Hypertension monitoring method based on knowledge graph of dynamic data and application
Through intelligent wearable devices, analyzing users' continuous physiological data, a hypertension risk prediction model is constructed, and a personalized health management plan is generated, which solves the problems of incomplete data and poor compliance in hypertension management, and achieves efficient early warning and management , reducing the risk of complications.
Patent Information
- Application Number
- CN202411151264.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-11-26
AI Technical Summary
The existing hypertension management methods have problems with incomplete data and poor patient compliance. Traditional static measurements are affected by emotions and the environment, and it is difficult for patients to persist in regular monitoring and recording of blood pressure, resulting in poor management results.
Using a knowledge graph method based on dynamic data, users' continuous physiological data are collected and analyzed through intelligent wearable devices, a hypertension risk prediction model is constructed, a personalized health management plan is generated, and timely intervention is conducted through a multi-level early warning mechanism.
Early warning and personalized management of hypertension are achieved, the effectiveness of blood pressure control and patient compliance are improved, and the complications and mortality of hypertension are reduced.
Smart Images

Figure CN119028559A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical health digital management technology, and in particular to a hypertension monitoring method and application based on a knowledge graph of dynamic data. Background Art
[0002] Hypertension is a chronic disease characterized by high blood pressure. It is considered one of the important risk factors for cardiovascular disease and can cause serious complications such as heart disease, stroke, and kidney disease. According to statistics from the World Health Organization (WHO), more than 1 billion people in the world suffer from hypertension, and millions of people die each year due to hypertension and its complications. Therefore, effective management and prevention of hypertension has become particularly important.
[0003] Existing methods for managing hypertension usually include medication, lifestyle intervention, and regular blood pressure monitoring. Traditional blood pressure monitoring methods mainly rely on static measurements during outpatient visits or regular measurements by users at home. However, these methods have some significant limitations. First, static measurements can only provide data at a specific point in time, which is easily affected by instantaneous factors such as emotions and environment, and cannot fully reflect the patient's actual health status. Secondly, many patients find it difficult to regularly monitor and record their blood pressure due to their busy work or lack of management awareness, resulting in poor management results.
[0004] With the rapid development of the Internet of Things, wearable devices and smart medical technology, smart wearable devices are gradually entering people's daily lives. These devices can continuously monitor and record a variety of physiological parameters, including heart rate, blood pressure, blood oxygen saturation, body temperature and activity, providing real-time and continuous health data. The integration of dynamic medical data and personalized health management has become a major problem that needs to be solved. Summary of the invention
[0005] In order to solve the above problems, the present invention provides a hypertension monitoring method and application based on a knowledge graph of dynamic data, which realizes early warning of hypertension and personalized health management by continuously monitoring and analyzing the physiological data of users wearing the device, so as to improve the effectiveness of blood pressure control and patient compliance. Combined with knowledge graph technology, multi-source heterogeneous medical data can be integrated, and accurate warning of hypertension risks can be achieved regardless of whether the patient has a history of hypertension.
[0006] In a first aspect, the present invention provides a method for monitoring hypertension based on a knowledge graph of dynamic data, which specifically comprises the following steps: S1. Collect the user's historical health data, collect the user's dynamic physiological health data through smart wearable devices, and pre-process the health data; S2, constructing a hypertension risk prediction model based on the preprocessed health data; S3. Construct a knowledge graph for hypertension health management, apply the knowledge graph for hypertension health management to the hypertension risk prediction model, and obtain a health knowledge graph for hypertension risk prediction; S4. Use the hypertension risk prediction health knowledge graph to evaluate the user's dynamic physiological health data; S5. Based on the evaluation results, if there is abnormal health data or the risk of hypertension is higher than the set value, the user will be warned; S6. Generate personalized health management plans based on the user's health data and living habits; S7. Make dynamic adjustments based on user performance and health data feedback.
[0007] Furthermore, the smart wearable device in S1 monitors and collects the user's dynamic physiological data in real time, including but not limited to heart rate, blood pressure, blood oxygen saturation, body temperature and activity level. The collection of the user's historical health data is specifically through a questionnaire survey to collect the user's historical data. The historical data includes the type of dynamic physiological data that the smart wearable device monitors and collects the user's dynamic physiological data in real time, including but not limited to heart rate, blood pressure, blood oxygen saturation, body temperature and activity level.
[0008] Furthermore, constructing the hypertension risk prediction model in S2 specifically involves learning the preprocessed basic data in combination with relevant data on the risk of hypertension to obtain a hypertension risk prediction model.
[0009] Furthermore, the pre-processing of health data in S1 is specifically as follows: Data cleaning: remove noise data and outliers; Data integration: integrating data sources collected from multiple sensors; Data transformation: Convert the original data into the characteristic values required for hypertension risk analysis.
[0010] Furthermore, the knowledge graph of hypertension health management constructed in S3 is specifically as follows: Labeling: label the preprocessed data and mark its source, type, time and other attributes; Knowledge extraction: Extract key knowledge points related to hypertension from medical literature and historical case data to form hypertension early warning management knowledge; Knowledge graph construction: The preprocessed data and hypertension early warning management knowledge are formed into knowledge graph nodes. The node types include user physiological parameters, user health data, medical knowledge points, pathological relationships, etc.; the user's hypertension diagnostic threshold and its relationship value with health indicators are input as the knowledge graph boundary.
[0011] Furthermore, the types of the knowledge graph nodes include: User physiological parameter node: including the user's age, gender, height, weight, living habits, etc.; User health data node: contains historical health data and dynamic physiological health data, including heart rate, blood pressure, blood oxygen saturation, body temperature, activity level, etc.; Medical knowledge nodes: including definitions, diagnostic criteria, treatment plans, drug information, etc. related to hypertension; Pathological relationship node: contains the association information and pathological relationship between hypertension and other diseases.
[0012] Furthermore, S4 also includes dynamic assessment: using the hypertension risk prediction health knowledge graph to conduct a comprehensive assessment of the user's dynamic physiological health data, including but not limited to the analysis of blood pressure fluctuation trends and heart rate abnormality patterns; The collected physiological parameters are input into the hypertension risk prediction health knowledge graph, compared with the user's historical health data and standard health indicators, and the probability of hypertension complications is output. When the probability of occurrence is greater than the set value, a warning message is issued.
[0013] Furthermore, the S5 specifically includes: Real-time warning: When the user's health data is detected to be abnormal or the risk of hypertension is higher than the set value, the system automatically generates warning information and notifies the user through the mobile terminal; There are three levels of warning: Level 1 warning - bracelet banner reminder, Level 2 warning - contact online backend doctor, Level 3 warning - call 120 and contact emergency contact; Early warning feedback: Users provide feedback on early warning information, and the hypertension risk prediction health knowledge graph optimizes and adjusts the early warning accuracy through feedback data.
[0014] Furthermore, the S6 specifically includes: Personalized management: Generate personalized health management plans based on the user's health data and living habits, adopt intervention measures such as recommended diet, exercise, and medication, and provide health guidance; Dietary intervention includes: providing supplementary dietary therapy suggestions for lowering blood pressure, lipids and blood sugar based on the risk factors output by the hypertension risk prediction health knowledge map; Exercise intervention includes: calculating the optimal daily exercise amount based on age, weight, BMI, daily exercise intensity, and cardiovascular and cerebrovascular disease history output by the health knowledge map for hypertension risk prediction, and recommending it to smart wearable devices, which calculate and display the day's exercise completion rate in real time; Drug intervention includes: transmitting the health data output by the hypertension risk prediction health knowledge graph to online doctors for prescription, and then recommending to users the combination of Chinese and Western medicine medication plans, the best time to take medicine, and the dosage of medicine.
[0015] In a second aspect, the present invention further provides a user-worn smart wearable device, which is applied to the above-mentioned hypertension monitoring method based on a knowledge graph of dynamic data, characterized in that it includes the following modules: a blood pressure measurement module, a heart rate monitoring module, a blood oxygen measurement module, a body temperature monitoring module, an accelerometer and motion sensor module, a wireless communication module and a power supply module, wherein the above modules are electrically connected to each other, and the user-worn smart wearable device can be paired and connected with the user's smart phone via Bluetooth; Blood pressure measurement module: can measure the user's blood pressure regularly or on demand, and ensure the accuracy and reliability of the measurement results through a high-precision blood pressure sensor; Heart rate monitoring module: monitors the user's heart rate changes in real time through photoelectric sensors or electrode sensors; Blood oxygen measurement module: monitors the user's blood oxygen saturation, reflecting the level of oxygen in the blood; Body temperature monitoring module: measures the user's body temperature in real time to help detect abnormal changes in body temperature; Accelerometer and motion sensor module: monitor the user's motion status, including steps, amount of exercise, activity type, etc.; Wireless communication module: supports Bluetooth or other wireless communication technologies, enabling the smart wearable device worn by the user to pair and connect with smart terminals such as smartphones; Power module: Provides stable power supply for the device.
[0016] The beneficial effects of the present invention are: 1. Comprehensiveness and dynamism: By continuously collecting the user's dynamic physiological data (such as heart rate, blood pressure, etc.), it can fully reflect the user's health status and update the monitoring results in real time. This dynamism helps to timely discover the potential risks of hypertension and take effective intervention measures.
[0017] 2. Personalized management: The hypertension monitoring method based on knowledge graph can provide personalized health management solutions according to the user's personal situation (such as age, gender, weight, living habits, etc.). It helps to improve the pertinence and effectiveness of management and better meet the health needs of users.
[0018] 3. Intelligent early warning: By building a hypertension risk prediction model, it can automatically identify abnormalities in the user's health data and issue early warning information. This intelligent early warning mechanism helps users pay attention to their health in a timely manner and take appropriate measures to reduce the risk of hypertension. Regardless of whether the patient has a history of hypertension, accurate early warning of hypertension risks can be achieved.
[0019] 4. Knowledge integration and sharing: The construction of the knowledge graph integrates rich knowledge resources in the medical field, including the definition, diagnostic criteria, and treatment plans of hypertension. The integration and sharing of this knowledge helps to improve the efficiency and quality of medical services and promote the optimal allocation of medical resources.
[0020] 5. Improve detection and treatment rates: Compared with occasional blood pressure measurement, dynamic blood pressure monitoring can more accurately reflect the user's blood pressure and avoid interference from factors such as emotions and exercise. Therefore, this method helps to improve the detection and treatment rates of hypertension, thereby reducing the complications and mortality of hypertension.
[0021] 6. Guide rational use of drugs: Dynamic data monitoring can help doctors more accurately evaluate patients' drug responses and treatment effects, thereby guiding rational use of drugs. This helps reduce adverse reactions and side effects of drugs and improve patients' medication compliance and treatment effects.
[0022] 7. By combining smart wearable devices with the knowledge graph hypertension monitoring method based on dynamic data, comprehensive and dynamic monitoring of users' hypertension risks can be achieved, providing users with personalized health management plans, improving the detection and treatment rates of hypertension, and reducing complications and mortality. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 The figure is a flowchart of a hypertension monitoring method based on a knowledge graph of dynamic data. DETAILED DESCRIPTION
[0024] The following is combined with Figure 1 The preferred embodiments of the present invention are described in detail so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more definite definition of the protection scope of the present invention.
[0025] The implementation process of the knowledge graph hypertension monitoring method based on dynamic data can be described in detail as follows: First, collect the user's historical health data, collect the user's dynamic physiological health data through smart wearable devices, and pre-process the health data; the smart wearable device monitors and collects the user's dynamic physiological data in real time, including but not limited to heart rate, blood pressure, blood oxygen saturation, body temperature and activity level. Collecting the user's historical health data specifically involves collecting the user's historical data through questionnaires. The historical data includes the type of dynamic physiological data that the smart wearable device monitors and collects in real time, including but not limited to heart rate, blood pressure, blood oxygen saturation, body temperature and activity level. The collection of this diversified data source provides a rich information foundation for building an accurate prediction model.
[0026] The specific preprocessing of health data is as follows: Data cleaning: remove noise data and outliers; data integration: integrate data sources collected from multiple sensors; data conversion: convert raw data into feature values required for hypertension risk analysis. This step ensures the data quality and accuracy for subsequent analysis.
[0027] The hypertension risk prediction model is constructed based on the pre-processed health data; the pre-processed basic data is combined with the relevant data on the risk of hypertension to learn and obtain the hypertension risk prediction model. This model is the basis for subsequent evaluation and early warning.
[0028] Then, a hypertension health management knowledge graph is constructed, and the hypertension health management knowledge graph is applied to the hypertension risk prediction model to obtain a hypertension risk prediction health knowledge graph; The specific construction of the knowledge graph for hypertension health management is as follows: Labeling: label the preprocessed data and mark its source, type, time and other attributes; Knowledge extraction: Extract key knowledge points related to hypertension from medical literature and historical case data to form hypertension early warning management knowledge; Knowledge graph construction: The preprocessed data and hypertension early warning management knowledge are formed into knowledge graph nodes. The node types include user physiological parameters, user health data, medical knowledge points, pathological relationships, etc.; the user's hypertension diagnostic threshold and its relationship value with health indicators are input as the knowledge graph boundary.
[0029] The types of knowledge graph nodes include: User physiological parameter node: including the user's age, gender, height, weight, living habits, etc.; User health data node: contains historical health data and dynamic physiological health data, including heart rate, blood pressure, blood oxygen saturation, body temperature, activity level, etc.; Medical knowledge nodes: including definitions, diagnostic criteria, treatment plans, drug information, etc. related to hypertension; Pathological relationship node: contains the association information and pathological relationship between hypertension and other diseases.
[0030] Through labeling, knowledge extraction and knowledge graph construction, hypertension-related knowledge, user health data and medical knowledge points are integrated into a knowledge graph. This graph not only contains the user's physiological parameters and health data, but also incorporates medical knowledge and pathological relationships, providing strong knowledge support for subsequent evaluation and early warning.
[0031] Use the hypertension risk prediction health knowledge graph to evaluate the user's dynamic physiological health data; Including but not limited to the analysis of blood pressure fluctuation trends and abnormal heart rate patterns; by analyzing blood pressure fluctuation trends, abnormal heart rate patterns, etc., potential health problems can be discovered in a timely manner.
[0032] The collected physiological parameters are input into the hypertension risk prediction health knowledge graph, compared with the user's historical health data and standard health indicators, and the probability of hypertension complications is output. When the probability of occurrence is greater than the set value, a warning message is issued.
[0033] According to the evaluation results, if there is an abnormality in health data or the risk of hypertension is higher than the set value, the user will be warned; Real-time warning: When it is detected that the user's health data is abnormal or the risk of hypertension is higher than the set value, the system automatically generates a warning message and notifies the user through the mobile terminal; There are three levels of warning: Level 1 warning - bracelet banner reminder, Level 2 warning - contact online backend doctor, Level 3 warning - call 120 and contact emergency contact; this multi-level warning mechanism ensures that users can receive timely attention and processing.
[0034] Early warning feedback: Users provide feedback on early warning information, and the hypertension risk prediction health knowledge graph optimizes and adjusts the early warning accuracy through feedback data. This feedback mechanism helps improve the accuracy and reliability of the system.
[0035] Generate personalized health management plans based on users’ health data and living habits; Finally, dynamic adjustments are made based on the user's execution and health data feedback. This flexibility and adaptability ensures that the health management plan can continue to meet the actual needs of users. Personalized management: Generate a personalized health management plan based on the user's health data and living habits, adopt intervention measures such as recommended diet, exercise, and medication, and provide health guidance; Dietary intervention includes: providing auxiliary dietary therapy suggestions for lowering blood pressure, lipids and blood sugar based on the risk factors output by the hypertension risk prediction health knowledge map; providing targeted dietary therapy suggestions to help users lower blood pressure, lipids and blood sugar.
[0036] The exercise intervention includes: calculating the optimal daily exercise amount based on age, weight, BMI, daily exercise intensity output from the hypertension risk prediction health knowledge map, and cardiovascular and cerebrovascular disease history, and recommending it to smart wearable devices. Smart wearable devices calculate and display the day's exercise completion rate in real time; smart wearable devices track the user's exercise completion status in real time, and provide feedback and incentives.
[0037] Drug intervention includes: transmitting the health data output from the hypertension risk prediction health knowledge map to online doctors for prescription, and recommending to users the combination of Chinese and Western medicine, the best time to take medicine, and the dosage of medicine. This personalized drug intervention helps improve treatment effects and reduce adverse reactions.
[0038] The detailed implementation process of the knowledge graph hypertension monitoring method based on dynamic data is as follows: 1. Data Collection and Preprocessing 1. Data Collection Collection through smart wearable devices: Users wear smart wearable devices (such as smart watches, health bracelets, etc.). These devices can monitor and collect users' dynamic physiological data in real time, including but not limited to heart rate, blood pressure, blood oxygen saturation, body temperature and activity level.
[0039] Historical data collection: Collect users’ historical health data through questionnaires. These data should include users’ basic information (such as age, gender, height, weight, etc.), living habits (such as eating habits, exercise habits, etc.), and previous health conditions (such as whether there is a family history of hypertension, whether they have ever suffered from hypertension, etc.).
[0040] 2. Data preprocessing Data cleaning: Clean the collected data to remove noise data and outliers to ensure the accuracy and reliability of the data.
[0041] Data integration: Integrate data sources from different sensors and questionnaires to form a unified data set.
[0042] Data transformation: Convert the original data into characteristic values suitable for hypertension risk analysis, such as calculating statistical indicators such as mean, standard deviation, and coefficient of variation.
[0043] 2. Model Construction and Knowledge Graph Construction 1. Construction of hypertension risk prediction model Using machine learning or deep learning algorithms, the preprocessed basic data is combined with relevant data on the risk of hypertension to build a hypertension risk prediction model. This model can predict the user's future risk of hypertension based on the user's physiological parameters and historical health data.
[0044] 2. Construction of knowledge graph for hypertension health management Labeling: Label the preprocessed data and annotate its source, type, time and other attributes to facilitate subsequent knowledge extraction and graph construction.
[0045] Knowledge extraction: Extract key knowledge points related to hypertension from medical literature, historical case data and other sources, such as the definition of hypertension, diagnostic criteria, treatment plans, drug information, etc., to form a hypertension early warning management knowledge base.
[0046] Knowledge graph construction: The preprocessed data and hypertension early warning management knowledge are formed into knowledge graph nodes. Node types include user physiological parameter nodes (such as age, gender, height, weight, etc.), user health data nodes (such as heart rate, blood pressure, blood oxygen saturation, etc.), medical knowledge nodes (such as hypertension definition, diagnostic criteria, etc.) and pathological relationship nodes (such as the association information between hypertension and other diseases, etc.). These nodes are connected to each other through relationship edges to form a complete knowledge graph.
[0047] III. Assessment and Early Warning 1. Dynamic evaluation The health knowledge graph for hypertension risk prediction is used to comprehensively evaluate the user's dynamic physiological health data. Potential health problems can be discovered in a timely manner by analyzing indicators such as blood pressure fluctuation trends and abnormal heart rate patterns.
[0048] The collected physiological parameters are input into the hypertension risk prediction health knowledge graph, compared with the user's historical health data and standard health indicators, and evaluation results such as the probability of hypertension complications are output.
[0049] 2. Early warning mechanism When the user's health data is detected to be abnormal or the risk of hypertension is higher than the set value, the system automatically generates an early warning message. The early warning message adopts different notification methods according to the different risk levels: Level 1 warning: A banner on a smart wearable device (such as a wristband) alerts the user.
[0050] Level 2 warning: Contact an online doctor or medical service platform to provide users with professional health consultation and advice.
[0051] Level 3 warning: In an emergency (such as a sharp rise in blood pressure that may be life-threatening), the system automatically dials 120 emergency number and contacts the user's emergency contact.
[0052] 4. Personalized Management 1. Dietary intervention Provide targeted dietary recommendations based on the user's health data and the output of the hypertension risk prediction health knowledge graph. The recommendations may include supplementary dietary recommendations for lowering blood pressure, lipids, and blood sugar, helping users improve their eating habits and reduce the risk of hypertension.
[0053] 2. Exercise intervention Based on the user's age, weight, BMI, and hypertension risk, the optimal daily exercise amount is calculated and recommended. Smart wearable devices track the user's exercise completion in real time, provide feedback and motivation, and help users stick to exercise and improve their physical fitness.
[0054] 3. Drug intervention After the user's health data is transmitted to the online doctor for diagnosis, a combination of Chinese and Western medicine medication plan is provided. The plan includes detailed information such as the best time to take the medicine and the dosage, helping users to use the medicine rationally and control their blood pressure levels.
[0055] 5. Dynamic Adjustment and Optimization 1. Dynamic adjustment: Dynamically adjust the health management plan based on the user's execution status and health data feedback. For example, adjust the diet and exercise plan according to the user's blood pressure changes; adjust the medication plan according to the doctor's diagnosis results, etc.
[0056] 2. Optimize the early warning accuracy: Through the early warning feedback data of users, the early warning accuracy of the hypertension risk prediction health knowledge map is continuously optimized and adjusted. This helps to improve the accuracy and reliability of the system and provide users with more accurate health management services.
[0057] In summary, the knowledge graph hypertension monitoring method based on dynamic data provided by the present invention provides users with comprehensive health management services through intelligent and personalized means. It not only improves the monitoring and early warning efficiency of hypertension, but also helps users improve their health status and quality of life through personalized intervention measures.
[0058] The present invention also provides a user-worn smart wearable device, which is applied to the above-mentioned hypertension monitoring method based on a knowledge graph of dynamic data, and includes the following modules: a blood pressure measurement module, a heart rate monitoring module, a blood oxygen measurement module, a body temperature monitoring module, an accelerometer and motion sensor module, a wireless communication module and a power supply module. The above modules are electrically connected to each other, and the user-worn smart wearable device can be paired and connected with the user's smart phone via Bluetooth.
[0059] Blood pressure measurement module: This module is one of the core components of the device and can measure the user's blood pressure regularly or on demand. The high-precision blood pressure sensor ensures the accuracy and reliability of the measurement results. Blood pressure data is an important indicator for assessing the user's risk of hypertension.
[0060] Heart rate monitoring module: Real-time monitoring of the user's heart rate changes, achieved through technologies such as photoelectric sensors or electrode sensors. Heart rate data is crucial for assessing cardiovascular health and detecting potential arrhythmias.
[0061] Blood oxygen measurement module: monitors the user's blood oxygen saturation, reflecting the level of oxygen in the blood. Blood oxygen data is of great significance for evaluating respiratory function, cardiopulmonary health, etc., and can also be used as a reference indicator for the risk of complications of hypertension.
[0062] Body temperature monitoring module: measures the user's body temperature in real time, helping to detect abnormal changes in body temperature, which may be related to infection, inflammation or other health problems. It is one of the important indicators for assessing overall health status.
[0063] Accelerometer and motion sensor module: This module is used to monitor the user's exercise status, including the number of steps, amount of exercise, activity type, etc. Through the accelerometer and advanced algorithms, the user's daily activity pattern can be analyzed to provide data support for the formulation of personalized exercise plans. At the same time, exercise data is also an important basis for evaluating the user's living habits and health status.
[0064] Wireless communication module: supports Bluetooth or other wireless communication technologies, so that the smart wearable device worn by the user can be paired with smart terminals such as smartphones. Through wireless transmission, the device can send the collected physiological data to the user's mobile phone in real time or at a fixed time for further analysis and processing.
[0065] Power module: Provides a stable power supply for the device to ensure that each module can work properly. Rechargeable batteries are usually used as the power source to support long-term wear and use.
[0066] In addition, the smart wearable device also has the following features: Portability and comfort: Lightweight and comfortable to wear, suitable for users to wear for a long time.
[0067] User-friendliness: Provides an intuitive interface and easy-to-use operation, allowing users to easily view and manage their health data.
[0068] Data security and privacy protection: Encryption and anonymization measures are taken during data transmission and storage to ensure the security and privacy of user data.
[0069] Smart wearable devices can achieve real-time monitoring and data continuity in hypertension management: Smart wearable devices can monitor the user's physiological parameters, including blood pressure, heart rate, etc., 24 hours a day. These data can form a continuous record to reflect the user's daily health status changes. This real-time monitoring can capture instantaneous or hidden hypertension that is difficult to capture with traditional static measurements, improving the accuracy of diagnosis. The monitored data can be analyzed, and when abnormalities (such as a sharp increase in blood pressure) are found, an early warning can be immediately issued to the user, and even a doctor or emergency service can be automatically contacted. This timely intervention can reduce the risk of complications from hypertension. Based on the data from continuous monitoring, doctors can more accurately assess the patient's blood pressure fluctuations and treatment effects, and thus develop personalized management plans. For example, adjust the drug dosage or treatment strategy according to the patient's blood pressure change pattern to improve the treatment effect and the patient's quality of life. Smart wearable devices can enhance patients' self-management ability and participation by providing intuitive health data feedback and personalized health management suggestions. Patients can view their health data at any time, understand their blood pressure control situation, and adjust their lifestyle and medication habits according to the suggestions. Smart wearable devices can transmit monitoring data to the cloud platform in real time to achieve data sharing and remote access. Doctors can remotely view patients' health data through the Internet, conduct remote consultation and treatment, and improve the accessibility and efficiency of medical services.
[0070] By combining smart wearable devices with a knowledge graph hypertension monitoring method based on dynamic data, it is possible to achieve comprehensive and dynamic monitoring of users' hypertension risks, provide users with personalized health management plans, improve the detection and treatment rates of hypertension, and reduce complications and mortality.
[0071] Any example of the present invention can be used as an independent technical solution or combined with other examples. All patents and publications mentioned in the specification of the present invention indicate that these are public technologies in the field and can be used in the present invention. All patents and publications cited here are also listed in the references, just like each publication is specifically cited separately. The present invention here can be implemented in the absence of any element or elements, one limitation or multiple limitations, and this limitation is not specifically stated here. The terms and expressions used here are descriptive methods, but not limited by them. There is no intention to indicate that these terms and explanations described in this book exclude any equivalent features, but it can be known that any appropriate changes or modifications can be made within the scope of the present invention and the claims. It can be understood that the embodiments described in the present invention are embodiments and features in some embodiments, and any person skilled in the art can make some changes and variations based on the essence of the present invention, and these changes and variations are also considered to belong to the scope of the present invention and the scope limited by the independent claims and the appended claims.
Claims
1. A hypertension monitoring method based on a knowledge graph of dynamic data, characterized in that: The specific steps include: S1. Collect the user's historical health data, collect the user's dynamic physiological health data through smart wearable devices, and pre-process the health data; S2, constructing a hypertension risk prediction model based on the preprocessed health data; S3. Construct a knowledge graph for hypertension health management, apply the knowledge graph for hypertension health management to the hypertension risk prediction model, and obtain a health knowledge graph for hypertension risk prediction; S4. Use the hypertension risk prediction health knowledge graph to evaluate the user's dynamic physiological health data; S5. Based on the evaluation results, if there is abnormal health data or the risk of hypertension is higher than the set value, the user will be warned; S6. Generate personalized health management plans based on the user's health data and living habits; S7. Make dynamic adjustments based on user performance and health data feedback.
2. A hypertension monitoring method based on a knowledge graph of dynamic data according to claim 1, characterized in that: The smart wearable device in S1 monitors and collects the user's dynamic physiological data in real time, including but not limited to heart rate, blood pressure, blood oxygen saturation, body temperature and activity level. The collection of the user's historical health data is specifically through a questionnaire survey to collect the user's historical data. The historical data includes the type of dynamic physiological data that the smart wearable device monitors and collects the user's dynamic physiological data in real time, including but not limited to heart rate, blood pressure, blood oxygen saturation, body temperature and activity level.
3. The hypertension monitoring method based on a knowledge graph of dynamic data according to claim 1, characterized in that: The construction of the hypertension risk prediction model in S2 specifically includes learning the preprocessed basic data in combination with relevant data on the risk of hypertension to obtain the hypertension risk prediction model.
4. The hypertension monitoring method based on a knowledge graph of dynamic data according to claim 1, characterized in that: The preprocessing of health data in S1 is specifically as follows: Data cleaning: remove noise data and outliers; Data integration: integrating data sources collected from multiple sensors; Data transformation: Convert the original data into the characteristic values required for hypertension risk analysis.
5. The hypertension monitoring method based on a knowledge graph of dynamic data according to claim 1, characterized in that: The knowledge graph for hypertension health management constructed in S3 is specifically as follows: Labeling: label the preprocessed data and mark its source, type, time and other attributes; Knowledge extraction: Extract key knowledge points related to hypertension from medical literature and historical case data to form hypertension early warning management knowledge; Knowledge graph construction: The pre-processed data and hypertension early warning management knowledge are formed into knowledge graph nodes. The node types include user physiological parameters, user health data, medical knowledge points, pathological relationships, etc. Input the user's hypertension diagnostic cutoff value and its relationship value with health indicators as the knowledge graph boundary.
6. A hypertension monitoring method based on a knowledge graph of dynamic data according to claim 5, characterized in that: The types of knowledge graph nodes include: User physiological parameter node: including the user's age, gender, height, weight, living habits, etc.; User health data node: contains historical health data and dynamic physiological health data, including heart rate, blood pressure, blood oxygen saturation, body temperature, activity level, etc.; Medical knowledge nodes: including definitions, diagnostic criteria, treatment plans, drug information, etc. related to hypertension; Pathological relationship node: contains the association information and pathological relationship between hypertension and other diseases.
7. The hypertension monitoring method based on a knowledge graph of dynamic data according to claim 1, characterized in that: The S4 also includes dynamic assessment: using the hypertension risk prediction health knowledge map to conduct a comprehensive assessment of the user's dynamic physiological health data, including but not limited to the analysis of blood pressure fluctuation trends and heart rate abnormality patterns; The collected physiological parameters are input into the hypertension risk prediction health knowledge graph, compared with the user's historical health data and standard health indicators, and the probability of hypertension complications is output. When the probability of occurrence is greater than the set value, a warning message is issued.
8. The hypertension monitoring method based on a knowledge graph of dynamic data according to claim 1, characterized in that: The S5 specifically includes: Real-time warning: When the user's health data is detected to be abnormal or the risk of hypertension is higher than the set value, the system automatically generates warning information and notifies the user through the mobile terminal; There are three levels of warning: Level 1 warning - bracelet banner reminder, Level 2 warning - contact online backend doctor, Level 3 warning - call 120 and contact emergency contact; Early warning feedback: Users provide feedback on early warning information, and the hypertension risk prediction health knowledge graph optimizes and adjusts the early warning accuracy through feedback data.
9. The hypertension monitoring method based on a knowledge graph of dynamic data according to claim 1, characterized in that: The S6 specifically includes: Personalized management: Generate personalized health management plans based on the user's health data and living habits, adopt intervention measures such as recommended diet, exercise, and medication, and provide health guidance; Dietary intervention includes: providing supplementary dietary therapy suggestions for lowering blood pressure, lipids and blood sugar based on the risk factors output by the hypertension risk prediction health knowledge map; Exercise intervention includes: calculating the optimal daily exercise amount based on age, weight, BMI, daily exercise intensity, and cardiovascular and cerebrovascular disease history output by the health knowledge map for hypertension risk prediction, and recommending it to smart wearable devices, which calculate and display the exercise completion rate of the day in real time; Drug intervention includes: transmitting the health data output by the hypertension risk prediction health knowledge graph to online doctors for prescription, and then recommending to users the combination of Chinese and Western medicine medication plans, the best time to take medicine, and the dosage of medicine.
10. A user wears a smart wearable device, applied to a hypertension monitoring method based on a knowledge graph of dynamic data as described in claims 1-9, characterized in that: It includes the following modules: blood pressure measurement module, heart rate monitoring module, blood oxygen measurement module, body temperature monitoring module, accelerometer and motion sensor module, wireless communication module and power module. The above modules are electrically connected to each other. The user wears the smart wearable device and can be paired with the user's smart phone via Bluetooth. Blood pressure measurement module: can measure the user's blood pressure regularly or on demand, and ensure the accuracy and reliability of the measurement results through a high-precision blood pressure sensor; Heart rate monitoring module: monitors the user's heart rate changes in real time through photoelectric sensors or electrode sensors; Blood oxygen measurement module: monitors the user's blood oxygen saturation, reflecting the level of oxygen in the blood; Body temperature monitoring module: measures the user's body temperature in real time to help detect abnormal changes in body temperature; Accelerometer and motion sensor module: monitor the user's motion status, including steps, amount of exercise, activity type, etc.; Wireless communication module: supports Bluetooth or other wireless communication technologies, enabling the smart wearable device worn by the user to pair and connect with smart terminals such as smartphones; Power module: Provides stable power supply for the device.
Citation Information
Cited By
Health assessment method based on blood pressure and heartbeat data and wearable intelligent device
CN121154113A
