Antenatal fetal monitoring method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a prenatal fetal monitoring method and device, electronic equipment, a storage medium and a program product. The method comprises the steps that multiple pieces of block monitoring data corresponding to multiple pregnant women in the current first time period are obtained, wherein the monitoring data comprise fetal heart monitoring data and uterine contraction monitoring data; for each pregnant woman, determining a fetal heart baseline based on the fetal heart monitoring data of the pregnant woman and determining a uterine contraction baseline based on the uterine contraction monitoring data; determining fetal heart characteristics according to the fetal heart base line and the fetal heart monitoring data, and determining uterine contraction characteristics according to the uterine contraction base line and the uterine contraction monitoring data; and predicting whether the fetus of the pregnant woman is abnormal or not according to the fetal heart characteristics and the uterine contraction characteristics. According to the method, abnormal feature recognition is carried out on the fetal heart data and the uterine contraction data, obtained in real time, of the pregnant woman, so that medical staff are prompted on the client side, the fetal heart monitoring efficiency and quality are effectively improved, and the situation of missing detection caused by human negligence is avoided.

Description

Technical Field

[0001] This application relates to the medical field of smart Internet of Things, and more particularly to a prenatal fetal monitoring method, device, electronic device, storage medium, and program product. Background Technology

[0002] Fetal heart rate monitoring in late pregnancy plays a crucial role in the safety of both the pregnant woman and the fetus. Currently, the mainstream fetal heart rate monitoring method used in hospitals is the three-in-one approach, which combines equipment monitoring, monitoring data curve presentation, and doctor's experience in interpreting the graphs.

[0003] However, the accuracy of monitoring data curves under current technology is limited, and it is difficult to perceive detailed changes with the naked eye. Furthermore, the doctor's subjective experience has a significant impact on the monitoring results. In addition, each fetal heart rate monitoring generates a large amount of fetal heart rate data. When faced with a large number of simultaneous monitoring tasks, it is difficult for doctors to maintain continuous attention, anticipate and detect abnormalities during the monitoring process, thus affecting the monitoring effectiveness. Summary of the Invention

[0004] This application provides a prenatal fetal monitoring method, device, electronic device, storage medium, and program product to automatically detect and alert pregnant women to abnormal fetal heart rate and uterine contractions.

[0005] In a first aspect, embodiments of this application provide a method for prenatal fetal monitoring, including:

[0006] Acquire multiple segments of monitoring data corresponding to multiple pregnant women within the current first time period, including fetal heart rate monitoring data and uterine contraction monitoring data;

[0007] For each pregnant woman, a fetal heart rate baseline is determined based on the fetal heart rate monitoring data and a uterine contraction baseline is determined based on the uterine contraction monitoring data.

[0008] Fetal heart characteristics are determined based on the fetal heart rate baseline and the fetal heart rate monitoring data, and uterine contraction characteristics are determined based on the uterine contraction baseline and the uterine contraction monitoring data;

[0009] Predict whether the fetus of the pregnant woman will develop abnormalities based on the described fetal heart rate characteristics and uterine contraction characteristics.

[0010] In one possible implementation, multiple data blocks corresponding to each pregnant woman are obtained by segmenting the monitoring data stream of the pregnant woman generated within the first time period according to a preset time length.

[0011] In one possible implementation, determining the fetal heart rate baseline based on the fetal heart rate monitoring data and the uterine contraction baseline based on the uterine contraction monitoring data for each pregnant woman includes:

[0012] Obtain the monitoring task identifier corresponding to the pregnant woman, and determine the target task processing node in the distributed task processing node based on the monitoring task identifier;

[0013] The pregnant woman's multiple data blocks are sent to the target task processing node, whereby the target task processing node is used to determine the fetal heart rate baseline, uterine contraction baseline, fetal heart rate characteristics, uterine contraction characteristics, and whether any fetal abnormalities have occurred based on the multiple data blocks.

[0014] In one possible implementation, determining the fetal heart rate baseline based on the fetal heart rate monitoring data of the pregnant woman and determining the uterine contraction baseline based on the uterine contraction monitoring data includes:

[0015] The fetal heart rate monitoring data were filtered using an improved wavelet transform.

[0016] If the filtered fetal heart rate monitoring data meets the first preset steady-state condition, the fetal heart rate baseline is determined based on the mean of the filtered fetal heart rate monitoring data;

[0017] The uterine contraction data were filtered using an improved wavelet transform;

[0018] If the filtered uterine contraction data meets the second preset steady-state condition, the uterine contraction baseline is determined based on the mean of the filtered uterine contraction monitoring data.

[0019] In one possible implementation, determining the fetal heart rate baseline based on the fetal heart rate monitoring data of the pregnant woman and determining the uterine contraction baseline based on the uterine contraction monitoring data further includes:

[0020] If the filtered fetal heart rate monitoring data does not meet the first preset steady-state condition, it is determined that the fetal heart rate monitoring data in the multiple block monitoring data is in an abnormal fluctuation state and has no baseline.

[0021] If the filtered uterine contraction monitoring data does not meet the second preset steady-state condition, it is determined that the uterine contraction monitoring data in the multiple segmented monitoring data is in an abnormal fluctuation state and has no baseline.

[0022] In one possible implementation, determining fetal heart characteristics based on the fetal heart rate baseline and the fetal heart rate monitoring data, and determining uterine contraction characteristics based on the uterine contraction baseline and the uterine contraction monitoring data, includes:

[0023] The fetal heart rate monitoring data is filtered using an improved wavelet transform, and cardiac motion features, baseline variability features, and deceleration features are analyzed from the filtered fetal heart rate monitoring data.

[0024] The uterine contraction monitoring data is filtered using an improved wavelet transform, and the uterine contraction morphology features and their relationship with uterine contractions are analyzed from the filtered uterine contraction monitoring data.

[0025] In one possible implementation, predicting whether the fetus of the pregnant woman has an abnormality based on the fetal heart rate characteristics and the uterine contraction characteristics includes:

[0026] Based on the preset abnormality identification rules and the cardiac characteristics, baseline variation characteristics, deceleration characteristics, uterine contraction morphology characteristics, and uterine contraction relationship characteristics, it is determined whether an abnormality has occurred.

[0027] In one possible implementation, the method further includes:

[0028] In response to the detection of an anomaly, the anomaly information is displayed in the monitoring interface.

[0029] Secondly, embodiments of this application provide a prenatal fetal monitoring device, comprising:

[0030] The acquisition unit is used to acquire multiple blocks of monitoring data corresponding to multiple pregnant women in the current first time period, including fetal heart rate monitoring data and uterine contraction monitoring data.

[0031] The first determining unit is used to determine the fetal heart rate baseline and the uterine contraction baseline for each pregnant woman based on the fetal heart rate monitoring data of that pregnant woman.

[0032] The second determining unit is used to determine fetal heart characteristics based on the fetal heart baseline and the fetal heart monitoring data, and to determine uterine contraction characteristics based on the uterine contraction baseline and the uterine contraction monitoring data.

[0033] The prediction unit is used to predict whether the fetus of the pregnant woman will develop abnormalities based on the fetal heart rate characteristics and the uterine contraction characteristics.

[0034] In one possible implementation, multiple data blocks corresponding to each pregnant woman are obtained by segmenting the monitoring data stream of the pregnant woman generated within the first time period according to a preset time length.

[0035] In one possible implementation, the first determining unit includes:

[0036] The acquisition module is used to acquire the monitoring task identifier corresponding to the pregnant woman and determine the target task processing node in the distributed task processing nodes based on the monitoring task identifier.

[0037] The sending module is used to send multiple data blocks of the pregnant woman to the target task processing node, wherein the target task processing node is used to determine the fetal heart rate baseline, uterine contraction baseline, fetal heart rate characteristics, uterine contraction characteristics, and whether fetal abnormalities have occurred based on the multiple data blocks.

[0038] In one possible implementation, the first determining unit includes:

[0039] The first processing module is used to filter the fetal heart rate monitoring data using an improved wavelet transform.

[0040] The first determining module is used to determine the fetal heart rate baseline based on the mean of the filtered fetal heart rate monitoring data if the filtered fetal heart rate monitoring data meets the first preset steady-state condition.

[0041] The second processing module is used to filter the uterine contraction data using an improved wavelet transform.

[0042] The second determining module is used to determine the uterine contraction baseline based on the mean of the filtered uterine contraction monitoring data if the filtered uterine contraction data meets the second preset steady-state condition.

[0043] In one possible implementation, the first determining unit further includes:

[0044] The third determining module is used to determine that if the filtered fetal heart rate monitoring data does not meet the first preset steady-state condition, the fetal heart rate monitoring data in the multiple block monitoring data is in an abnormal fluctuation state and has no baseline.

[0045] The fourth determination module is used to determine that if the filtered uterine contraction monitoring data does not meet the second preset steady-state condition, the uterine contraction monitoring data in the multiple block monitoring data is in an abnormal fluctuation state and has no baseline.

[0046] In one possible implementation, the second determining unit includes:

[0047] The third processing module is used to filter the fetal heart rate monitoring data using an improved wavelet transform, and to analyze the cardiac characteristics, baseline variation characteristics and deceleration characteristics of the filtered fetal heart rate monitoring data.

[0048] The fourth processing module is used to filter the uterine contraction monitoring data using an improved wavelet transform, and to analyze the uterine contraction morphology features and the relationship features with uterine contractions in the filtered uterine contraction monitoring data.

[0049] In one possible implementation, the prediction unit includes:

[0050] The first prediction module is used to predict whether the fetus has any abnormalities based on the cardiac-related features and the baseline variation features, wherein the abnormalities include cardiac-related abnormalities and baseline variation abnormalities.

[0051] In one possible implementation, the prediction unit includes:

[0052] The second prediction module is used to predict whether deceleration anomalies have occurred based on deceleration characteristics.

[0053] The fifth determining module is used to determine whether a uterine contraction relationship exists based on the uterine contraction morphology characteristics corresponding to the multiple segmented monitoring data.

[0054] The sixth determining module is used to respond to the occurrence of the deceleration abnormality and to determine the existence of the uterine contraction relationship, and to determine whether it is a late deceleration abnormality based on the uterine contraction morphology characteristics and deceleration characteristics.

[0055] In one possible implementation, the device further includes:

[0056] The display unit is used to display the abnormality information of the detected abnormality in the monitoring interface.

[0057] Thirdly, embodiments of this application provide a prenatal fetal monitoring device, including: a memory and a processor;

[0058] The memory stores computer-executed instructions;

[0059] The processor executes computer execution instructions stored in the memory, such that the processor, when executed, is used to implement the first aspect and / or various possible implementations of the first aspect.

[0060] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0061] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, is used to implement the first aspect and / or various possible implementations of the first aspect.

[0062] This application provides a prenatal fetal monitoring method, device, electronic device, storage medium, and program product. By acquiring multiple blocks of monitoring data corresponding to multiple pregnant women within a current first time period, including fetal heart rate monitoring data and uterine contraction monitoring data, for each pregnant woman, a fetal heart rate baseline is determined based on the fetal heart rate monitoring data, and a uterine contraction baseline is determined based on the uterine contraction monitoring data. Fetal heart rate characteristics are determined based on the fetal heart rate baseline and fetal heart rate monitoring data, and uterine contraction characteristics are determined based on the uterine contraction baseline and uterine contraction monitoring data. The system predicts whether the fetus is abnormal based on the fetal heart rate characteristics, or predicts whether the fetus of the pregnant woman will develop abnormalities based on the fetal heart rate characteristics and uterine contraction characteristics. This enables the identification of abnormal features in the real-time acquired fetal heart rate and uterine contraction data of pregnant women, thereby prompting medical personnel on the client side. This effectively improves the efficiency and quality of fetal heart rate monitoring and avoids missed detections due to human negligence. Attached Figure Description

[0063] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0064] Figure 1 A schematic diagram illustrating a scenario for prenatal fetal monitoring provided in this application;

[0065] Figure 2 A flowchart illustrating a prenatal fetal monitoring method provided in this application. Figure 1 ;

[0066] Figure 3 A flowchart illustrating a prenatal fetal monitoring method provided in this application. Figure 2 ;

[0067] Figure 4 A flowchart illustrating a prenatal fetal monitoring method provided in this application. Figure 3 ;

[0068] Figure 5 A flowchart illustrating a prenatal fetal monitoring method provided in this application. Figure 4 ;

[0069] Figure 6 A schematic diagram of a prenatal fetal monitoring client provided in this application Figure 1 ;

[0070] Figure 7 A schematic diagram of a prenatal fetal monitoring client provided in this application Figure 2 ;

[0071] Figure 8 A schematic diagram of a prenatal fetal monitoring client provided in this application Figure 3;

[0072] Figure 9 This application provides a schematic diagram of the structure of a prenatal fetal monitoring device.

[0073] Figure 10 This is a schematic diagram of the structure of a prenatal fetal monitoring device provided in this application.

[0074] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0075] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0076] Prenatal checkups are a medical procedure that involves regularly monitoring the health of pregnant women and fetuses during pregnancy. Prenatal checkups include fetal heart rate monitoring, which is performed every two weeks or every week to ensure the health of the fetus and prevent adverse pregnancy outcomes.

[0077] Currently, the mainstream fetal heart rate monitoring method used in hospitals is the three-in-one approach, which combines equipment monitoring, monitoring data curve presentation, and doctor's experience in interpreting the graphs. However, existing technology does not have the ability to identify fetal heart rate monitoring data. Doctors can only judge whether all displayed curves are normal or abnormal by themselves, which relies heavily on manpower and doctor's experience. When faced with a large number of pregnant women's fetal heart rate data, it is easy to cause omissions or misjudgments, affecting the monitoring effect.

[0078] The prenatal fetal monitoring methods, devices, and equipment provided in this application are intended to solve the aforementioned technical problems.

[0079] Figure 1 This is a schematic diagram of a prenatal fetal monitoring scenario provided in this application.

[0080] like Figure 1As shown, the sensors of the monitor 101 can contact the pregnant woman's abdomen. These sensors may include, for example, a fetal heart rate sensor and a uterine contraction sensor to detect fetal heart rate data and uterine contraction data in real time. The monitor can send the detected data to a data center 102. The data center 102 can store fetal heart rate data and uterine contraction data for multiple pregnant women. The server 103 can retrieve the fetal heart rate data and uterine contraction data for multiple pregnant women from the data center, generate display content based on the data, and send the display content to the monitoring terminal 104 for display.

[0081] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0082] Figure 2 A flowchart illustrating a prenatal fetal monitoring method provided in this application. Figure 1 ,like Figure 2 As shown, the method includes:

[0083] S201. Obtain multiple monitoring data blocks corresponding to multiple pregnant women in the current first time period. The monitoring data includes fetal heart rate monitoring data and uterine contraction monitoring data.

[0084] For example, the execution entity of the prenatal fetal monitoring method in this embodiment can be a server. The server can obtain monitoring data corresponding to multiple pregnant women within the current first time period, and divide the monitoring data of each pregnant woman into blocks according to a preset duration.

[0085] S202. For each pregnant woman, the fetal heart rate baseline is determined based on the pregnant woman's fetal heart rate monitoring data, and the uterine contraction baseline is determined based on the uterine contraction monitoring data.

[0086] For example, the server described above can use an initialization algorithm module to determine the fetal heart rate baseline and uterine contraction baseline. The initialization algorithm module includes a baseline module, which includes a fetal heart rate baseline module and a uterine contraction baseline module. The data processing pipeline inputs preprocessed monitoring data from multiple pregnant women into the baseline module in batches to calculate the fetal heart rate baseline and uterine contraction baseline.

[0087] The fetal heart rate baseline module uses the decision tree algorithm in supervised learning to perform hierarchical analysis of fetal heart rate steady-state data. The first-level analysis of steady-state interval data determines whether the current fetal heart rate steady-state data meets the fetal heart rate baseline conditions. If it does, the mean of the fetal heart rate steady-state data is used to represent the fetal heart rate baseline steady-state standard, thus obtaining the fetal heart rate baseline. If it does not meet the conditions, the second-level analysis of the current fetal heart rate steady-state interval data is performed.

[0088] The fetal heart rate baseline module performs an improved wavelet transform filter on the current fetal heart rate steady-state interval data to determine whether the current fetal heart rate steady-state data meets the fetal heart rate baseline conditions. If it does, the mean of the fetal heart rate steady-state data is used to represent the fetal heart rate baseline steady-state standard, thus obtaining the fetal heart rate baseline. If it does not meet the conditions, the steady-state interval data is in a fluctuating state and there is no fetal heart rate baseline.

[0089] The contraction baseline module accumulates contraction data blocks in batches and performs improved wavelet transform filtering on the accumulated contraction data blocks to obtain steady-state contraction data.

[0090] The decision tree algorithm in supervised learning is used to perform hierarchical analysis on the steady-state data of uterine contractions. The first-level analysis of the steady-state interval data determines whether the current steady-state data of uterine contractions meets the uterine contraction baseline conditions. If it does, the mean of the steady-state data of uterine contractions is used to represent the steady-state standard of the uterine contraction baseline, thereby obtaining the uterine contraction baseline. If it does not meet the conditions, the second-level analysis of the current steady-state interval data of uterine contractions is performed.

[0091] The current steady-state contraction data is further improved by wavelet transform filtering to determine whether the current steady-state contraction data meets the contraction baseline conditions. If it does, the mean of the steady-state contraction data is used to represent the steady-state standard of the contraction baseline, thus obtaining the contraction baseline. If it does not meet, the steady-state data is in a fluctuating state and there is no contraction baseline.

[0092] S203. Determine fetal heart characteristics based on fetal heart rate baseline and fetal heart rate monitoring data, and determine uterine contraction characteristics based on uterine contraction baseline and uterine contraction monitoring data.

[0093] For example, the fetal heart rate feature recognition module performs an overall improved wavelet filter analysis on the fetal heart rate batch data based on the fetal heart rate baseline and abnormal fetal heart rate features to obtain graded features containing various types of fetal heart rate abnormalities. The graded fetal heart rate features of each abnormality are then subjected to improved Naive Bayes and decision tree graded analysis to determine the fetal heart rate features.

[0094] The contraction feature recognition module comprises two parts: contraction morphology feature recognition and contraction relationship feature recognition. For contraction morphology feature recognition, a comprehensive improved wavelet filter analysis is performed on the contraction batch data to obtain multi-level feature interval data. Decision tree hierarchical analysis and improved Naive Bayes classification are then applied to this multi-level feature interval data to determine if it meets the saliency feature criteria. If not, contractions are not present; if so, it is considered a suspected contraction feature. Secondary analysis is then performed on the feature interval data that meets the saliency feature criteria to determine if it meets the secondary feature criteria. If not, contractions are not present; if so, it is considered a suspected contraction feature. Finally, tertiary analysis is performed on the feature interval data that meets the secondary feature criteria to determine if it meets the shallow-level feature criteria. If so, the data represents a contraction morphology; otherwise, contractions are not present.

[0095] Simultaneously, the uterine contraction feature recognition module needs to accumulate uterine contraction morphology feature block data to identify uterine contraction relationship features. It then performs an overall improved wavelet filter analysis on the uterine contraction morphology feature block data to obtain multi-level feature interval data. Decision tree hierarchical analysis and improved Naive Bayes classification are then performed on the multi-level feature interval data to determine whether the multi-level feature interval data conforms to the conventional uterine contraction relationship. If it does, a uterine contraction relationship exists; if it does not, a uterine contraction relationship is suspected. A second-level analysis is then performed on the feature interval data that meets the significant feature conditions to determine whether it conforms to the minimum uterine contraction relationship. If it does not, a uterine contraction relationship does not exist; if it does, a uterine contraction relationship exists.

[0096] S204. Predict whether the fetus is abnormal based on fetal heart rate characteristics, or predict whether the fetus of the pregnant woman will develop abnormalities based on fetal heart rate characteristics and uterine contraction characteristics.

[0097] For example, based on the fetal heart rate characteristics and uterine contraction characteristics of the current pregnant woman obtained in step S203, a similarity comparison is made with known abnormal fetal heart rate characteristics and abnormal uterine contraction characteristics to predict whether the fetus will develop abnormalities.

[0098] This application provides a prenatal fetal monitoring method that acquires multiple blocks of monitoring data corresponding to multiple pregnant women within a current first time period. The monitoring data includes fetal heart rate monitoring data and uterine contraction monitoring data. For each pregnant woman, a fetal heart rate baseline is determined based on the fetal heart rate monitoring data, and a uterine contraction baseline is determined based on the uterine contraction monitoring data. Fetal heart rate characteristics are determined based on the fetal heart rate baseline and fetal heart rate monitoring data, and uterine contraction characteristics are determined based on the uterine contraction baseline and uterine contraction monitoring data. The method predicts whether the fetus is abnormal based on the fetal heart rate characteristics, or predicts whether the fetus of the pregnant woman will develop abnormalities based on the fetal heart rate characteristics and uterine contraction characteristics. This method enables the identification of abnormal features in the real-time acquired fetal heart rate data and uterine contraction data of pregnant women, thereby prompting medical staff on the client side. This effectively improves the efficiency and quality of fetal heart rate monitoring and avoids missed detections due to human negligence.

[0099] Figure 3 A flowchart illustrating a prenatal fetal monitoring method provided in this application. Figure 2 ,like Figure 3 As shown, in this embodiment... Figure 2 Based on the examples, a prenatal fetal monitoring method is described in detail, the method comprising:

[0100] S301. Obtain multiple monitoring data blocks corresponding to multiple pregnant women in the current first time period. The monitoring data includes fetal heart rate monitoring data and uterine contraction monitoring data.

[0101] Each pregnant woman has multiple data blocks, which are obtained by dividing the monitoring data stream of that pregnant woman generated in the first time period according to a preset time length.

[0102] For example, the multiple data blocks corresponding to each pregnant woman are obtained by dividing the monitoring data stream of the pregnant woman generated in the first time period according to a preset time length.

[0103] S302. Obtain the monitoring task identifier corresponding to the pregnant woman, and determine the target task processing node in the distributed task processing node according to the monitoring task identifier; send multiple blocks of data of the pregnant woman to the target task processing node, wherein the target task processing node is used to determine the fetal heart rate baseline, uterine contraction baseline, fetal heart rate characteristics, uterine contraction characteristics and determine whether fetal abnormalities occur based on the multiple blocks of data.

[0104] For example, the monitoring task identifier corresponding to the pregnant woman is obtained. Different monitoring task identifiers correspond to different nodes of the distributed task processing node. The target task processing node in the distributed task processing node is determined according to the monitoring task identifier. The multiple blocks of data of the pregnant woman are sent to the target task processing node.

[0105] S303. Filter the fetal heart rate monitoring data using an improved wavelet transform; if the filtered fetal heart rate monitoring data meets the first preset steady-state condition, determine the fetal heart rate baseline based on the mean of the filtered fetal heart rate monitoring data.

[0106] In one example, if the filtered fetal heart rate monitoring data does not meet the first preset steady-state condition, it is determined that the fetal heart rate monitoring data in the multiple segmented monitoring data is in an abnormal fluctuation state and has no baseline.

[0107] For example, the initialization algorithm module includes a baseline module, which includes a fetal heart rate baseline module and a uterine contraction baseline module. The data processing pipeline inputs the preprocessed monitoring data of multiple pregnant women into the baseline module in batches to calculate the fetal heart rate baseline and uterine contraction baseline.

[0108] The fetal heart rate baseline module uses the decision tree algorithm in supervised learning to perform hierarchical analysis of fetal heart rate steady-state data. The first-level analysis of steady-state interval data determines whether the current fetal heart rate steady-state data meets the fetal heart rate baseline conditions. If it does, the mean of the fetal heart rate steady-state data is used to represent the fetal heart rate baseline steady-state standard, thus obtaining the fetal heart rate baseline. If it does not meet the conditions, the second-level analysis of the current fetal heart rate steady-state interval data is performed.

[0109] The fetal heart rate baseline module performs an improved wavelet transform filter on the current fetal heart rate steady-state interval data to determine whether the current fetal heart rate steady-state data meets the fetal heart rate baseline conditions. If it does, the mean of the fetal heart rate steady-state data is used to represent the fetal heart rate baseline steady-state standard, thus obtaining the fetal heart rate baseline. If it does not meet the conditions, the steady-state interval data is in a fluctuating state and there is no fetal heart rate baseline.

[0110] S304. Filter the uterine contraction data using an improved wavelet transform; if the filtered uterine contraction data meets the second preset steady-state condition, determine the uterine contraction baseline based on the mean of the filtered uterine contraction monitoring data.

[0111] In one example, if the filtered uterine contraction monitoring data does not meet the second preset steady-state condition, it is determined that the uterine contraction monitoring data in the multiple block monitoring data is in an abnormal fluctuation state and has no baseline.

[0112] For example, the contraction baseline module accumulates contraction data blocks in batches and performs improved wavelet transform filtering on the accumulated contraction data blocks to obtain steady-state contraction data.

[0113] The decision tree algorithm in supervised learning is used to perform hierarchical analysis on the steady-state data of uterine contractions. The first-level analysis of the steady-state interval data determines whether the current steady-state data of uterine contractions meets the uterine contraction baseline conditions. If it does, the mean of the steady-state data of uterine contractions is used to represent the steady-state standard of the uterine contraction baseline, thereby obtaining the uterine contraction baseline. If it does not meet the conditions, the second-level analysis of the current steady-state interval data of uterine contractions is performed.

[0114] The current steady-state contraction data is further improved by wavelet transform filtering to determine whether the current steady-state contraction data meets the contraction baseline conditions. If it does, the mean of the steady-state contraction data is used to represent the steady-state standard of the contraction baseline, thus obtaining the contraction baseline. If it does not meet, the steady-state data is in a fluctuating state and there is no contraction baseline.

[0115] S305. The fetal heart rate monitoring data is filtered using an improved wavelet transform, and the cardiac characteristics, baseline variability characteristics, and deceleration characteristics of the filtered fetal heart rate monitoring data are analyzed.

[0116] For example, the fetal heart rate feature recognition module performs an overall improved wavelet filter analysis on the fetal heart rate batch data based on the fetal heart rate baseline and abnormal fetal heart rate features to obtain graded features containing various types of fetal heart rate abnormalities. The module then performs improved Naive Bayes and decision tree graded analysis on the graded fetal heart rate features of each abnormality to determine whether the fetal heart rate feature is a cardiac motion feature, a baseline variation feature, or a deceleration feature.

[0117] S306. The uterine contraction monitoring data is filtered using an improved wavelet transform. The morphological characteristics of uterine contractions and their relationship with uterine contractions are analyzed from the filtered uterine contraction monitoring data.

[0118] For example, the contraction feature recognition module includes two parts: contraction morphology feature recognition and contraction relationship feature recognition. For contraction morphology feature recognition, the batch data of contractions needs to undergo overall improved wavelet filtering analysis to obtain multi-level feature interval data. Decision tree hierarchical analysis and improved Naive Bayes classification are then performed on the multi-level feature interval data to determine whether the multi-level feature interval data meets the saliency feature conditions. If not, there is no contraction; if so, it is a suspected contraction feature. Secondary analysis is then performed on the feature interval data that meets the saliency feature conditions to determine whether it meets the secondary feature conditions. If not, there is no contraction; if so, it is a suspected contraction feature. Tertiary analysis is then performed on the feature interval data that meets the secondary feature conditions to determine whether it meets the shallow-level feature conditions. If so, the data represents a contraction morphology; otherwise, there is no contraction.

[0119] Simultaneously, the uterine contraction feature recognition module needs to accumulate uterine contraction morphology feature block data to identify uterine contraction relationship features. It then performs an overall improved wavelet filter analysis on the uterine contraction morphology feature block data to obtain multi-level feature interval data. Decision tree hierarchical analysis and improved Naive Bayes classification are then performed on the multi-level feature interval data to determine whether the multi-level feature interval data conforms to the conventional uterine contraction relationship. If it does, a uterine contraction relationship exists; if it does not, a uterine contraction relationship is suspected. A second-level analysis is then performed on the feature interval data that meets the significant feature conditions to determine whether it conforms to the minimum uterine contraction relationship. If it does not, a uterine contraction relationship does not exist; if it does, a uterine contraction relationship exists.

[0120] S307. Based on cardiac characteristics and baseline variability, predict whether the fetus will have abnormalities, including cardiac abnormalities and baseline variability abnormalities.

[0121] In one example, step S307 includes:

[0122] Predict whether deceleration anomalies have occurred based on deceleration characteristics;

[0123] Determine whether a uterine contraction relationship exists based on the uterine contraction morphology characteristics corresponding to multiple segmented monitoring data;

[0124] In response to the occurrence of deceleration abnormalities and the confirmation of uterine contractions, it is determined whether it is a late deceleration abnormality based on the morphological characteristics of the contractions and the characteristics of the deceleration.

[0125] For example, based on the fetal heart rate characteristics and uterine contraction characteristics of the current pregnant woman obtained in step S306, a similarity comparison is made with known abnormal fetal heart rate characteristics and abnormal uterine contraction characteristics to predict whether the fetus will develop an abnormality. If deceleration characteristics are present, it is determined whether it is an abnormal deceleration. The uterine contraction relationship is determined based on the obtained uterine contraction pattern. If it is determined to be an abnormal deceleration, and there is a uterine contraction relationship that meets the conditions for late deceleration abnormality, then it is determined to be a late uterine contraction abnormality.

[0126] S308. In response to the detection of an anomaly, the anomaly information is displayed in the monitoring interface.

[0127] For example, if abnormal features are detected in the fetal heart rate data or uterine contraction data of a pregnant woman, the abnormal time period of the fetal heart rate curve and uterine contraction curve displayed in the first monitoring interface will be yellow or red according to the classification of abnormal features, to indicate to medical staff that the fetal heart rate and / or uterine contraction are abnormal. When the fetal heart rate data and uterine contraction data are normal, the corresponding fetal heart rate curve will be blue and the uterine contraction curve will be green.

[0128] This application provides a prenatal fetal monitoring method that acquires multiple blocks of monitoring data corresponding to multiple pregnant women within a current first time period. The monitoring data includes fetal heart rate monitoring data and uterine contraction monitoring data. For each pregnant woman, a fetal heart rate baseline is determined based on the fetal heart rate monitoring data, and a uterine contraction baseline is determined based on the uterine contraction monitoring data. Fetal heart rate characteristics are determined based on the fetal heart rate baseline and fetal heart rate monitoring data, and uterine contraction characteristics are determined based on the uterine contraction baseline and uterine contraction monitoring data. The method predicts whether the fetus is abnormal based on the fetal heart rate characteristics, or predicts whether the fetus of the pregnant woman will develop abnormalities based on the fetal heart rate characteristics and uterine contraction characteristics. This method enables the identification of abnormal features in the real-time acquired fetal heart rate data and uterine contraction data of pregnant women, thereby prompting medical staff on the client side. This effectively improves the efficiency and quality of fetal heart rate monitoring and avoids missed detections due to human negligence.

[0129] Figure 4 A flowchart illustrating a prenatal fetal monitoring method provided in this application. Figure 3 ,like Figure 4 As shown, the method includes:

[0130] S401. Display the first monitoring interface. The first monitoring interface displays the first monitoring information corresponding to multiple pregnant women in the current first time period. The first monitoring information includes a list of pregnant women and / or fetal heart rate and uterine contraction curves. The fetal heart rate and uterine contraction curves include fetal heart rate monitoring curves and uterine contraction monitoring curves. The fetal heart rate and uterine contraction curves are obtained from the fetal heart rate monitoring and uterine contraction monitoring data in the current monitoring period.

[0131] In this application, the monitoring information for pregnant women includes monitoring of the pregnant woman's vital signs and monitoring of the fetus's vital signs.

[0132] The prenatal fetal monitoring method described in this application can be implemented by a terminal device or a server. The terminal device can include a mobile terminal or a fixed terminal such as a desktop computer. The aforementioned terminal device can be connected to one or more displays.

[0133] Taking a terminal device as the executing entity as an example, the terminal device can receive display information from the server and then display the fetal heart rate and uterine contraction curve. The server can parse the monitoring data obtained from monitoring instruments used to monitor the fetus and generate display information based on the parsing results. This monitoring data can include fetal heart rate monitoring data and uterine contraction monitoring data.

[0134] In some implementations, each pregnant woman can use a corresponding monitoring device to monitor both fetal and maternal vital signs. The server can generate displayable first monitoring information for each pregnant woman based on the monitoring data. This first monitoring information is then sent to the monitoring terminal for display.

[0135] The monitoring terminal's display screen can show the first monitoring interface. This first monitoring interface can display monitoring information for multiple pregnant women within the current first time period.

[0136] In some application scenarios, the aforementioned multiple pregnant woman monitoring information includes a list of pregnant women with multiple monitoring records.

[0137] In some application scenarios, the aforementioned monitoring information for pregnant women includes a list of pregnant women and the corresponding fetal heart rate and uterine contraction curves.

[0138] In some application scenarios, the server can obtain monitoring data from the data center that stores the data detected by the fetal monitoring instrument, process the monitoring data, and then generate the first monitoring information and the second monitoring information to be displayed.

[0139] The aforementioned data center can upload fetal heart rate data and uterine contraction data to the aforementioned server in real time through a data synchronization component.

[0140] The server may include a Message Queuing Telemetry Transport (MQTT) data receiving server. This server can receive fetal heart rate and uterine contraction data for each pregnant woman, and can divide this data into blocks according to time periods, resulting in multiple data blocks. To reduce the load on individual data processing units, a distributed computing system can be designed with a Change Data Capture (CDC) mechanism. This mechanism can capture insert, update, and delete operations in the database in real time and transmit these change data to other systems, such as real-time data analysis platforms. CDC is a distributed architecture that supports massive data synchronization.

[0141] After parsing the data, the corresponding real-time monitoring task is found based on the file name in the monitoring data. The parsed data is then distributed to the data processing pipeline corresponding to the real-time monitoring task. The data processing pipeline processes the received data, saves the processed data to the database, and pushes the processed data to the fetal heart monitoring workstation in real time through the data conduit, thus presenting it to the front-end fetal heart monitoring page of medical staff.

[0142] The data processing pipeline involves two parts: preprocessing and formal processing.

[0143] During preprocessing, data cleaning is performed first, removing invalid data. A time-series data engine is used to temporarily store data points in a time-series format, while duplicate data is also removed. The cleaned data is then divided into blocks, transforming data points into data blocks. Based on the time-series number of each data point, it is aggregated and assigned to the corresponding data block (the size of the data block can be determined based on configuration and dynamically adjusted during runtime; the default is on the order of 10 seconds). The data block CDC mechanism monitors changes in the data block queue in real time. When the latest data block meets the conditions (number of blocks or duration of existence), it is pushed to subsequent computational processes to drive formal processing.

[0144] During formal processing, the data is first standardized and converted into platform standard data, which is then persistently stored in the database. This data block is then pushed to the fetal heart monitoring terminal in real time via a data conduit, and the fetal heart monitoring terminal displays the fetal heart monitoring interface.

[0145] The fetal heart rate monitoring interface includes a first monitoring interface, which displays the monitoring information of multiple pregnant women within the current first time period. The first time period is the time span from the start to the end of the current fetal heart rate monitoring cycle. For some application scenarios, please refer to... Figure 6 , Figure 6 A schematic diagram of a prenatal fetal monitoring client provided in this application Figure 1 The aforementioned first monitoring interface 601 may include two parts: a left side and a right side. The left side displays a list of pregnant women 602 in a vertical arrangement, while the right side displays the fetal heart rate and uterine contraction curves of four pregnant women through four chart boxes (top, bottom, left, and right). In these application scenarios, the monitoring terminal is a large-screen monitor in the delivery room or a computer, etc.

[0146] In some application scenarios, the aforementioned first monitoring interface may include a list of pregnant women.

[0147] The pregnant woman list includes each pregnant woman's name, ID number, bed number, and number of messages. The header of each chart box contains the pregnant woman's monitoring information, including name, ID number, gestational week, bed number, paper feed speed, monitoring start time, and monitoring duration. The four charts correspond to the information of four consecutive pregnant women in the left-hand pregnant woman list. The center of the chart box displays the fetal heart rate and uterine contraction curves, with the upper half of the middle section showing the fetal heart rate curve and the lower half showing the uterine contraction curve. Below the chart box are the pregnant woman's vital signs information, including body temperature, respiratory rate, blood oxygen saturation, pulse rate, diastolic blood pressure, systolic blood pressure, and mean blood pressure.

[0148] Medical staff can also use the page-turning button in the lower right corner of the first monitoring page to switch the display box of the pregnant woman's fetal heart rate and uterine contraction on the right side of the first monitoring page, and view the fetal heart rate and uterine contraction curves of other pregnant women on the left.

[0149] S402. If an abnormality is detected in the fetus of at least one of the multiple pregnant women, the abnormality information of the first fetus corresponding to the at least one pregnant woman will be displayed on the first monitoring interface.

[0150] In other words, if any pregnant woman's fetus is found to have an abnormality based on monitoring information, the corresponding fetal abnormality information will be displayed on the first monitoring interface. For example... Figure 6 The first fetal abnormality information 604 shown is illustrated.

[0151] The "First Fetal Abnormality Information" mentioned here is only for the purpose of distinguishing between the information displayed on the first monitoring interface and the information displayed on the second monitoring interface. The "First Fetal Abnormality Information" can include the "Second Abnormality Information."

[0152] The aforementioned data processing pipeline can invoke the fetal heart rate feature calculation engine to process fetal heart rate and uterine contraction data. Based on the time range of the data blocks, corresponding feature calculation windows are established, and the data covered by each window is queried from the database and calculated and identified: fetal heart rate baseline, uterine contractions, abnormal fetal heart rate features, etc. If the feature calculation detects a suspected abnormality, the abnormality will be notified in real time to the fetal heart rate monitoring workstation via the data conduit and pushed to the front-end monitoring page of medical staff.

[0153] The data processing pipeline queries and calculates / identifies the data covered by each window through the initialization algorithm module. The initialization algorithm module consists of two parts: a baseline module and a feature recognition module. The baseline module calculates the fetal heart rate baseline and uterine contraction baseline. The fetal heart rate baseline (FHR-baseline, BFHR) refers to the fetal heart rate recorded when there is no fetal movement or uterine contractions. The normal fetal heart rate baseline range is 110 to 160 beats per minute. The fetal heart rate baseline includes the number of heartbeats per minute and FHR variability. FHR variability refers to small periodic fluctuations in FHR; the normal baseline variability amplitude is 6–25 bpm, and the frequency is 3–6 beats per minute. These variations indicate that the fetus has a certain reserve capacity and are a sign of fetal health. The uterine contraction baseline usually refers to the pressure changes of uterine contractions recorded during fetal heart rate monitoring; it reflects the strength and frequency of uterine muscle contractions. Monitoring the uterine contraction baseline helps to observe the activity of the uterus during labor.

[0154] The data processing pipeline inputs preprocessed fetal heart rate and uterine contraction data blocks into the baseline module in batches to calculate the fetal heart rate baseline and uterine contraction baseline. The baseline module is divided into a fetal heart rate baseline module and a uterine contraction baseline module. The fetal heart rate baseline module accumulates the batch fetal heart rate data and performs wavelet transform filtering on the accumulated batch fetal heart rate data to obtain the steady-state fetal heart rate data.

[0155] The decision tree algorithm in supervised learning is used to perform hierarchical analysis on the fetal heart rate steady-state data. The first-level analysis of the steady-state interval data determines whether the current fetal heart rate steady-state data meets the fetal heart rate baseline conditions. If it does, the mean of the fetal heart rate steady-state data is used to represent the fetal heart rate baseline steady-state standard, thus obtaining the fetal heart rate baseline. If it does not meet the conditions, the second-level analysis is performed on the current fetal heart rate steady-state interval data.

[0156] The current steady-state fetal heart rate data is further improved by wavelet transform filtering to determine whether the current steady-state fetal heart rate data meets the fetal heart rate baseline conditions. If it does, the mean of the steady-state fetal heart rate data is used to represent the steady-state standard of the fetal heart rate baseline, thus obtaining the fetal heart rate baseline. If it does not meet, the steady-state data is in a fluctuating state and there is no fetal heart rate baseline.

[0157] The contraction baseline module can accumulate contraction data blocks and perform improved wavelet transform filtering on the accumulated batch of contraction data blocks to obtain steady-state contraction data.

[0158] The decision tree algorithm in supervised learning is used to perform hierarchical analysis on the steady-state data of uterine contractions. The first-level analysis of the steady-state interval data determines whether the current steady-state data of uterine contractions meets the uterine contraction baseline conditions. If it does, the mean of the steady-state data of uterine contractions is used to represent the steady-state standard of the uterine contraction baseline, thereby obtaining the uterine contraction baseline. If it does not meet the conditions, the second-level analysis of the current steady-state interval data of uterine contractions is performed.

[0159] The current steady-state contraction data is further improved by wavelet transform filtering to determine whether the current steady-state contraction data meets the contraction baseline conditions. If it does, the mean of the steady-state contraction data is used to represent the steady-state standard of the contraction baseline, thus obtaining the contraction baseline. If it does not meet, the steady-state data is in a fluctuating state and there is no contraction baseline.

[0160] The fetal heart rate feature recognition module performs an overall improved wavelet filter analysis on the batch of fetal heart rate data to obtain hierarchical features containing various abnormalities. An improved decision tree algorithm is constructed to analyze the hierarchical features of various abnormalities. Based on the analysis results, the Naive Bayes algorithm in the improved supervised learning algorithm is used to obtain various fetal heart rate abnormalities.

[0161] The contraction feature recognition module comprises two parts: contraction morphology feature recognition and contraction relationship feature recognition. For contraction morphology feature recognition, a comprehensive improved wavelet filter analysis is performed on the contraction batch data to obtain multi-level feature interval data. Decision tree hierarchical analysis and improved Naive Bayes classification are then applied to this multi-level feature interval data to determine if it meets the saliency feature criteria. If not, contractions are not present; if so, it is considered a suspected contraction feature. Secondary analysis is then performed on the feature interval data that meets the saliency feature criteria to determine if it meets the secondary feature criteria. If not, contractions are not present; if so, it is considered a suspected contraction feature. Finally, tertiary analysis is performed on the feature interval data that meets the secondary feature criteria to determine if it meets the shallow-level feature criteria. If so, the data represents a contraction morphology; otherwise, contractions are not present.

[0162] Simultaneously, the uterine contraction feature recognition module needs to accumulate uterine contraction morphology feature block data to identify uterine contraction relationship features. It then performs an overall improved wavelet filter analysis on the uterine contraction morphology feature block data to obtain multi-level feature interval data. Decision tree hierarchical analysis and improved Naive Bayes classification are then performed on the multi-level feature interval data to determine whether the multi-level feature interval data conforms to the conventional uterine contraction relationship. If it does, a uterine contraction relationship exists; if it does not, a uterine contraction relationship is suspected. A second-level analysis is then performed on the feature interval data that meets the significant feature conditions to determine whether it conforms to the minimum uterine contraction relationship. If it does not, a uterine contraction relationship does not exist; if it does, a uterine contraction relationship exists.

[0163] If there are any abnormalities in the fetus of a pregnant woman under monitoring, the abnormal data stream passes through the monitoring instrument central station and enters the MQTT server. The MQTT server then distributes the data to the corresponding data processing pipeline. The data processing pipeline performs feature processing on the fetal heart rate and uterine contraction data blocks, identifies abnormal features in the monitoring data, and labels the fetal heart rate monitoring data according to the category of abnormal features. This allows the fetal heart rate monitoring APP or fetal heart rate monitoring workstation website to receive the labeled fetal heart rate monitoring data and display the abnormalities under different abnormal features according to the labeled categories.

[0164] Abnormal features in fetal heart rate monitoring data are shown in Table 1: Class I and Class II. Specific abnormal features include: mild bradycardia (e.g., marked B), mild tachycardia (T), mild minimal variability or absence of variability (AV&MV), suspected significant decelerations (ED, LD, VD), suspected slow decelerations (ED, LD, VD), early decelerations (ED), late decelerations (LD), and variable decelerations (VD). These abnormal features are highlighted in yellow on the fetal heart rate and uterine contraction curve on the APP and web page. Severe bradycardia (B), severe tachycardia (T), severe minimal variability or absence of variability (AV&MV), suspected frequent decelerations (RD), and suspected prolonged decelerations (PA) are highlighted in red on the fetal heart rate and uterine contraction curve on the APP and web page.

[0165] Table 1 Abnormal Characteristics Table

[0166]

[0167]

[0168] Both the fetal heart rate monitoring app and website have a CTG (Cardiotocography) AI analysis function switch, which is on by default. Medical staff can choose whether to enable it as needed. If the switch is enabled, abnormal markers are rendered at the central monitoring station, and different colored markers can be seen on the app and website. If the switch is disabled, abnormal markers are not rendered at the central monitoring station, and different colored markers cannot be seen on the app and website. This embodiment is based on the case where the CTG AI switch is enabled.

[0169] If the fetus of a pregnant woman shows abnormalities, the abnormal time period of the fetal heart rate curve and uterine contraction curve displayed on the first monitoring interface will be yellow or red, indicating to medical staff that the fetal heart rate and / or uterine contraction are abnormal. When the fetal heart rate data and uterine contraction data are normal, the corresponding fetal heart rate curve will be blue and the uterine contraction curve will be green.

[0170] In some implementations, the first monitoring information includes a list of pregnant women displayed in a first window and fetal heart rate and uterine contraction curves for each of the multiple pregnant women displayed in a second window; each pregnant woman's fetal heart rate and uterine contraction curve corresponds to a sub-window in the second window; and

[0171] Step S202 above includes: displaying a first abnormality alert in the pregnant woman list, the first abnormality alert including the number of unprocessed fetal abnormality information, and

[0172] For each of the at least one pregnant woman, display an error message in the corresponding sub-window.

[0173] Each abnormal data point corresponds to an abnormality alert message. These alerts are used to notify medical staff of any unreviewed or unmanaged fetal abnormalities. The number of alert messages represents the number of unmanaged fetal abnormalities. When the fetal heart rate monitoring app and web browser receive abnormal fetal heart rate and uterine contraction data, an abnormality alert message is displayed in the pregnant woman's list on the front-end page. The upper right corner of each pregnant woman's sub-window in the list displays the number of abnormality alert messages for that woman. If medical staff do not view the alerts, the alerts remain indefinitely, and the number accumulates as more abnormal alerts are added. If a medical staff member clicks to view the abnormality alerts, the number of abnormality alert messages displayed in the upper right corner will be 0.

[0174] In some implementations, the first monitoring information includes a list of pregnant women; and step S202 above includes:

[0175] The second abnormality alert is displayed in the list of pregnant women. The second abnormality alert includes the number of unprocessed fetal abnormalities. The second abnormality alert is related to the personalized abnormality settings of the pregnant woman corresponding to the user who logged into the first monitoring interface.

[0176] The first monitoring interface allows for personalized settings for pregnant women, such as labeling them as transferred patients, newly registered patients, or their educational level. A second abnormal alert is displayed in the pregnant woman list to prompt medical staff to check for abnormal alerts based on the individual settings of the pregnant woman.

[0177] S403. In response to the display command of the personal monitoring interface for the target pregnant woman, the first monitoring interface is switched to the second monitoring interface. The second monitoring interface displays the second monitoring information of the target pregnant woman, including the fetal heart rate and uterine contraction curve of the target pregnant woman and the corresponding second fetal abnormality information.

[0178] For example, medical staff can click on any pregnant woman's information box in the pregnant woman list box on the left side of the first monitoring interface as needed, thereby entering the fetal heart rate monitoring page for the corresponding pregnant woman, i.e., the second monitoring interface. The second monitoring page only displays the personal monitoring interface information of the target pregnant woman clicked by the medical staff. The second monitoring interface may include different display areas, such as two display areas, one above the other. Please refer to [reference needed]. Figure 7 , Figure 7 A schematic diagram of a prenatal fetal monitoring client provided in this application Figure 2 . Figure 7This is the second monitoring page, displaying only the monitoring data for the pregnant woman on the left. The curves in the upper half (701) represent the fetal heart rate and uterine contractions for that woman, while the lower half displays other vital signs information. These include body temperature, respiratory rate, blood oxygen saturation, pulse rate, diastolic blood pressure, systolic blood pressure, and mean blood pressure. The right-hand frame (703) is an abnormality editing box, which can be used by medical staff to edit abnormalities.

[0179] In addition, the aforementioned second monitoring interface also includes information about the pregnant woman, including her name, ID number, gestational age, bed number, paper feeding speed, monitoring start time, and monitoring duration.

[0180] When medical staff click on the information box of a pregnant woman whose fetal heart rate and uterine contraction curves show abnormalities in the first monitoring interface, they will enter the second monitoring interface where the pregnant woman is located. They can directly see the pregnant woman's fetal heart rate and uterine contraction curves and the abnormal information displayed on the front-end page.

[0181] S404. According to the abnormal list display instruction executed on the second monitoring interface, display the abnormal list within the second time period. The abnormal list includes multiple second fetal abnormal information corresponding to the fetus of the target pregnant woman in the second time period. The second time period includes at least one first time period after the start time of the current monitoring task, and at least one first time period includes the current first time period.

[0182] For example, the second monitoring page also includes a button to switch between the first and second time periods. If the current page displays the fetal heart rate and uterine contraction curves within the first time period, clicking the switch button will switch to the fetal heart rate and uterine contraction curves within the second time period. If the current page displays the fetal heart rate and uterine contraction curves within the second time period, clicking the switch button will switch to the fetal heart rate and uterine contraction curves within the first time period. Medical staff can access the second monitoring page by clicking on the list of pregnant women, which will display the fetal heart rate and uterine contraction curves within the first time period by default.

[0183] The first time period is one fetal heart rate and uterine contraction monitoring cycle. If the real-time monitoring of the pregnant woman is initiated every half hour, and each fetal heart rate and uterine contraction monitoring can last forty minutes or one hour, then the first time period is forty minutes or one hour. The second time period is the fetal heart rate monitoring curve of all monitoring cycles with abnormal conditions after the start of fetal heart rate and uterine contraction monitoring. For example, if fetal heart rate and uterine contraction monitoring is initiated and the monitoring time lasts for three hours, then after initiation, the first wave of fetal heart rate and uterine contraction monitoring is conducted, stopped after forty minutes, and resumed after thirty minutes until the end of three hours. Within three hours, some monitoring cycles have abnormal monitoring curves and some monitoring cycles have no abnormal monitoring curves. The second time period includes all abnormal conditions in the first time period.

[0184] In response to medical staff clicking the switch button, the second monitoring page displays a list of curves showing all abnormal conditions during the second time period.

[0185] This application provides a prenatal fetal monitoring method, device, electronic device, storage medium, and program product. By displaying a first monitoring interface, the first monitoring information of multiple pregnant women is shown. If an abnormality is detected in the fetus of at least one of the pregnant women, the first monitoring interface displays the corresponding first fetal abnormality information for that at least one pregnant woman. In response to a display command for a personal monitoring interface for a target pregnant woman, the first monitoring interface is switched to a second monitoring interface. The second monitoring interface displays the fetal heart rate and uterine contraction curve of the target pregnant woman and the corresponding second fetal abnormality information. Based on an abnormality list display command executed on the second monitoring interface, an abnormality list for a second time period is displayed. This achieves the goal of displaying any detected abnormality on the monitoring interface, intuitively alerting the doctor to the abnormality, reducing missed diagnoses due to insufficient medical resources or doctor experience. Simultaneously, it can extract and discriminate features from the monitoring information of multiple pregnant women, effectively improving the monitoring efficiency of abnormalities.

[0186] Figure 5 A flowchart illustrating a prenatal fetal monitoring method provided in this application. Figure 4 ,like Figure 5 As shown, the method includes:

[0187] S501. Display the first monitoring interface. The first monitoring interface displays the first monitoring information corresponding to multiple pregnant women in the current first time period. The first monitoring information includes a list of pregnant women and / or fetal heart rate and uterine contraction curves. The fetal heart rate and uterine contraction curves include fetal heart rate monitoring curves and uterine contraction monitoring curves. The fetal heart rate and uterine contraction curves are obtained from the fetal heart rate monitoring and uterine contraction monitoring data in the current monitoring period.

[0188] The steps in this embodiment can be referred to step S401 above, and will not be repeated here.

[0189] S502. If an abnormality is detected in the fetus of at least one of the multiple pregnant women, the abnormality information of the first fetus corresponding to the at least one pregnant woman will be displayed on the first monitoring interface.

[0190] The first monitoring information includes a list of pregnant women displayed in the first window and fetal heart rate and uterine contraction curves for each of the multiple pregnant women displayed in the second window.

[0191] In other words, if any pregnant woman's fetus is found to have an abnormality based on the monitoring information, the abnormality information of the first fetus corresponding to that pregnant woman will be displayed on the first monitoring interface.

[0192] The "First Fetal Abnormality Information" mentioned here is only for the purpose of distinguishing between the information displayed on the first monitoring interface and the information displayed on the second monitoring interface. The "First Fetal Abnormality Information" can include the "Second Abnormality Information."

[0193] After receiving fetal heart rate monitoring data and uterine contraction monitoring data from multiple pregnant women, the aforementioned server can invoke the fetal heart rate feature calculation engine to process the data. Based on the time range of the data blocks, corresponding feature calculation windows are established, and the data covered by each window is queried from the database and calculated and identified: fetal heart rate baseline, uterine contractions, abnormal fetal heart rate features, etc. If the feature calculation detects a suspected abnormality, the abnormality will be notified in real time to the fetal heart rate monitoring workstation via the data conduit and pushed to the front-end monitoring page of medical staff.

[0194] Step S502 also includes the following steps:

[0195] First, for each of at least one pregnant woman, information about the first fetal abnormality is displayed in a preset display area corresponding to the time period in which the fetal abnormality occurred.

[0196] Each abnormal data point corresponds to an abnormality alert message. These alerts are used to notify medical staff of any unreviewed or unmanaged fetal abnormalities. The number of alert messages represents the number of unmanaged fetal abnormalities. When the fetal heart rate monitoring app and web browser receive abnormal fetal heart rate and uterine contraction data, an abnormality alert message is displayed in the pregnant woman's list on the front-end page. The upper right corner of each pregnant woman's sub-window in the list displays the number of abnormality alert messages for that woman. If medical staff do not view the alerts, the alerts remain indefinitely, and the number accumulates as more abnormal alerts are added. If a medical staff member clicks to view the abnormality alerts, the number of abnormality alert messages displayed in the upper right corner will be 0.

[0197] Secondly, highlight the portions of the fetal heart rate monitoring curve and the uterine contraction curve that correspond to the time periods in the contraction curve.

[0198] The first monitoring interface allows for personalized settings for pregnant women, such as labeling them as transferred patients, newly registered patients, or their educational level. A second abnormal alert is displayed in the pregnant woman list to prompt medical staff to check for abnormal alerts based on the individual settings of the pregnant woman.

[0199] S503. In response to the display command of the personal monitoring interface for the target pregnant woman, the first monitoring interface is switched to the second monitoring interface. The second monitoring interface displays the second monitoring information of the target pregnant woman, including the fetal heart rate and uterine contraction curve of the target pregnant woman and the corresponding second fetal abnormality information.

[0200] For example, medical staff can click on any pregnant woman's information box in the list box on the left side of the first monitoring interface as needed, thereby entering the fetal heart rate monitoring page of the corresponding pregnant woman, which is the second monitoring interface. The second monitoring page only displays the personal monitoring interface information of the target pregnant woman clicked by the medical staff. The upper half of the second monitoring interface displays the pregnant woman's information, including name, number, gestational week, bed number, paper feed speed, monitoring start time, and monitoring duration. The middle part is a fetal heart rate and uterine contraction curve chart box. The upper half of the middle part is the fetal heart rate curve, and the lower half is the uterine contraction curve. Below the chart box is the pregnant woman's vital signs information, including body temperature, respiratory rate, blood oxygen, pulse rate, diastolic blood pressure, systolic blood pressure, and mean blood pressure.

[0201] When medical staff click on the information box of a pregnant woman whose fetal heart rate and uterine contraction curves show abnormalities in the first monitoring interface, they will enter the second monitoring interface where the pregnant woman is located. They can directly see the pregnant woman's fetal heart rate and uterine contraction curves and the abnormal information displayed on the front-end page.

[0202] S504. According to the abnormal list display instruction executed on the second monitoring interface, display the abnormal list within the second time period. The abnormal list includes multiple second fetal abnormal information corresponding to the fetus of the target pregnant woman in the second time period. The second time period includes at least one first time period after the start time of the current monitoring task, and at least one first time period includes the current first time period.

[0203] For example, the second monitoring page also includes a button to switch between the first and second time periods. If the current page displays the fetal heart rate and uterine contraction curves within the first time period, clicking the switch button will switch to the fetal heart rate and uterine contraction curves within the second time period. If the current page displays the fetal heart rate and uterine contraction curves within the second time period, clicking the switch button will switch to the fetal heart rate and uterine contraction curves within the first time period. Medical staff can access the second monitoring page by clicking on the list of pregnant women, which will display the fetal heart rate and uterine contraction curves within the first time period by default.

[0204] The first time period is one fetal heart rate and uterine contraction monitoring cycle. If the real-time monitoring of the pregnant woman is initiated every half hour, and each fetal heart rate and uterine contraction monitoring can last forty minutes or one hour, then the first time period is forty minutes or one hour. The second time period is the fetal heart rate monitoring curve of all monitoring cycles with abnormalities after the start of fetal heart rate and uterine contraction monitoring. For example, if fetal heart rate and uterine contraction monitoring is initiated and the monitoring time lasts for three hours, then after initiation, the first wave of fetal heart rate and uterine contraction monitoring is conducted, stopped after forty minutes, and resumed after thirty minutes, until the end of three hours. Within three hours, some monitoring cycles have abnormal monitoring curves and some monitoring cycles have no abnormalities. The second time period includes all the first time periods with abnormalities.

[0205] In response to medical staff clicking the switch button, the second monitoring page displays a list of curves showing all abnormal conditions during the second time period.

[0206] S505. Receive abnormal editing operation, update the fetal abnormality information corresponding to the target pregnant woman in the second monitoring interface according to the result of the abnormal editing operation; and synchronously update the second fetal abnormality information corresponding to the target pregnant woman in other monitoring terminals.

[0207] The exception editing operation includes one or more of the following: adding exception information, modifying exception information, and deleting exception information.

[0208] Step S505 also includes:

[0209] Receive editing instructions for the target abnormality in the abnormality list or the target abnormality in the second fetal abnormality information, display the abnormality modification window, and receive deletion operations for the target abnormality or modification operations for the existing abnormality information of the target abnormality in the abnormality modification window.

[0210] Alternatively, it can receive abnormal editing instructions for the fetal heart rate and uterine contraction curve of the target pregnant woman corresponding to the third time period in the second monitoring interface, display the abnormal addition window, and receive the new abnormal information entered in the abnormal addition window.

[0211] In some application scenarios, the abnormality list, fetal heart rate and uterine contraction curves, and second fetal abnormality information can be displayed on the second monitoring interface. In these scenarios, users can edit any abnormality in the abnormality list. When medical staff double-click an abnormal curve in the fetal heart rate and uterine contraction curve list, an editing window for that abnormal curve appears. Users can then delete the abnormal information, causing the abnormal curve to revert to its normal color and no longer display any abnormal information. Alternatively, modifications to the abnormal information, such as changing a Class I abnormality to a Class II abnormality, will change the abnormal curve from yellow to red, and the displayed abnormal information will change accordingly.

[0212] In some applications, the second monitoring interface displays the fetal heart rate and uterine contraction curves corresponding to the target pregnant woman, as well as information on any abnormalities in the second fetus. In these scenarios, medical staff can also edit abnormal curves that were previously displayed as normal but were not identified. For example... Figure 7 As shown, users can select curve 704 within a target time period in the fetal heart rate and uterine contraction curve, and trigger the operation of editing anomalies on that curve segment, thereby displaying the anomaly editing window 703. The system receives newly added anomaly information entered in the anomaly editing window 703 and displays it on the curve according to the anomaly information. The third time period is the time period where the anomaly curves not displayed are marked by medical staff.

[0213] For example, medical staff can also make a secondary judgment on the displayed abnormalities based on their own experience, and click on the abnormal information prompts of the fetal heart rate and uterine contraction curves on the second monitoring page to edit the abnormal information prompts.

[0214] For example, medical staff can click on any pregnant woman's information box in the list box on the left side of the first monitoring interface as needed, thereby entering the fetal heart rate monitoring page of the corresponding pregnant woman, which is the second monitoring interface. The second monitoring page only displays the personal monitoring interface information of the target pregnant woman clicked by the medical staff. The upper half of the second monitoring interface displays the pregnant woman's information, including name, number, gestational week, bed number, paper feed speed, monitoring start time, and monitoring duration. The middle part is a fetal heart rate and uterine contraction curve chart box. The upper half of the middle part is the fetal heart rate curve, and the lower half is the uterine contraction curve. Below the chart box is the pregnant woman's vital signs information, including body temperature, respiratory rate, blood oxygen, pulse rate, diastolic blood pressure, systolic blood pressure, and mean blood pressure.

[0215] When medical staff click on the information box of a pregnant woman whose fetal heart rate and uterine contraction curves show abnormalities in the first monitoring interface, they will enter the second monitoring interface where the pregnant woman is located. They can directly see the pregnant woman's fetal heart rate and uterine contraction curves and the abnormal information displayed on the front-end page.

[0216] S506 The second monitoring interface also includes an event addition control, which displays an event addition window in response to receiving a trigger operation performed on the event addition control; and receives event information related to the target pregnant woman and / or drug information used by the target pregnant woman entered in the event addition window.

[0217] For example, during the monitoring of a pregnant woman, the medications she takes and the events that occur over a period of time may have a certain impact on the fetal heart rate and uterine contraction data. Therefore, in response to the click of the event addition control by medical staff, an event and medication addition window can be displayed, and the event / medication display area on the second monitoring page can be displayed according to the content entered by the medical staff.

[0218] S507. Based on the selection operation of the first target time period performed on the second monitoring interface, display the second monitoring information within the first target time period. The first target time period is a historical time period corresponding to this monitoring task.

[0219] The first monitoring information includes the latest vital sign parameter values ​​of the pregnant woman; the second monitoring information includes trend information of multiple vital sign parameter values ​​of the pregnant woman corresponding to the first target time period.

[0220] Step S507 also includes the following steps:

[0221] The first step of step S507 is to receive a trigger operation on the historical monitoring records displayed in the second monitoring interface, display a monitoring task switching window, and receive a viewing command for the target historical task entered in the task switching window.

[0222] The second step of step S507 is to display the monitoring task list in the displayed list of pregnant women and receive a viewing instruction for the target pregnant woman's historical monitoring tasks in the monitoring task list.

[0223] In the third step of step S507, for abnormal information in the fetal heart rate and uterine contraction curve of the target historical monitoring task, the fetal heart rate and uterine contraction curve is displayed for a first preset time before the start time of the abnormal information and a second preset time after the end time of the abnormal information.

[0224] For example, in late pregnancy, fetal heart rate monitoring is often required every two weeks or every week. The fetal heart rate monitoring data from each visit to the hospital is stored and the monitoring period is marked, thus forming historical monitoring data. In response to the first target time period selected by the medical staff on the second monitoring interface, the monitoring information within that time period is displayed. The first target time period is one of many historical monitoring events preceding the current monitoring task, and the monitoring information within that time period constitutes the second monitoring information.

[0225] In response to the first step of step S507, when the medical staff clicks the historical monitoring record button in the second monitoring interface, a window for switching historical monitoring tasks pops up. Based on the viewing instruction of the target historical task entered by the medical staff in the window, the monitoring window of the corresponding historical task is switched.

[0226] Regarding the second step of step S507, medical staff can also click the monitoring task viewing button in the pregnant woman list, which will bring up the monitoring task list in the second monitoring interface. Medical staff can then select the monitoring task of the required historical event segment from the monitoring task list and switch to the monitoring window of the corresponding historical task.

[0227] Regarding the third step of step S507, for abnormal information in the fetal heart rate and uterine contraction curve of the target historical monitoring task, display the fetal heart rate and uterine contraction curve for a first preset duration before the start time of the abnormal information and a second preset duration after the end time of the abnormal information. Please refer to... Figure 8 , Figure 8 A schematic diagram of a prenatal fetal monitoring client provided in this application Figure 3 . Figure 8 The page displays the abnormal monitoring data for pregnant women. The left side is marked with data from April 17, 2024 to June 14, 2024. This means the curve on the page represents the segment of abnormal monitoring data for pregnant women listed in the left-hand column during this period. The right side of the page also displays a list of abnormalities that occurred during the aforementioned time period.

[0228] S508. Display the list of anomalies in the second time period according to the anomaly list display instruction executed on the second monitoring interface; wherein, the second time period includes multiple first time periods after the start time of the current monitoring task, and the multiple first time periods include the current first time period.

[0229] For example, the second monitoring page also includes a button to switch between the first and second time periods. If the current page displays the fetal heart rate and uterine contraction curves within the first time period, clicking the switch button will switch to the fetal heart rate and uterine contraction curves within the second time period. If the current page displays the fetal heart rate and uterine contraction curves within the second time period, clicking the switch button will switch to the fetal heart rate and uterine contraction curves within the first time period. Medical staff can access the second monitoring page by clicking on the list of pregnant women, which will display the fetal heart rate and uterine contraction curves within the first time period by default.

[0230] The first time period is one fetal heart rate and uterine contraction monitoring cycle. If the real-time monitoring of the pregnant woman is initiated every half hour, and each fetal heart rate and uterine contraction monitoring can last forty minutes or one hour, then the first time period is forty minutes or one hour. The second time period is the fetal heart rate monitoring curve of all monitoring cycles with abnormalities after the start of fetal heart rate and uterine contraction monitoring. For example, if fetal heart rate and uterine contraction monitoring is initiated and the monitoring time lasts for three hours, then after initiation, the first wave of fetal heart rate and uterine contraction monitoring is conducted, stopped after forty minutes, and resumed after thirty minutes, until the end of three hours. Within three hours, some monitoring cycles have abnormal monitoring curves and some monitoring cycles have no abnormalities. The second time period includes all the first time periods with abnormalities.

[0231] In response to medical staff clicking the switch button, the second monitoring page displays a list of curves showing all abnormal conditions during the second time period.

[0232] This application provides a prenatal fetal monitoring method, device, electronic device, storage medium, and program product. It displays a first monitoring interface showing the first monitoring information of multiple pregnant women. If an abnormality is detected in the fetus of at least one of the pregnant women, the first monitoring interface displays the corresponding first fetal abnormality information for that at least one pregnant woman. Responding to a display command for a personal monitoring interface for a target pregnant woman, the first monitoring interface switches to a second monitoring interface. The second monitoring interface displays the fetal heart rate and uterine contraction curve of the target pregnant woman and the corresponding second fetal abnormality information. Based on an abnormality list display command executed on the second monitoring interface, an abnormality list for a second time period is displayed. This achieves the goal of displaying detected abnormalities on the monitoring interface, intuitively alerting doctors to the abnormalities and reducing missed diagnoses due to insufficient medical resources or doctor experience. Simultaneously, it can extract and distinguish features from the monitoring information of multiple pregnant women, effectively improving the monitoring efficiency of abnormalities. Medical staff can add, delete, modify, and query abnormalities, and can also add special cases such as events and medications, effectively meeting the flexibility and operability needs of medical staff. Furthermore, it allows viewing the pregnant woman's historical monitoring records, facilitating doctors to review past treatments and improving the efficiency of monitoring pregnant women.

[0233] Figure 9 This is a schematic diagram of the structure of a prenatal fetal monitoring device provided in this application, such as... Figure 9 As shown, the prenatal fetal monitoring device 90 provided in this embodiment includes:

[0234] The acquisition unit 901 is used to acquire multiple blocks of monitoring data corresponding to multiple pregnant women in the current first time period. The monitoring data includes fetal heart rate monitoring data and uterine contraction monitoring data.

[0235] The first determining unit 902 is used to determine the fetal heart rate baseline and the uterine contraction baseline for each pregnant woman based on the pregnant woman's fetal heart rate monitoring data and the uterine contraction monitoring data.

[0236] The second determining unit 903 is used to determine fetal heart characteristics based on the fetal heart baseline and fetal heart monitoring data, and to determine uterine contraction characteristics based on the uterine contraction baseline and uterine contraction monitoring data.

[0237] Prediction unit 904 is used to predict whether the fetus of the pregnant woman will develop abnormalities based on fetal heart rate characteristics and uterine contraction characteristics.

[0238] In one possible implementation, multiple data blocks corresponding to each pregnant woman are obtained by segmenting the monitoring data stream of that pregnant woman generated within a first time period according to a preset time length.

[0239] In one possible implementation, the first determining unit 902 includes:

[0240] The acquisition module 9021 is used to acquire the monitoring task identifier corresponding to the pregnant woman and determine the target task processing node in the distributed task processing node based on the monitoring task identifier.

[0241] The sending module 9022 is used to send multiple blocks of data of the pregnant woman to the target task processing node. The target task processing node is used to determine the fetal heart rate baseline, uterine contraction baseline, fetal heart rate characteristics, uterine contraction characteristics and determine whether there is any fetal abnormality based on the multiple blocks of data.

[0242] In one possible implementation, the first determining unit 902 includes:

[0243] The first processing module 9023 is used to filter the fetal heart rate monitoring data using an improved wavelet transform.

[0244] The first determining module 9024 is used to determine the fetal heart baseline based on the mean of the filtered fetal heart monitoring data if the filtered fetal heart monitoring data meets the first preset steady-state condition.

[0245] The second processing module 9025 is used to filter the uterine contraction data using an improved wavelet transform.

[0246] The second determining module 9026 is used to determine the uterine contraction baseline based on the mean of the filtered uterine contraction monitoring data if the filtered uterine contraction data meets the second preset steady-state condition.

[0247] In one possible implementation, the first determining unit 902 further includes:

[0248] The third determining module 9027 is used to determine that if the filtered fetal heart rate monitoring data does not meet the first preset steady-state condition, the fetal heart rate monitoring data in the multiple block monitoring data is in an abnormal fluctuation state and has no baseline.

[0249] The fourth determination module 9028 is used to determine that if the filtered uterine contraction monitoring data does not meet the second preset steady-state condition, the uterine contraction monitoring data in the multiple block monitoring data is in an abnormal fluctuation state and has no baseline.

[0250] In one possible implementation, the second determining unit 903 includes:

[0251] The third processing module 9031 is used to filter the fetal heart rate monitoring data using improved wavelet transform, and to analyze the cardiac characteristics, baseline variation characteristics and deceleration characteristics of the filtered fetal heart rate monitoring data.

[0252] The fourth processing module 9032 is used to filter the uterine contraction monitoring data using an improved wavelet transform, and to analyze the uterine contraction morphology features and the relationship features with uterine contractions in the filtered uterine contraction monitoring data.

[0253] In one possible implementation, the prediction unit 904 includes:

[0254] The first prediction module 9041 is used to predict whether the fetus has any abnormalities based on cardiac-related characteristics and baseline variability characteristics. Abnormalities include cardiac-related abnormalities and baseline variability abnormalities.

[0255] In one possible implementation, the prediction unit 904 includes:

[0256] The second prediction module 9042 is used to predict whether a deceleration anomaly has occurred based on the deceleration characteristics.

[0257] The fifth determining module 9043 is used to determine whether there is a uterine contraction relationship based on the uterine contraction morphology characteristics corresponding to multiple segmented monitoring data.

[0258] The sixth determining module 9044 is used to respond to the occurrence of deceleration abnormality and to determine the existence of uterine contraction relationship, and to determine whether it is a late deceleration abnormality based on the morphological characteristics of uterine contractions and deceleration characteristics.

[0259] In one possible implementation, the device 90 further includes:

[0260] Display unit 905 is used to display abnormal information of the detected abnormality on the monitoring interface.

[0261] The prenatal fetal monitoring device provided in this embodiment can perform the method provided in the above-described method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0262] Figure 10 This is a structural diagram of a prenatal fetal monitoring device provided in this application. Figure 10 As shown, the electronic device 100 provided in this embodiment includes at least one processor 1001 and a memory 1002. Optionally, the device 100 further includes a communication component 1003. The processor 1001, memory 1002, and communication component 1003 are connected via a bus 1004.

[0263] In a specific implementation, at least one processor 1001 executes computer execution instructions stored in memory 1002, causing at least one processor 1001 to perform the above-described method.

[0264] The specific implementation process of processor 1001 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0265] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0266] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0267] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0268] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0269] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0270] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0271] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0272] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0273] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0274] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0275] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0276] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0277] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for prenatal fetal monitoring, comprising: Acquire multiple segments of monitoring data corresponding to multiple pregnant women within the current first time period, including fetal heart rate monitoring data and uterine contraction monitoring data; For each pregnant woman, a fetal heart rate baseline is determined based on the fetal heart rate monitoring data and a uterine contraction baseline is determined based on the uterine contraction monitoring data. Fetal heart characteristics are determined based on the fetal heart rate baseline and the fetal heart rate monitoring data, and uterine contraction characteristics are determined based on the uterine contraction baseline and the uterine contraction monitoring data; Predicting whether the fetus is abnormal based on the fetal heart rate characteristics, or predicting whether the fetus of the pregnant woman will develop abnormalities based on the fetal heart rate characteristics and the uterine contraction characteristics.

2. The method according to claim 1, characterized in that, Each pregnant woman has multiple data blocks, which are obtained by segmenting the monitoring data stream of that pregnant woman generated within the first time period according to a preset time length.

3. The method according to claim 1, characterized in that, For each pregnant woman, determining the fetal heart rate baseline based on the fetal heart rate monitoring data and determining the uterine contraction baseline based on the uterine contraction monitoring data includes: Obtain the monitoring task identifier corresponding to the pregnant woman, and determine the target task processing node in the distributed task processing node based on the monitoring task identifier; The pregnant woman's multiple data blocks are sent to the target task processing node, whereby the target task processing node is used to determine the fetal heart rate baseline, uterine contraction baseline, fetal heart rate characteristics, uterine contraction characteristics, and whether any fetal abnormalities have occurred based on the multiple data blocks.

4. The method according to claim 1, characterized in that, The determination of the fetal heart rate baseline based on the fetal heart rate monitoring data of the pregnant woman and the determination of the uterine contraction baseline based on the uterine contraction monitoring data include: The fetal heart rate monitoring data were filtered using an improved wavelet transform. If the filtered fetal heart rate monitoring data meets the first preset steady-state condition, the fetal heart rate baseline is determined based on the mean of the filtered fetal heart rate monitoring data; The uterine contraction data were filtered using an improved wavelet transform; If the filtered uterine contraction data meets the second preset steady-state condition, the uterine contraction baseline is determined based on the mean of the filtered uterine contraction monitoring data.

5. The method according to claim 4, characterized in that, The determination of the fetal heart rate baseline based on the fetal heart rate monitoring data of the pregnant woman and the determination of the uterine contraction baseline based on the uterine contraction monitoring data further include: If the filtered fetal heart rate monitoring data does not meet the first preset steady-state condition, it is determined that the fetal heart rate monitoring data in the multiple block monitoring data is in an abnormal fluctuation state and has no baseline. If the filtered uterine contraction monitoring data does not meet the second preset steady-state condition, it is determined that the uterine contraction monitoring data in the multiple segmented monitoring data is in an abnormal fluctuation state and has no baseline.

6. The method according to claim 1, characterized in that, The process of determining fetal heart characteristics based on the fetal heart rate baseline and the fetal heart rate monitoring data, and determining uterine contraction characteristics based on the uterine contraction baseline and the uterine contraction monitoring data, includes: The fetal heart rate monitoring data is filtered using an improved wavelet transform, and cardiac motion features, baseline variability features, and deceleration features are analyzed from the filtered fetal heart rate monitoring data. The uterine contraction monitoring data is filtered using an improved wavelet transform, and the uterine contraction morphology features and their relationship with uterine contractions are analyzed from the filtered uterine contraction monitoring data.

7. The method according to claim 6, characterized in that, The method of predicting whether the fetus is abnormal based on the fetal heart rate characteristics, or predicting whether the fetus of the pregnant woman is abnormal based on the fetal heart rate characteristics and the uterine contraction characteristics, includes: Based on the cardiac-related features and the baseline variability features, it is predicted whether the fetus will have any abnormalities, including cardiac-related abnormalities and baseline variability abnormalities.

8. The method according to claim 1, characterized in that, The method of predicting whether the fetus of the pregnant woman will have abnormalities based on the fetal heart rate characteristics and the uterine contraction characteristics includes: Predict whether deceleration anomalies have occurred based on deceleration characteristics; Determine whether a uterine contraction relationship exists based on the uterine contraction morphology characteristics corresponding to the multiple segmented monitoring data; In response to the occurrence of the aforementioned deceleration anomaly and the determination of the existence of the aforementioned uterine contraction relationship, it is determined whether it is a late deceleration anomaly based on the uterine contraction morphology and deceleration characteristics.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: In response to the detection of an anomaly, the anomaly information is displayed in the monitoring interface.

10. A prenatal fetal monitoring device, comprising: The acquisition unit is used to acquire multiple blocks of monitoring data corresponding to multiple pregnant women in the current first time period, including fetal heart rate monitoring data and uterine contraction monitoring data. The first determining unit is used to determine the fetal heart rate baseline and the uterine contraction baseline for each pregnant woman based on the fetal heart rate monitoring data of that pregnant woman. The second determining unit is used to determine fetal heart characteristics based on the fetal heart baseline and the fetal heart monitoring data, and to determine uterine contraction characteristics based on the uterine contraction baseline and the uterine contraction monitoring data. The prediction unit is used to predict whether the fetus is abnormal based on the fetal heart rate characteristics, or to predict whether the fetus of the pregnant woman is abnormal based on the fetal heart rate characteristics and the uterine contraction characteristics.

11. A prenatal fetal monitoring device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-8.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-8.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1-8.

Images