A multi-functional vital sign monitoring method and system

Abstract

The embodiment of the application provides a kind of multifunctional vital sign monitoring method and system.Therein, the real-time vital sign signal of user under different physiological state is acquired, and combined with environmental parameter, form multidimensional monitoring data set;According to the multidimensional monitoring data set, the monitoring frequency and accuracy of real-time vital sign signal are dynamically adjusted by applying intelligent control algorithm, generate data collection strategy, and based on the data collection strategy, collect vital sign data;Based on the vital sign data, the abnormal situation of monitored vital sign is analyzed and processed using instant evaluation engine, generate health status evaluation result and personalized health suggestion;The health status evaluation result and personalized suggestion are safely synchronized to the medical monitoring system of user, to realize remote medical service and continuity health management.The technical scheme provided by the embodiment of the application improves the accuracy and efficiency of health monitoring.

Description

TECHNICAL FIELD

[0001] The embodiment of the present application relates to the technical field of intelligent health monitoring and remote medical technology, and particularly relates to a multifunctional vital sign monitoring method and system. BACKGROUND

[0002] With the aging of the population and the increasing incidence of chronic diseases, there is an increasing demand for continuous health monitoring and remote medical services. In scenarios such as home care, hospital wards, and rehabilitation centers, real-time acquisition of multi-dimensional vital sign data and environmental parameters of users is crucial for accurate assessment of user health status. In addition, modern health management not only requires timely warning of abnormal conditions, but also expects to provide personalized health advice to help users better manage their own health. Therefore, a multifunctional vital sign monitoring method that can combine multi-dimensional data, dynamically adjust monitoring strategies, and achieve remote synchronization is needed.

[0003] Currently, there are various vital sign monitoring devices and technologies on the market, including wearable devices, home medical instruments, and hospital-level monitoring systems. These devices can usually collect basic vital sign data and collect and transmit data at a pre-set fixed frequency. Some advanced devices are also equipped with preliminary data analysis functions that can identify common abnormal conditions and issue alerts. However, most existing solutions mainly focus on single-dimensional data collection, lack comprehensive consideration of environmental parameters, and the data collection strategy is fixed and cannot be flexibly adjusted according to the specific state and needs of the user.

[0004] However, although existing technologies meet the basic vital sign monitoring needs to some extent, there are still several deficiencies. Fixed-frequency data collection can result in wasted resources in low-risk states and failure to capture key changes in time in high-risk states. Most existing devices perform data analysis based on general algorithms without fully considering the influence of individual differences and environmental factors, resulting in health advice that is not personalized and targeted. Many devices do not have secure synchronization capabilities, making it difficult to achieve efficient remote medical care and continuous health management, limiting the ability of doctors to understand and intervene in the health status of patients in real time.

[0005] In summary, existing vital sign monitoring technologies and devices still have room for improvement in flexibility, personalization, and remote services. The present application aims to achieve more accurate, efficient, and personalized vital sign monitoring by introducing intelligent control algorithms and real-time evaluation engines, combining multi-dimensional data sets, thereby improving user experience and the quality of remote medical services. SUMMARY

[0006] The embodiment of the present application provides a multifunctional vital sign monitoring method and system to solve the problem of low accuracy and efficiency of health monitoring in the prior art.

[0007] In a first aspect, the embodiments of the present application provide a multifunctional vital sign monitoring method, comprising:

[0008] acquiring real-time vital sign signals of a user in different physiological states, and combining environmental parameters to form a multi-dimensional monitoring data set;

[0009] applying an intelligent control algorithm to dynamically adjust the monitoring frequency and accuracy of the real-time vital sign signals according to the multi-dimensional monitoring data set, generating a data collection strategy, and collecting vital sign data based on the data collection strategy;

[0010] based on the vital sign data, using an instant evaluation engine to analyze and process the monitored vital sign abnormal conditions, combining information of gender, height, weight, genetic history and past medical history to generate a health status evaluation result and personalized health advice;

[0011] safely synchronizing the health status evaluation result and personalized advice to the user's medical monitoring system to realize remote medical services and continuous health management.

[0012] Optionally, the application of an intelligent control algorithm to dynamically adjust the monitoring frequency and accuracy of the real-time vital sign signals according to the multi-dimensional monitoring data set, generating a data collection strategy, and collecting vital sign data based on the data collection strategy, comprises:

[0013] using data analysis technology and the multi-dimensional monitoring data set to identify changes in the user's behavior patterns, activity levels and environment to obtain information reflecting the user's current state;

[0014] According to the information reflecting the user's current state, evaluating the demand for monitoring frequency and accuracy under the current state to generate a preliminary monitoring demand evaluation result;

[0015] combining historical vital sign data to develop a personalized monitoring frequency and accuracy strategy to optimize the preliminary monitoring demand evaluation result to obtain an optimized monitoring strategy;

[0016] using the optimized monitoring strategy to dynamically control the monitoring frequency and accuracy of the vital sign signal acquisition device to obtain vital sign data.

[0017] Optionally, the application of an intelligent control algorithm to dynamically adjust the monitoring frequency and accuracy of the real-time vital sign signals according to the multi-dimensional monitoring data set, generating a data collection strategy, and collecting vital sign data based on the data collection strategy, comprises:

[0018] using a behavior pattern recognition algorithm to classify the user's activity type based on the information reflecting the user's current state to obtain a classification result of the user's activity type;

[0019] According to the classification result of the user activity type and the environmental parameter, an influence of the environmental parameter on a user health condition is evaluated, and an environmental adaptability evaluation result is obtained;

[0020] Based on the environmental adaptability evaluation result, a pre-trained context perception model is applied to predict a potential health risk level of the user in the current state, and a health risk prediction report is generated;

[0021] According to the health risk prediction report, a demand for monitoring frequency and accuracy in the current state is determined, and a monitoring demand level is obtained;

[0022] Based on the specific monitoring demand level, a preliminary monitoring demand evaluation result is generated.

[0023] Optionally, the historical vital sign data is combined to develop a personalized monitoring frequency and accuracy strategy, and the preliminary monitoring demand evaluation result is optimized to obtain an optimized monitoring strategy, including:

[0024] The preliminary monitoring demand evaluation result is used to refine the monitoring demand of the user in different contexts, and a specific monitoring demand specification is generated;

[0025] According to the specific monitoring demand specification, a long-term behavior pattern, a health condition change trend and vital sign data of the user are integrated to construct a historical model of user behavior and health;

[0026] Based on the historical model of user behavior and health, a machine learning algorithm is applied to construct a personalized prediction model suitable for the user, wherein the personalized prediction model can predict future behavior patterns of the user and their impact on health;

[0027] The personalized prediction model and the specific monitoring demand specification are used to develop a monitoring frequency and accuracy strategy for different contexts, and an optimized monitoring strategy is generated.

[0028] Optionally, based on the vital sign data, an instant evaluation engine is used to analyze and process the monitored vital sign abnormality, and information of gender, height, weight, genetic disease history and past medical history is combined to generate a health condition evaluation result and personalized health suggestions, including:

[0029] The vital sign data is analyzed in real time by using the instant evaluation engine, and a vital sign abnormality detection report is obtained;

[0030] Based on a fuzzy logic reasoning mechanism, the vital sign abnormality detection report is determined, and a vital sign abnormality confirmation result is generated;

[0031] based on the vital sign abnormality confirmation result, a pre-trained health risk prediction model is used to evaluate the current health status of the user by comparing the long-term health data of the user with similar cases, and a health status evaluation result is generated;

[0032] Using the health status evaluation result, combined with the user's gender, height, weight, genetic history, living habits, activity level and past medical history, customized health advice is provided for the user, and personalized health advice is generated.

[0033] Optionally, the vital sign abnormality detection report is determined based on the fuzzy logic reasoning mechanism, and a vital sign abnormality confirmation result is generated, comprising:

[0034] Using the fuzzy logic reasoning mechanism, the abnormal conditions in the vital sign abnormality detection report are analyzed to obtain a preliminary abnormal parameter list;

[0035] The key vital sign parameters corresponding to the preliminary abnormal parameter list are extracted and compared with the preset standard range to identify parameter values that exceed the normal range, and an abnormal parameter set is generated, the key vital sign parameters including heart rate, blood pressure and respiratory rate;

[0036] Based on the abnormal parameter set that exceeds the standard range, combined with the fuzzy logic rule base, each abnormal parameter is assigned a weight value to generate a weighted abnormal parameter set;

[0037] Using the fuzzy reasoning algorithm, the weighted abnormal parameter set is comprehensively evaluated, the scores of each abnormal parameter are calculated through the fuzzy membership function and the reasoning rules, and the vital sign abnormality confirmation result is obtained combined with the overall health status.

[0038] Optionally, based on the vital sign abnormality confirmation result, a pre-trained health risk prediction model is used to comprehensively evaluate the current health status of the user by comparing the long-term health data of the user with similar cases, and a health status evaluation result is generated, comprising:

[0039] Using the pre-trained health risk prediction model, based on the vital sign abnormality confirmation result, a preliminary health risk assessment report is obtained by performing preliminary evaluation processing on the current health status of the user;

[0040] According to the preliminary health risk assessment report, combined with the long-term health data of the user, the health status of the user is analyzed in depth, and a personalized health data analysis result is generated, the long-term health data including past medical history, living habits, activity level;

[0041] Based on the personalized health data analysis result, similar cases in the medical database are searched for comparative analysis processing, and a similar case comparative analysis result is generated;

[0042] Adjust parameters of the health risk prediction model by using the comparative analysis result of the similar cases, optimize the health risk prediction model, and obtain an optimized health risk prediction model;

[0043] According to the optimized health risk prediction model, the current health status of the user is evaluated by comprehensively considering the abnormality confirmation result, the long-term health data and the similar case information, and a health status evaluation result is generated.

[0044] In a second aspect, the embodiments of the present application provide a multifunctional vital sign monitoring system, comprising:

[0045] An acquisition module is configured to acquire real-time vital sign signals of a user in different physiological states, and form a multi-dimensional monitoring data set in combination with environmental parameters;

[0046] An adjustment module is configured to apply an intelligent control algorithm to dynamically adjust the monitoring frequency and accuracy according to the multi-dimensional monitoring data set, generate a data collection strategy, and minimize energy consumption to obtain vital sign data;

[0047] An analysis module is configured to analyze the monitored vital sign abnormality based on the vital sign data by using an instant evaluation engine, and generate a health status evaluation result and personalized health suggestions in combination with information of gender, height, weight, genetic history and past medical history;

[0048] A synchronization module is configured to safely synchronize the health status evaluation result and the personalized suggestions to a medical monitoring system of the user, support remote medical services, and realize continuous health management.

[0049] In a third aspect, the embodiments of the present application provide a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component, and realize a multifunctional vital sign monitoring method as described in the first aspect.

[0050] In a fourth aspect, the embodiments of the present application provide a computer storage medium, which stores a computer program; when the computer program is executed by a computer, a multifunctional vital sign monitoring method as described in the first aspect is realized.

[0051] In the embodiments of the present application, real-time vital sign signals of a user in different physiological states are obtained, and combined with environmental parameters to form a multi-dimensional monitoring data set; according to the multi-dimensional monitoring data set, an intelligent control algorithm is applied to dynamically adjust the monitoring frequency and accuracy of real-time vital sign signals, generate a data collection strategy, and based on the data collection strategy, collect vital sign data; based on the vital sign data, an instant evaluation engine is used to analyze and process the monitored vital sign abnormal conditions, and combined with information of gender, height, weight, genetic history and past medical history, a health status evaluation result and personalized health advice are generated; the health status evaluation result and personalized advice are safely synchronized to the user's medical monitoring system to realize remote medical service and continuous health management.

[0052] The technical scheme of the present application has the following beneficial effects:

[0053] The present application can more comprehensively reflect the health status of the user by combining multi-dimensional real-time vital sign signals and environmental parameters, reducing false positives and false negatives. The intelligent control algorithm dynamically adjusts the monitoring frequency and accuracy according to the actual situation, avoiding unnecessary high-frequency data collection, thereby prolonging the service life of the device and saving energy. The instant evaluation engine provides personalized health advice to help users better understand and manage their health status, improving user satisfaction. The health status evaluation result and advice are safely synchronized to the medical monitoring system, allowing doctors to obtain the latest health information of patients in a timely manner, enabling efficient remote diagnosis and treatment. Through continuous monitoring and data analysis, long-term health trend analysis is provided for users, which helps to early detect potential health problems and take preventive measures.

[0054] Further, the embodiments of the present application also relate to the application of intelligent control algorithm and instant evaluation engine to realize dynamic monitoring of user's vital sign data and real-time evaluation of health status. Specifically, by using data analysis technology and multi-dimensional monitoring data set, the behavior pattern, activity level and environmental change of the user are identified to obtain information reflecting the current state of the user. Based on this information, the demand for monitoring frequency and accuracy under the current state is evaluated, a preliminary monitoring demand evaluation result is generated, and the strategy is optimized in combination with historical vital sign data to develop a personalized monitoring frequency and accuracy strategy to dynamically control the monitoring parameters of the acquisition device. In addition, the instant evaluation engine is used to analyze and process the vital sign data in real time to generate an abnormality detection report, and the abnormality is confirmed through a fuzzy logic reasoning mechanism. Based on the abnormality confirmation result, the long-term health data of the user and similar cases are compared, and a pre-trained health risk prediction model is used to evaluate the current health status of the user, and finally a health status evaluation result and customized health advice are generated.

[0055] Through the above method, the present application significantly improves the accuracy and flexibility of vital sign monitoring. First, the intelligent control algorithm dynamically adjusts the monitoring frequency and accuracy according to the real-time state of the user, ensuring that key health information can be captured under different physiological states, while avoiding resource waste. Second, the introduction of the instant evaluation engine enables abnormal situations to be quickly identified and confirmed, enhancing the timeliness of early warning. Finally, by combining the user's historical health data and similar cases, personalized health recommendations are generated, improving the relevance and effectiveness of health management. Overall, this method not only optimizes resource utilization, but also significantly improves the quality and user experience of remote medical services, achieving efficient, accurate, and personalized continuous health management.

[0056] These aspects or other aspects of the present application will be more apparent in the following description of embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor under the premise of the drawings.

[0058] Figure 1 A flow chart of a multifunctional vital sign monitoring method provided by the present application is shown;

[0059] Figure 2 A structural schematic diagram of a multifunctional vital sign monitoring system provided by the present application is shown;

[0060] Figure 3 A structural schematic diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0061] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application.

[0062] In some of the flowcharts described in the description and claims of the present application and in the above-described figures, a plurality of operations are included in the description of the flowcharts in a particular order, but it should be clearly understood that the operations can be executed or performed in parallel or in an order different from that in which they appear herein, and the serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, the flowcharts can include more or fewer operations, and the operations can be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. herein are used to distinguish different messages, devices, modules, etc., and do not represent the order of succession, nor do "first" and "second" represent different types.

[0063] The technical solutions in the embodiments of the present application will be described clearly and completely in the description of the embodiments of the present application in combination with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0064] Figure 1 A flowchart of a multifunctional vital sign monitoring method is provided for the embodiments of the present application, as shown in Figure 1 The method comprises:

[0065] 101, acquiring real-time vital sign signals of a user in different physiological states, and combining environmental parameters to form a multi-dimensional monitoring data set;

[0066] This step involves collecting real-time vital sign signals of a user from multiple sensors and data sources, including but not limited to heart rate, blood pressure, blood oxygen saturation, respiratory rate, etc. These physiological parameters can reflect the current physical condition of the user. At the same time, environmental parameters such as temperature, humidity, air quality, and light intensity are also combined to provide more comprehensive background information. By integrating these physiological and environmental data, a multi-dimensional monitoring data set is formed for subsequent analysis and decision-making.

[0067] Firstly, the system collects real-time vital sign data of the user through wearable devices (such as smart watches, bracelets) and other medical instruments (such as sphygmomanometers, pulse oximeters). At the same time, environmental sensors (such as temperature and humidity sensors, air quality monitors) also record the surrounding environmental conditions synchronously. All these data are transmitted to a central processing unit or a cloud platform for preliminary data cleaning and formatting processing to ensure the integrity and consistency of the data. Then, these multi-dimensional data are stored in a structured database to provide a basis for subsequent intelligent control algorithms and real-time evaluation engines.

[0068] Assuming in a home care scenario, an elderly person with chronic obstructive pulmonary disease wears a multifunctional health monitoring bracelet. This bracelet not only continuously monitors heart rate, blood oxygen saturation, and respiratory rate, but also records indoor temperature and air quality through the built-in environmental sensor. When the elderly person is resting at home, the system automatically collects these data and uploads them to the cloud platform. By combining these physiological and environmental data, the system can better understand the health status of the elderly person, for example, in the case of poor air quality, changes in respiratory rate may indicate the risk of exacerbation.

[0069] 102. According to the multi-dimensional monitoring data set, an intelligent control algorithm is applied to dynamically adjust the monitoring frequency and accuracy of real-time vital signs signals, generate a data collection strategy, and collect vital signs data based on the data collection strategy;

[0070] This step aims to analyze the multi-dimensional monitoring data set using an intelligent control algorithm to identify the user's behavior patterns, activity levels, and changes in the environment, thereby dynamically adjusting the monitoring frequency and accuracy. This not only improves the flexibility and relevance of data collection, but also avoids unnecessary resource waste. The intelligent control algorithm learns from the user's historical data and behavior habits, allowing it to predict and adapt to different user needs, ensuring that critical information is captured at critical moments.

[0071] The intelligent control algorithm first performs in-depth analysis on the multi-dimensional monitoring data set, identifying the user's daily behavior patterns and activity level changes. For example, distinguishing between resting and exercise states, or identifying different stages in the sleep cycle. Then, the algorithm assesses the demand for monitoring frequency and accuracy in the current state based on this information, generating a preliminary monitoring demand assessment result. Next, combined with the user's historical vital signs data, the preliminary assessment result is optimized to develop a personalized monitoring frequency and accuracy strategy. Finally, according to the optimized strategy, the working mode of the vital signs signal acquisition device is dynamically controlled to ensure efficient and accurate data collection.

[0072] Continuing the above example, in the home care scenario, the intelligent control algorithm learns from the elderly person's historical data that he usually has a short-term increase in heart rate after getting up in the morning, and is relatively stable during nighttime sleep. Therefore, the system will appropriately increase the monitoring frequency of heart rate and blood oxygen saturation in the morning to capture potential abnormalities; while at night, it will reduce the monitoring frequency to save power and reduce interference. In addition, when the indoor air quality decreases, the system will automatically increase the monitoring accuracy of respiratory rate to timely detect any abnormal changes and ensure the safety of the elderly person.

[0073] 103. Based on the vital signs data, the real-time assessment engine is used to analyze and process the abnormal vital signs detected, and combined with information such as gender, height, weight, genetic history and past medical history, to generate health status assessment results and personalized health recommendations.

[0074] This step utilizes a real-time assessment engine to analyze and process vital sign data in real time, identifying and confirming abnormalities. The real-time assessment engine, combined with fuzzy logic reasoning, can quickly and accurately determine abnormal events and generate detailed anomaly detection reports. Based on these reports, the system further compares the user's long-term health data with similar cases, using a pre-trained health risk prediction model to assess the user's current health status, ultimately generating a health status assessment result and customized health recommendations. This process not only improves the timeliness of alerts but also provides personalized health management guidance.

[0075] The real-time assessment engine receives vital sign data from the acquisition device and performs real-time data analysis and anomaly detection. Once an anomaly is detected, the engine uses fuzzy logic reasoning to confirm the anomaly type and severity, generating an anomaly detection report. Subsequently, the system compares the anomaly detection results with the user's long-term health data (such as gender, height, weight, genetic history, past medical history, and lifestyle habits) and searches similar cases in the medical database to find matching reference cases. A pre-trained health risk prediction model uses this information to assess the user's current health status and generate a detailed health assessment result. Finally, the system combines the user's lifestyle habits, activity level, and past medical history to provide customized health recommendations to help them take appropriate preventative and treatment measures.

[0076] Continuing with the home care scenario above, when the real-time assessment engine detects a sudden drop in the elderly person's blood oxygen saturation, the system immediately activates a fuzzy logic reasoning mechanism to confirm that this is an acute hypoxic event. The system then retrieves the elderly person's historical health data, discovering that they have experienced similar hypoxic symptoms in the past, and reviews similar cases, concluding that it is likely due to poor indoor air quality. After assessment, the health risk prediction model determines that there is a high health risk in this situation and recommends that the elderly person immediately improve indoor ventilation and contact a doctor. The system will also remind family members to pay attention to the elderly person's condition and provide specific coping measures, such as adjusting the room ventilation time and preparing oxygen cylinders.

[0077] 104. Securely synchronize the health status assessment results and personalized recommendations to the user's medical monitoring system to achieve remote medical services and continuous health management.

[0078] This step is responsible for synchronizing the health assessment results and personalized recommendations to the user's medical monitoring system securely, ensuring efficient sharing of this information among doctors, patients, and their families. Through encryption communication technology and security protocols, the safety and privacy of data transmission are guaranteed. Remote medical services enable doctors to understand the latest health status of patients in real time, conduct remote diagnosis and intervention, while continuous health management helps to track the health trends of patients over a long period of time, providing continuous personalized support.

[0079] The system transmits the generated health assessment results and personalized recommendations to the user's medical monitoring system through a secure channel. During this process, encryption technologies such as Advanced Encryption Standard (AES) are used to ensure that data cannot be stolen or tampered with during transmission. After receiving the data, the medical monitoring system automatically updates the patient's electronic health record and notifies relevant medical staff. Doctors can view the latest health information of patients through mobile applications or web portals at any time, and make remote diagnosis and treatment recommendations. In addition, the system will regularly send health reports and recommendations to patients and their families, keeping communication smooth and ensuring that patients receive continuous attention and support.

[0080] In the above home care scenario, the system synchronizes the health assessment results and personalized recommendations of the elderly to the mobile application of their attending physician through an encrypted channel. The doctor can view the latest health data of the elderly during the period of going out for diagnosis, understand the reasons for the decrease in their blood oxygen saturation and the suggestions provided by the system. At the same time, the doctor can also communicate directly with the elderly and their families through the application, guide them on how to improve indoor air quality, and arrange necessary medical examinations. In addition, the system regularly sends health reports to the elderly and their families, helping them better manage the health of the elderly and ensure that their quality of life continues to improve.

[0081] Through the implementation of steps 101 to 104, the present application realizes the intelligent management of the whole process from data collection to remote medical services. First, the construction of multi-dimensional monitoring data set ensures the comprehensiveness and accuracy of the data; second, the intelligent regulation algorithm dynamically adjusts the monitoring strategy, improving the resource utilization efficiency and the pertinence of data collection; third, the introduction of the instant evaluation engine significantly enhances the identification and early warning ability of abnormal situations; finally, the safe synchronization mechanism guarantees the effective transmission and privacy protection of information, realizing efficient remote medical services and continuous health management. Overall, this method not only optimizes each link of health monitoring, but also significantly improves user experience and the quality of medical services, providing a comprehensive, intelligent, and efficient health management solution for users.

[0082] Optionally, the step 102 of applying an intelligent regulation algorithm to dynamically adjust the monitoring frequency and accuracy of real-time vital signs signals based on the multi-dimensional monitoring data set to generate a data collection strategy, and collecting vital signs data based on the data collection strategy, comprises: using data analysis techniques and the multi-dimensional monitoring data set to identify the user's behavior patterns, activity levels, and changes in the environment to obtain information reflecting the user's current state; evaluating the demand for monitoring frequency and accuracy under the current state based on the information reflecting the user's current state to generate a preliminary monitoring demand evaluation result; combining historical vital signs data to develop a personalized monitoring frequency and accuracy strategy to optimize the preliminary monitoring demand evaluation result to obtain an optimized monitoring strategy; and using the optimized monitoring strategy to dynamically control the monitoring frequency and accuracy of the vital signs signal collection device to obtain vital signs data.

[0083] To solve the problem that the monitoring strategy is not flexible and personalized, in some embodiments, the step 102 of evaluating the demand for monitoring frequency and accuracy under the current state based on the information reflecting the user's current state to generate a preliminary monitoring demand evaluation result, comprises:

[0084] Using a behavior pattern recognition algorithm, classifying the user's activity type based on the information reflecting the user's current state to obtain a classification result of the user's activity type; evaluating the impact of the environmental parameters on the user's health status based on the classification result of the user's activity type and the environmental parameters to obtain an environmental adaptability evaluation result; applying a pre-trained context perception model to predict the potential health risk level of the user under the current state based on the environmental adaptability evaluation result to generate a health risk prediction report; determining the demand for monitoring frequency and accuracy under the current state based on the health risk prediction report to obtain a monitoring demand level; and generating a preliminary monitoring demand evaluation result based on the specific monitoring demand level.

[0085] In this embodiment, the behavior pattern recognition algorithm is used to analyze the user's activity type, such as resting, walking, running, or sleeping, etc. By combining data from sensors like accelerometers and gyroscopes, the user's activity can be classified. These data not only reflect the user's daily behavior patterns, but also provide important information about their physical state. Environmental parameters include temperature, humidity, air quality, and light intensity, which can affect the user's health. For example, high humidity can exacerbate respiratory problems, while low air quality can increase the risk of cardiovascular disease. Therefore, environmental parameters are an important component of assessing the user's health risk. The context-aware model is a pre-trained machine learning model that can predict the potential health risk level based on the user's behavior patterns and environmental parameters. It is trained using a large amount of historical data and similar cases, and can provide accurate health risk predictions and guide the adjustment of monitoring strategies. The health risk prediction report is based on the output of the context-aware model, detailing the potential health risks of the user in the current state, including risk levels, possible influencing factors, and recommended measures. This report is the basis for determining the specific monitoring requirement level. The monitoring requirement level is determined by the system based on the health risk prediction report, and specifies the specific requirements for monitoring frequency and accuracy in the current state, divided into high requirement (frequent and accurate), medium requirement (moderate), and low requirement (lower frequency and accuracy). This helps optimize resource utilization and ensure that critical health information is captured in different situations.

[0086] In the embodiments of the present application, first, the algorithm identifies the user's activity patterns, such as resting, walking, or exercising, by analyzing sensor data such as accelerometers and gyroscopes. Second, the system considers the environmental conditions in which the user is located (such as temperature, humidity, air quality), and combines the activity type to assess the potential impact of these environmental factors on the user's health. Then, the model uses historical data and similar cases to predict the user's health risk level under the current activity and environmental conditions. Further, the system determines whether more frequent and accurate data collection is needed, or whether the monitoring intensity can be appropriately reduced to save energy, based on the content of the health risk prediction report. Finally, the system integrates all the evaluation information to form the final preliminary monitoring requirement evaluation result, guiding the subsequent data collection strategy.

[0087] Here is a specific example:

[0088] In a home care scenario, assume a child with asthma wears a smart bracelet with built-in accelerometers, gyroscopes, and environmental sensors. When the child is playing at home, the behavior pattern recognition algorithm identifies that he is performing vigorous exercise. At the same time, the environmental sensor records that the indoor air quality is poor, with a high PM2.5 index. Based on this information, the system assesses the impact of environmental parameters on the child's health status, concluding that poor air quality may exacerbate asthma symptoms.

[0089] Next, the context-aware model predicts a high level of health risk for the child based on historical health data and similar cases under the current activity and environmental conditions, generating a detailed health risk prediction report. Based on this report, the system determines that increased monitoring frequency and accuracy are needed to better capture any abnormal changes in the current state. Therefore, the system sets the monitoring requirement level to "high demand" and increases the monitoring frequency of heart rate, respiratory rate, and blood oxygen saturation over the next period of time.

[0090] Finally, the system generates a preliminary monitoring requirement assessment result to guide the subsequent collection of vital signs data. This dynamic adjustment not only improves the targeting of monitoring, but also ensures that critical health information can be captured in a timely manner during critical moments, helping parents and doctors better manage the child's health status.

[0091] To address the issue of insufficient individualization of the preliminary monitoring requirement assessment result, in some embodiments, the historical vital signs data is combined in step 102 to develop a personalized monitoring frequency and accuracy strategy, which is optimized for the preliminary monitoring requirement assessment result to obtain an optimized monitoring strategy, including:

[0092] The preliminary monitoring requirement assessment result is used to refine the monitoring requirements of the user under different situations, generating a specific monitoring requirement explanation. Based on the specific monitoring requirement explanation, the user's long-term behavior patterns, health status trends, and vital signs data are integrated to build a historical model of user behavior and health. Based on the historical model of user behavior and health, a machine learning algorithm is applied to build a personalized prediction model suitable for the user, which can predict the user's future behavior patterns and their impact on health. The personalized prediction model and the specific monitoring requirement explanation are used to develop monitoring frequency and accuracy strategies for different situations, generating an optimized monitoring strategy.

[0093] In this embodiment, the specific monitoring requirement description is a detailed description of the user's monitoring needs in different situations, including specific activity types (such as rest, exercise), environmental conditions (such as temperature, humidity), and corresponding health risk levels. These descriptions are used to guide the subsequent monitoring strategy development. The user behavior and health history model integrates the user's long-term behavior patterns, health condition trends, and vital sign data, and can fully reflect the relationship between the user's daily activities and health status. By analyzing these data, potential factors affecting health can be identified, and future behavior patterns and health risks can be predicted. The personalized prediction model is a model constructed based on machine learning algorithms, which is trained using the user's historical data to predict the user's future behavior patterns and their impact on health. This model can provide highly personalized health recommendations and monitoring strategies based on individual differences. The optimized monitoring strategy is developed by the system according to the personalized prediction model and the specific monitoring requirement description, and the monitoring frequency and accuracy strategy in different situations are determined. These strategies not only consider the current health status, but also anticipate future changes, ensuring the flexibility and relevance of monitoring.

[0094] In the embodiments of the present application, first, the system describes in detail the user's monitoring needs in different activity types and environmental conditions based on the preliminary assessment results, such as the need for more frequent heart rate monitoring when exercising in a high humidity environment. Second, the system analyzes the user's long-term data to identify the relationship between behavior patterns and health conditions, such as finding that a certain user's blood pressure rises during a specific time period due to work stress. Third, the system uses machine learning techniques to train a personalized prediction model based on the historical model data, enabling it to accurately predict the user's future behavior patterns and health impacts. Finally, the system dynamically adjusts the monitoring strategy based on the output of the personalized prediction model and the specific monitoring requirement description, ensuring that key health information is captured in different situations while avoiding resource waste.

[0095] Here is a specific example:

[0096] In a home care scenario, assume that an elderly patient with high blood pressure wears a smart health monitoring bracelet. The bracelet collects real-time data such as heart rate, blood pressure, activity level, and combines environmental parameters such as temperature and humidity. When the system finds that the patient's blood pressure usually rises within an hour after getting up in the morning based on the preliminary monitoring requirement assessment results, it will refine the monitoring requirements for this situation and generate a specific monitoring requirement description, indicating that blood pressure monitoring frequency needs to be increased during this period.

[0097] Next, the system integrates the patient's long-term behavior patterns (such as the habit of walking in the morning every day), health condition trends (such as a larger fluctuation in morning blood pressure), and vital sign data to build a historical model of user behavior and health. By analyzing these data, the system identifies that morning walking may be one of the reasons for the increase in blood pressure.

[0098] Then, the system applies machine learning algorithms to build a personalized prediction model for the patient based on the historical model. This model not only predicts the patient's future behavior patterns (such as whether they will continue to adhere to morning walking), but also assesses their impact on health (such as the specific impact of morning walking on blood pressure).

[0099] Finally, the system uses the personalized prediction model and specific monitoring requirement specifications to develop a monitoring frequency and precision strategy for the morning walking scenario. For example, increase the frequency of blood pressure monitoring half an hour before morning walking, and maintain high-frequency monitoring during the walking process. This optimized monitoring strategy not only improves the targeting of monitoring, but also helps doctors better understand the patient's health status in daily life, thereby providing more personalized health management recommendations.

[0100] In this way, the system not only solves the problem of insufficient individualization of preliminary monitoring requirement assessment results, but also realizes forward-looking and flexible management of user health status, significantly improving the quality of telemedicine services and user experience.

[0101] To solve the problem of inaccurate vital sign anomaly detection and health recommendations, in some embodiments, the instant evaluation engine in step 103 analyzes and processes the monitored vital sign anomalies based on the vital sign data, generates health status evaluation results and personalized health recommendations, including

[0102] Using the instant evaluation engine, the vital sign data is analyzed and processed in real time to obtain a vital sign anomaly detection report; based on the fuzzy logic reasoning mechanism, the vital sign anomaly detection report is determined to generate a vital sign anomaly confirmation result; based on the vital sign anomaly confirmation result, the user's current health status is evaluated using a pre-trained health risk prediction model by comparing the user's long-term health data and similar cases to generate a health status evaluation result; using the health status evaluation result, the user's lifestyle, activity level, and medical history are combined to provide customized health recommendations for the user to generate personalized health recommendations.

[0103] In this embodiment, the instant assessment engine is a real-time processing system that rapidly analyzes vital sign data (such as heart rate, blood pressure, oxygen saturation, etc.) from sensors to identify potential abnormalities. The engine generates detailed vital sign abnormality detection reports within a short time frame using complex algorithms and rule sets. The vital sign abnormality detection report details any abnormalities found during monitoring, including specific values of abnormal parameters, time of occurrence, and severity. It provides a snapshot of the current state and lays the foundation for further analysis. The fuzzy logic reasoning mechanism is a mathematical method used to handle uncertainty and fuzzy information. In this solution, the fuzzy logic reasoning mechanism is used to confirm abnormalities in the vital sign abnormality detection report, considering various factors (such as data fluctuations, environmental influences) to determine the authenticity and severity of abnormalities. The vital sign abnormality confirmation result is the final confirmed vital sign abnormality situation after processing by the fuzzy logic reasoning mechanism. These confirmation results are the basis for the next step of health assessment, ensuring the accuracy and reliability of abnormality detection. The health risk prediction model is a pre-trained machine learning model that can predict the risk level of the current health status based on the user's long-term health data and similar cases. The model is trained using a large amount of historical data and similar cases to improve the accuracy of the prediction. The personalized health recommendations are based on the health status assessment results, combined with the user's lifestyle, activity level, and medical history, and the system provides customized health recommendations for the user. These recommendations aim to help users take appropriate preventive and treatment measures to improve their health status.

[0104] In the embodiments of the present application, first, the instant assessment engine receives and processes data from sensors, identifies any abnormalities, and generates detailed abnormality detection reports. Second, the system applies a fuzzy logic reasoning mechanism, considering various factors (such as data fluctuations, environmental influences), to confirm the authenticity and severity of abnormalities, generating final vital sign abnormality confirmation results. Then, the system uses a health risk prediction model, combining the user's historical health data and similar cases, to comprehensively assess the current health status, generating detailed health status assessment results. Finally, the system provides specific health recommendations based on the health status assessment results, helping users take appropriate preventive and treatment measures to improve their health status.

[0105] Here is a specific example:

[0106] In a home care scenario, assume an elderly person with chronic obstructive pulmonary disease wears a multifunctional health monitoring bracelet. The bracelet continuously monitors heart rate, oxygen saturation, and respiratory rate, and transmits data to the instant assessment engine in real time.

[0107] When the elderly person is resting at home, the instant assessment engine detects a sudden drop in his blood oxygen saturation to 85%, which is below the normal range. The system immediately generates a vital sign abnormality detection report, recording the specific values and time of the abnormality.

[0108] Next, the system applies a fuzzy logic reasoning mechanism, considering the elderly person's daily activity patterns and the current indoor air quality (low humidity, high PM2.5 index), confirming that this blood oxygen saturation drop is an acute hypoxia event, generating a vital sign abnormality confirmation result.

[0109] Then, the system uses a pre-trained health risk prediction model, combining the elderly person's historical health data (such as past medical history, lifestyle habits) and similar cases, to assess their current health status. The model predicts a high health risk in this situation, especially considering the elderly person's past similar hypoxia symptoms.

[0110] Finally, the system provides customized health recommendations for the elderly person based on the health status assessment results. For example, it suggests that he immediately improve indoor ventilation, increase air humidity, and contact a doctor for further examination. At the same time, the system reminds family members to pay attention to the elderly person's condition and prepares necessary medical equipment (such as oxygen tanks). In addition, the system also sends regular health reports to the elderly person and their family members, helping them better manage the elderly person's health status.

[0111] In this way, the system not only solves the problem of inaccurate vital sign abnormality detection and health recommendations, but also realizes real-time monitoring and personalized management of users' health status, significantly improving the quality of remote medical services and user experience.

[0112] To solve the problem of inaccurate abnormality confirmation in the vital sign abnormality detection report, in some embodiments, the fuzzy logic reasoning mechanism in step 103 determines the vital sign abnormality detection report and generates a vital sign abnormality confirmation result, including:

[0113] Using the fuzzy logic reasoning mechanism, analyze the abnormality in the vital sign abnormality detection report to obtain a preliminary abnormal parameter list; extract the key vital sign parameters corresponding to the preliminary abnormal parameter list and compare them with the preset standard range to identify parameter values that exceed the normal range, generating an abnormal parameter set, the key vital sign parameters include heart rate, blood pressure, and respiratory rate; based on the abnormal parameter set that exceeds the standard range, combine the fuzzy logic rule base to assign weights to each abnormal parameter, generating a weighted abnormal parameter set; use fuzzy reasoning algorithms to comprehensively evaluate the weighted abnormal parameter set, calculate the score of each abnormal parameter through fuzzy membership functions and reasoning rules, and combine the overall health status to obtain a vital sign abnormality confirmation result.

[0114] In this embodiment, the fuzzy logic reasoning mechanism is a mathematical method for handling uncertainty and fuzzy information, suitable for describing and processing imprecise data. In this solution, the fuzzy logic reasoning mechanism is used to analyze the abnormality in the vital sign anomaly detection report, considering various factors such as data fluctuations and environmental influences to determine the authenticity and severity of the anomaly. The preliminary abnormal parameter list is obtained by initially screening all abnormal conditions in the vital sign anomaly detection report. This list contains all possible abnormal parameters and their corresponding values, providing a basis for further analysis. Key vital sign parameters are those closely related to health status, including heart rate, blood pressure, and respiratory rate. They have important reference value in evaluating user health status and can provide key clues about potential health problems. The abnormal parameter set is a collection of key vital sign parameters extracted from the preliminary abnormal parameter list and compared with the preset standard range. It only contains parameter values that exceed the normal range and is used for subsequent weight assignment and comprehensive evaluation. The weighted abnormal parameter set is a collection of each abnormal parameter after weight assignment according to the fuzzy logic rule base. The weight reflects the influence of different parameters on the overall health status, ensuring the accuracy and individualization of the evaluation. The fuzzy membership function is a mathematical tool for mapping input variables to membership values in the [0, 1] interval, representing the degree or likelihood of a certain condition. In this solution, the fuzzy membership function is used to evaluate the severity of each abnormal parameter. The fuzzy reasoning rule is a set of predefined rules that guide the fuzzy reasoning algorithm on how to calculate the output result based on the input data. In this solution, the fuzzy reasoning rule helps the system combine the overall health status of multiple abnormal parameters to obtain the final vital sign anomaly confirmation result.

[0115] In the embodiments of the present application, first, the system identifies and lists all possible abnormal parameters and their corresponding values as the basis for further analysis. Second, the system only retains key vital sign parameters (such as heart rate, blood pressure, and respiratory rate) and compares them with the preset standard range to find parameter values that exceed the normal range. Then, the system assigns appropriate weights to each abnormal parameter according to the fuzzy logic rule base, reflecting its influence on the overall health status. Finally, the system uses the fuzzy reasoning algorithm to evaluate the scores of all abnormal parameters according to the fuzzy membership function and reasoning rules, and finally generates the vital sign anomaly confirmation result, ensuring the accuracy and reliability of the evaluation.

[0116] Here is a specific example:

[0117] In a home care scenario, assume an elderly person with chronic obstructive pulmonary disease wears a multifunctional health monitoring bracelet. The bracelet continuously monitors heart rate, blood oxygen saturation, and respiratory rate and transmits data to the real-time evaluation engine in real time.

[0118] When the elderly person is resting at home, the instant assessment engine detects a sudden drop in his blood oxygen saturation to 85%, which is below the normal range. The system immediately generates an abnormal vital sign detection report, recording the specific values and time of the abnormality.

[0119] Next, the system uses a fuzzy logic reasoning mechanism to preliminarily analyze all abnormal conditions in the abnormal detection report, generating a preliminary abnormal parameter list, including parameters such as blood oxygen saturation, heart rate, and respiratory rate.

[0120] Then, the system extracts key vital sign parameters (heart rate, blood pressure, respiratory rate) and compares them with the pre-set standard range. The results show that the blood oxygen saturation (85%) is significantly lower than the normal range (90%-100%), while the heart rate and respiratory rate are also in the marginal range. The system generates an abnormal parameter set containing only the blood oxygen saturation parameter that exceeds the normal range.

[0121] Next, the system assigns weights to the blood oxygen saturation based on the abnormal parameter set and the fuzzy logic rule base. According to the rule base, the weight of blood oxygen saturation is higher because it has a direct impact on the health of patients with chronic obstructive pulmonary disease. The system generates a weighted abnormal parameter set, in which the blood oxygen saturation is assigned a higher weight value.

[0122] Finally, the system uses a fuzzy reasoning algorithm to comprehensively evaluate the weighted abnormal parameter set. Through the fuzzy membership function and reasoning rules, the system calculates the score of blood oxygen saturation and combines the overall health status of the elderly person (such as medical history and lifestyle habits) to obtain the final vital sign abnormality confirmation result - acute hypoxia event. The system confirms the authenticity and severity of this abnormality and generates a detailed abnormality confirmation report.

[0123] In this way, the system not only solves the problem of inaccurate confirmation of abnormal conditions in the vital sign abnormality detection report, but also achieves rapid and accurate identification of abnormal conditions, significantly improving the quality of remote medical services and user experience. This detailed evaluation method helps doctors better understand the current health status of patients, so as to take timely and effective intervention measures.

[0124] To solve the problem of incomplete and personalized health status assessment, in some embodiments, the pre-trained health risk prediction model is used to comprehensively evaluate the current health status of the user based on the vital sign abnormality confirmation result by comparing the long-term health data of the user with similar cases, generating a health status evaluation result, including:

[0125] The pre-trained health risk prediction model is used to preliminarily evaluate the current health status of the user based on the vital sign abnormality confirmation result, and a preliminary health risk assessment report is obtained. According to the preliminary health risk assessment report, the health status of the user is analyzed in depth by combining the long-term health data of the user, and a personalized health data analysis result is generated. The long-term health data includes past medical history, lifestyle, and activity level. Based on the personalized health data analysis result, similar cases in the medical database are searched for comparative analysis, and a similar case comparative analysis result is generated. The health risk prediction model is adjusted based on the similar case comparative analysis result, and the health risk prediction model is optimized to obtain an optimized health risk prediction model. According to the optimized health risk prediction model, the abnormality confirmation result, the long-term health data, and the similar case information are considered comprehensively to evaluate the current health status of the user, and a health status evaluation result is generated.

[0126] In this embodiment, the pre-trained health risk prediction model is a machine learning model trained on a large amount of historical data and similar cases, which can quickly evaluate the preliminary health risk of the user based on the input vital sign abnormality confirmation result. The model uses advanced algorithms such as neural networks and decision trees to ensure the accuracy and reliability of the evaluation. The preliminary health risk assessment report is the first evaluation report generated based on the vital sign abnormality confirmation result, which describes the preliminary risk level of the user's current health status in detail. This report provides basic information for subsequent in-depth analysis. Long-term health data includes the user's past medical history, lifestyle, and activity level, which can provide long-term background information about the user's health status. Long-term health data is crucial for identifying potential health problems and developing personalized health management strategies. The personalized health data analysis result is generated by in-depth analysis of the user's long-term health data. This result not only reflects the user's current health status, but also reveals their health trends and potential risk factors. The similar case comparative analysis result is generated by searching for similar cases in the medical database and comparing them with the user's situation. Similar cases provide additional reference information, which helps to more accurately assess the user's health risk. The optimized health risk prediction model is adjusted and optimized based on the personalized health data analysis result and the similar case comparative analysis result, making it more suitable for individual differences. The optimized model improves the accuracy of prediction and better reflects the user's actual health status.

[0127] In the embodiments of the present application, first, the system inputs the abnormality confirmation result into the pre-trained health risk prediction model, generates a preliminary health risk assessment report, and records the user's current health risk level. Second, the system deeply analyzes the user's long-term health data, identifies potential factors that may affect health, and generates detailed personalized health data analysis results. Next, the system searches for similar cases to the user's situation, conducts comparative analysis, identifies common problems and solutions in similar cases, and generates similar case comparative analysis results. Further, the system adjusts the parameters of the health risk prediction model according to the information of similar cases, so that it is more suitable for individual differences of the user, and improves the accuracy of prediction. Finally, the system uses the optimized health risk prediction model to generate the final health status assessment result, ensuring the comprehensiveness and personalization of the assessment.

[0128] The following is a specific example:

[0129] In the home care scenario, assume that an old man with chronic obstructive pulmonary disease wears a multifunctional health monitoring bracelet. The bracelet continuously monitors heart rate, blood oxygen saturation, and respiratory rate, and transmits data to the real-time assessment engine in real time.

[0130] When the old man is resting at home, the system detects that his blood oxygen saturation suddenly drops to 85%, which is lower than the normal range. The system immediately generates a vital sign abnormality detection report and confirms that it is an acute hypoxia event through the fuzzy logic reasoning mechanism, generating a vital sign abnormality confirmation result.

[0131] Next, the system uses the pre-trained health risk prediction model to preliminarily assess the old man's current health status based on this acute hypoxia event, and generates a preliminary health risk assessment report, indicating that there is a high acute health risk.

[0132] Then, the system combines the old man's long-term health data (such as past medical history, lifestyle, activity level) to deeply analyze his health status. The system finds that the old man has a history of chronic obstructive pulmonary disease and has recently increased outdoor activity time, which may expose him to poor air quality environments. The system generates a detailed personalized health data analysis result, revealing the impact of these factors on the old man's health.

[0133] Next, the system searches for similar cases in the medical database and finds several patients who also have chronic obstructive pulmonary disease and have experienced acute hypoxia events in similar environments. Through comparative analysis, the system finds that these patients have the common characteristics of poor indoor air quality and excessive exercise, and generates similar case comparative analysis results.

[0134] Subsequently, the system used comparative analysis of similar cases to adjust the parameters of the health risk prediction model, optimizing the model to better adapt to individual differences among the elderly. The optimized model improved the accuracy of predicting acute hypoxic events.

[0135] Finally, based on the optimized health risk prediction model, and taking into account anomaly confirmation results, long-term health data, and information from similar cases, the system comprehensively assesses the elderly person's current health status and generates a detailed health assessment report. The system recommends that the elderly person immediately improve indoor ventilation, reduce outdoor activities, and contact a doctor for further examination. In addition, the system will regularly send health reports to the elderly person and their family to help them better manage their health.

[0136] In this way, the system not only solves the problems of insufficient comprehensiveness and personalization in health assessment, but also achieves accurate assessment and personalized management of users' health status, significantly improving the quality of telemedicine services and user experience. This meticulous assessment method helps doctors better understand patients' current health status, thereby enabling them to take timely and effective intervention measures.

[0137] This application considers that with the increasing focus on health management, especially the needs of patients with chronic diseases and the elderly, accurate and personalized health monitoring has become particularly important. Traditional vital sign monitoring methods often use fixed-frequency data collection, which cannot be flexibly adjusted according to the user's real-time status, leading to wasted resources or missed key health information. Therefore, a dynamic monitoring strategy based on intelligent control algorithms has been developed. This strategy aims to accurately assess the monitoring frequency and accuracy requirements of the user's current state through behavioral pattern recognition, environmental parameter evaluation, and context-aware models. Thus, a new alternative solution is proposed, which includes:

[0138] Based on the information reflecting the user's current state, assess the monitoring frequency and accuracy requirements under the current state, and generate preliminary monitoring requirement assessment results, including:

[0139] Using a behavior pattern recognition algorithm, based on the information reflecting the user's current state, the user's activity type is classified to obtain the classification result of the user's activity type;

[0140] The weighted activity type classification accuracy A is calculated using the following formula. acc :

[0141]

[0142] Among them, A acc This represents the weighted activity type classification accuracy, where N represents the total number of samples, and C represents the total number of samples. i T represents the classification result of the i-th sample.i This represents the true label of the i-th sample. It is an indicator function that returns 1 if the condition is true, and 0 otherwise. act，i This represents the activity weight of the i-th sample, used to emphasize the importance of different activity types;

[0143] Based on the classification results of user activity types and combined with environmental parameters, a comprehensive assessment is conducted on how these factors affect user health, resulting in an environmental adaptability assessment.

[0144] The environmental adaptability score E is calculated using the following formula. score :

[0145]

[0146] Among them, E score This represents the environmental adaptability score, where M represents the number of environmental parameters, and w j E represents the weight of the j-th environmental parameter. j β represents the influence value of the j-th environmental parameter (such as temperature, humidity, etc.). j It is the exponential factor of the j-th environmental parameter, used to adjust the influence intensity of each parameter;

[0147] Based on the environmental adaptability assessment results, a pre-trained context-aware model is applied to predict the potential health risk level of users in the current state and generate a health risk prediction report.

[0148] The health risk probability P can be calculated using the following formula. risk :

[0149] P risk =σ(W T x+b+λ·log(E score ))

[0150] Among them, P risk σ represents the probability of health risk, σ is the Sigmoid function, used to map the result of the linear combination to the interval [0, 1], representing the likelihood of health risk, W is the weight vector of the context-aware model, x is the input feature vector, b is the bias term, and λ is the adjustment coefficient, used to adjust the impact of environmental adaptability score on health risk prediction.

[0151] Based on the health risk prediction report, the specific requirements for monitoring frequency and accuracy under the current conditions are determined. In high-risk situations, more frequent and more accurate data collection is required; while in low-risk or stable situations, the monitoring intensity can be appropriately reduced to save energy, thus obtaining the specific monitoring requirement level.

[0152] The specific monitoring requirement level D can be obtained using the following formula.level :

[0153]

[0154] where D level represents the monitoring demand level, P threshold is the preset risk threshold to distinguish between high and low demand states, δ is the time sensitivity coefficient, and Δt is the time interval since the last assessment, considering the increasing risk over time;

[0155] Integrate the specific monitoring demand level to generate a preliminary monitoring demand assessment result.

[0156] The following explains each parameter in detail:

[0157] N: Total number of samples. This refers to the total number of samples in the dataset used to evaluate the behavior pattern recognition algorithm, usually collected by data collection devices such as smart bands, sensors, and user activity data over a period of time.

[0158] C i : Classification result of the i-th sample. This is the result of classifying each sample by the behavior pattern recognition algorithm, usually obtained through a machine learning model or rule engine.

[0159] T i : True label of the i-th sample. This is the actual activity type label of each sample, usually provided by manual annotation or known standard data.

[0160] I(C i = T i ): Indicator function. This is a binary function that returns 1 when the condition is true, otherwise returns 0. It is used to determine whether the classification result is correct.

[0161] w act，i : Activity weight of the i-th sample. Different activity types have different health importance, so different weights are assigned. These weights can be determined through expert knowledge or historical data analysis.

[0162] M: Number of environmental parameters. This refers to the number of environmental factors considered, such as temperature, humidity, air quality, etc., usually collected in real time by environmental sensors.

[0163] w j : Weight of the j-th environmental parameter. Different environmental parameters have different effects on health, so different weights are assigned. These weights can be determined through expert knowledge or historical data analysis.

[0164] E j: Impact value of the jth environmental parameter. This is the specific measurement of each environmental parameter, such as temperature 22℃, humidity 60% and so on.

[0165] α j : Exponential factor of the jth environmental parameter. Used to adjust the impact strength of each environmental parameter, so that certain parameters (such as air quality) have greater impact in certain situations. The exponential factor can be set according to experimental data or expert opinion.

[0166] σ: Sigmoid function. Used to map the result of linear combination to the interval [0, 1], representing the possibility of health risk. The sigmoid function ensures that the output value is within a reasonable range, facilitating interpretation and application.

[0167] W: Weight vector of the context-aware model. This is the parameter of the pre-trained context-aware model, usually learned from a large amount of historical data through machine learning algorithms.

[0168] x: Input feature vector. This is a feature vector containing user's current state information, such as vital sign data, activity type classification results, etc.

[0169] b: Bias term. This is a constant term of the context-aware model, used to adjust the baseline prediction value of the model.

[0170] λ: Adjustment coefficient. Used to adjust the environmental adaptability score E score to health risk prediction. This coefficient can be adjusted according to actual situation to balance the importance of environmental factors and other features.

[0171] log(E score ): Logarithmic value of environmental adaptability score. Using logarithmic form is to smooth the impact of environmental parameters and prevent extreme values from having excessive influence on prediction results.

[0172] P threshold : Preset risk threshold. This is the benchmark value to distinguish between high demand and low demand states, usually set according to clinical experience and historical data.

[0173] δ: Time sensitivity coefficient. Used to adjust the risk increase over time, reflecting the impact of time on health risk. This coefficient can be set according to the user's health status and living habits.

[0174] Δt: Time interval since the last evaluation. This refers to the length of time since the last evaluation, usually in hours or days.

[0175] Here is a specific example:

[0176] Assume in a home care scenario, an elderly patient with hypertension wears a multifunctional health monitoring bracelet. The bracelet continuously monitors vital sign data such as heart rate, blood pressure, and respiratory rate, and records environmental parameters such as temperature and humidity through environmental sensors. The following are the specific implementation steps:

[0177] The system first uses a behavior pattern recognition algorithm to classify the user's activity type based on information reflecting the user's current state (such as accelerometer and gyroscope data). For example, over a period of time, the system collects N = 100 sample data, which contains the classification results and true labels of activity types such as rest, walking, and running.

[0178] The weighted activity type classification accuracy A is calculated by the following formula acc :

[0179]

[0180] Assume that C i and T i represent the classification result and true label of the i-th sample, I(C i = T i ) is an indicator function that returns 1 when the classification is correct, otherwise returns 0, and w act，i is the activity weight of the i-th sample.

[0181] Substitute the numerical calculation:

[0182]

[0183] That is, the weighted activity type classification accuracy is 95%, indicating that the behavior pattern recognition algorithm has good classification effect in this time period;

[0184] Next, the system evaluates how to affect the user's health condition based on the classification result of the user's activity type and the environmental parameters (such as temperature and humidity), and obtains the environmental adaptability evaluation result. For example, the indoor temperature is 22℃ and the humidity is 60%;

[0185] The environmental adaptability score E is calculated by the following formula score :

[0186]

[0187] Assume that M = 2, indicating that there are two environmental parameters (temperature and humidity), w1 = 0.6 and w2 = 0.4 are the weights of temperature and humidity, E1 = 22 and E2 = 60 are the influence values of temperature and humidity, and α1 = 1.2 and α2 = 1.5 are the exponential factors of temperature and humidity;

[0188] Substitute the numerical calculation:

[0189] E score = 0.6 · 22 1.2 + 0.4 · 60 1.5 ≈ 0.6 · 74.86 + 0.4 · 288.44 ≈ 44.92 + 115.38 = 160.30 The system applies the pre-trained context-aware model to predict the potential health risk level of the user in the current state, generating a health risk prediction report. Assuming that the input feature vector x includes the user's historical health data and current vital sign data, the result of linear combination is mapped to the [0, 1] interval using the Sigmoid function, representing the likelihood of health risk;

[0190] The health risk probability P is calculated by the following formula risk :

[0191] P risk = σ(W T x + b + λ · log(E score ))

[0192] Assuming W T x + b = -0.5, which is the output of the context-aware model, λ = 0.01, and the adjustment coefficient is used to adjust the influence of environmental adaptability score on health risk prediction;

[0193] Substituting the numerical values, we have:

[0194] P risk = σ(-0.5 + 0.01 · log(160.30)) ≈ σ(-0.5 + 0.01 · 2.20) ≈ σ(-0.478) ≈ 0.38

[0195] That is, the health risk probability is about 38%, indicating that there is a certain health risk in the current state, but it has not reached a high risk level;

[0196] According to the health risk prediction report, the system determines the specific needs for monitoring frequency and accuracy in the current state. Assuming that the preset risk threshold P threshold = 0.5, the time sensitivity coefficient δ = 0.05, and the time interval Δt since the last evaluation = 2 hours.

[0197] The specific monitoring demand level D level is obtained by the following formula:

[0198]

[0199] Substituting the numerical values, we have:

[0200] P threshold• (1 + δ·Δt) = 0.5·(1 + 0.05·2) = 0.5·1.1 = 0.55

[0201] Since P risk = 0.38 < 0.55, the monitoring requirement level of the system is "low requirement", which means that the monitoring intensity can be appropriately reduced to save energy under the current state.

[0202] Through the practical application of the above formula, the system not only accurately identifies the activity type of the user, but also comprehensively evaluates the influence of environmental parameters on the health status, and predicts potential health risks through the context perception model. Finally, the system determines the current monitoring requirement level according to the health risk probability, and realizes the reasonable allocation of resources. This refined monitoring strategy helps to improve the efficiency of health management and user experience, ensuring that key health information can be captured under different circumstances, while avoiding unnecessary resource waste.

[0203] The present application considers that with the development of medical technology and the increasing emphasis on health management, precise and personalized health assessment is particularly important. Traditional health assessment methods often rely on the experience of doctors and limited data, and it is difficult to fully consider individual differences and long-term health data of users. Therefore, a comprehensive assessment system based on pre-trained health risk prediction model and similar case comparison analysis is developed, which aims to achieve comprehensive assessment of the current health status of users through multi-level data analysis, and therefore proposes a new optional scheme, which includes:

[0204] Based on the vital sign abnormality confirmation result, the current health status of the user is comprehensively evaluated using the pre-trained health risk prediction model by comparing the long-term health data of the user with similar cases, and a health status evaluation result is generated, including:

[0205] Using the pre-trained health risk prediction model, the current health status of the user is preliminarily evaluated based on the vital sign abnormality confirmation result, and a preliminary health risk score is obtained;

[0206] The preliminary health risk score R initial is calculated by the following formula:

[0207]

[0208] Where R initial is the preliminary health risk score, N is the number of abnormal parameters, w risk，i is the risk weight of the i-th abnormal parameter, A i is the risk score of the i-th abnormal parameter, β i is the exponential factor of the i-th abnormal parameter, which is used to adjust the influence strength of each parameter.

[0209] According to the preliminary health risk assessment report, combined with the user's long-term health data, the user's health status is deeply analyzed to generate a personalized health score;

[0210] The personalized health score S is calculated by the following formula personal :

[0211]

[0212] Where S personal represents the personalized health score, α, β, γ are the weight coefficients of each factor, H represents the past medical history score, L represents the life habit score, A represents the activity level score, and γ H , γ L , γ A are the exponential factors of each factor, used to adjust the importance of different factors;

[0213] Based on the results of personalized health data analysis, search for similar cases in the medical database, find cases matching the user's situation, and conduct comparative analysis to generate a comprehensive assessment process and generate the final health status assessment score;

[0214] The similar case score C is calculated by the following formula similarity :

[0215]

[0216] Where C similarity represents the similar case score, S user represents the user's personalized health score, S case represents the health score of the similar case, and σ is the standard deviation, used to adjust the sensitivity of the similarity function;

[0217] Using the comparative analysis results of similar cases, adjust the parameters of the health risk prediction model, optimize the model to better adapt to the individual differences of the user, and obtain the optimized health risk prediction model;

[0218] According to the optimized health risk prediction model, comprehensively consider the abnormal confirmation result, long-term health data and similar case information, and perform a comprehensive assessment process on the user's current health status to generate a health status assessment score;

[0219] The health status assessment score F is calculated by the following formula final :

[0220]

[0221] Where F finalrepresents the health condition assessment score, θ1, θ2, θ3 are the weight coefficients of each part, representing the influence degree of the preliminary health risk score, personalized health score and similar case score respectively, δ R , δ S , δ C are the index factors of each part, used to adjust the influence strength of different factors.

[0222] The following explains each parameter in detail:

[0223] N: Number of abnormal parameters. This refers to the number of parameters in vital sign data that are identified as abnormal, such as heart rate, blood pressure, etc. These parameters are usually obtained through real-time monitoring devices (such as smart bands, sensors).

[0224] w risk，i : Risk weight of the i-th abnormal parameter. Different parameters have different influence on health risk, so different weights are given. These weights can be determined by expert knowledge or historical data analysis.

[0225] A i : Risk score of the i-th abnormal parameter. This is the risk score calculated according to the specific value of each abnormal parameter, usually obtained through pre-set scoring rules or machine learning models.

[0226] β i : Index factor of the i-th abnormal parameter. Used to adjust the influence strength of each abnormal parameter, so that certain parameters (such as heart problems) have greater influence in certain situations. The index factor can be set according to experimental data or expert opinion.

[0227] α, β, γ: Weight coefficients of each factor. Different factors (past medical history, lifestyle, activity level) have different influence on health condition, so different weights are given. These weights can be determined by expert knowledge or historical data analysis.

[0228] H: Past medical history score. This is the score calculated based on the user's historical disease records, usually obtained through medical records or user-provided information.

[0229] L: Lifestyle score. This is the score calculated based on the user's daily life habits (such as diet, exercise, smoking, etc.), usually obtained through questionnaires or user input data.

[0230] A: Activity level score. This is the score calculated based on the user's daily activity amount (such as walking steps, exercise time, etc.), usually obtained through smart bands or other monitoring devices.

[0231] γ H , γ L , γA : Exponential factor for each factor. Used to adjust the importance of different factors, so that certain factors (such as medical history) have a greater impact in certain situations. The exponential factor can be set according to experimental data or expert opinion.

[0232] S user : Personalized health score of the user. This is the score of the user's current health condition calculated by the above formula.

[0233] S case : Health score of similar cases. This is the health score of cases found in the medical database that match the user's situation, usually obtained through search algorithms and comparison analysis.

[0234] σ: Standard deviation. Used to adjust the sensitivity of the similarity function, ensuring that the similarity evaluation is neither too lenient nor too strict. The standard deviation can be adjusted according to actual conditions.

[0235] θ1, θ2, θ3: Weighting coefficients for each part. Different evaluation parts (preliminary health risk score, personalized health score, similar case score) have different degrees of influence on the final health condition evaluation, so different weights are given. These weights can be determined through expert knowledge or historical data analysis.

[0236] δ R , δ S , δ C : Exponential factor for each part. Used to adjust the influence strength of different evaluation parts, so that certain parts (such as the preliminary health risk score) have a greater impact in certain situations. The exponential factor can be set according to experimental data or expert opinion.

[0237] The reasons for designing each sub-item are introduced as follows:

[0238] Consider the impact of medical history on current health condition. Weight α emphasizes the importance of medical history, while exponential factor γ H flexibly adjusts its influence.

[0239] Consider the impact of lifestyle on current health condition. Weight β emphasizes the importance of lifestyle, while exponential factor γ L flexibly adjusts its influence.

[0240] Consider the impact of activity level on current health condition. Weight γ emphasizes the importance of activity level, while exponential factor γ A flexibly adjusts its influence.

[0241] The weighted index form of each factor is added to consider the contribution of all factors to the health status and generate a comprehensive personalized health score. This approach ensures that each factor is appropriately reflected in the final score while maintaining the interpretability of the assessment results.

[0242] Consider the impact of the preliminary health risk score on the current health status. The weight θ1 emphasizes the importance of the preliminary health risk score, while the index factor δ R Flexibly adjust its impact.

[0243] Consider the impact of the personalized health score on the current health status. The weight θ2 emphasizes the importance of the personalized health score, while the index factor δ S Flexibly adjust its impact.

[0244] Consider the impact of the similar case score on the current health status. The weight θ3 emphasizes the importance of the similar case score, while the index factor δ C Flexibly adjust its impact.

[0245] The weighted index form of each part is added to consider the contribution of all evaluation parts to the health status and generate a comprehensive health status evaluation score. This approach ensures that each evaluation part is appropriately reflected in the final evaluation results while maintaining the interpretability and accuracy of the evaluation results.

[0246] The overall design of this formula aims to achieve a comprehensive evaluation of the user's current health status. By introducing a multi-dimensional evaluation method, the system can comprehensively consider the user's current state, long-term health data, and similar case information to generate a personalized health status evaluation result. Specifically, through the comprehensive evaluation of the preliminary health risk score, the personalized health score, and the similar case score, the system can fully capture the user's health status, ensuring the comprehensiveness and accuracy of the evaluation results. The introduction of weight coefficients and index factors allows the system to flexibly adjust the importance of different factors and evaluation parts, ensuring that the evaluation results adapt to the needs of different users. The use of similar case comparison analysis results to optimize the health risk prediction model enables the system to continuously improve and adapt to individual differences of users, improving the accuracy of the evaluation. Through comprehensive evaluation, the system can dynamically adjust the monitoring strategy, ensuring the effectiveness of health monitoring while reasonably allocating resources and avoiding unnecessary waste.

[0247] This method not only improves the efficiency and accuracy of health management, but also enhances the user experience, ensuring that key health information is captured in different situations and helping users better manage their health status.

[0248] Here is a specific example:

[0249] Assuming in a home care scenario, an elderly patient with high blood pressure wears a multifunctional health monitoring bracelet. The bracelet continuously monitors vital signs data such as heart rate, blood pressure, respiratory rate, etc., and records environmental parameters such as temperature, humidity, etc. in combination with environmental sensors. The following are the specific implementation steps:

[0250] The system first uses a pre-trained health risk prediction model to preliminarily assess the user's current health status based on the abnormality confirmation results of vital signs, and obtains a preliminary health risk score;

[0251] The preliminary health risk score R is calculated by the following formula initial :

[0252]

[0253] Assuming, N = 3, indicating that there are three abnormal parameters (heart rate, blood pressure, blood oxygen saturation), w risk，1 = 0.4, w risk，2 = 0.3, w risk，3 = 0.3 are the risk weights of each abnormal parameter, A1 = 8, A2 = 7, A3 = 6 are the risk scores of each abnormal parameter, β1 = 1.2, β2 = 1.1, β3 = 1.0 are the exponential factors of each abnormal parameter;

[0254] Substitute the numerical value to calculate:

[0255]

[0256] Next, the system combines the user's long-term health data (such as past medical history, lifestyle, activity level) to conduct in-depth analysis on the user's health status, and generates a personalized health score;

[0257] The personalized health score S is calculated by the following formula personal :

[0258]

[0259] Assuming, α = 0.4, β = 0.3, γ = 0.3 are the weight coefficients of each factor, H = 7, L = 6, A = 8 are the past medical history score, lifestyle score, activity level score, respectively, γ H = 1.2, γ L = 1.1, γ A = 1.0 are the exponential factors of each factor;

[0260] Substitute the numerical value to calculate:

[0261] S personal = 0.4·7 1.2 + 0.3·61.1 +0.3·8 1.0 ≈0.4·12.58+0.3·6.6+0.3·8

[0262] ≈5.03+1.98+2.4≈9.41

[0263] The system searches for similar cases in the medical database based on the analysis results of personalized health data, finds cases that match the user's situation, conducts comparative analysis, and generates a similar case score.

[0264] The similar case score C is calculated by the following formula similarity :

[0265]

[0266] Assume that S user = 9.41, the user's personalized health score, S case = 9.3, the health score of the similar case, σ = 0.5, the standard deviation used to adjust the sensitivity of the similarity function;

[0267] Substitute the numerical values for calculation:

[0268]

[0269] Finally, the system comprehensively considers the abnormality confirmation result, long-term health data, and similar case information according to the optimized health risk prediction model to comprehensively evaluate and process the user's current health status, and generates a health status evaluation score.

[0270] The health status evaluation score F is calculated by the following formula final :

[0271]

[0272] Assume that θ1 = 0.4, θ2 = 0.3, and θ3 = 0.3 are the weight coefficients of each part, δ R = 1.2, δ S = 1.1, and δ C = 1.0 are the exponential factors of each part;

[0273] Substitute the numerical values for calculation:

[0274] F final = 0.4·9.17 1.2 + 0.3·9.41 1.1 + 0.3·0.976 1.0

[0275] ≈0.4·13.25+0.3·10.24+0.3·0.976

[0276] ≈5.3+3.07+0.29≈8.66

[0277] Through the practical application of the above formula, the system not only accurately assesses the impact of vital sign abnormality confirmation results on the current health status, but also conducts in-depth analysis combined with the user's long-term health data and similar cases to generate personalized health scores. Finally, by comprehensively considering all factors, the system generates a health status assessment score F final = 8.66, indicating that the user's current health status has certain risks, but overall is still within a controllable range.

[0278] This refined assessment method helps doctors and family members better understand the patient's health status, so as to take timely and effective intervention measures. For example, the system suggests that the elderly pay attention to controlling blood pressure in daily life, maintain good living habits, and regularly conduct health check-ups. In addition, the system will regularly send health reports to the elderly and their family members to help them better manage the health status of the elderly. In this way, the system realizes comprehensive assessment and personalized management of the user's health status, significantly improving the quality of remote medical services and user experience.

[0279] Figure 2 A structural schematic diagram of a multifunctional vital sign monitoring system is provided for the embodiments of the present application, as shown in Figure 2 The system comprises:

[0280] The acquisition module 21 is configured to acquire real-time vital sign signals of a user in different physiological states, and form a multi-dimensional monitoring data set in combination with environmental parameters;

[0281] The adjustment module 22 is configured to apply an intelligent control algorithm to dynamically adjust the monitoring frequency and accuracy based on the multi-dimensional monitoring data set, generate a data collection strategy, and minimize energy consumption to obtain vital sign data;

[0282] The analysis module 23 is configured to analyze the monitored vital sign abnormality based on the vital sign data using an instant assessment engine, and generate a health status assessment result and personalized health suggestions in combination with information such as gender, height, weight, genetic history, and past medical history;

[0283] The synchronization module 24 is configured to safely synchronize the health status assessment result and personalized suggestions to the user's medical monitoring system, support remote medical services, and realize continuous health management.

[0284] Figure 2 The multifunctional vital sign monitoring system can perform Figure 1The multi-functional vital sign monitoring method of the embodiments shown will not be described again in terms of implementation principle and technical effects. The specific manner in which each module and unit in the multi-functional vital sign monitoring system in the above embodiments performs operations has been described in detail in the embodiments related to the method, and will not be described in detail here.

[0285] In one possible design, Figure 2 The multi-functional vital sign monitoring system of the embodiments shown can be implemented as a computing device, such as a computer. Figure 3 As shown, the computing device can include a storage component 31 and a processing component 32.

[0286] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32.

[0287] The processing component 32 is configured to perform the above Figure 1 The multi-functional vital sign monitoring method of the embodiments.

[0288] The processing component 32 can include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic elements for executing the above method.

[0289] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0290] Of course, the computing device can also include other components, such as an input / output interface, a display component, a communication component, etc.

[0291] The input / output interface provides an interface between the processing component and peripheral interface modules, which can be output devices, input devices, etc.

[0292] The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, etc.

[0293] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform, and the computing device can be a cloud server, and the processing component and the storage component can be basic server resources rented or purchased from the cloud computing platform.

[0294] The embodiment of the application further provides a computer storage medium storing a computer program, and the computer program can realize the method when executed by a computer. Figure 1 The multifunctional vital sign monitoring method of the embodiment shown.

[0295] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, the device and the unit described above can refer to the corresponding process in the foregoing method embodiments, and will not be described here.

[0296] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0297] Through the description of the foregoing embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and the necessary general hardware platform, and of course, it can also be realized by hardware. Based on such understanding, the foregoing technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the method described in each embodiment or some parts of the embodiment.

[0298] Finally, it should be noted that: the foregoing embodiments are only used to illustrate the technical solutions of the application, and not to limit them; although the application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application.

Claims

1. A multifunctional vital sign monitoring method, characterized in that, include: The system acquires real-time vital signs signals of users under different physiological states and combines them with environmental parameters to form a multi-dimensional monitoring dataset. Based on the multi-dimensional monitoring dataset, an intelligent control algorithm is applied to dynamically adjust the monitoring frequency and accuracy of real-time vital signs signals, generate a data collection strategy, and collect vital signs data based on the data collection strategy. Based on the vital signs data, the real-time assessment engine analyzes and processes the detected abnormal vital signs, and combines information such as gender, height, weight, genetic history and past medical history to generate health status assessment results and personalized health recommendations. The health status assessment results and personalized recommendations are securely synchronized to the user's medical monitoring system to enable remote medical services and continuous health management; The process involves dynamically adjusting the monitoring frequency and accuracy of real-time vital signs signals using an intelligent control algorithm based on the multi-dimensional monitoring dataset, generating a data collection strategy, and collecting vital sign data based on the data collection strategy, including: By utilizing data analysis techniques and the aforementioned multi-dimensional monitoring dataset, we can identify changes in user behavior patterns, activity levels, and the environment they are in, thereby obtaining information that reflects the user's current state. Based on the information reflecting the user's current state, assess the current state's requirements for monitoring frequency and accuracy, and generate preliminary monitoring requirement assessment results. By combining historical vital sign data, a personalized monitoring frequency and accuracy strategy is developed, and the preliminary monitoring needs assessment results are optimized to obtain an optimized monitoring strategy. Using the optimized monitoring strategy, the monitoring frequency and accuracy of the vital signs signal acquisition equipment are dynamically controlled to obtain vital signs data; Based on the information reflecting the user's current state, the system assesses the monitoring frequency and accuracy requirements under the current state, generating a preliminary monitoring requirement assessment result, including: Using a behavior pattern recognition algorithm, based on the information reflecting the user's current state, the user's activity type is classified to obtain the classification result of the user's activity type; The weighted activity type classification accuracy is calculated using the following formula. : ； in, This indicates the accuracy of the weighted activity type classification. Represents the total number of samples. Indicates the first The classification results of each sample Indicates the first The true label of each sample It is an indicator function that returns 1 when the condition is true, and returns 0 otherwise. Indicates the first The activity weights of each sample are used to emphasize the importance of different activity types; Based on the classification results of user activity types and combined with environmental parameters, a comprehensive assessment is conducted on how these factors affect user health, resulting in an environmental adaptability assessment. The environmental adaptability score is calculated using the following formula. : ； in, Indicates the environmental adaptability score. Indicates the number of environmental parameters. Indicates the first The weights of each environmental parameter, Indicates the first The influence value of each environmental parameter It is the first An exponential factor for each environmental parameter is used to adjust the intensity of the influence of each parameter. Based on the environmental adaptability assessment results, a pre-trained context-aware model is applied to predict the potential health risk level of users in the current state and generate a health risk prediction report. Calculate the probability of health risk using the following formula. : ； in, Indicates the probability of health risk. It is the Sigmoid function, used to map the result of a linear combination to... Within the range, it represents the probability of health risk. It is the weight vector of the context-aware model. It is the input feature vector. It is a bias term. It is an adjustment coefficient used to adjust the impact of environmental adaptability score on health risk prediction; Based on the health risk prediction report, the specific requirements for monitoring frequency and accuracy under the current conditions are determined. In high-risk situations, more frequent and more accurate data collection is required; while in low-risk or stable situations, the monitoring intensity can be appropriately reduced to save energy, thus obtaining the specific monitoring requirement level. The specific monitoring requirement level can be obtained using the following formula. : ； in, Indicates the level of monitoring needs. These are preset risk thresholds used to distinguish between high and low demand states. It is the time sensitivity coefficient. It is the time interval since the last assessment, used to account for the increase in risk over time; By integrating the specific monitoring requirement levels, a preliminary monitoring requirement assessment result is generated.

2. The method according to claim 1, characterized in that, The process involves combining historical vital sign data to develop personalized monitoring frequency and accuracy strategies, optimizing the initial monitoring needs assessment results, and obtaining an optimized monitoring strategy, including: Using the preliminary monitoring needs assessment results, the monitoring needs of users in different scenarios are refined to generate specific monitoring needs descriptions. Based on the specific monitoring requirements, integrate users' long-term behavioral patterns, health status trends, and vital sign data to construct a historical model of user behavior and health. Based on the historical model of user behavior and health, a personalized prediction model suitable for users is constructed by applying machine learning algorithms. The personalized prediction model can predict the user's future behavior patterns and their impact on health. Using the personalized prediction model and the specific monitoring requirements, strategies for monitoring frequency and accuracy are formulated for different scenarios, and optimized monitoring strategies are generated.

3. The method according to claim 1, characterized in that, Based on the vital sign data, the system uses a real-time assessment engine to analyze and process any abnormalities in the monitored vital signs. This analysis, combined with information on gender, height, weight, genetic history, and past medical history, generates a health status assessment and personalized health recommendations, including: The vital signs data are analyzed and processed in real time using an instant assessment engine to obtain a vital signs abnormality detection report. The abnormal vital signs detection report is determined based on the fuzzy logic reasoning mechanism, and an abnormal vital signs confirmation result is generated. Based on the confirmed results of abnormal vital signs, the user's current health status is assessed by comparing the user's long-term health data and similar cases, and a pre-trained health risk prediction model is used to generate a health status assessment result. Using the health status assessment results, combined with the user's gender, height, weight, genetic history, lifestyle habits, activity level, and past medical history, customized health advice is provided to the user, generating personalized health recommendations.

4. The method according to claim 3, characterized in that, The process of determining the abnormal vital signs detection report based on the fuzzy logic reasoning mechanism and generating a confirmation result of abnormal vital signs includes: Using fuzzy logic reasoning, the abnormalities in the vital sign abnormality detection report are analyzed to obtain a preliminary list of abnormal parameters; Extract the key vital signs parameters corresponding to the preliminary list of abnormal parameters, compare them with the preset standard range, identify parameter values ​​that exceed the normal range, and generate an abnormal parameter set. The key vital signs parameters include heart rate, blood pressure, and respiratory rate. Based on the set of abnormal parameters that are outside the normal range, and combined with the fuzzy logic rule base, a weighted set of abnormal parameters is generated by assigning weights to each abnormal parameter. The weighted abnormal parameter set is comprehensively evaluated using a fuzzy inference algorithm. The score of each abnormal parameter is calculated by using a fuzzy membership function and inference rules. Combined with the overall health status, the result confirming abnormal vital signs is obtained.

5. The method according to claim 3, characterized in that, Based on the confirmation of abnormal vital signs, the user's current health status is comprehensively assessed using a pre-trained health risk prediction model by comparing the user's long-term health data and similar cases, generating a health status assessment result, including: Using a pre-trained health risk prediction model, based on the confirmed results of abnormal vital signs, a preliminary assessment of the user's current health status is performed to obtain a preliminary health risk assessment report. Based on the preliminary health risk assessment report and combined with the user's long-term health data, an in-depth analysis of the user's health status is conducted to generate personalized health data analysis results. The long-term health data includes past medical history, lifestyle habits, and activity levels. Based on the personalized health data analysis results, similar cases in the medical database are searched for comparative analysis to generate similar case comparison analysis results. Using the results of the comparative analysis of similar cases, the parameters of the health risk prediction model are adjusted and the health risk prediction model is optimized to obtain the optimized health risk prediction model. Based on the optimized health risk prediction model, and taking into account the abnormality confirmation results, long-term health data, and similar case information, the user's current health status is assessed, and a health status assessment result is generated.

6. A multifunctional vital signs monitoring system, used to execute the multifunctional vital signs monitoring method according to any one of claims 1 to 5, characterized in that, include: The acquisition module is used to acquire real-time vital signs signals of users under different physiological states, and combine them with environmental parameters to form a multi-dimensional monitoring dataset. The adjustment module is used to dynamically adjust the monitoring frequency and accuracy based on the multi-dimensional monitoring dataset using an intelligent control algorithm, generate a data collection strategy, and minimize energy consumption to obtain vital sign data. The analysis module is used to analyze and process the monitored abnormalities in vital signs based on the vital sign data using an instant assessment engine, and generate health status assessment results and personalized health recommendations by combining information such as gender, height, weight, genetics and past medical history. The synchronization module is used to securely synchronize the health status assessment results and personalized suggestions to the user's medical monitoring system, supporting remote medical services and enabling continuous health management.

7. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a multifunctional vital sign monitoring method as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that, The device contains a computer program, which, when executed by a computer, implements a multifunctional vital sign monitoring method as described in any one of claims 1 to 5.

Images