Night blood pressure monitoring method and system

Abstract

The invention provides a night blood pressure monitoring method and system, and the method comprises the steps: obtaining the pre-sleep collection data of a patient, the pulse monitoring information of the patient, and the respiration monitoring information of the patient, and recognizing the current physical state information of the patient based on the pre-sleep collection data of the patient; identifying blood pressure change distribution information of the user on the basis of the pulse monitoring information of the patient and the respiration monitoring information of the patient, and generating blood pressure prediction information of the patient through a blood pressure prediction network on the basis of the current physical state information of the patient and the blood pressure change distribution information of the patient; and on the basis of the blood pressure prediction information of the patient, identifying blood pressure abnormity information of the patient, and on the basis of the blood pressure abnormity information of the patient, generating a blood pressure abnormity monitoring report of the patient and blood pressure abnormity early warning information of the patient. By adopting the scheme, the blood pressure monitoring accuracy of the patient can be improved.

Description

Technical Field

[0001] This invention relates to the fields of artificial intelligence and smart medical technology, and in particular to a method and system for nighttime blood pressure monitoring. Background Technology

[0002] Human blood pressure follows a circadian rhythm, with nighttime blood pressure typically 10% to 20% lower than daytime blood pressure. This is a crucial mechanism for protecting arterial health. However, some individuals (especially the elderly, those with hypertension, or diabetes) may experience "non-dipper blood pressure" (a drop of less than 10% at night), known as nocturnal hypertension. This type of hypertension often presents with no obvious symptoms and is easily overlooked. However, compared to daytime blood pressure, nighttime blood pressure is actually more closely linked to fatal and non-fatal cardiovascular events (such as stroke, myocardial infarction, and cardiovascular death). Therefore, close monitoring of nighttime blood pressure is essential for detecting hidden blood pressure abnormalities, more accurately assessing a patient's blood pressure status, developing personalized treatment plans, and reducing the incidence of adverse events.

[0003] 24-hour ambulatory blood pressure monitoring is the gold standard for assessing nocturnal blood pressure, but the equipment is usually expensive and requires professional operation and interpretation of the results, which limits its widespread use in primary healthcare institutions. In addition, due to the large size and inconvenience of wearing the equipment, some patients may experience discomfort, especially at night while sleeping, which can affect sleep quality. Exercise, emotional fluctuations, and changes in diet can also affect the measurement results, leading to monitoring errors. Summary of the Invention

[0004] The main objective of this invention is to provide a method and system for nighttime blood pressure monitoring, which aims to solve the problem that existing technologies suffer from large errors in nighttime blood pressure monitoring due to limitations in equipment accessibility and the susceptibility of measurement results to external factors such as the subject's exercise, emotional fluctuations, dietary changes, and sleep quality during the monitoring period.

[0005] To achieve the above objectives, the present invention provides a method for nighttime blood pressure monitoring, the method comprising:

[0006] Acquire the patient's pre-sleep data, including the patient's pulse monitoring information and the patient's respiratory monitoring information, and identify the patient's current physical state information based on the pre-sleep data;

[0007] Based on the patient's pulse monitoring information and respiratory monitoring information, the blood pressure change distribution information of the user is identified, and based on the patient's current physical status information and the patient's blood pressure change distribution information, blood pressure prediction information of the patient is generated through a blood pressure prediction network;

[0008] Based on the patient's blood pressure prediction information, abnormal blood pressure information of the patient is identified, and based on the abnormal blood pressure information of the patient, a blood pressure abnormality monitoring report and a blood pressure abnormality early warning information of the patient are generated.

[0009] Optionally, identifying the patient's current physical state information based on the patient's pre-sleep data includes:

[0010] The data collected before sleep is broken down into monitoring data for each monitoring type;

[0011] Based on the monitoring data of each monitoring type, the patient's pre-sleep physical condition assessment value is identified through a physical condition evaluation strategy.

[0012] Based on the patient's pre-sleep physical condition assessment, the patient's current physical condition information is identified through a physical condition analysis strategy.

[0013] Optionally, identifying the user's blood pressure change distribution information based on the patient's pulse monitoring information and respiratory monitoring information includes:

[0014] Based on the patient's pulse monitoring information, identify the distribution information of the patient's pulse changes, and based on the patient's respiratory monitoring information, identify the distribution information of the patient's respiratory characteristic changes;

[0015] Based on the patient's pulse change distribution information and respiratory characteristic change distribution information, the patient's blood pressure change distribution information is identified through a blood pressure recognition model.

[0016] Optionally, the step of generating blood pressure prediction information for the patient based on the patient's current physical condition information and the patient's blood pressure change distribution information through a blood pressure prediction network includes:

[0017] Based on the patient's physical condition information, the parameters affecting the patient's blood pressure changes are identified, and the initial blood pressure prediction network is adjusted based on the parameters affecting the blood pressure changes to obtain the blood pressure prediction network.

[0018] Based on the blood pressure change distribution information, fit the blood pressure change distribution curve of the patient, and identify the blood pressure curve distribution characteristics of the blood pressure change distribution curve;

[0019] Based on the blood pressure curve distribution characteristics, the blood pressure curve change trend and the blood pressure curve range change trend are identified. Based on the blood pressure curve change trend and the blood pressure curve range change trend, the blood pressure prediction information of the patient is generated through the blood pressure prediction network.

[0020] Optionally, identifying abnormal blood pressure information in the patient based on the patient's predicted blood pressure information includes:

[0021] Based on the patient's predicted blood pressure information and the patient's blood pressure change distribution information, a blood pressure change distribution map of the patient during the target time period is generated;

[0022] Based on the blood pressure change distribution map, the abnormal blood pressure change data corresponding to each abnormal time period of the patient is identified through the blood pressure abnormality identification strategy. Based on the abnormal blood pressure change data corresponding to each abnormal time period, the abnormality type and abnormal blood pressure characteristic data corresponding to each abnormal time period are identified.

[0023] The abnormal type corresponding to each abnormal time period and the abnormal blood pressure characteristic data corresponding to each abnormal time period are used as the patient's blood pressure abnormality information.

[0024] Optionally, generating a blood pressure abnormality monitoring report and a blood pressure abnormality early warning information for the patient based on the patient's blood pressure abnormality information includes:

[0025] Based on the abnormal type corresponding to each abnormal time period and the abnormal blood pressure characteristic data corresponding to each abnormal time period, the abnormal level corresponding to each abnormal time period is identified through an abnormal level evaluation strategy.

[0026] Based on the abnormality level corresponding to each of the abnormal time periods, the risky abnormal time periods in each of the abnormal time periods are filtered out, and based on the abnormality level corresponding to each of the risky abnormal time periods, the blood pressure abnormality early warning strategy corresponding to each of the risky abnormal time periods is identified.

[0027] Based on the abnormality type and abnormal blood pressure characteristic data corresponding to each of the aforementioned abnormal risk periods, blood pressure warning information corresponding to each of the aforementioned abnormal risk periods is generated through a blood pressure abnormality warning strategy. The blood pressure warning information corresponding to each of the aforementioned abnormal risk periods is then used to conduct risk warning processing for medical staff according to the risk warning strategy.

[0028] Based on the abnormal type, abnormal blood pressure characteristic data, and abnormal level corresponding to each abnormal time period, a blood pressure abnormality monitoring report for the patient is generated using a preset blood pressure abnormality detection report template.

[0029] Furthermore, to achieve the above objectives, the present invention also provides a nighttime blood pressure monitoring system, the nighttime blood pressure monitoring system comprising:

[0030] The acquisition module is used to acquire the patient's pre-sleep data, the patient's pulse monitoring information, and the patient's respiratory monitoring information, and to identify the patient's current physical state information based on the pre-sleep data.

[0031] The identification module is used to identify the user's blood pressure change distribution information based on the patient's pulse monitoring information and the patient's respiratory monitoring information, and to generate the patient's blood pressure prediction information through a blood pressure prediction network based on the patient's current physical status information and the patient's blood pressure change distribution information.

[0032] The generation module is used to identify abnormal blood pressure information of the patient based on the patient's blood pressure prediction information, and generate a blood pressure abnormality monitoring report and a blood pressure abnormality early warning information of the patient based on the abnormal blood pressure information.

[0033] Optionally, the acquisition module is specifically used for:

[0034] The data collected before sleep is broken down into monitoring data for each monitoring type;

[0035] Based on the monitoring data of each monitoring type, the patient's pre-sleep physical condition assessment value is identified through a physical condition evaluation strategy.

[0036] Based on the patient's pre-sleep physical condition assessment, the patient's current physical condition information is identified through a physical condition analysis strategy.

[0037] Optionally, the identification module is specifically used for:

[0038] Based on the patient's pulse monitoring information, identify the distribution information of the patient's pulse changes, and based on the patient's respiratory monitoring information, identify the distribution information of the patient's respiratory characteristic changes;

[0039] Based on the patient's pulse change distribution information and respiratory characteristic change distribution information, the patient's blood pressure change distribution information is identified through a blood pressure recognition model.

[0040] Optionally, the identification module is specifically used for:

[0041] Based on the patient's physical condition information, the parameters affecting the patient's blood pressure changes are identified, and the initial blood pressure prediction network is adjusted based on the parameters affecting the blood pressure changes to obtain the blood pressure prediction network.

[0042] Based on the blood pressure change distribution information, fit the blood pressure change distribution curve of the patient, and identify the blood pressure curve distribution characteristics of the blood pressure change distribution curve;

[0043] Based on the blood pressure curve distribution characteristics, the blood pressure curve change trend and the blood pressure curve range change trend are identified. Based on the blood pressure curve change trend and the blood pressure curve range change trend, the blood pressure prediction information of the patient is generated through the blood pressure prediction network.

[0044] Optionally, the generation module is specifically used for:

[0045] Based on the patient's predicted blood pressure information and the patient's blood pressure change distribution information, a blood pressure change distribution map of the patient during the target time period is generated;

[0046] Based on the blood pressure change distribution map, the abnormal blood pressure change data corresponding to each abnormal time period of the patient is identified through the blood pressure abnormality identification strategy. Based on the abnormal blood pressure change data corresponding to each abnormal time period, the abnormality type and abnormal blood pressure characteristic data corresponding to each abnormal time period are identified.

[0047] The abnormal type corresponding to each abnormal time period and the abnormal blood pressure characteristic data corresponding to each abnormal time period are used as the patient's blood pressure abnormality information.

[0048] Optionally, the generation module is specifically used for:

[0049] Based on the abnormal type corresponding to each abnormal time period and the abnormal blood pressure characteristic data corresponding to each abnormal time period, the abnormal level corresponding to each abnormal time period is identified through an abnormal level evaluation strategy.

[0050] Based on the abnormality level corresponding to each of the abnormal time periods, the risky abnormal time periods in each of the abnormal time periods are filtered out, and based on the abnormality level corresponding to each of the risky abnormal time periods, the blood pressure abnormality early warning strategy corresponding to each of the risky abnormal time periods is identified.

[0051] Based on the abnormality type and abnormal blood pressure characteristic data corresponding to each of the aforementioned abnormal risk periods, blood pressure warning information corresponding to each of the aforementioned abnormal risk periods is generated through a blood pressure abnormality warning strategy. The blood pressure warning information corresponding to each of the aforementioned abnormal risk periods is then used to conduct risk warning processing for medical staff according to the risk warning strategy.

[0052] Based on the abnormal type, abnormal blood pressure characteristic data, and abnormal level corresponding to each abnormal time period, a blood pressure abnormality monitoring report for the patient is generated using a preset blood pressure abnormality detection report template.

[0053] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0054] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0055] Fifthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0056] This invention provides a method and system for nighttime blood pressure monitoring. The method includes: acquiring pre-sleep data of a patient, including the patient's pulse monitoring information and respiratory monitoring information; identifying the patient's current physical state information based on the pre-sleep data; identifying the patient's blood pressure variation distribution information based on the patient's pulse monitoring information and respiratory monitoring information; generating blood pressure prediction information for the patient through a blood pressure prediction network based on the patient's current physical state information; identifying abnormal blood pressure information based on the patient's blood pressure prediction information; and generating a blood pressure abnormality monitoring report and a blood pressure abnormality warning report based on the abnormal blood pressure information. This solution combines data collected before the patient's sleep, pulse monitoring information, and respiratory monitoring information to identify the distribution of blood pressure changes. It eliminates the need for complex blood pressure monitoring equipment; the user only needs to wear a wrist pulse monitoring bracelet and a breathing mask to monitor their blood pressure in real time at night, significantly reducing discomfort. Furthermore, this solution can combine the analyzed blood pressure distribution information to perform real-time blood pressure prediction, thereby predicting abnormal blood pressure information and generating a blood pressure abnormality monitoring report and early warning information. This achieves both real-time and accurate blood pressure monitoring and timely alerts and risk analysis for medical personnel, improving the efficiency and accuracy of identifying abnormal blood pressure, thus effectively enhancing the accuracy of blood pressure monitoring. Attached Figure Description

[0057] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a flowchart of the nighttime blood pressure monitoring method provided in an embodiment of the present invention;

[0059] Figure 2 This is a schematic diagram of the structure of the nighttime blood pressure monitoring system provided in an embodiment of the present invention;

[0060] Figure 3 An internal structural diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0061] The nighttime blood pressure monitoring method provided in this invention is applied to a nighttime blood pressure monitoring system. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application. The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or accompanying drawings of this application are used to distinguish different objects, not to describe a particular order.

[0062] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0063] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0064] The nighttime blood pressure monitoring method provided in this application embodiment can be applied to nighttime blood pressure monitoring environments. This method can be applied to a terminal, a server, or a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, etc. The terminal identifies the patient's blood pressure variation distribution information by combining data collected before the patient's sleep, pulse monitoring information, and respiratory monitoring information. It eliminates the need for complex blood pressure monitoring equipment; the user only needs to wear a wrist pulse monitoring bracelet and a breathing mask to monitor the user's blood pressure in real time at night, greatly reducing discomfort. Furthermore, this solution can combine the analyzed blood pressure variation distribution information to perform real-time blood pressure prediction, thereby predicting abnormal blood pressure information and generating a blood pressure abnormality monitoring report and a blood pressure abnormality warning. This achieves both real-time and accurate blood pressure monitoring and immediate abnormality warnings and risk analysis for medical personnel, improving the efficiency and accuracy of identifying abnormal blood pressure, thus effectively improving the accuracy of blood pressure monitoring.

[0065] In one embodiment, such as Figure 1 As shown, a method for monitoring blood pressure at night is provided. Taking the application of this method in a terminal as an example, the method includes the following steps:

[0066] Step S101: Obtain the patient's pre-sleep data, the patient's pulse monitoring information, and the patient's respiratory monitoring information, and identify the patient's current physical status information based on the pre-sleep data.

[0067] In this embodiment, the terminal responds to the information upload operation of the staff, acquiring the pre-sleep physical test data collected by the staff before the patient's sleep and the pre-sleep physical test data actively filled in by the patient, thus obtaining the patient's pre-sleep data. This pre-sleep data includes, but is not limited to, data on diet, physical activity, mood, and medication. Then, the terminal collects the patient's heart rate changes in real time during nighttime rest through a pulse monitoring bracelet worn by the patient, and collects the patient's breathing changes in real time during nighttime rest through a breathing mask worn over the patient's mouth. This breathing mask, similar in shape to a face mask, has an internal airflow sensor that can collect airflow changes during the patient's breathing process in real time without obstructing normal breathing. Finally, based on the patient's pre-sleep data, the terminal identifies the patient's current physical condition. The physical state information is used to characterize the patient's physical signs before sleep. This physical state information includes, for example, physical fatigue, physical health, physical illness, physical excitement, physical satiety, and physical hunger. Different physical states can affect the patient's blood pressure changes during rest, thus leading to abnormal nighttime blood pressure changes. Therefore, analyzing the user's physical state first helps to improve the accuracy of nighttime blood pressure changes.

[0068] Step S102: Based on the patient's pulse monitoring information and respiratory monitoring information, identify the user's blood pressure change distribution information, and based on the patient's current physical condition information, generate the patient's blood pressure prediction information through a blood pressure prediction network.

[0069] In this embodiment, the terminal identifies the user's blood pressure variation distribution information based on the patient's pulse and respiration monitoring information. Then, based on the patient's current physical condition information, it generates the patient's predicted blood pressure information through a blood pressure prediction network. The terminal presets a blood pressure fitting strategy to fit the patient's blood pressure information based on the pulse and respiration monitoring information. This allows the patient to obtain accurate blood pressure variation distribution information without wearing complex blood pressure monitoring devices. The specific fitting process of the blood pressure fitting strategy will be explained in detail later. This blood pressure prediction network is a deep learning-based convolutional neural network, which can fit the patient's future blood pressure variation information based on the linear relationship of blood pressure changes.

[0070] Step S103: Based on the patient's blood pressure prediction information, identify the patient's abnormal blood pressure information, and based on the patient's abnormal blood pressure information, generate the patient's abnormal blood pressure monitoring report and the patient's abnormal blood pressure warning information.

[0071] In this embodiment, the terminal identifies abnormal blood pressure information based on the patient's blood pressure prediction information, and generates a blood pressure abnormality monitoring report and a blood pressure abnormality warning information based on the abnormal blood pressure information. The abnormal blood pressure information includes the abnormal type corresponding to the abnormal time period and abnormal blood pressure characteristic data in the blood pressure prediction information. The abnormal type includes, but is not limited to, excessively high blood pressure, excessively low blood pressure, and abnormal blood pressure fluctuations.

[0072] Based on the above solution, by combining data collected before the patient's sleep, pulse monitoring information, and respiratory monitoring information, the distribution of the patient's blood pressure changes can be identified. No complex blood pressure monitoring equipment is required; only a wrist pulse monitoring bracelet and a breathing mask are needed for real-time monitoring of the user's blood pressure at night. Wearing discomfort is greatly reduced. Furthermore, this solution can combine the analyzed blood pressure distribution information to perform real-time blood pressure prediction, thereby predicting abnormal blood pressure information and generating a blood pressure abnormality monitoring report and early warning information. This achieves both real-time and accurate blood pressure monitoring and immediate alerts and risk analysis for medical personnel, improving the efficiency and accuracy of identifying abnormal blood pressure, thus effectively enhancing the accuracy of blood pressure monitoring.

[0073] Optionally, based on the patient's pre-sleep data, identify the patient's current physical status information, including: breaking down the pre-sleep data into monitoring data of various monitoring types; based on the monitoring data of each monitoring type, identifying the patient's pre-sleep physical status assessment value through a physical status evaluation strategy; and based on the patient's pre-sleep physical status assessment value, identifying the patient's current physical status information through a physical status analysis strategy.

[0074] In this embodiment, the terminal collects data before sleep and breaks it down into monitoring data of various monitoring types. These monitoring types include, but are not limited to, medication status monitoring, mood status monitoring, activity status monitoring, and dietary status monitoring. For example, the monitoring data for each monitoring type includes medication timeliness (whether medication was taken, whether it was taken on time, etc.) and mood status monitoring (calm, excitement, frustration, sadness, anger, happiness, joy, shame, fear, tension, etc.).

[0075] Then, based on the monitoring data from each monitoring type, the terminal identifies the patient's pre-sleep physical state assessment value through a physical state evaluation strategy. This strategy includes the data ranges for each monitoring type corresponding to different physical state assessment values. The terminal then uses range adaptation to identify the assessment value the patient might be in for each physical state, thus obtaining the pre-sleep physical state assessment value. Next, the terminal filters assessment values ​​exceeding a preset threshold from these values, identifying the corresponding physical state as the patient's current physical state information. Through this method, the patient may be in one or more physical states simultaneously; for example, the patient may be simultaneously in a state of hunger and a state of excitement.

[0076] Based on the above scheme, by comprehensively analyzing the patient's physical condition, one or more possible physical conditions of the patient can be identified, thereby improving the accuracy and comprehensiveness of identifying the patient's physical condition before sleep.

[0077] Optionally, based on the patient's pulse monitoring information and the patient's respiratory monitoring information, the user's blood pressure change distribution information is identified, including: based on the patient's pulse monitoring information, identifying the patient's pulse change distribution information, and based on the patient's respiratory monitoring information, identifying the patient's respiratory characteristic change distribution information; based on the patient's pulse change distribution information and the patient's respiratory characteristic change distribution information, the patient's blood pressure change distribution information is identified through a blood pressure recognition model.

[0078] In this embodiment, the terminal identifies the distribution information of the patient's pulse changes based on the patient's pulse monitoring information, and identifies the distribution information of the patient's respiratory characteristics based on the patient's respiratory monitoring information. The pulse change distribution information includes the pulse intensity, pulse rate, and duration of a single pulse, represented as a pulse change distribution map. The respiratory characteristic distribution information includes the patient's respiratory rate, airflow rate, and duration of a single breath, represented as a respiratory change distribution map.

[0079] Then, based on the patient's pulse and respiratory characteristic distribution information, the terminal identifies the patient's blood pressure distribution information using a blood pressure recognition model. The principle behind this blood pressure recognition model is to train a deep learning convolutional neural network using a large number of respiratory, pulse, and blood pressure change samples to obtain the correspondence between respiratory, pulse, and blood pressure changes. This allows the system to directly use the respiratory and pulse change distribution information as input data to identify the patient's blood pressure distribution information.

[0080] Based on the above scheme, by combining changes in respiration and pulse, the patient's blood pressure changes can be obtained. This reduces the cost of blood pressure monitoring, ensures the accuracy of blood pressure monitoring, and greatly improves the user experience.

[0081] Optionally, based on the patient's current physical condition information and the patient's blood pressure change distribution information, a blood pressure prediction network is used to generate the patient's blood pressure prediction information, including: identifying parameters affecting the patient's blood pressure changes based on the patient's physical condition information, and adjusting the initial blood pressure prediction network based on the parameters affecting the blood pressure changes to obtain the blood pressure prediction network; fitting the patient's blood pressure change distribution curve based on the blood pressure change distribution information, and identifying the blood pressure curve distribution characteristics; identifying the blood pressure curve change trend and the blood pressure curve range change trend based on the blood pressure curve distribution characteristics, and generating the patient's blood pressure prediction information through the blood pressure prediction network based on the blood pressure curve change trend and the blood pressure curve range change trend.

[0082] In this embodiment, the terminal identifies parameters affecting the patient's blood pressure changes based on the patient's physical condition information, and adjusts the initial blood pressure prediction network based on these parameters to obtain the blood pressure prediction network. Specifically, the terminal presets blood pressure change influence parameter values ​​corresponding to different physical condition information. Then, based on the patient's physical condition information, the terminal determines the corresponding blood pressure change influence parameter for that patient. When the patient is in one or more physical conditions, the terminal sums the blood pressure change influence parameter values ​​corresponding to different physical condition information to obtain the patient's corresponding blood pressure change influence parameter. Each blood pressure change influence parameter value corresponding to each physical condition information includes positive parameter values ​​and negative parameter values.

[0083] Then, based on the blood pressure change distribution information, the terminal fits the patient's blood pressure change distribution curve and identifies the blood pressure curve distribution characteristics. This feature recognition method uses a linear feature recognition network to identify information such as blood pressure change characteristics, blood pressure range change characteristics, and blood pressure trend characteristics.

[0084] Finally, based on the distribution characteristics of the blood pressure curve, the terminal identifies the trend of change in the blood pressure curve and the trend of change in the range of the blood pressure curve. Based on these trends, it generates the patient's blood pressure prediction information through a blood pressure prediction network. This blood pressure prediction network is a linear trend prediction neural network based on Holt's linear trend method.

[0085] Based on the above scheme, by combining the patient's physical condition information with the currently monitored blood pressure change distribution curve, the patient's blood pressure change distribution information can be predicted, thereby improving the accuracy of the prediction of the patient's blood pressure change distribution.

[0086] Optionally, based on the patient's blood pressure prediction information, identify the patient's abnormal blood pressure information, including: generating a blood pressure change distribution map of the patient during a target time period based on the patient's blood pressure prediction information and the patient's blood pressure change distribution information; based on the blood pressure change distribution map, identifying the abnormal blood pressure change data corresponding to each abnormal time period through a blood pressure abnormality identification strategy, and identifying the abnormal type and abnormal blood pressure feature data corresponding to each abnormal time period based on the abnormal blood pressure change data corresponding to each abnormal time period; and using the abnormal type and abnormal blood pressure feature data corresponding to each abnormal time period as the patient's abnormal blood pressure information.

[0087] In this embodiment, the terminal generates a blood pressure change distribution map of the patient during a target time period based on the patient's predicted blood pressure information and the patient's blood pressure change distribution information. The target time period is the time from the moment the patient falls asleep until the moment the patient wakes up.

[0088] Then, based on the blood pressure change distribution map, the terminal uses a blood pressure anomaly identification strategy to identify abnormal blood pressure change data corresponding to each abnormal time period. Based on this abnormal blood pressure change data, the terminal identifies the abnormal type and abnormal blood pressure characteristic data corresponding to each abnormal time period. The abnormal time period is defined as the time period in which the blood pressure change exceeds a certain threshold. When short-interval, discontinuous time periods exist, the abnormal time period is the total time period encompassing all short-interval, discontinuous time periods. For example, a short-interval, discontinuous time period is a time period where the interval between two or more time periods is less than one minute.

[0089] Finally, the terminal uses the abnormality type corresponding to each abnormal time period and the abnormal blood pressure characteristic data corresponding to each abnormal time period as the patient's blood pressure abnormality information.

[0090] Based on the above scheme, by splitting and identifying abnormal time periods, abnormal types, and abnormal blood pressure characteristic data in the blood pressure distribution chart, the accuracy and comprehensiveness of the analysis of abnormal blood pressure in patients are improved.

[0091] Optionally, based on the patient's abnormal blood pressure information, a blood pressure abnormality monitoring report and a blood pressure abnormality early warning information are generated, including: identifying the abnormal level corresponding to each abnormal time period based on the abnormality type and abnormal blood pressure characteristic data corresponding to each abnormal time period through an abnormality level evaluation strategy; filtering high-risk abnormal time periods within each abnormal time period based on the abnormal level corresponding to each abnormal time period, and identifying a blood pressure abnormality early warning strategy corresponding to each high-risk abnormal time period based on the abnormality level corresponding to each high-risk abnormal time period; generating blood pressure early warning information corresponding to each high-risk abnormal time period based on the abnormality type and abnormal blood pressure characteristic data corresponding to each high-risk abnormal time period through the blood pressure abnormality early warning strategy, and performing risk warning processing on medical staff according to the risk warning strategy; and generating a patient's blood pressure abnormality monitoring report based on the abnormality type, abnormal blood pressure characteristic data, and abnormal level corresponding to each abnormal time period through a preset blood pressure abnormality detection report template.

[0092] In this embodiment, the terminal identifies the abnormal level corresponding to each abnormal time period based on the abnormal type and abnormal blood pressure feature data corresponding to each abnormal time period through an abnormal level evaluation strategy. Specifically, different abnormal levels for each abnormal type correspond to a range of abnormal blood pressure feature data, and the terminal identifies the abnormal level corresponding to each abnormal time period through range adaptation.

[0093] The terminal filters out high-risk abnormal periods based on the abnormality level corresponding to each abnormal time period, and identifies the corresponding blood pressure abnormality warning strategy for each high-risk abnormal period based on the abnormality level corresponding to each high-risk abnormal period. High-risk abnormal periods are those corresponding to abnormal levels exceeding a preset level threshold. Each abnormality level corresponds to a blood pressure abnormality warning strategy. This blood pressure abnormality warning strategy includes, but is not limited to, warning signals (color, frequency, sound) and warning content (the patient risk corresponding to that abnormality level).

[0094] Then, based on the abnormality type and abnormal blood pressure characteristic data corresponding to each abnormal risk period, the terminal generates blood pressure warning information corresponding to each abnormal risk period through the blood pressure abnormality warning strategy for each abnormal risk period, and performs risk warning processing on medical staff according to the risk warning strategy.

[0095] Finally, based on the abnormality type, abnormal blood pressure characteristic data, and abnormality level corresponding to each abnormal time period, the terminal generates a blood pressure abnormality monitoring report for the patient using a preset blood pressure abnormality detection report template.

[0096] Based on the above scheme, by screening for risk warnings for different abnormal periods and generating blood pressure abnormality monitoring reports, it is possible to ensure accurate and comprehensive acquisition of all monitoring information of patients' blood pressure monitoring at night, and to provide real-time warnings to medical staff when patients' blood pressure is abnormal at night, so as to avoid life-threatening risks caused by sudden blood pressure abnormalities.

[0097] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0098] Based on the same inventive concept, this application also provides a nighttime blood pressure monitoring system for implementing the aforementioned nighttime blood pressure monitoring method. The solution provided by this system is similar to the implementation described in the above method; therefore, the specific limitations of the one or more nighttime blood pressure monitoring system embodiments provided below can be found in the limitations of the nighttime blood pressure monitoring method described above, and will not be repeated here.

[0099] Further reference Figure 2 As a response to the above Figure 1 The present application provides an embodiment of a nighttime blood pressure monitoring system 200, which includes an acquisition module 210, an identification module 220, and a generation module 230, wherein:

[0100] The acquisition module 210 is used to acquire the patient's pre-sleep data, the patient's pulse monitoring information, and the patient's respiratory monitoring information, and to identify the patient's current physical state information based on the pre-sleep data.

[0101] The identification module 220 is used to identify the user's blood pressure change distribution information based on the patient's pulse monitoring information and the patient's respiratory monitoring information, and to generate the patient's blood pressure prediction information through a blood pressure prediction network based on the patient's current physical status information and the patient's blood pressure change distribution information.

[0102] The generation module 230 is used to identify abnormal blood pressure information of the patient based on the patient's blood pressure prediction information, and generate a blood pressure abnormality monitoring report and a blood pressure abnormality early warning information of the patient based on the abnormal blood pressure information.

[0103] Optionally, the acquisition module 210 is specifically used for:

[0104] The data collected before sleep is broken down into monitoring data for each monitoring type;

[0105] Based on the monitoring data of each monitoring type, the patient's pre-sleep physical condition assessment value is identified through a physical condition evaluation strategy.

[0106] Based on the patient's pre-sleep physical condition assessment, the patient's current physical condition information is identified through a physical condition analysis strategy.

[0107] Optionally, the identification module 220 is specifically used for:

[0108] Based on the patient's pulse monitoring information, identify the distribution information of the patient's pulse changes, and based on the patient's respiratory monitoring information, identify the distribution information of the patient's respiratory characteristic changes;

[0109] Based on the patient's pulse change distribution information and respiratory characteristic change distribution information, the patient's blood pressure change distribution information is identified through a blood pressure recognition model.

[0110] Optionally, the identification module 220 is specifically used for:

[0111] Based on the patient's physical condition information, the parameters affecting the patient's blood pressure changes are identified, and the initial blood pressure prediction network is adjusted based on the parameters affecting the blood pressure changes to obtain the blood pressure prediction network.

[0112] Based on the blood pressure change distribution information, fit the blood pressure change distribution curve of the patient, and identify the blood pressure curve distribution characteristics of the blood pressure change distribution curve;

[0113] Based on the blood pressure curve distribution characteristics, the blood pressure curve change trend and the blood pressure curve range change trend are identified. Based on the blood pressure curve change trend and the blood pressure curve range change trend, the blood pressure prediction information of the patient is generated through the blood pressure prediction network.

[0114] Optionally, the generation module 230 is specifically used for:

[0115] Based on the patient's predicted blood pressure information and the patient's blood pressure change distribution information, a blood pressure change distribution map of the patient during the target time period is generated;

[0116] Based on the blood pressure change distribution map, the abnormal blood pressure change data corresponding to each abnormal time period of the patient is identified through the blood pressure abnormality identification strategy. Based on the abnormal blood pressure change data corresponding to each abnormal time period, the abnormality type and abnormal blood pressure characteristic data corresponding to each abnormal time period are identified.

[0117] The abnormal type corresponding to each abnormal time period and the abnormal blood pressure characteristic data corresponding to each abnormal time period are used as the patient's blood pressure abnormality information.

[0118] Optionally, the generation module 230 is specifically used for:

[0119] Based on the abnormal type corresponding to each abnormal time period and the abnormal blood pressure characteristic data corresponding to each abnormal time period, the abnormal level corresponding to each abnormal time period is identified through an abnormal level evaluation strategy.

[0120] Based on the abnormality level corresponding to each of the abnormal time periods, the risky abnormal time periods in each of the abnormal time periods are filtered out, and based on the abnormality level corresponding to each of the risky abnormal time periods, the blood pressure abnormality early warning strategy corresponding to each of the risky abnormal time periods is identified.

[0121] Based on the abnormality type and abnormal blood pressure characteristic data corresponding to each of the aforementioned abnormal risk periods, blood pressure warning information corresponding to each of the aforementioned abnormal risk periods is generated through a blood pressure abnormality warning strategy. The blood pressure warning information corresponding to each of the aforementioned abnormal risk periods is then used to conduct risk warning processing for medical staff according to the risk warning strategy.

[0122] Based on the abnormal type, abnormal blood pressure characteristic data, and abnormal level corresponding to each abnormal time period, a blood pressure abnormality monitoring report for the patient is generated using a preset blood pressure abnormality detection report template.

[0123] The modules in the aforementioned nighttime blood pressure monitoring system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0124] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown, the computer device includes a processor, memory, communication interface, display screen, and input system connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a nighttime blood pressure monitoring method. The display screen can be an LCD screen or an e-ink screen. The input system can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0125] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0126] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any one of the first aspects.

[0127] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0128] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0129] It should be noted that the patient information (including but not limited to patient device information, patient personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the patient or fully authorized by all parties.

[0130] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0131] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0132] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for monitoring blood pressure at night, characterized in that, The method includes: Acquire the patient's pre-sleep data, including the patient's pulse monitoring information and the patient's respiratory monitoring information, and identify the patient's current physical state information based on the pre-sleep data; Based on the patient's pulse monitoring information and respiratory monitoring information, the blood pressure change distribution information of the user is identified, and based on the patient's current physical status information and the patient's blood pressure change distribution information, blood pressure prediction information of the patient is generated through a blood pressure prediction network; Based on the patient's blood pressure prediction information, abnormal blood pressure information of the patient is identified, and based on the abnormal blood pressure information of the patient, a blood pressure abnormality monitoring report and a blood pressure abnormality early warning information of the patient are generated.

2. The method according to claim 1, characterized in that, The process of identifying the patient's current physical state information based on the patient's pre-sleep data includes: The data collected before sleep is broken down into monitoring data for each monitoring type; Based on the monitoring data of each monitoring type, the patient's pre-sleep physical condition assessment value is identified through a physical condition evaluation strategy. Based on the patient's pre-sleep physical condition assessment, the patient's current physical condition information is identified through a physical condition analysis strategy.

3. The method according to claim 1, characterized in that, The process of identifying the user's blood pressure variation distribution information based on the patient's pulse monitoring information and respiratory monitoring information includes: Based on the patient's pulse monitoring information, identify the distribution information of the patient's pulse changes, and based on the patient's respiratory monitoring information, identify the distribution information of the patient's respiratory characteristic changes; Based on the patient's pulse change distribution information and respiratory characteristic change distribution information, the patient's blood pressure change distribution information is identified through a blood pressure recognition model.

4. The method according to claim 1, characterized in that, The process of generating blood pressure prediction information for the patient based on the patient's current physical condition information and the patient's blood pressure change distribution information through a blood pressure prediction network includes: Based on the patient's physical condition information, the parameters affecting the patient's blood pressure changes are identified, and the initial blood pressure prediction network is adjusted based on the parameters affecting the blood pressure changes to obtain the blood pressure prediction network. Based on the blood pressure change distribution information, fit the blood pressure change distribution curve of the patient, and identify the blood pressure curve distribution characteristics of the blood pressure change distribution curve; Based on the blood pressure curve distribution characteristics, the blood pressure curve change trend and the blood pressure curve range change trend are identified. Based on the blood pressure curve change trend and the blood pressure curve range change trend, the blood pressure prediction information of the patient is generated through the blood pressure prediction network.

5. The method according to claim 1, characterized in that, The step of identifying abnormal blood pressure information in the patient based on the patient's predicted blood pressure information includes: Based on the patient's predicted blood pressure information and the patient's blood pressure change distribution information, a blood pressure change distribution map of the patient during the target time period is generated; Based on the blood pressure change distribution map, the abnormal blood pressure change data corresponding to each abnormal time period of the patient is identified through the blood pressure abnormality identification strategy. Based on the abnormal blood pressure change data corresponding to each abnormal time period, the abnormality type and abnormal blood pressure characteristic data corresponding to each abnormal time period are identified. The abnormal type corresponding to each abnormal time period and the abnormal blood pressure characteristic data corresponding to each abnormal time period are used as the patient's blood pressure abnormality information.

6. The method according to claim 5, characterized in that, The process of generating a blood pressure abnormality monitoring report and a blood pressure abnormality early warning information based on the patient's blood pressure abnormality information includes: Based on the abnormal type corresponding to each abnormal time period and the abnormal blood pressure characteristic data corresponding to each abnormal time period, the abnormal level corresponding to each abnormal time period is identified through an abnormal level evaluation strategy. Based on the abnormality level corresponding to each of the abnormal time periods, the risky abnormal time periods in each of the abnormal time periods are filtered out, and based on the abnormality level corresponding to each of the risky abnormal time periods, the blood pressure abnormality early warning strategy corresponding to each of the risky abnormal time periods is identified. Based on the abnormality type and abnormal blood pressure characteristic data corresponding to each of the aforementioned abnormal risk periods, blood pressure warning information corresponding to each of the aforementioned abnormal risk periods is generated through a blood pressure abnormality warning strategy. The blood pressure warning information corresponding to each of the aforementioned abnormal risk periods is then used to conduct risk warning processing for medical staff according to the risk warning strategy. Based on the abnormal type, abnormal blood pressure characteristic data, and abnormal level corresponding to each abnormal time period, a blood pressure abnormality monitoring report for the patient is generated using a preset blood pressure abnormality detection report template.

7. A nighttime blood pressure monitoring system, characterized in that, The system includes: The acquisition module is used to acquire the patient's pre-sleep data, the patient's pulse monitoring information, and the patient's respiratory monitoring information, and to identify the patient's current physical state information based on the pre-sleep data. The identification module is used to identify the user's blood pressure change distribution information based on the patient's pulse monitoring information and the patient's respiratory monitoring information, and to generate the patient's blood pressure prediction information through a blood pressure prediction network based on the patient's current physical status information and the patient's blood pressure change distribution information. The generation module is used to identify abnormal blood pressure information of the patient based on the patient's blood pressure prediction information, and generate a blood pressure abnormality monitoring report and a blood pressure abnormality early warning information of the patient based on the abnormal blood pressure information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images