Blood pressure interpretation processing method and device based on ambulatory blood pressure monitoring and related equipment

Abstract

The invention belongs to the field of medical health, provides a blood pressure interpretation processing method and device based on ambulatory blood pressure monitoring and related equipment, and aims to solve the problem of low interpretation efficiency of ambulatory blood pressure monitoring in the prior art. Predicting the blood pressure change trend, performing blood pressure anomaly detection, determining a corresponding health suggestion according to the blood pressure change trend and the blood pressure anomaly detection, and generating an ambulatory blood pressure monitoring report based on a preset visual display mode and according to the blood pressure change trend, the blood pressure anomaly detection and the health suggestion; according to the method, the blood pressure dynamic data corresponding to ambulatory blood pressure monitoring can be automatically analyzed, the accurate, comprehensive and readable interpretation report can be automatically generated, ambulatory blood pressure monitoring can be conveniently and effectively interpreted, the blood pressure monitoring efficiency and accuracy are improved, and the method is particularly suitable for being used in ambulatory blood pressure monitoring in a home nursing scene.

Description

Technical Field

[0001] The present application relates to the field of medical health, and in particular to a blood pressure interpretation and processing method, device, computer equipment and computer-readable storage medium based on dynamic blood pressure monitoring. Background Art

[0002] Traditional blood pressure monitoring methods mostly rely on manual measurement and recording, which is not only time-consuming and laborious, but also difficult to capture the natural fluctuations of blood pressure throughout the day. As a result, ambulatory blood pressure monitoring (ABPM) has emerged. Ambulatory blood pressure monitoring is a method used to assess a patient's blood pressure level during daily activities. It usually involves wearing a portable blood pressure recording device that automatically measures the patient's blood pressure at multiple predetermined time points throughout the day. This method is very useful for diagnosing white coat hypertension, concealed hypertension, and monitoring the effect of long-term blood pressure control.

[0003] Existing dynamic blood pressure monitoring devices and their supporting software systems are usually able to collect data automatically. However, although existing ABPM systems can achieve continuous monitoring, most devices can only simply record blood pressure values ​​and cannot automatically analyze these data and provide useful interpretations. They still rely mainly on doctors or professionals to interpret the data.

[0004] With the aging of the population and the rising incidence of chronic diseases, the demand for convenient and effective dynamic blood pressure monitoring is increasing. Therefore, how to conveniently and effectively interpret dynamic blood pressure monitoring has become a technical problem that needs to be urgently solved in blood pressure monitoring. Summary of the invention

[0005] The present application provides a blood pressure interpretation and processing method, device, computer equipment and computer-readable storage medium based on dynamic blood pressure monitoring, which can solve the technical problem of low efficiency in interpreting dynamic blood pressure monitoring in traditional technologies.

[0006] In the first aspect, the present application provides a blood pressure interpretation and processing method based on dynamic blood pressure monitoring, including: based on a preset wearable blood pressure monitoring device, collecting blood pressure dynamic data corresponding to dynamic blood pressure monitoring, and obtaining the blood pressure dynamic data; preprocessing the blood pressure dynamic data to obtain preprocessed blood pressure data; based on a preset feature extraction method, and based on the preprocessed blood pressure data, extracting target blood pressure features; based on a preset machine learning model, and based on the target blood pressure features, predicting the blood pressure change trend, and performing blood pressure abnormality detection to obtain blood pressure abnormality detection results; determining health advice based on the blood pressure change trend and the blood pressure abnormality detection results; based on a preset visual display method, and based on the blood pressure change trend, the blood pressure abnormality detection results and the health advice, generating a dynamic blood pressure monitoring report.

[0007] In the second aspect, the present application provides a blood pressure interpretation and processing device based on dynamic blood pressure monitoring, including: a first acquisition unit, used to collect blood pressure dynamic data corresponding to dynamic blood pressure monitoring based on a preset wearable blood pressure monitoring device, and obtain the blood pressure dynamic data; a data preprocessing unit, used to preprocess the blood pressure dynamic data to obtain preprocessed blood pressure data; a feature extraction unit, used to extract target blood pressure features based on a preset feature extraction method and according to the preprocessed blood pressure data; a second acquisition unit, used to predict blood pressure change trends based on a preset machine learning model and according to the target blood pressure features, and perform blood pressure abnormality detection to obtain blood pressure abnormality detection results; a first determination unit, used to determine health advice based on the blood pressure change trend and the blood pressure abnormality detection results; a first generation unit, used to generate a dynamic blood pressure monitoring report based on a preset visual display method and according to the blood pressure change trend, the blood pressure abnormality detection results and the health advice.

[0008] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the blood pressure interpretation and processing method based on dynamic blood pressure monitoring are implemented.

[0009] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor executes the steps of the blood pressure interpretation and processing method based on dynamic blood pressure monitoring.

[0010] The present application provides a blood pressure interpretation and processing method, device, computer equipment and computer-readable storage medium based on dynamic blood pressure monitoring. The method obtains blood pressure dynamic data, and extracts target blood pressure characteristics based on the pre-processed blood pressure dynamic data, and then predicts the blood pressure change trend based on a preset machine learning model, and performs blood pressure abnormality detection, and determines corresponding health recommendations based on the blood pressure change trend and blood pressure abnormality detection, and finally generates a dynamic blood pressure monitoring report based on a preset visual display method and according to the blood pressure change trend, blood pressure abnormality detection and health recommendations. The method can automatically analyze the blood pressure dynamic data corresponding to the dynamic blood pressure monitoring, and automatically generate an accurate, comprehensive and easy-to-read interpretation report, so as to realize convenient and effective interpretation of dynamic blood pressure monitoring, conveniently and effectively improve the efficiency and accuracy of blood pressure monitoring, and is particularly suitable for long-term management of dynamic blood pressure monitoring in home care scenarios in the medical and health field. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 A flow chart of a blood pressure interpretation and processing method based on dynamic blood pressure monitoring provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of a first sub-process of a blood pressure interpretation and processing method based on dynamic blood pressure monitoring provided in an embodiment of the present application;

[0014] Figure 3 A schematic diagram of a second sub-process of the blood pressure interpretation and processing method based on dynamic blood pressure monitoring provided in an embodiment of the present application;

[0015] Figure 4 A schematic block diagram of a blood pressure interpretation and processing device based on dynamic blood pressure monitoring provided in an embodiment of the present application;

[0016] Figure 5 A schematic block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0019] The embodiments of the present application provide a blood pressure interpretation and processing method based on dynamic blood pressure monitoring, which can be applied to computer devices including but not limited to wearable devices, smart phones, desktop computers, servers, cloud platforms, etc., and can be used in the long-term management of dynamic blood pressure monitoring in home care scenarios including but not limited to the medical and health fields.

[0020] Faced with the technical problem of low efficiency in interpreting dynamic blood pressure monitoring in traditional technologies, the inventors proposed a blood pressure interpretation and processing method based on dynamic blood pressure monitoring in an embodiment of the present application. The core idea of ​​the embodiment of the present application is: based on a wearable blood pressure monitoring device, continuously collect blood pressure dynamic data and obtain blood pressure dynamic data, and then process the blood pressure dynamic data based on the blood pressure dynamic data, and automatically generate an easy-to-understand interpretation report including but not limited to blood pressure trend charts, abnormal situation warnings, and recommended measures based on a machine learning model. Compared with the traditional ABPM system that can only simply record blood pressure values ​​and cannot automatically analyze these data and provide useful interpretations, the embodiment of the present application can automatically analyze the blood pressure dynamic data corresponding to dynamic blood pressure monitoring based on the background, and automatically generate an accurate, comprehensive, and easy-to-read interpretation report, which can conveniently and effectively interpret dynamic blood pressure monitoring, conveniently and effectively improve the efficiency and accuracy of blood pressure monitoring, and is particularly suitable for dynamic blood pressure monitoring in home care scenarios in the medical and health field.

[0021] Some embodiments of the present application are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0022] See also Figure 1 , Figure 1 The following is a flow chart of a blood pressure interpretation and processing method based on dynamic blood pressure monitoring provided in an embodiment of the present application. Figure 1 As shown, the method includes but is not limited to the following steps S11-S16:

[0023] S11. Based on a preset wearable blood pressure monitoring device, blood pressure dynamic data corresponding to dynamic blood pressure monitoring is collected, and the blood pressure dynamic data is obtained.

[0024] Explanatory note, a wearable blood pressure monitoring device refers to a blood pressure monitoring device based on wearable technology (WT). A wearable blood pressure monitoring device may be a wearable device with a blood pressure monitoring function. The wearable blood pressure monitoring device includes but is not limited to smart bracelets, smart watches, and portable or wearable dedicated blood pressure monitors.

[0025] Based on the preset wearable blood pressure monitoring device, ambulatory blood pressure monitoring (ABPM) is performed, the blood pressure dynamic data corresponding to the dynamic blood pressure monitoring is collected, and the blood pressure dynamic data is obtained. The blood pressure dynamic data represents the data of dynamic changes in blood pressure within a preset time period, such as the data of dynamic changes in blood pressure of the user within a preset time period such as 24 hours. The blood pressure dynamic data includes but is not limited to blood pressure-related indicators such as systolic pressure (high pressure), diastolic pressure (low pressure), and heart rate.

[0026] S12: pre-processing the blood pressure dynamic data to obtain pre-processed blood pressure data.

[0027] Explanatory speaking, data preprocessing refers to a series of processing performed on the collected raw blood pressure dynamic data before blood pressure dynamic data analysis in order to improve data quality. Data preprocessing includes data cleaning, data conversion, data integration, etc. The purpose is to remove irrelevant data, fill in missing values, smooth noise data, etc.

[0028] Based on the above conception and description, after obtaining the blood pressure dynamic data, the blood pressure dynamic data is cleaned, missing value filling, outlier detection, standardization and other operations are performed using the Pandas library in Python to obtain pre-processed blood pressure data to ensure the quality of the pre-processed blood pressure data, and then ensure the accuracy of subsequent blood pressure data analysis.

[0029] S13. Based on a preset feature extraction method and according to the preprocessed blood pressure data, extract target blood pressure features.

[0030] Explanatoryly, blood pressure characteristics, namely target blood pressure characteristics, are set in advance. The target blood pressure characteristics indicate what kind of blood pressure characteristics are extracted based on the preprocessed blood pressure data. The target blood pressure characteristics include but are not limited to the highest systolic pressure, the lowest diastolic pressure, the average systolic pressure, the average diastolic pressure, the standard deviation of blood pressure, the range of blood pressure, the characteristics of blood pressure changes over time, and the characteristics of the impact of circadian rhythm on blood pressure.

[0031] The pre-set feature extraction method is called the preset feature extraction method. The preset feature extraction method refers to a method for extracting different data features of pre-processed blood pressure data to obtain corresponding blood pressure features. The preset feature extraction method includes but is not limited to methods for statistics, calculation, extraction, analysis and processing of the above-mentioned pre-processed blood pressure data from different dimensions, so as to obtain corresponding target blood pressure features in different dimensions. The target blood pressure features include but are not limited to statistical blood pressure features, time series blood pressure features, and physiological blood pressure features.

[0032] Based on the above concepts and settings, based on the preset feature extraction method and according to the preprocessed blood pressure data, the target blood pressure characteristics are extracted. The target blood pressure characteristics include but are not limited to the statistical blood pressure characteristics corresponding to the mean systolic pressure, mean diastolic pressure, standard deviation of blood pressure, and range of blood pressure, the time series blood pressure characteristics corresponding to the characteristics of blood pressure changes over time, and the physiological blood pressure characteristics corresponding to the blood pressure characteristics manifested by the influence of circadian rhythm on blood pressure.

[0033] Exemplarily, key features of blood pressure data, such as mean systolic blood pressure, diastolic blood pressure, standard deviation of blood pressure, etc., are extracted through the Scikit-learn library, wherein the Scikit-learn library (i.e., scikits.learn, also known as sklearn) is a software machine learning library for the Python programming language, which has various classification, regression and clustering algorithms, including support vector machines, random forests, and gradient boosting.

[0034] S14. Based on a preset machine learning model and according to the target blood pressure characteristics, the blood pressure change trend is predicted, and blood pressure abnormality detection is performed to obtain blood pressure abnormality detection results.

[0035] Explanativily, a machine learning model is pre-set, i.e., a preset machine learning model. The preset machine learning model represents an instance algorithm for predicting blood pressure changes and detecting blood pressure anomalies. An algorithm is a series of instructions or rules for solving a problem, which can be a precise mathematical formula or a strategy for solving a problem. A neural network can be regarded as a special algorithm, and a neural network can express many other algorithms. The preset machine learning model selects appropriate algorithms including but not limited to support vector machines (SVM), random forests (RF) or neural networks (NN), and the preset machine learning model can be developed and trained using deep learning frameworks including but not limited to TensorFlow and PyTorch. The deep learning framework defines the specific structure and connection method of the neural network.

[0036] According to the above conception and setting, based on the preset machine learning model and according to the target blood pressure characteristics, the blood pressure change trend is predicted. The predicted blood pressure change trend represents the change trend of blood pressure fluctuations estimated based on the historical blood pressure data. The blood pressure change trend includes a trend of high blood pressure, a trend of low blood pressure, and normal and stable blood pressure. Blood pressure abnormality detection is performed to obtain blood pressure abnormality detection results. The blood pressure abnormality detection results include normal blood pressure detection and abnormal blood pressure detection. Among them, when the preset machine learning model is used to predict the blood pressure change trend, algorithms based on time series analysis technology corresponding to the ARIMA model and LSTM neural network can be used to predict the blood pressure change trend. Time series analysis is a method for studying time series data. It predicts future numerical changes by analyzing and modeling past observations. When the preset machine learning model is used for blood pressure abnormality detection, it can be used, but not limited to, to identify abnormal blood pressure characteristics by setting thresholds and using anomaly detection algorithms. The anomaly detection algorithms include but are not limited to random forest algorithm (IsolationForest) and local outlier factor algorithm (Local Outlier Factor, LOF).

[0037] S15. Determine health advice based on the blood pressure change trend and the abnormal blood pressure detection result.

[0038] Explanatory, health advice is determined based on the blood pressure change trend and the abnormal blood pressure detection result, and the health advice includes lifestyle advice, medical advice, and observation advice. For example, when the blood pressure change trend is normal and stable or the blood pressure abnormality detection result is normal, the user can maintain the previous lifestyle. Otherwise, according to the degree of blood pressure change trend or the severity of the blood pressure abnormality, the user is advised to adjust the previous lifestyle or seek medical treatment, thereby providing personalized advice to the user based on the analysis results of dynamic blood pressure monitoring, which can realize convenient and effective interpretation of dynamic blood pressure monitoring.

[0039] S16. Generate a dynamic blood pressure monitoring report based on a preset visual display method and according to the blood pressure change trend, the abnormal blood pressure detection result and the health advice.

[0040] Explanatory, pre-set visualization mode, that is, preset visualization mode, visualization means using computer graphics and image processing technology to convert data into graphics or images and display them on the screen, and perform interactive processing. It displays data and information through visual elements (such as charts and graphs), making complex data intuitive and easy to understand, and helping people better understand the patterns, trends and correlations behind the data. Preset visualization display methods include but are not limited to images, charts, and highlights.

[0041] According to the above concepts and settings, based on the preset visual display method, and according to the blood pressure change trend, blood pressure abnormality detection results and health advice, a dynamic blood pressure monitoring report is generated. For example, the blood pressure change trend is displayed in the form of a chart in the dynamic blood pressure monitoring report. When the blood pressure abnormality detection result is abnormal blood pressure, the blood pressure abnormality corresponding to the blood pressure abnormality detection result is displayed in bold red in the dynamic blood pressure monitoring report, and the health advice is displayed in green in the dynamic blood pressure monitoring report.

[0042] In addition, after the dynamic blood pressure monitoring report is generated, the dynamic blood pressure monitoring report can also be provided to the terminals corresponding to doctors and other relevant personnel through mobile applications, web interfaces or other forms. When the dynamic blood pressure monitoring report is generated based on a cloud platform, the dynamic blood pressure monitoring report can also be provided to the terminals corresponding to the patients, including but not limited to wearable devices, through mobile applications, web interfaces or other forms.

[0043] In the embodiment of the present application, by acquiring blood pressure dynamic data and extracting target blood pressure characteristics based on the preprocessed blood pressure dynamic data, the blood pressure change trend is predicted based on a preset machine learning model, and blood pressure abnormality detection is performed. Based on the blood pressure change trend and blood pressure abnormality detection, corresponding health recommendations are determined. Finally, based on a preset visual display method, and based on the blood pressure change trend, blood pressure abnormality detection and health recommendations, a dynamic blood pressure monitoring report is generated. The blood pressure dynamic data corresponding to the dynamic blood pressure monitoring can be automatically analyzed, and an accurate, comprehensive and easy-to-read interpretation report can be automatically generated, so as to realize convenient and effective interpretation of dynamic blood pressure monitoring, conveniently and effectively improve the efficiency and accuracy of blood pressure monitoring, and is particularly suitable for dynamic blood pressure monitoring in home care scenarios in the medical and health field.

[0044] In one embodiment, based on a preset feature extraction method and according to the preprocessed blood pressure data, extracting a target blood pressure feature includes at least one of the following:

[0045] Based on a preset feature statistical method, the pre-processed blood pressure data is statistically analyzed to obtain statistical blood pressure features included in the target blood pressure features;

[0046] Based on a preset time series analysis method, extracting the characteristics of blood pressure changes over time corresponding to the preprocessed blood pressure data, and obtaining the time series blood pressure characteristics included in the target blood pressure characteristics;

[0047] Based on a preset physiological feature extraction method, the physiological blood pressure features corresponding to the preprocessed blood pressure data are extracted to obtain the physiological blood pressure features included in the target blood pressure features.

[0048] Explanatoryly, a pre-set feature statistical method, i.e., a preset feature statistical method, represents a blood pressure feature obtained based on a statistical method. The preset feature statistical method includes but is not limited to the mean method, the standard deviation method, and the range method. The corresponding blood pressure features include but are not limited to the mean systolic pressure, the mean diastolic pressure, the standard deviation of blood pressure, and the range of blood pressure.

[0049] A time series analysis method is set in advance, that is, a preset time series analysis method. The preset time series analysis method represents a preprocessed blood pressure data analysis method based on time series analysis technology. The time series analysis technology includes but is not limited to a sliding window method and a neural network method for time series prediction. The corresponding blood pressure feature can be called a time series blood pressure feature. The time series blood pressure feature represents the characteristics of blood pressure changes over time extracted from the preprocessed blood pressure data.

[0050] The physiological feature extraction method is pre-set, that is, the preset physiological feature extraction method. The preset physiological feature extraction method refers to the extraction method corresponding to the feature defined by physiological knowledge. The feature defined by physiological knowledge can be called physiological blood pressure feature. The physiological blood pressure feature includes but is not limited to the blood pressure feature corresponding to the influence of circadian rhythm on blood pressure.

[0051] According to the above concepts and settings, based on the preset feature statistical method, the preprocessed blood pressure data is statistically processed to obtain the statistical blood pressure characteristics included in the target blood pressure characteristics. For example, multiple statistical characteristics corresponding to the mean systolic pressure, mean diastolic pressure, standard deviation of blood pressure, and range of blood pressure are extracted from the preprocessed blood pressure data.

[0052] Based on a preset time series analysis method, the characteristics of blood pressure changes over time corresponding to the preprocessed blood pressure data are extracted to obtain the time series blood pressure characteristics included in the target blood pressure characteristics. For example, a preset time series analysis technique, such as a sliding window method, is applied to extract the characteristics of blood pressure changes over time to obtain the corresponding time series blood pressure characteristics.

[0053] Based on a preset physiological feature extraction method, the physiological-based blood pressure features corresponding to the preprocessed blood pressure data are extracted to obtain the physiological blood pressure features included in the target blood pressure features. For example, physiological knowledge is used to define features corresponding to the effects of circadian rhythm on blood pressure, including but not limited to, to obtain corresponding physiological blood pressure features.

[0054] The embodiment of the present application, by extracting the statistical blood pressure characteristics, time series blood pressure characteristics, and physiological blood pressure characteristics contained in the blood pressure dynamic data, can conduct an in-depth analysis of the blood pressure fluctuations corresponding to the dynamic blood pressure from different dimensions, and then generate a corresponding dynamic blood pressure monitoring report based on the statistical blood pressure characteristics, time series blood pressure characteristics, and physiological blood pressure characteristics included in the target blood pressure characteristics, which can further improve the accuracy and efficiency of dynamic blood pressure monitoring.

[0055] In one embodiment, based on a preset visual display mode and according to the blood pressure change trend, the abnormal blood pressure detection result and the health advice, a dynamic blood pressure monitoring report is generated, including:

[0056] Based on a preset chart format, the blood pressure change trend is displayed in the dynamic blood pressure monitoring report.

[0057] Explanatory note, a pre-set chart form, i.e., a preset chart form, represents a specific form of displaying data and information in a graphical manner. The preset chart form includes but is not limited to a scatter chart, a column chart, a bar chart, a line chart, a surface chart, and a radar chart.

[0058] According to the above concept and setting, based on the preset visual display mode, and according to the blood pressure change trend, blood pressure abnormality detection results and health recommendations, when generating a dynamic blood pressure monitoring report, the blood pressure change trend is displayed based on a preset chart form, such as a line chart, to obtain a blood pressure change trend chart, that is, a chart is used to display the predicted blood pressure change trend, and it is included in the dynamic blood pressure monitoring report, that is, the dynamic blood pressure monitoring report includes a blood pressure change trend chart

[0059] The embodiment of the present application automatically uses charts to display the blood pressure change trend and then generates a dynamic blood pressure monitoring report. This allows relevant personnel to easily view and understand the blood pressure monitoring results in an intuitive manner, thereby improving the readability of the dynamic blood pressure monitoring report and achieving convenient and effective interpretation of dynamic blood pressure monitoring. This conveniently and effectively improves the efficiency and accuracy of blood pressure monitoring and is particularly suitable for long-term management of dynamic blood pressure monitoring in home care scenarios in the medical and health field.

[0060] See also Figure 2 , Figure 2 This is a schematic diagram of the first sub-process of the blood pressure interpretation and processing method based on dynamic blood pressure monitoring provided in the embodiment of the present application. Figure 2 As shown, in this embodiment, based on the preset machine learning model and according to the target blood pressure characteristics, the blood pressure change trend is predicted, and blood pressure abnormality detection is performed to obtain the blood pressure abnormality detection result, including:

[0061] S21. Predicting a blood pressure change trend based on a preset blood pressure prediction model included in a preset machine learning model and according to the target blood pressure characteristics;

[0062] S22. Based on the preset blood pressure abnormality detection algorithm included in the preset machine learning model and according to the target blood pressure characteristics, perform blood pressure abnormality detection to obtain a blood pressure abnormality detection result.

[0063] Explanatoryly, a blood pressure prediction model is pre-set, i.e., a preset blood pressure prediction model, and the preset blood pressure prediction model is included in the preset machine learning model, i.e., the preset blood pressure prediction model is a subset or component of the preset machine learning model. The preset blood pressure prediction model represents a model for estimating future blood pressure values ​​based on historical blood pressure data corresponding to dynamic blood pressure monitoring. The preset blood pressure prediction model represents a model for predicting blood pressure change trends based on time series analysis technology. The preset blood pressure prediction model includes but is not limited to ARIMA model and LSTM neural network.

[0064] A blood pressure anomaly detection algorithm is pre-set, that is, a preset blood pressure anomaly detection algorithm, and the preset blood pressure anomaly detection algorithm is included in a preset machine learning model, that is, the preset blood pressure anomaly detection algorithm is a subset or component of the preset machine learning model. The preset blood pressure anomaly detection algorithm means that abnormal blood pressure data that is inconsistent with the target blood pressure data distribution is discovered through data mining methods. It can also be called outlier blood pressure point or abnormal blood pressure value detection. The preset blood pressure anomaly detection algorithm includes but is not limited to random forest (Isolation Forest), local outlier factor algorithm (Local Outlier Factor, LOF), and long short-term memory network (LSTM).

[0065] In summary, the preset machine learning model can not only predict the trend of blood pressure changes, but also detect blood pressure abnormalities.

[0066] According to the above-mentioned conception and setting, based on the preset blood pressure prediction model contained in the preset machine learning model, and according to the target blood pressure characteristics, the blood pressure change trend is predicted, so that the future blood pressure trend is predicted by analyzing the historical blood pressure data, and the blood pressure change trend prediction is realized, and multi-dimensional dynamic blood pressure monitoring is realized. Based on the preset blood pressure abnormality detection algorithm contained in the preset machine learning model, and according to the target blood pressure characteristics, blood pressure abnormality detection is performed to obtain blood pressure abnormality detection results, thereby automatically identifying blood pressure values ​​beyond the normal range, and then realizing a comprehensive and easy-to-read dynamic blood pressure monitoring interpretation.

[0067] In the embodiment of the present application, a preset blood pressure prediction model included in a preset machine learning model is used to predict the blood pressure change trend according to the target blood pressure characteristics, and a preset blood pressure abnormality detection algorithm is used to perform blood pressure abnormality detection according to the target blood pressure characteristics to obtain a blood pressure abnormality detection result. The blood pressure fluctuations corresponding to the dynamic blood pressure can be evaluated from different dimensions, and then a corresponding dynamic blood pressure monitoring report can be generated, which can further improve the accuracy and efficiency of dynamic blood pressure monitoring.

[0068] In one embodiment, the abnormal blood pressure detection result is abnormal blood pressure; and a dynamic blood pressure monitoring report is generated according to the blood pressure change trend, the abnormal blood pressure detection result and the health advice, including:

[0069] Generating a blood pressure abnormality warning according to the blood pressure abnormality;

[0070] The abnormal blood pressure warning is included in the dynamic blood pressure monitoring report.

[0071] Explanatory note, when the abnormal blood pressure detection result is abnormal blood pressure, it indicates that the abnormal blood pressure exceeds the corresponding preset indicator threshold, that is, the degree of blood pressure abnormality has reached a certain degree. At this time, based on the abnormal blood pressure, an abnormal blood pressure warning is generated. The abnormal blood pressure warning indicates an advance warning of abnormal blood pressure. At this time, although the disease has not occurred, there is a great risk of developing a blood pressure disease. The abnormal blood pressure warning is included in the dynamic blood pressure monitoring report to remind relevant personnel of the blood pressure risk corresponding to the dynamic blood pressure monitoring, especially for the abnormal blood pressure warning, to carry out timely intervention, such as adjusting lifestyle, seeking medical treatment, etc., to prevent the abnormal blood pressure from becoming more serious and causing blood pressure diseases.

[0072] In the embodiment of the present application, when the abnormal blood pressure detection result is abnormal blood pressure, an abnormal blood pressure warning is automatically generated in the dynamic blood pressure monitoring report, thereby automatically generating an easy-to-read interpretation report corresponding to the dynamic blood pressure monitoring, so that relevant personnel can be aware of the abnormal blood pressure situation in time, and the dynamic blood pressure monitoring can be interpreted conveniently and effectively, thereby conveniently and effectively improving the efficiency and accuracy of blood pressure monitoring, and is particularly suitable for long-term management of dynamic blood pressure monitoring in home care scenarios in the medical and health field.

[0073] In one embodiment, based on a preset visual display mode and according to the blood pressure change trend, the abnormal blood pressure detection result and the health advice, a dynamic blood pressure monitoring report is generated, including:

[0074] Based on a preset differentiated display method, the blood pressure change trend, the abnormal blood pressure warning and the health advice are displayed differently.

[0075] Explanatoryly, the pre-set differentiated display mode is called the preset differentiated display mode. The preset differentiated display mode means that different display modes are used to display the different parts of the content contained in the dynamic blood pressure monitoring report. The preset differentiated display mode includes but is not limited to display styles such as font color, font size, font format, as well as display forms such as text and charts.

[0076] According to the above concepts and settings, based on the preset differentiated display methods, blood pressure change trends, abnormal blood pressure warnings and health recommendations are displayed differently using different display methods, thereby achieving diversity and key points in the dynamic blood pressure monitoring report display, which can further improve the readability and intuitiveness of the dynamic blood pressure monitoring report, especially when the abnormal blood pressure detection result is abnormal blood pressure, it can improve the warning effect and efficiency of the abnormal blood pressure warning.

[0077] The embodiment of the present application highlights the blood pressure change trend, abnormal blood pressure warning and health advice based on a preset differentiated display method, which can further improve the readability and intuitive effect of the dynamic blood pressure monitoring report on the basis of accurate, comprehensive and easy-to-read dynamic blood pressure monitoring report content, and improve the warning effect of abnormal blood pressure warning, and can further improve the convenient and effective interpretation effect of dynamic blood pressure monitoring, thereby conveniently and effectively improving the efficiency and accuracy of blood pressure monitoring, and is particularly suitable for long-term management of dynamic blood pressure monitoring in home care scenarios in the medical and health field.

[0078] See also Figure 3 , Figure 3 This is a schematic diagram of a second sub-process of the blood pressure interpretation and processing method based on dynamic blood pressure monitoring provided in an embodiment of the present application. Figure 3 As shown, in this embodiment, determining health advice according to the blood pressure change trend and the abnormal blood pressure detection result includes:

[0079] S31, obtaining the user's preset historical daily behavior information data;

[0080] S32. Determine lifestyle recommendations based on a preset health recommendation model and according to the blood pressure change trend, the abnormal blood pressure detection result, and the preset historical daily behavior information data.

[0081] Explanatoryly, a pre-set health advice model is referred to as a preset health advice model. The preset health advice model refers to a recommendation model for making corresponding health advice based on input information such as blood pressure change trends, abnormal blood pressure detection results, historical daily behavior information data, etc. The preset health advice model includes but is not limited to deep learning models such as the DeepFM model, and large-scale pre-trained models such as BERT and GPT.

[0082] According to the above concept and arrangement, when determining health advice according to the blood pressure change trend and the blood pressure abnormality detection result, the user's preset historical daily behavior information data is obtained, and the preset historical daily behavior information data includes but is not limited to exercise information and sleep information. The preset historical daily behavior information data can be collected by a smart terminal including but not limited to a smart bracelet and a smart watch. In particular, when dynamic blood pressure monitoring is performed based on the above smart terminal, the corresponding preset historical daily behavior information data can be collected at the same time, and then based on the preset health advice model, and according to the blood pressure change trend, the blood pressure abnormality detection result, and the preset historical daily behavior information data, the lifestyle advice is determined. For example, when the blood pressure change trend is normal and stable or the blood pressure abnormality detection result is normal, the user can maintain the past lifestyle. It can also be determined according to the preset historical daily behavior information data that the user has a small amount of exercise and poor sleep. The user is advised to ensure an appropriate amount of exercise and sufficient sleep. Otherwise, according to the degree of the blood pressure change trend, the severity of the blood pressure abnormality or the situation that the historical daily behavior is not good enough, the user is advised to adjust the past lifestyle or seek medical treatment, so as to provide the user with personalized comprehensive advice based on the analysis results of dynamic blood pressure monitoring, so as to realize convenient and effective interpretation of dynamic blood pressure monitoring.

[0083] The embodiment of the present application combines the user's preset historical daily behavior information data and, based on a preset health advice model, determines lifestyle advice based on blood pressure change trends, abnormal blood pressure detection results, and preset historical daily behavior information data, and then automatically generates an accurate, comprehensive, and easy-to-read interpretation report, which can conveniently and effectively interpret dynamic blood pressure monitoring, conveniently and effectively improve the efficiency and accuracy of blood pressure monitoring, and is particularly suitable for long-term management of dynamic blood pressure monitoring in home care scenarios in the medical and health field.

[0084] It should be noted that the blood pressure interpretation and processing methods based on dynamic blood pressure monitoring described in the above embodiments can recombine the technical features contained in different embodiments as needed to obtain a combined implementation plan, but they are all within the scope of protection required by this application.

[0085] See also Figure 4 , Figure 4 This is a schematic block diagram of a blood pressure interpretation and processing device based on dynamic blood pressure monitoring provided in an embodiment of the present application. Corresponding to the above-mentioned blood pressure interpretation and processing method based on dynamic blood pressure monitoring, an embodiment of the present application also provides a blood pressure interpretation and processing device based on dynamic blood pressure monitoring. Figure 4As shown, the blood pressure interpretation and processing device based on dynamic blood pressure monitoring includes a unit for executing the blood pressure interpretation and processing method based on dynamic blood pressure monitoring. The blood pressure interpretation and processing device based on dynamic blood pressure monitoring can be configured in a computer device including but not limited to a wearable blood pressure monitoring device, a smart phone, a server, and a cloud platform. Specifically, please refer to Figure 4 The blood pressure interpretation and processing device 40 based on dynamic blood pressure monitoring includes a first acquisition unit 41, a data preprocessing unit 42, a feature extraction unit 43, a second acquisition unit 44, a first determination unit 45 and a first generation unit 46.

[0086] The first acquisition unit 41 is used to collect blood pressure dynamic data corresponding to dynamic blood pressure monitoring based on a preset wearable blood pressure monitoring device, and acquire the blood pressure dynamic data;

[0087] A data preprocessing unit 42, used for preprocessing the blood pressure dynamic data to obtain preprocessed blood pressure data;

[0088] A feature extraction unit 43, configured to extract target blood pressure features based on a preset feature extraction method and according to the preprocessed blood pressure data;

[0089] A second acquisition unit 44 is used to predict the blood pressure change trend based on a preset machine learning model and according to the target blood pressure characteristics, and perform blood pressure abnormality detection to obtain a blood pressure abnormality detection result;

[0090] A first determining unit 45 is used to determine health advice according to the blood pressure change trend and the abnormal blood pressure detection result;

[0091] The first generating unit 46 is used to generate a dynamic blood pressure monitoring report based on a preset visual display mode and according to the blood pressure change trend, the blood pressure abnormality detection result and the health advice.

[0092] In one embodiment, the feature extraction unit 43 includes at least one of the following subunits:

[0093] A statistical subunit, configured to statistically analyze the preprocessed blood pressure data based on a preset characteristic statistical method to obtain statistical blood pressure characteristics included in the target blood pressure characteristics;

[0094] A first extraction subunit is used to extract the characteristics of blood pressure changes over time corresponding to the pre-processed blood pressure data based on a preset time series analysis method, and obtain the time series blood pressure characteristics included in the target blood pressure characteristics;

[0095] The second extraction subunit is used to extract the physiological blood pressure characteristics corresponding to the preprocessed blood pressure data based on a preset physiological characteristic extraction method, and obtain the physiological blood pressure characteristics included in the target blood pressure characteristics.

[0096] In one embodiment, the first generating unit 46 is specifically configured to display the blood pressure change trend in the dynamic blood pressure monitoring report based on a preset chart format.

[0097] In one embodiment, the second obtaining unit 44 includes:

[0098] A prediction subunit, configured to predict a blood pressure change trend based on a preset blood pressure prediction model included in a preset machine learning model and according to the target blood pressure characteristics;

[0099] The detection subunit is used to perform blood pressure abnormality detection based on a preset blood pressure abnormality detection algorithm included in a preset machine learning model and according to the target blood pressure characteristics to obtain a blood pressure abnormality detection result.

[0100] In one embodiment, the abnormal blood pressure detection result is abnormal blood pressure; the first generating unit 46 includes:

[0101] A generating subunit, configured to generate an abnormal blood pressure warning according to the abnormal blood pressure;

[0102] A subunit is included, which is used to include the abnormal blood pressure warning into the dynamic blood pressure monitoring report.

[0103] In one embodiment, the first generating unit 46 is specifically configured to display the blood pressure change trend, the abnormal blood pressure warning and the health advice differently based on a preset differentiated display method.

[0104] In one embodiment, the first determining unit 45 includes:

[0105] The acquisition subunit is used to acquire the user's preset historical daily behavior information data;

[0106] The determination subunit is used to determine lifestyle recommendations based on a preset health recommendation model and according to the blood pressure change trend, the blood pressure abnormality detection result, and the preset historical daily behavior information data.

[0107] It should be noted that technical personnel in the relevant field can clearly understand that the specific implementation process of the above-mentioned blood pressure interpretation and processing device based on dynamic blood pressure monitoring and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0108] At the same time, the division and connection method of each unit in the above-mentioned blood pressure interpretation and processing device based on dynamic blood pressure monitoring is only for illustrative purposes. In other embodiments, the blood pressure interpretation and processing device based on dynamic blood pressure monitoring can be divided into different units as needed, and each unit in the blood pressure interpretation and processing device based on dynamic blood pressure monitoring can also adopt a different connection sequence and method to complete all or part of the functions of the above-mentioned blood pressure interpretation and processing device based on dynamic blood pressure monitoring.

[0109] The blood pressure interpretation and processing device based on dynamic blood pressure monitoring can be implemented in the form of a computer program. The computer program can be used in a computer program such as Figure 5 Runs on the computer device shown.

[0110] See also Figure 5 , Figure 5 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a computer device such as a desktop computer or a server, or may be a component or part in other devices.

[0111] See also Figure 5 The computer device 500 includes a processor 502, a memory and a network interface 505 connected via a system bus 501, wherein the memory may include a non-volatile storage medium 503 and an internal memory 504, and the memory may also be a volatile storage medium.

[0112] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute the above-mentioned blood pressure interpretation and processing method based on dynamic blood pressure monitoring.

[0113] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0114] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the above-mentioned blood pressure interpretation and processing method based on dynamic blood pressure monitoring.

[0115] The network interface 505 is used to communicate with other devices over the network. Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the present application scheme, and does not constitute a limitation on the computer device 500 to which the present application scheme is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structure and function of the memory and the processor are the same as those of the present application scheme. Figure 5 The embodiments shown are consistent and will not be described again here.

[0116] Among them, the processor 502 is used to run a computer program 5032 stored in the memory to implement the following steps: based on a preset wearable blood pressure monitoring device, collecting blood pressure dynamic data corresponding to dynamic blood pressure monitoring, and obtaining the blood pressure dynamic data; preprocessing the blood pressure dynamic data to obtain preprocessed blood pressure data; based on a preset feature extraction method, and according to the preprocessed blood pressure data, extracting target blood pressure features; based on a preset machine learning model, and according to the target blood pressure features, predicting the blood pressure change trend, and performing blood pressure abnormality detection to obtain blood pressure abnormality detection results; determining health advice based on the blood pressure change trend and the blood pressure abnormality detection results; based on a preset visual display method, and according to the blood pressure change trend, the blood pressure abnormality detection results and the health advice, generating a dynamic blood pressure monitoring report.

[0117] In one embodiment, the processor 502 implements at least one of the following steps when extracting the target blood pressure feature based on the preprocessed blood pressure data based on the preset feature extraction method:

[0118] Based on a preset feature statistical method, the pre-processed blood pressure data is statistically analyzed to obtain statistical blood pressure features included in the target blood pressure features;

[0119] Based on a preset time series analysis method, extracting the characteristics of blood pressure changes over time corresponding to the preprocessed blood pressure data, and obtaining the time series blood pressure characteristics included in the target blood pressure characteristics;

[0120] Based on a preset physiological feature extraction method, the physiological blood pressure features corresponding to the preprocessed blood pressure data are extracted to obtain the physiological blood pressure features included in the target blood pressure features.

[0121] In one embodiment, when the processor 502 generates a dynamic blood pressure monitoring report based on a preset visual display mode and according to the blood pressure change trend, the abnormal blood pressure detection result and the health advice, the processor 502 specifically implements the following steps:

[0122] Based on a preset chart format, the blood pressure change trend is displayed in the dynamic blood pressure monitoring report.

[0123] In one embodiment, the processor 502 implements the following steps when predicting the blood pressure change trend based on the preset machine learning model and according to the target blood pressure characteristics, and performing blood pressure abnormality detection to obtain the blood pressure abnormality detection result:

[0124] Based on a preset blood pressure prediction model included in a preset machine learning model and according to the target blood pressure characteristics, predicting a blood pressure change trend;

[0125] Based on the preset blood pressure abnormality detection algorithm included in the preset machine learning model and according to the target blood pressure characteristics, blood pressure abnormality detection is performed to obtain a blood pressure abnormality detection result.

[0126] In one embodiment, the abnormal blood pressure detection result is abnormal blood pressure; when the processor 502 generates a dynamic blood pressure monitoring report according to the blood pressure change trend, the abnormal blood pressure detection result and the health advice, the processor 502 specifically implements the following steps:

[0127] Generating a blood pressure abnormality warning according to the blood pressure abnormality;

[0128] The abnormal blood pressure warning is included in the dynamic blood pressure monitoring report.

[0129] In one embodiment, when the processor 502 generates a dynamic blood pressure monitoring report based on a preset visual display mode and according to the blood pressure change trend, the abnormal blood pressure detection result and the health advice, the following steps are specifically implemented:

[0130] Based on a preset differentiated display method, the blood pressure change trend, the abnormal blood pressure warning and the health advice are displayed differently.

[0131] In one embodiment, when determining health advice according to the blood pressure change trend and the abnormal blood pressure detection result, the processor 502 specifically implements the following steps:

[0132] Obtain the user's preset historical daily behavior information data;

[0133] Based on a preset health advice model, and according to the blood pressure change trend, the abnormal blood pressure detection result, and the preset historical daily behavior information data, lifestyle advice is determined.

[0134] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0135] Those skilled in the art will appreciate that all or part of the processes in the method for implementing the above embodiment can be completed by a computer program, which can be stored in a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0136] Therefore, the present application also provides a computer-readable storage medium. The computer-readable storage medium may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, and the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the following steps:

[0137] A computer program product, when running on a computer, enables the computer to execute the steps of the blood pressure interpretation and processing method based on dynamic blood pressure monitoring described in the above embodiments.

[0138] The computer-readable storage medium may be an internal storage unit of the aforementioned device, such as a hard disk or memory of the device. The computer-readable storage medium may also be an external storage device of the device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the device and an external storage device.

[0139] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0140] The storage medium is a physical, non-transient storage medium, for example, it can be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk, etc., which can store computer programs.

[0141] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0142] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0143] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present application can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present application 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.

[0144] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for an electronic device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0145] The software tools or components not provided by our company that appear in the embodiments of this application are merely examples and do not represent actual use.

[0146] The relevant data collection appearing in the embodiments of the present application complies with the requirements of relevant laws and regulations, such as GDPR (General Data Protection Regulation of the European Union) or information security standards of other countries and regions.

[0147] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A blood pressure interpretation and processing method based on dynamic blood pressure monitoring, characterized in that: include: Based on a preset wearable blood pressure monitoring device, blood pressure dynamic data corresponding to dynamic blood pressure monitoring is collected, and the blood pressure dynamic data is obtained; Preprocessing the blood pressure dynamic data to obtain preprocessed blood pressure data; Based on a preset feature extraction method and according to the preprocessed blood pressure data, extracting a target blood pressure feature; Based on a preset machine learning model and according to the target blood pressure characteristics, the blood pressure change trend is predicted, and blood pressure abnormality detection is performed to obtain blood pressure abnormality detection results; Determining health advice based on the blood pressure change trend and the abnormal blood pressure detection result; Based on a preset visual display method, and according to the blood pressure change trend, the abnormal blood pressure detection results and the health advice, a dynamic blood pressure monitoring report is generated.

2. The blood pressure interpretation and processing method based on dynamic blood pressure monitoring according to claim 1, characterized in that: Based on a preset feature extraction method and according to the preprocessed blood pressure data, extracting a target blood pressure feature includes at least one of the following: Based on a preset feature statistical method, the pre-processed blood pressure data is statistically analyzed to obtain statistical blood pressure features included in the target blood pressure features; Based on a preset time series analysis method, extracting the characteristics of blood pressure changes over time corresponding to the preprocessed blood pressure data, and obtaining the time series blood pressure characteristics included in the target blood pressure characteristics; Based on a preset physiological feature extraction method, the physiological blood pressure features corresponding to the preprocessed blood pressure data are extracted to obtain the physiological blood pressure features included in the target blood pressure features.

3. The blood pressure interpretation and processing method based on dynamic blood pressure monitoring according to claim 1, characterized in that: Based on the preset visual display mode, and according to the blood pressure change trend, the abnormal blood pressure detection result and the health advice, a dynamic blood pressure monitoring report is generated, including: Based on a preset chart format, the blood pressure change trend is displayed in the dynamic blood pressure monitoring report.

4. The blood pressure interpretation and processing method based on dynamic blood pressure monitoring according to claim 1, characterized in that: Based on the preset machine learning model and according to the target blood pressure characteristics, the blood pressure change trend is predicted, and blood pressure abnormality detection is performed to obtain blood pressure abnormality detection results, including: Based on a preset blood pressure prediction model included in a preset machine learning model and according to the target blood pressure characteristics, predicting a blood pressure change trend; Based on the preset blood pressure abnormality detection algorithm included in the preset machine learning model and according to the target blood pressure characteristics, blood pressure abnormality detection is performed to obtain a blood pressure abnormality detection result.

5. The blood pressure interpretation and processing method based on dynamic blood pressure monitoring according to any one of claims 1 to 3, characterized in that: The abnormal blood pressure detection result is abnormal blood pressure; Generate a dynamic blood pressure monitoring report based on the blood pressure change trend, the abnormal blood pressure detection result and the health advice, including: Generating a blood pressure abnormality warning according to the blood pressure abnormality; The abnormal blood pressure warning is included in the dynamic blood pressure monitoring report.

6. The blood pressure interpretation and processing method based on dynamic blood pressure monitoring according to claim 5, characterized in that: Based on the preset visual display mode, and according to the blood pressure change trend, the abnormal blood pressure detection result and the health advice, a dynamic blood pressure monitoring report is generated, including: Based on a preset differentiated display method, the blood pressure change trend, the abnormal blood pressure warning and the health advice are displayed differently.

7. The blood pressure interpretation and processing method based on dynamic blood pressure monitoring according to claim 1, characterized in that: Determining health advice based on the blood pressure change trend and the abnormal blood pressure detection result, including: Obtain the user's preset historical daily behavior information data; Based on a preset health advice model, and according to the blood pressure change trend, the abnormal blood pressure detection result, and the preset historical daily behavior information data, lifestyle advice is determined.

8. A blood pressure interpretation and processing device based on dynamic blood pressure monitoring, characterized in that: include: A first acquisition unit, configured to collect blood pressure dynamic data corresponding to dynamic blood pressure monitoring based on a preset wearable blood pressure monitoring device, and acquire the blood pressure dynamic data; A data preprocessing unit, used for preprocessing the blood pressure dynamic data to obtain preprocessed blood pressure data; a feature extraction unit, configured to extract target blood pressure features based on a preset feature extraction method and according to the preprocessed blood pressure data; A second acquisition unit is used to predict the blood pressure change trend based on a preset machine learning model and according to the target blood pressure characteristics, and perform blood pressure abnormality detection to obtain a blood pressure abnormality detection result; A first determining unit, configured to determine health advice according to the blood pressure change trend and the abnormal blood pressure detection result; The first generating unit is used to generate a dynamic blood pressure monitoring report based on a preset visual display mode and according to the blood pressure change trend, the blood pressure abnormality detection result and the health advice.

9. A computer device, characterized in that: The computer device comprises a memory and a processor connected to the memory; the memory is used to store a computer program; the processor is used to run the computer program to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 can be implemented.

Images