level deviation vector and the deviation vector, wherein the first Euclidean distance has a first weight identifier; calculate the first proportion deviation between the proportion of the number of N-level deviation indicators and the proportion of the number of deviation indicators, wherein the first proportion deviation has a second weight identifier; perform weighted summation of the first Euclidean distance and the first proportion deviation according to the first weight identifier and the second weight identifier to obtain the N-level distribution distance.

[0057] Furthermore, the abnormality prediction module 14 is further configured to perform the following steps: Based on the static indicators, strictly consistent benchmark parameters are constructed. When the input indicators are exactly the same as the strictly consistent benchmark parameters, the strictly consistent constraint conditions are deemed to be met. Based on the deviation vector and the vector distance threshold, a first fault-tolerant consistent benchmark parameter is constructed. Based on the deviation indicator quantity ratio and the ratio deviation threshold, a second fault-tolerant consistent benchmark parameter is constructed. When the deviation distance between the input deviation vector and the first fault-tolerant consistent benchmark parameter is less than or equal to the vector distance threshold, and the ratio deviation between the input deviation indicator quantity ratio and the second fault-tolerant consistent benchmark parameter is less than or equal to the ratio deviation threshold, the fault-tolerant consistent constraint conditions are deemed to be met.

[0058] Through the above-mentioned detailed description of a real-time obstetric care optimization method based on big data in this specification, those skilled in the art can clearly know that this embodiment is a real-time obstetric care optimization system based on big data. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0059] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A real-time obstetric nursing optimization method based on big data, characterized in that: include: Taking the static index of the obstetric nursing object as a constant and the dynamic index as a variable, a plurality of abnormal nursing logs are retrieved, wherein any abnormal nursing log includes an abnormal dynamic index set; Based on the abnormal dynamic indicator set, statistical dynamic indicators are collected from the central dynamic indicators of the plurality of abnormal nursing logs, where the number of log entries is greater than or equal to a log entry threshold, and the edge dynamic indicators, where the number of log entries is less than the log entry threshold; Count the deviation vectors of the central dynamic index monitoring values ​​of obstetric care objects, as well as the number and proportion of deviation indicators of the marginal dynamic index monitoring values; Predicting the probability of abnormal nursing that simultaneously satisfies the static index, the deviation vector, and the ratio of the number of deviation indexes; When the abnormal nursing probability is greater than or equal to the abnormal probability threshold, the nursing end is reminded to perform nursing optimization.

2. The method according to claim 1, characterized in that Based on the abnormal dynamic indicator set, the dynamic indicators are counted as central dynamic indicators of the plurality of abnormal nursing logs, where the number of log entries is greater than or equal to the log entry threshold, and edge dynamic indicators, where the number of log entries is less than the log entry threshold, including: Extracting a first abnormal dynamic indicator set of a first abnormal nursing log of the plurality of abnormal nursing logs, wherein the first abnormal dynamic indicator set is counted in a preset length time zone before the nursing object has an abnormality; Counting the deviation frequency of the first abnormal dynamic indicator of the first abnormal dynamic indicator set in the preset length time zone; When the deviation frequency of the first abnormal dynamic indicator is greater than or equal to the deviation frequency threshold, it is considered that the number of log entries of the first abnormal dynamic indicator increases by one; The dynamic indicators are traversed, and statistics are performed based on the multiple abnormal nursing logs to obtain the central dynamic indicator in which the number of logs is greater than or equal to the log number threshold, and the edge dynamic indicator in which the number of logs is less than the log number threshold.

3. The method according to claim 1, characterized in that Predicting the probability of abnormal nursing that simultaneously satisfies the static index, the deviation vector, and the ratio of the number of deviation indexes includes: According to the static indicators, a strict consistency constraint condition is constructed, and according to the deviation vector and the ratio of the deviation indicators, a fault-tolerant consistency constraint condition is constructed, wherein the strictly consistent representation state must be exactly the same, and the fault-tolerant consistent representation state deviation must be less than or equal to the deviation threshold; Based on the strict consistency constraint condition and the fault-tolerant consistency constraint condition, online retrieval of obstetric nursing record data stored in the blockchain; The abnormal care triggering frequency ratio of the obstetric care record data is counted and set as the abnormal care probability.

4. The method according to claim 3, characterized in that Based on the strict consistency constraint and the fault-tolerant consistency constraint, online retrieval of obstetric nursing record data stored in blockchain includes: Based on the strict consistency constraint and the fault-tolerant consistency constraint, the first-level obstetric nursing record data stored in the blockchain is retrieved online; When the data volume of the first-level obstetric nursing record data is less than or equal to the data volume threshold, the first-level deviation vector and the first-level deviation index quantity ratio are calculated, wherein the data volume threshold is greater than or equal to 5000; The fault-tolerant consistency constraint condition is updated according to the first-level deviation vector and the first-level deviation index quantity ratio, the first-level fault-tolerant consistency constraint condition is obtained, and the second-level obstetric nursing record data stored in the blockchain is retrieved online in combination with the strict consistency constraint condition; Until the data volume of the first-level obstetric care record data to the N-level obstetric care record data is greater than or equal to the data volume threshold, or when N is equal to 5, the first-level obstetric care record data to the N-level obstetric care record data are added to the obstetric care record data, where N is an integer.

5. The method according to claim 4, characterized in that Counting the abnormal nursing trigger frequency ratio of the obstetric nursing record data, and setting it as the abnormal nursing probability, includes: Calculate the N-level deviation vector and the N-level deviation index quantity ratio of the N-level obstetric nursing record data, and set the deviation distance between the deviation vector and the deviation index quantity ratio as the N-level distribution distance; Until the N-level deviation vector and the N-level deviation index quantity ratio of the first-level obstetric nursing record data are calculated, the deviation distance from the deviation vector and the deviation index quantity ratio is set as the first-level distribution distance; Calculate the sum of distribution distances from the first-level distribution distance to the N-level distribution distance; Calculate the ratio of the first-level distribution distance to the total of the distribution distances, subtract the ratio from 1, and generate a first-level distribution weight, until an N-level distribution weight is obtained; The abnormal care probability is obtained by weighting and fusing the abnormal care trigger frequency ratio of each level according to the first-level distribution weight up to the N-level distribution weight.

6. The method according to claim 5, characterized in that Calculating the N-level deviation vector and the N-level deviation index quantity ratio of the N-level obstetric nursing record data, and the deviation distance from the deviation vector and the deviation index quantity ratio, set as the N-level distribution distance, including: Calculating a first Euclidean distance between the N-level deviation vector and the deviation vector, wherein the first Euclidean distance has a first weight identifier; Calculate a first proportion deviation between the proportion of the number of the N-level deviation indicators and the proportion of the number of the deviation indicators, wherein the first proportion deviation has a second weight identifier; According to the first weight identifier and the second weight identifier, a weighted sum is performed on the first Euclidean distance and the first proportion deviation to obtain the N-level distribution distance.

7. The method according to claim 3, characterized in that According to the static indicators, strict consistency constraints are constructed, and according to the deviation vector and the ratio of the deviation indicators, fault-tolerant consistency constraints are constructed, including: Based on the static indicators, strict consistency benchmark parameters are constructed. When the input indicators are completely the same as the strict consistency benchmark parameters, the strict consistency constraint conditions are deemed to be met. Based on the deviation vector and the vector distance threshold, a first fault-tolerant consistent benchmark parameter is constructed, and based on the deviation index quantity proportion and the proportion deviation threshold, a second fault-tolerant consistent benchmark parameter is constructed; When the deviation distance between the input deviation vector and the first fault-tolerant consistent benchmark parameter is less than or equal to the vector distance threshold, and the deviation between the proportion of the input deviation index quantity and the proportion of the second fault-tolerant consistent benchmark parameter is less than or equal to the proportion deviation threshold, it is deemed that the fault-tolerant consistent constraint condition is met.

8. A real-time obstetric care optimization system based on big data, characterized in that: A method for optimizing obstetric real-time nursing based on big data according to any one of claims 1 to 7, the system comprising: An information retrieval module, used to retrieve multiple abnormal nursing logs using static indicators of obstetric nursing objects as constants and dynamic indicators as variables, wherein any abnormal nursing log includes an abnormal dynamic indicator set; A statistical screening module, for counting dynamic indicators based on the abnormal dynamic indicator set, a central dynamic indicator whose number of occurrence logs of the plurality of abnormal nursing logs is greater than or equal to a log number threshold, and an edge dynamic indicator whose number of occurrence logs is less than the log number threshold; The deviation statistics module is used to count the deviation vectors of the central dynamic index monitoring values ​​of obstetric care objects and the number and proportion of deviation indicators of the marginal dynamic index monitoring values; An abnormality prediction module, used to predict the probability of abnormal nursing that satisfies the static index, the deviation vector and the ratio of the number of deviation indexes at the same time; The nursing optimization module is used to remind the nursing end to perform nursing optimization when the abnormal nursing probability is greater than or equal to the abnormal probability threshold.

Images