Assessment methods, systems, electronic devices and media for children's active health systems

Abstract

The present application provides an evaluation method, system, electronic device and medium for a children's active health system. The method obtains the current health assessment data of the target child through a physiological sensor cluster, and sends the current health assessment data to an active health assessment platform, so that the active health assessment platform obtains the historical health assessment data sequence of the target child based on the identity information, and uses the child's active health assessment model to determine the predicted characteristic value, and then determines the data status of the current health assessment data based on the predicted characteristic value and the current health assessment data. When the data status is a pending data status, a health assessment data pending confirmation instruction is sent to at least one monitoring terminal in the monitoring terminal cluster to achieve timely detection of abnormal conditions and notify the monitoring terminals of relevant medical staff, thereby performing timely abnormal confirmation of health assessment data, which helps to improve the efficiency and accuracy of children's health management.

Description

Technical Field

[0001] The present application relates to data processing technology, and in particular to an evaluation method, system, electronic device and medium for a children's active health system. Background Art

[0002] The existing child health assessment system primarily relies on regular physical examinations and manually recorded data to assess health status. This approach has several shortcomings: first, the infrequency of data collection makes it difficult to capture real-time changes in children's health status; second, data analysis methods are limited, making it difficult to extract valuable health trend information from large amounts of data; and third, the lack of automated and intelligent assessment tools makes the assessment process cumbersome and prone to errors. Furthermore, medical staff often only discover children's health issues after the fact, making it difficult to intervene and address them in a timely manner. Summary of the Invention

[0003] The present application provides an evaluation method, system, electronic device and medium for a children's active health system, which is used to promptly detect abnormal conditions and notify the monitoring terminals of relevant medical staff, thereby promptly confirming abnormalities in health assessment data, which helps to improve the efficiency and accuracy of children's health management.

[0004] In a first aspect, the present application provides a method for evaluating a child's active health system, which is applied to an evaluation system for a child's active health system. The evaluation system for the child's active health system includes a physiological sensor cluster, an active health evaluation platform, and a monitoring terminal cluster. Each physiological sensor in the physiological sensor cluster and each monitoring terminal in the monitoring terminal cluster are respectively communicatively connected to the active health evaluation platform. The method includes:

[0005] Acquiring current health assessment data of the target child through the physiological sensor cluster, and sending the current health assessment data to the active health assessment platform, the current health assessment data including the identity information of the target child and heart rate data within a preset monitoring period;

[0006] The active health assessment platform obtains a historical health assessment data sequence of the target child based on the identity information;

[0007] The active health assessment platform uses a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence. The prediction feature value includes a first prediction feature value and a second prediction feature value. The first prediction feature value is used to characterize the predicted health assessment data based on the historical health assessment data sequence, and the second prediction feature value is used to characterize the change rate of the predicted health assessment data based on the historical health assessment data sequence.

[0008] The active health assessment platform determines the data status of the current health assessment data based on the predicted characteristic value and the current health assessment data, and when the data status is a data state to be confirmed, sends a health assessment data to-be-confirmed instruction to at least one monitoring terminal in the monitoring terminal cluster, wherein the health assessment data to-be-confirmed instruction includes the current health assessment data, the historical health assessment data sequence and the predicted characteristic value.

[0009] In the above scheme, the current health assessment data of the target child is obtained through the physiological sensor cluster, and the current health assessment data is sent to the active health assessment platform, so that the active health assessment platform obtains the historical health assessment data sequence of the target child according to the identity information, and uses the preset child active health assessment model to determine the predicted characteristic value according to the historical health assessment data sequence, and then determines the data status of the current health assessment data according to the predicted characteristic value and the current health assessment data, and when the data status is the data status to be confirmed, sends a health assessment data to-be-confirmed instruction to at least one monitoring terminal in the monitoring terminal cluster, so as to realize timely detection of abnormal situations, and notify the monitoring terminals of relevant medical staff, so as to perform timely abnormal confirmation of health assessment data, which helps to improve the efficiency and accuracy of children's health management.

[0010] In addition, children's health data is obtained in real time through a physiological sensor cluster to ensure the timeliness and accuracy of the data. The active health assessment platform uses historical health data to provide a basis for prediction and improve the accuracy of the prediction. Through the preset children's active health assessment model, future health assessment data and its rate of change are predicted to provide a basis for health intervention. Then, abnormal data is processed for pending confirmation to ensure the reliability and accuracy of the data and avoid misjudgment, so that abnormal situations can be discovered in time and relevant personnel can be notified to take corresponding measures.

[0011] Optionally, the active health assessment platform utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, including:

[0012] The active health assessment platform determines a first estimated value based on the historical health assessment data sequence;

[0013] The active health assessment platform determines a second estimated value based on the historical health assessment data sequence and the first estimated value;

[0014] The active health assessment platform determines a third estimated value based on the historical health assessment data sequence and the second estimated value;

[0015] The active health assessment platform determines a fourth estimated value based on the historical health assessment data sequence and the third estimated value;

[0016] The active health assessment platform determines the first prediction feature value according to the first estimated value, the second estimated value, the third estimated value, and the fourth estimated value.

[0017] In the above scheme, the final predicted characteristic value is determined by iterative calculation of multiple estimated values, and the true value is approached by using multiple stages of step-by-step estimation (first estimated value to fourth estimated value) to reduce errors, thereby more accurately reflecting the trend of children's health data and improving prediction accuracy.

[0018] Optionally, the active health assessment platform utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, including:

[0019] The active health assessment platform uses formula 1 and according to the historical health assessment data sequence Determine the first prediction feature value, where Formula 1 is:

[0020]

[0021] in, is the first predicted feature value, are respectively the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient; Based on The first estimate of Based on and The second estimate of Based on and The third estimate of Based on and The fourth estimate of .

[0022] In the above solution, the calculation method of the first prediction characteristic value is clarified, making the prediction process more standardized and reproducible. Through the above formula 1, using specific weight coefficients combined with historical data for prediction can improve the accuracy and reliability of the prediction.

[0023] In the above formula 1, by combining multiple estimates and their corresponding weight coefficients, the impact of multiple factors on health assessment data is comprehensively considered, thereby achieving a comprehensive and integrated consideration of historical health assessment data. This multi-factor comprehensive approach can improve the accuracy and robustness of predictions and reduce the deviations or errors that may be caused by a single factor. The weight coefficients in the formula are adjustable, which means that the weights can be optimized according to actual conditions or data characteristics to better adapt to different prediction scenarios and needs. The adjustability of the weight coefficients increases the flexibility and adaptability of the model. In addition, as new health assessment data is added, the weight coefficients can also be updated through a certain mechanism to ensure that the model can adapt to changes in data and maintain a high level of prediction accuracy.

[0024] Optionally, before the active health assessment platform determines the first prediction feature value according to the first estimated value, the second estimated value, the third estimated value, and the fourth estimated value, the further step includes:

[0025] The active health assessment platform determines a maximum health assessment value and a median health assessment value based on the historical health assessment data sequence. The maximum health assessment value and the median health assessment value are used to input into a preset estimation characteristic function to determine the first estimation value, the second estimation value, the third estimation value and the fourth estimation value.

[0026] In the above scheme, by determining the maximum and median values ​​of historical data as input, the model can more comprehensively consider the characteristics of historical data, which helps the model to more accurately capture the changing patterns of data. It can not only enhance the robustness of the model and make it unaffected by outliers, but also improve the prediction accuracy.

[0027] Optionally, in determining the first prediction feature value according to the historical health assessment data sequence Previously, it also included:

[0028] The active health assessment platform uses Formula 2 and determines the first estimated value based on the historical health assessment data sequence The second estimated value , the third estimated value and the fourth estimated value , wherein the formula 2 is:

[0029]

[0030] in, is the maximum health assessment value in the historical health assessment data sequence, is the median health assessment value in the historical health assessment data series, is the preset offset value, is the preset monitoring time step, The historical health assessment data sequence Monitoring time nodes, To estimate the characteristic function.

[0031] In the above scheme, by specifically calculating each estimated value, the model's prediction results can be ensured to be more accurate and reliable. Furthermore, in Formula 2 above, full use is made of the statistical information (such as maximum and median values) in the historical health assessment data series. This information can reflect the overall distribution and changing trends of the data, providing an important reference for prediction. Then, by introducing the estimated characteristic function, different function forms can be designed to calculate the estimated values ​​based on specific needs and data characteristics. This flexibility enables the model to adapt to different prediction scenarios and data characteristics. Therefore, by comprehensively considering multiple aspects of historical data (such as maximum and median values) and combining them with the estimated characteristic function for detailed calculation, it helps to improve the accuracy and reliability of the predicted characteristic values, thereby enhancing the performance of the entire health assessment system.

[0032] Optionally, the active health assessment platform utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, further comprising:

[0033] The active health assessment determines the second predicted characteristic value according to the historical health assessment data sequence and the preset estimated characteristic function.

[0034] In the above scheme, by calculating the second predicted characteristic value (predicted rate of change of health assessment data), more dimensions of information are provided for health assessment. Predicting the rate of change of health assessment data helps to detect potential health problems in advance and provide guidance for health intervention.

[0035] Optionally, the active health assessment platform utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, further comprising:

[0036] The active health assessment platform uses formula 3 and according to the historical health assessment data sequence Determine the second prediction characteristic value, the formula 3 is:

[0037]

[0038] in, is the second predicted feature value.

[0039] In the above scenario, Equation 3 can be used to predict the rate of change of health assessment data, which is crucial for assessing changing trends in children's health and implementing early intervention. By understanding the rate of change of health assessment data, doctors, parents, or guardians can more quickly identify potential health problems or signs of improvement, allowing them to make more timely decisions. Furthermore, taking the rate of change of health assessment data into account can make health assessments more comprehensive and accurate, helping the system to promptly detect abnormal trends and notify guardians or medical staff to take necessary measures. This not only helps to promptly identify changing trends in children's health, but also supports more accurate risk assessments, ensuring more effective child health management.

[0040] Optionally, the active health assessment platform determines the data status of the current health assessment data according to the predicted characteristic value and the current health assessment data, including:

[0041] The active health assessment platform determines a first deviation characteristic value based on the first predicted characteristic value and the current health assessment data;

[0042] The active health assessment platform determines the change rate of the current health assessment data based on the current health assessment data and the historical health assessment data sequence;

[0043] The active health assessment platform determines a second deviation characteristic value based on the second predicted characteristic value and the current health assessment data change rate;

[0044] If the active health assessment platform determines that the first deviation characteristic value is greater than the preset first deviation threshold or the second deviation characteristic value is greater than the preset second deviation threshold, the data state of the current health assessment data is determined to be the data state to be confirmed.

[0045] In the above scheme, by comparing the deviation between the predicted value and the actual value, it can be determined whether the current data needs further confirmation to verify the reliability of the current health assessment data, so as to perform confirmation processing on abnormal data and avoid misjudgment and misoperation.

[0046] Optionally, the active health assessment platform determines the data status of the current health assessment data according to the predicted characteristic value and the current health assessment data, including:

[0047] The active health assessment platform determines a first deviation characteristic value based on the first predicted characteristic value and the current health assessment data;

[0048] The active health assessment platform uses Formula 4 to determine the current health assessment data change rate based on the current health assessment data and the historical health assessment data sequence. Formula 4 is:

[0049]

[0050] in, The rate of change of the current health assessment data;

[0051] The active health assessment platform determines a second deviation characteristic value based on the second predicted characteristic value and the current health assessment data change rate;

[0052] If the active health assessment platform determines that the first deviation characteristic value is greater than the preset first deviation threshold or the second deviation characteristic value is greater than the preset second deviation threshold, the data state of the current health assessment data is determined to be the data state to be confirmed.

[0053] In the above scheme, the change rate of the current health assessment data is calculated to provide a basis for determining the data status, and then, the first deviation characteristic value and the second deviation characteristic value are combined to more accurately judge the status of the current health assessment data.

[0054] Optionally, after at least one monitoring terminal in the monitoring terminal cluster sends a health assessment data confirmation instruction, the method further includes:

[0055] The monitoring terminal sends a health assessment data confirmation instruction to the active health assessment platform in response to the health assessment data to be confirmed instruction;

[0056] The active health assessment platform generates an updated health assessment data sequence based on the historical health assessment data sequence and the current health assessment data in response to the health assessment data to be confirmed instruction;

[0057] The active health assessment platform updates the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient according to the updated health assessment data sequence to generate a first updated weight coefficient, a second updated weight coefficient, a third updated weight coefficient and a fourth updated weight coefficient, wherein the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient are used to determine the first predicted characteristic value, and the first updated weight coefficient, the second updated weight coefficient, the third updated weight coefficient and the fourth updated weight coefficient are used to determine the predicted characteristic value of the next time node.

[0058] In the above scheme, the data sequence is updated according to the confirmed health assessment data to ensure the timeliness and accuracy of the data. In addition, by updating the weight coefficient, the system can continuously improve itself as new data is added. While improving the accuracy of subsequent predictions, it can also improve the adaptability and long-term stability of the prediction model and achieve continuous optimization of the model.

[0059] Optionally, after at least one monitoring terminal in the monitoring terminal cluster sends a health assessment data confirmation instruction, the method further includes:

[0060] The monitoring terminal sends a health assessment data confirmation instruction to the active health assessment platform in response to the health assessment data to be confirmed instruction;

[0061] The active health assessment platform generates an updated health assessment data sequence based on the historical health assessment data sequence and the current health assessment data in response to the health assessment data to be confirmed instruction. ;

[0062] The active health assessment platform uses formula 5 and updates the health assessment data sequence according to the The first weight coefficient The second weight coefficient , the third weight coefficient and the fourth weight coefficient Update to generate the first updated weight coefficient , the second updated weight coefficient , the third update weight coefficient And the fourth update weight coefficient , wherein the first update weight coefficient , the second updated weight coefficient , the third updated weight coefficient and the fourth updated weight coefficient For determining the predicted characteristic value of the next time node, the formula 5 is:

[0063]

[0064] in, is the preset adjustment factor.

[0065] In the above scheme, Formula 5 allows the weight coefficient to be dynamically adjusted based on the latest feedback from new health assessment data, thereby improving the adaptability of the prediction model to new data. This dynamic adaptability is particularly important for dealing with scenarios such as children's health assessments, which change significantly over time and may be affected by multiple factors. As health assessment data continues to accumulate and update, the dynamic adjustment of the weight coefficients through Formula 5 can gradually optimize the prediction model, thereby improving the accuracy of predictions for future health assessment data. It can be seen that this weight coefficient update mechanism helps to ensure the stability and effectiveness of the model and ensure that the prediction model can adapt to changes in data. In addition, the above weights can be adjusted to adapt to the prediction of health assessment data for different individuals.

[0066] Optionally, the evaluation system of the children's active health system includes a user terminal cluster, each user terminal in the user terminal cluster is communicatively connected to the active health evaluation platform; after at least one monitoring terminal in the monitoring terminal cluster sends a health evaluation data confirmation instruction, it also includes:

[0067] The monitoring terminal sends a health assessment data abnormality instruction to the active health assessment platform in response to the health assessment data pending confirmation instruction;

[0068] In response to the health assessment data abnormality instruction, the active health assessment platform sends a health assessment data abnormality report to the target user terminal corresponding to the identity information in the user terminal cluster, where the health assessment data abnormality report includes the updated health assessment data sequence.

[0069] In the above solution, by adding the function of user terminal cluster, health abnormality reports can be sent to the corresponding users in a timely manner, thereby ensuring that guardians or relevant responsible persons can quickly understand and deal with children's health problems, thereby improving the responsiveness and practicality of the entire system.

[0070] In a second aspect, the present application provides an assessment system for a child's active health system, comprising: a physiological sensor cluster, an active health assessment platform, and a monitoring terminal cluster, wherein each physiological sensor in the physiological sensor cluster and each monitoring terminal in the monitoring terminal cluster are respectively communicatively connected to the active health assessment platform;

[0071] Acquiring current health assessment data of the target child through the physiological sensor cluster, and sending the current health assessment data to the active health assessment platform, the current health assessment data including the identity information of the target child and heart rate data within a preset monitoring period;

[0072] The active health assessment platform obtains a historical health assessment data sequence of the target child based on the identity information;

[0073] The active health assessment platform uses a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence. The prediction feature value includes a first prediction feature value and a second prediction feature value. The first prediction feature value is used to characterize the predicted health assessment data based on the historical health assessment data sequence, and the second prediction feature value is used to characterize the change rate of the predicted health assessment data based on the historical health assessment data sequence.

[0074] The active health assessment platform determines the data status of the current health assessment data based on the predicted characteristic value and the current health assessment data, and when the data status is a data state to be confirmed, sends a health assessment data confirmation instruction to at least one monitoring terminal in the monitoring terminal cluster, and the health assessment data confirmation instruction includes the current health assessment data, the historical health assessment data sequence and the predicted characteristic value.

[0075] Optionally, the active health assessment platform utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, including:

[0076] The active health assessment platform determines a first estimated value based on the historical health assessment data sequence;

[0077] The active health assessment platform determines a second estimated value based on the historical health assessment data sequence and the first estimated value;

[0078] The active health assessment platform determines a third estimated value based on the historical health assessment data sequence and the second estimated value;

[0079] The active health assessment platform determines a fourth estimated value based on the historical health assessment data sequence and the third estimated value;

[0080] The active health assessment platform determines the first prediction feature value according to the first estimated value, the second estimated value, the third estimated value, and the fourth estimated value.

[0081] Optionally, the active health assessment platform utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, including:

[0082] The active health assessment platform uses formula 1 and according to the historical health assessment data sequence Determine the first prediction feature value, where Formula 1 is:

[0083]

[0084] in, is the first predicted feature value, are respectively the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient; Based on The first estimate of Based on and The second estimate of Based on and The third estimate of Based on and The fourth estimate of .

[0085] Optionally, before the active health assessment platform determines the first prediction feature value according to the first estimated value, the second estimated value, the third estimated value, and the fourth estimated value, the further step includes:

[0086] The active health assessment platform determines a maximum health assessment value and a median health assessment value based on the historical health assessment data sequence. The maximum health assessment value and the median health assessment value are used to input into a preset estimation characteristic function to determine the first estimation value, the second estimation value, the third estimation value and the fourth estimation value.

[0087] Optionally, before determining the first prediction feature value according to the historical health assessment data sequence, the method further includes:

[0088] The active health assessment platform uses Formula 2 and determines the first estimated value based on the historical health assessment data sequence The second estimated value , the third estimated value and the fourth estimated value , wherein the formula 2 is:

[0089]

[0090] in, is the maximum health assessment value in the historical health assessment data sequence, is the median health assessment value in the historical health assessment data series, is the preset offset value, is the preset monitoring time step, The historical health assessment data sequence Monitoring time nodes, To estimate the characteristic function.

[0091] Optionally, the active health assessment platform utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, further comprising:

[0092] The active health assessment determines the second predicted characteristic value according to the historical health assessment data sequence and the preset estimated characteristic function.

[0093] Optionally, the active health assessment platform utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, further comprising:

[0094] The active health assessment platform uses formula 3 and according to the historical health assessment data sequence Determine the second prediction characteristic value, the formula 3 is:

[0095]

[0096] in, is the second predicted feature value.

[0097] Optionally, the active health assessment platform determines the data status of the current health assessment data according to the predicted characteristic value and the current health assessment data, including:

[0098] The active health assessment platform determines a first deviation characteristic value based on the first predicted characteristic value and the current health assessment data;

[0099] The active health assessment platform determines the change rate of the current health assessment data based on the current health assessment data and the historical health assessment data sequence;

[0100] The active health assessment platform determines a second deviation characteristic value based on the second predicted characteristic value and the current health assessment data change rate;

[0101] If the active health assessment platform determines that the first deviation characteristic value is greater than the preset first deviation threshold or the second deviation characteristic value is greater than the preset second deviation threshold, the data state of the current health assessment data is determined to be the data state to be confirmed.

[0102] Optionally, the active health assessment platform determines the data status of the current health assessment data according to the predicted characteristic value and the current health assessment data, including:

[0103] The active health assessment platform determines a first deviation characteristic value based on the first predicted characteristic value and the current health assessment data;

[0104] The active health assessment platform uses Formula 4 to determine the current health assessment data change rate based on the current health assessment data and the historical health assessment data sequence. Formula 4 is:

[0105]

[0106] in, The rate of change of the current health assessment data;

[0107] The active health assessment platform determines a second deviation characteristic value based on the second predicted characteristic value and the current health assessment data change rate;

[0108] If the active health assessment platform determines that the first deviation characteristic value is greater than the preset first deviation threshold or the second deviation characteristic value is greater than the preset second deviation threshold, the data state of the current health assessment data is determined to be the data state to be confirmed.

[0109] Optionally, after at least one monitoring terminal in the monitoring terminal cluster sends a health assessment data confirmation instruction, the method further includes:

[0110] The monitoring terminal sends a health assessment data confirmation instruction to the active health assessment platform in response to the health assessment data to be confirmed instruction;

[0111] The active health assessment platform generates an updated health assessment data sequence based on the historical health assessment data sequence and the current health assessment data in response to the health assessment data to be confirmed instruction;

[0112] The active health assessment platform updates the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient according to the updated health assessment data sequence to generate a first updated weight coefficient, a second updated weight coefficient, a third updated weight coefficient and a fourth updated weight coefficient, wherein the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient are used to determine the first predicted characteristic value, and the first updated weight coefficient, the second updated weight coefficient, the third updated weight coefficient and the fourth updated weight coefficient are used to determine the predicted characteristic value of the next time node.

[0113] Optionally, after at least one monitoring terminal in the monitoring terminal cluster sends a health assessment data confirmation instruction, the method further includes:

[0114] The monitoring terminal sends a health assessment data confirmation instruction to the active health assessment platform in response to the health assessment data to be confirmed instruction;

[0115] The active health assessment platform generates an updated health assessment data sequence based on the historical health assessment data sequence and the current health assessment data in response to the health assessment data to be confirmed instruction. ;

[0116] The active health assessment platform uses formula 5 and updates the health assessment data sequence according to the The first weight coefficient The second weight coefficient , the third weight coefficient and the fourth weight coefficient Update to generate the first updated weight coefficient , the second updated weight coefficient , the third update weight coefficient And the fourth update weight coefficient , wherein the first update weight coefficient , the second updated weight coefficient , the third updated weight coefficient and the fourth updated weight coefficient For determining the predicted characteristic value of the next time node, the formula 5 is:

[0117]

[0118] in, is the preset adjustment factor.

[0119] Optionally, the evaluation system of the children's active health system includes a user terminal cluster, each user terminal in the user terminal cluster is communicatively connected to the active health evaluation platform; after at least one monitoring terminal in the monitoring terminal cluster sends a health evaluation data confirmation instruction, it also includes:

[0120] The monitoring terminal sends a health assessment data abnormality instruction to the active health assessment platform in response to the health assessment data pending confirmation instruction;

[0121] In response to the health assessment data abnormality instruction, the active health assessment platform sends a health assessment data abnormality report to the target user terminal corresponding to the identity information in the user terminal cluster, where the health assessment data abnormality report includes the updated health assessment data sequence.

[0122] In a third aspect, the present application provides an electronic device, comprising:

[0123] processor; and,

[0124] a memory for storing executable instructions of the processor;

[0125] The processor is configured to perform any possible method described in the first aspect by executing the executable instructions.

[0126] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement any possible method described in the first aspect.

[0127] The evaluation method, system, electronic device and medium of the children's active health system provided in this application obtain the current health assessment data of the target child through a physiological sensor cluster, and send the current health assessment data to the active health assessment platform, so that the active health assessment platform obtains the historical health assessment data sequence of the target child based on the identity information, and uses the preset children's active health assessment model to determine the predicted characteristic value based on the historical health assessment data sequence, and then determines the data status of the current health assessment data based on the predicted characteristic value and the current health assessment data, and when the data status is a data state to be confirmed, sends a health assessment data to-be-confirmed instruction to at least one monitoring terminal in the monitoring terminal cluster, so as to realize timely detection of abnormal situations and notify the monitoring terminals of relevant medical staff, thereby performing timely abnormal confirmation of health assessment data, which helps to improve the efficiency and accuracy of children's health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0128] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0129] Figure 1 This is a flowchart of a method for evaluating a child's active health system according to an exemplary embodiment of the present application;

[0130] Figure 2 This is a flowchart of a method for evaluating a child's active health system according to another exemplary embodiment of the present application;

[0131] Figure 3 1 is a schematic structural diagram of an evaluation system for a children's active health system according to an exemplary embodiment of the present application;

[0132] Figure 4 It is a structural diagram of an electronic device according to an exemplary embodiment of the present application.

[0133] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0134] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0135] In order to solve the above problems, the embodiments provided in this application integrate physiological sensor clusters, active health assessment platforms and monitoring terminal clusters to achieve comprehensive collection, intelligent analysis and timely feedback of children's health data, thereby effectively improving the level and efficiency of children's health management.

[0136] In order to achieve the above objectives, the technical solutions conceived by the present invention mainly include the following aspects:

[0137] Data acquisition system:

[0138] A physiological sensor cluster, including heart rate sensors, temperature sensors, and other types of sensors, collects real-time health assessment data from target children, including their identity information and physiological indicators such as heart rate over a preset monitoring period. These sensors communicate with each monitoring terminal in the cluster to ensure timely data upload and storage.

[0139] Data processing and analysis platform:

[0140] The active health assessment platform, the core of data processing and analysis, first retrieves a series of historical health assessment data from a historical database based on the target child's identity information. It then uses a pre-defined child active health assessment model to analyze and model this historical data and determine predictive eigenvalues. These predictive eigenvalues ​​include a first predictive eigenvalue (representing the predicted health assessment data based on the historical data) and a second predictive eigenvalue (representing the rate of change of the predicted health assessment data based on the historical data).

[0141] Anomaly detection and feedback mechanism:

[0142] The active health assessment platform compares and analyzes predicted eigenvalues ​​with current health assessment data collected in real time. By calculating metrics such as deviation eigenvalues ​​and rates of change, it determines whether the current data is abnormal. Upon detecting abnormal data (i.e., data in the pending confirmation state), the platform immediately sends a health assessment data pending confirmation instruction to at least one monitoring terminal in the monitoring terminal cluster, providing the current data, historical data series, and predicted eigenvalues ​​as reference information. Upon receiving the instruction, the monitoring terminal can further verify the data and send a confirmation or exception instruction to the platform.

[0143] Model optimization and adaptive adjustment:

[0144] Once the data is confirmed, the platform generates an updated health assessment data sequence based on the historical and current health assessment data. Simultaneously, a specific update formula is used to dynamically adjust the weight coefficients in the model to adapt to changing data trends and ensure the accuracy and stability of the prediction model. Furthermore, the system supports access to user terminal clusters, enabling the immediate transmission of abnormal health assessment data reports to targeted users, enabling remote monitoring and timely intervention.

[0145] By implementing the technical solution of this application, the following significant technical effects can be achieved:

[0146] Real-time monitoring and accurate assessment: Real-time monitoring and accurate assessment of children's health data can be achieved to promptly identify potential health problems and provide strong support for medical intervention.

[0147] Improve management efficiency: Automated and intelligent data processing and analysis processes significantly improve the efficiency of child health management and reduce the workload of medical staff.

[0148] Enhanced data reliability: Through anomaly detection and feedback mechanisms, the reliability of health assessment data is effectively improved, avoiding misjudgments and erroneous operations.

[0149] Model adaptive optimization: Dynamically adjust the weight coefficient of the prediction model according to the new health assessment data, achieving adaptive optimization and long-term stability of the model.

[0150] In summary, the inventive concept of this application is to provide a comprehensive, efficient and accurate evaluation method and system for children's active health system, which is of great significance for improving the level of children's health management.

[0151] Figure 1 FIG. 1 is a flow chart of a method for evaluating a child's active health system according to an exemplary embodiment of the present application. Figure 1 As shown, the evaluation method of the children's active health system provided in this embodiment includes:

[0152] S101. Acquire current health assessment data of a target child through a physiological sensor cluster, and send the current health assessment data to an active health assessment platform.

[0153] The method provided in this embodiment can be applied to the evaluation system of the children's active health system. The evaluation system of the children's active health system includes a physiological sensor cluster, an active health evaluation platform, and a monitoring terminal cluster. Each physiological sensor in the physiological sensor cluster and each monitoring terminal in the monitoring terminal cluster are respectively connected to the active health evaluation platform in communication. These physiological sensors include but are not limited to heart rate sensors, body temperature sensors, etc., which can monitor and record key physiological indicators of children such as heart rate and body temperature in real time. The collected data includes the identity information of the target child (such as name, age, gender, etc.) and heart rate data within a preset monitoring period. These data are sent to the active health evaluation platform via wireless communication to ensure the real-time and accuracy of the data.

[0154] In this step, the current health assessment data of the target child is obtained through the physiological sensor cluster and sent to the active health assessment platform. The current health assessment data includes the identity information of the target child and the heart rate data within the preset monitoring time.

[0155] Specifically, each sensor in the physiological sensor cluster is equipped with a built-in wireless communication module, enabling it to automatically establish a connection with a specific monitoring terminal in the monitoring terminal cluster. The monitoring terminal acts as a data transfer station, forwarding the collected sensor data to the active health assessment platform via a more stable network connection (such as Wi-Fi, 4G / 5G, etc.). During this process, the security and integrity of data transmission are ensured through encryption technology and verification mechanisms.

[0156] S102. The active health assessment platform obtains the historical health assessment data sequence of the target child based on the identity information.

[0157] In this step, after receiving the current health assessment data, the active health assessment platform first retrieves the corresponding historical health assessment data sequence from the database based on the identity information contained in the data (such as the child's ID number). This historical data records the changes in the child's physiological indicators at different time points, providing a basis for subsequent data analysis and prediction.

[0158] The active health assessment platform features an efficient data retrieval mechanism that can quickly locate and extract historical health records for target children. The platform also includes data cleaning and preprocessing capabilities, automatically identifying and removing outliers or missing data to ensure data quality for analysis.

[0159] S103. The active health assessment platform uses a preset children's active health assessment model and determines the predicted characteristic value based on the historical health assessment data sequence.

[0160] In this step, the active health assessment platform uses a preset children's active health assessment model and determines the predicted characteristic value based on the historical health assessment data sequence. The predicted characteristic value includes a first predicted characteristic value and a second predicted characteristic value. The first predicted characteristic value is used to characterize the predicted health assessment data based on the historical health assessment data sequence, and the second predicted characteristic value is used to characterize the change rate of the predicted health assessment data based on the historical health assessment data sequence.

[0161] Optionally, the above-mentioned preset child active health assessment model can be constructed by using dynamic differential equations to form a child digital twin health profile.

[0162] Specifically, the platform can utilize a pre-defined active health assessment model for children, performing data analysis and prediction based on retrieved historical health assessment data sequences. The model uses complex algorithms and machine learning techniques to identify patterns and trends in the data and determine predictive eigenvalues. These predictive eigenvalues ​​include a first predictive eigenvalue (representing the predicted health assessment data based on historical data) and a second predictive eigenvalue (representing the rate of change of the predicted health assessment data based on historical data).

[0163] Specifically, the model first analyzes and models historical data, extracting key features and constructing a predictive model. The model then calculates the first and second predicted feature values ​​based on the latest historical data input. These predicted values ​​not only reflect the child's current and future health status expectations but also provide important information on health status trends.

[0164] In one possible implementation, the active health assessment platform may determine a first estimate based on a historical health assessment data sequence; the active health assessment platform may determine a second estimate based on a historical health assessment data sequence and the first estimate; the active health assessment platform may determine a third estimate based on a historical health assessment data sequence and the second estimate; the active health assessment platform may determine a fourth estimate based on a historical health assessment data sequence and the third estimate; the active health assessment platform may determine a first predictive feature value based on the first estimate, the second estimate, the third estimate, and the fourth estimate.

[0165] Furthermore, before the active health assessment platform determines the first prediction feature value according to the first estimated value, the second estimated value, the third estimated value, and the fourth estimated value, the following steps may be further included:

[0166] The active health assessment platform determines the maximum health assessment value and the median health assessment value based on the historical health assessment data sequence. The maximum health assessment value and the median health assessment value are used to input into the preset estimation characteristic function to determine the first estimation value, the second estimation value, the third estimation value and the fourth estimation value.

[0167] The final predicted characteristic value is determined through iterative calculation of multiple estimated values, and the true value is approached by using multiple stages of step-by-step estimation (first estimated value to fourth estimated value), thereby reducing errors, thereby more accurately reflecting the trend of children's health data and improving prediction accuracy.

[0168] Furthermore, proactive health assessments can determine a second predicted characteristic value based on historical health assessment data sequences and a preset estimated characteristic function. This second predicted characteristic value (the predicted rate of change in health assessment data) provides additional information for health assessments. Predicting the rate of change in health assessment data can help identify potential health issues in advance and provide guidance for health interventions.

[0169] S104. The active health assessment platform determines the data status of the current health assessment data according to the predicted characteristic value and the current health assessment data.

[0170] In this step, the active health assessment platform determines the data status of the current health assessment data based on the predicted characteristic value and the current health assessment data, and when the data status is a data state to be confirmed, sends a health assessment data to-be-confirmed instruction to at least one monitoring terminal in the monitoring terminal cluster. The health assessment data to-be-confirmed instruction includes the current health assessment data, the historical health assessment data sequence, and the predicted characteristic value.

[0171] After obtaining the predicted characteristic values, the active health assessment platform compares and analyzes them with the current health assessment data collected in real time. By calculating indicators such as deviation characteristic values ​​and rate of change, the platform can determine whether there are any anomalies in the current data. If the data status is determined to be pending confirmation (i.e., there is a significant deviation or abnormal trend), the platform will immediately send a health assessment data pending confirmation instruction to at least one monitoring terminal in the monitoring terminal cluster. This instruction contains key information such as the current health assessment data, historical health assessment data series, and predicted characteristic values, so that the operator of the monitoring terminal can quickly understand the data background and anomalies. After receiving the instruction, the monitoring terminal will immediately initiate the data verification process and confirm the authenticity and accuracy of the data through communication with medical staff. Once the data is confirmed or new issues are discovered, the monitoring terminal will send corresponding feedback instructions to the active health assessment platform.

[0172] In one possible implementation, the active health assessment platform determines a first deviation characteristic value based on the first predicted characteristic value and the current health assessment data; the active health assessment platform determines the rate of change of the current health assessment data based on the current health assessment data and the historical health assessment data sequence; the active health assessment platform determines a second deviation characteristic value based on the second predicted characteristic value and the rate of change of the current health assessment data; if the active health assessment platform determines that the first deviation characteristic value is greater than the preset first deviation threshold or the second deviation characteristic value is greater than the preset second deviation threshold, then the data status of the current health assessment data is determined to be a data status to be confirmed.

[0173] In this embodiment, the current health assessment data of the target child is obtained through a physiological sensor cluster, and the current health assessment data is sent to an active health assessment platform, so that the active health assessment platform obtains the historical health assessment data sequence of the target child based on the identity information, and uses a preset child active health assessment model to determine the predicted characteristic value based on the historical health assessment data sequence, and then determines the data status of the current health assessment data based on the predicted characteristic value and the current health assessment data, and when the data status is a data status to be confirmed, sends a health assessment data to-be-confirmed instruction to at least one monitoring terminal in the monitoring terminal cluster, so as to realize timely detection of abnormal situations, and notify the monitoring terminals of relevant medical staff, so as to perform timely abnormal confirmation of health assessment data, which helps to improve the efficiency and accuracy of child health management.

[0174] Figure 2 FIG. 1 is a flow chart of an evaluation method for a children's active health system according to another exemplary embodiment of the present application. Figure 2 As shown, the method provided in this embodiment includes:

[0175] S201. Acquire current health assessment data of the target child through a physiological sensor cluster, and send the current health assessment data to an active health assessment platform.

[0176] In this step, the current health assessment data of the target child is obtained through the physiological sensor cluster and sent to the active health assessment platform. The current health assessment data includes the identity information of the target child and the heart rate data within the preset monitoring time.

[0177] Specifically, each sensor in the physiological sensor cluster is equipped with a built-in wireless communication module, enabling it to automatically establish a connection with a specific monitoring terminal in the monitoring terminal cluster. The monitoring terminal acts as a data transfer station, forwarding the collected sensor data to the active health assessment platform via a more stable network connection (such as Wi-Fi, 4G / 5G, etc.). During this process, the security and integrity of data transmission are ensured through encryption technology and verification mechanisms.

[0178] S202. The active health assessment platform obtains a historical health assessment data sequence of the target child based on the identity information.

[0179] In this step, after receiving the current health assessment data, the active health assessment platform first retrieves the corresponding historical health assessment data sequence from the database based on the identity information contained in the data (such as the child's ID number). This historical data records the changes in the child's physiological indicators at different time points, providing a basis for subsequent data analysis and prediction.

[0180] The active health assessment platform features an efficient data retrieval mechanism that can quickly locate and extract historical health records for target children. The platform also includes data cleaning and preprocessing capabilities, automatically identifying and removing outliers or missing data to ensure data quality for analysis.

[0181] S203. The active health assessment platform uses a preset children's active health assessment model and determines a prediction feature value based on a historical health assessment data sequence.

[0182] In this step, the active health assessment platform uses a preset children's active health assessment model and determines the predicted characteristic value based on the historical health assessment data sequence. The predicted characteristic value includes a first predicted characteristic value and a second predicted characteristic value. The first predicted characteristic value is used to characterize the predicted health assessment data based on the historical health assessment data sequence, and the second predicted characteristic value is used to characterize the change rate of the predicted health assessment data based on the historical health assessment data sequence.

[0183] In one possible implementation, the active health assessment platform utilizes Formula 1 and uses the historical health assessment data series Determine the first predicted characteristic value, where Formula 1 is:

[0184]

[0185] in, is the first predicted eigenvalue, are respectively the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient; Based on The first estimate of Based on and The second estimate of Based on and The third estimate of Based on and The fourth estimate of .

[0186] In the above formula 1, by combining multiple estimates and their corresponding weight coefficients, the impact of multiple factors on health assessment data is comprehensively considered, thereby achieving a comprehensive and integrated consideration of historical health assessment data. This multi-factor comprehensive approach can improve the accuracy and robustness of predictions and reduce the deviations or errors that may be caused by a single factor. The weight coefficients in the formula are adjustable, which means that the weights can be optimized according to actual conditions or data characteristics to better adapt to different prediction scenarios and needs. The adjustability of the weight coefficients increases the flexibility and adaptability of the model. In addition, as new health assessment data is added, the weight coefficients can also be updated through a certain mechanism to ensure that the model can adapt to changes in data and maintain a high level of prediction accuracy.

[0187] Determine the first prediction feature value based on the historical health assessment data series Previously, it also included:

[0188] The active health assessment platform uses formula 2 and determines the first estimate based on the historical health assessment data series , the second estimate , the third estimate and the fourth estimate , where Formula 2 is:

[0189]

[0190] in, is the maximum health assessment value in the historical health assessment data series, is the median health assessment value in the historical health assessment data series, is the preset offset value, is the preset monitoring time step, The first Monitoring time nodes, To estimate the characteristic function.

[0191] In the above scheme, by specifically calculating each estimated value, the model's prediction results can be ensured to be more accurate and reliable. Furthermore, in Formula 2 above, full use is made of the statistical information (such as maximum and median values) in the historical health assessment data series. This information can reflect the overall distribution and changing trends of the data, providing an important reference for prediction. Then, by introducing the estimated characteristic function, different function forms can be designed to calculate the estimated values ​​based on specific needs and data characteristics. This flexibility enables the model to adapt to different prediction scenarios and data characteristics. Therefore, by comprehensively considering multiple aspects of historical data (such as maximum and median values) and combining them with the estimated characteristic function for detailed calculation, it helps to improve the accuracy and reliability of the predicted characteristic values, thereby enhancing the performance of the entire health assessment system.

[0192] In addition, the active health assessment platform uses a pre-set children's active health assessment model and determines predictive feature values ​​based on historical health assessment data series, and also includes:

[0193] The active health assessment platform uses formula 3 and is based on the historical health assessment data series. Determine the second prediction feature value, formula 3 is:

[0194]

[0195] in, is the second predicted feature value.

[0196] In the above scenario, Equation 3 can be used to predict the rate of change of health assessment data, which is crucial for assessing changing trends in children's health and implementing early intervention. By understanding the rate of change of health assessment data, doctors, parents, or guardians can more quickly identify potential health problems or signs of improvement, allowing them to make more timely decisions. Furthermore, taking the rate of change of health assessment data into account can make health assessments more comprehensive and accurate, helping the system to promptly detect abnormal trends and notify guardians or medical staff to take necessary measures. This not only helps to promptly identify changing trends in children's health, but also supports more accurate risk assessments, ensuring more effective child health management.

[0197] S204: The active health assessment platform determines the data status of the current health assessment data according to the predicted characteristic value and the current health assessment data.

[0198] In this step, the active health assessment platform determines the data status of the current health assessment data based on the predicted characteristic value and the current health assessment data, and when the data status is a data state to be confirmed, sends a health assessment data to-be-confirmed instruction to at least one monitoring terminal in the monitoring terminal cluster. The health assessment data to-be-confirmed instruction includes the current health assessment data, the historical health assessment data sequence, and the predicted characteristic value.

[0199] In one possible implementation, the active health assessment platform determines a first deviation characteristic value based on the first predicted characteristic value and the current health assessment data;

[0200] The active health assessment platform uses formula 4.1 to determine the current health assessment data change rate based on the current health assessment data and the historical health assessment data sequence. Formula 4.1 is:

[0201]

[0202] in, Assess the rate of change of data for current health;

[0203] The active health assessment platform determines a second deviation characteristic value based on the second predicted characteristic value and the current health assessment data change rate;

[0204] If the active health assessment platform determines that the first deviation characteristic value is greater than the preset first deviation threshold or the second deviation characteristic value is greater than the preset second deviation threshold, the data state of the current health assessment data is determined to be a pending data state.

[0205] Optionally, the active health assessment platform can also use formula 4.2 and use a dynamic differential equation to determine the change rate of the current health assessment data based on the current health assessment data and the historical health assessment data sequence. Formula 4.2 is:

[0206]

[0207] in, x(t) is the state variable vector of the system, which changes with time t. In this embodiment, it can be S i ; dx / dt is the derivative of the state variable vector with respect to time t, which describes the rate of change of the state variable; f It is a vector function that defines the relationship between the rate of change of the state variable and the current state, input, time and parameters; f for Dynamically changing functional relationships; u(t) is an external input vector that may change over time, affecting the dynamic behavior of the system and is calculated using actual data; p It is a parameter vector containing constant or variable parameters that affect the dynamic behavior of the system and can be determined by experience.

[0208] S205: The monitoring terminal sends a health assessment data confirmation instruction to the active health assessment platform in response to the health assessment data confirmation instruction.

[0209] In response to the health assessment data pending confirmation instruction, the monitoring terminal sends a health assessment data confirmation instruction to the active health assessment platform. After the active health assessment platform sends the health assessment data pending confirmation instruction to at least one monitoring terminal in the monitoring terminal cluster, the monitoring terminal receives the instruction. This instruction contains the current health assessment data, the historical health assessment data sequence, and the predicted feature value. The operator of the monitoring terminal reviews this data to assess the authenticity and accuracy of the current health assessment data.

[0210] After the operator of the monitoring terminal confirms that the current health assessment data is correct or has undergone necessary adjustments, a health assessment data confirmation instruction will be sent to the active health assessment platform through the monitoring terminal. This step confirms the accuracy and validity of the data.

[0211] S206 : The active health assessment platform generates an updated health assessment data sequence according to the historical health assessment data sequence and the current health assessment data in response to the health assessment data pending confirmation instruction.

[0212] In this step, after receiving the health assessment data confirmation instruction from the monitoring terminal, the active health assessment platform will generate an updated health assessment data sequence based on the historical health assessment data sequence and the currently confirmed health assessment data. This updated sequence will include all confirmed historical data and the newly confirmed current data, providing comprehensive data support for subsequent health assessments.

[0213] Specifically, the active health assessment platform responds to the health assessment data confirmation instruction and generates an updated health assessment data sequence based on the historical health assessment data sequence and the current health assessment data. .

[0214] S207. The active health assessment platform updates the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient according to the updated health assessment data sequence to generate a first updated weight coefficient, a second updated weight coefficient, a third updated weight coefficient and a fourth updated weight coefficient.

[0215] In this step, the active health assessment platform updates the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient according to the updated health assessment data sequence to generate the first updated weight coefficient, the second updated weight coefficient, the third updated weight coefficient and the fourth updated weight coefficient, wherein the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient are used to determine the first predicted characteristic value, and the first updated weight coefficient, the second updated weight coefficient, the third updated weight coefficient and the fourth updated weight coefficient are used to determine the predicted characteristic value of the next time node.

[0216] In one possible implementation, the active health assessment platform uses Formula 5 and updates the health assessment data sequence according to For the first weight coefficient , the second weight coefficient , the third weight coefficient and the fourth weight coefficient Update to generate the first updated weight coefficient , the second updated weight coefficient , the third update weight coefficient And the fourth update weight coefficient , where the first updated weight coefficient is , the second updated weight coefficient , the third update weight coefficient And the fourth update weight coefficient Formula 5 is used to determine the predicted feature value of the next time node:

[0217]

[0218] in, is the preset adjustment factor.

[0219] Based on the above embodiment, the evaluation system of the children's active health system may further include a user terminal cluster, each user terminal in the user terminal cluster being communicatively connected to the active health evaluation platform; after at least one monitoring terminal in the monitoring terminal cluster sends a health evaluation data confirmation instruction, the system may further include:

[0220] The monitoring terminal sends a health assessment data abnormality instruction to the active health assessment platform in response to the health assessment data pending confirmation instruction.

[0221] The active health assessment platform responds to the health assessment data abnormality instruction and sends a health assessment data abnormality report to the target user terminal corresponding to the identity information in the user terminal cluster. The health assessment data abnormality report includes an updated health assessment data sequence.

[0222] Specifically, after the active health assessment platform sends a health assessment data confirmation instruction to at least one monitoring terminal in the monitoring terminal cluster, if the operator of the monitoring terminal finds that the current health assessment data is abnormal (such as significantly deviating from the normal range or inconsistent with historical data trends), the monitoring terminal will send a health assessment data abnormal instruction to the active health assessment platform through the monitoring terminal. This instruction marks the current data as abnormal and requests further processing.

[0223] Upon receiving a health assessment data anomaly indication from a monitoring terminal, the active health assessment platform immediately analyzes the indication to identify the specific content and circumstances of the anomaly. Based on the information contained in the anomaly indication, the platform further analyzes the discrepancies between the current health assessment data and historical data to verify the authenticity and severity of the anomaly.

[0224] After confirming a data anomaly, the proactive health assessment platform will generate a detailed health assessment data anomaly report based on the currently confirmed anomaly data, historical health assessment data series, and updated health assessment data series (if available). This report will include the details of the anomaly data, the time of the anomaly, possible cause analysis, and recommendations for follow-up actions.

[0225] The proactive health assessment platform sends health assessment data anomaly reports to target user terminals (such as children's parents or guardians) corresponding to the abnormal data through user terminal clusters. The reports are presented in an easy-to-understand format, ensuring users can quickly understand any abnormalities in their children's health data and take appropriate action.

[0226] After receiving a report on abnormal health assessment data, users will be able to promptly understand changes in their child's health status and take appropriate measures based on the recommendations in the report. If necessary, users can contact medical institutions or professionals for further consultation and treatment.

[0227] Figure 3 FIG. 1 is a schematic diagram of a structure of an evaluation system for a children's active health system according to an exemplary embodiment of the present application. Figure 3 As shown, the evaluation system 300 for the children's active health system provided in this embodiment includes:

[0228] A physiological sensor cluster 310, an active health assessment platform 320, and a monitoring terminal cluster 330, wherein each physiological sensor in the physiological sensor cluster 310 and each monitoring terminal in the monitoring terminal cluster 330 are respectively in communication with the active health assessment platform 320;

[0229] Acquire current health assessment data of the target child through the physiological sensor cluster 310 and send the current health assessment data to the active health assessment platform 320 , wherein the current health assessment data includes the identity information of the target child and heart rate data within a preset monitoring period;

[0230] The active health assessment platform 320 obtains a historical health assessment data sequence of the target child based on the identity information;

[0231] The active health assessment platform 320 uses a preset child active health assessment model and determines a prediction feature value based on the historical health assessment data sequence. The prediction feature value includes a first prediction feature value and a second prediction feature value. The first prediction feature value is used to represent the predicted health assessment data based on the historical health assessment data sequence, and the second prediction feature value is used to represent the change rate of the predicted health assessment data based on the historical health assessment data sequence.

[0232] The active health assessment platform 320 determines the data status of the current health assessment data based on the predicted characteristic value and the current health assessment data, and when the data status is a data state to be confirmed, sends a health assessment data confirmation instruction to at least one monitoring terminal in the monitoring terminal cluster 330, and the health assessment data confirmation instruction includes the current health assessment data, the historical health assessment data sequence and the predicted characteristic value.

[0233] Optionally, the active health assessment platform 320 uses a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, including:

[0234] The active health assessment platform 320 determines a first estimated value based on the historical health assessment data sequence;

[0235] The active health assessment platform 320 determines a second estimated value based on the historical health assessment data sequence and the first estimated value;

[0236] The active health assessment platform 320 determines a third estimated value based on the historical health assessment data sequence and the second estimated value;

[0237] The active health assessment platform 320 determines a fourth estimated value based on the historical health assessment data sequence and the third estimated value;

[0238] The active health assessment platform 320 determines the first prediction feature value according to the first estimated value, the second estimated value, the third estimated value, and the fourth estimated value.

[0239] Optionally, the active health assessment platform 320 uses a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, including:

[0240] The active health assessment platform 320 uses formula 1 and according to the historical health assessment data sequence Determine the first prediction feature value, where Formula 1 is:

[0241]

[0242] in, is the first predicted feature value, are respectively the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient; Based on The first estimate of Based on and The second estimate of Based on and The third estimate of Based on and The fourth estimate of .

[0243] Optionally, before the active health assessment platform 320 determines the first prediction feature value according to the first estimated value, the second estimated value, the third estimated value, and the fourth estimated value, the further step includes:

[0244] The active health assessment platform 320 determines the maximum health assessment value and the median health assessment value based on the historical health assessment data sequence, and the maximum health assessment value and the median health assessment value are used to input into a preset estimation characteristic function to determine the first estimation value, the second estimation value, the third estimation value and the fourth estimation value.

[0245] Optionally, in determining the first prediction feature value according to the historical health assessment data sequence Previously, it also included:

[0246] The active health assessment platform 320 uses Formula 2 and determines the first estimated value based on the historical health assessment data sequence The second estimated value , the third estimated value and the fourth estimated value , wherein the formula 2 is:

[0247]

[0248] in, is the maximum health assessment value in the historical health assessment data sequence, is the median health assessment value in the historical health assessment data series, is the preset offset value, is the preset monitoring time step, The historical health assessment data sequence Monitoring time nodes, To estimate the characteristic function.

[0249] Optionally, the active health assessment platform 320 utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, further comprising:

[0250] The active health assessment determines the second predicted characteristic value according to the historical health assessment data sequence and the preset estimated characteristic function.

[0251] Optionally, the active health assessment platform 320 utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, further comprising:

[0252] The active health assessment platform 320 uses formula 3 and according to the historical health assessment data sequence Determine the second prediction characteristic value, the formula 3 is:

[0253]

[0254] in, is the second predicted feature value.

[0255] Optionally, the active health assessment platform 320 determines the data status of the current health assessment data according to the predicted characteristic value and the current health assessment data, including:

[0256] The active health assessment platform 320 determines a first deviation characteristic value based on the first predicted characteristic value and the current health assessment data;

[0257] The active health assessment platform 320 determines the change rate of the current health assessment data based on the current health assessment data and the historical health assessment data sequence;

[0258] The active health assessment platform 320 determines a second deviation characteristic value based on the second predicted characteristic value and the current health assessment data change rate;

[0259] If the active health assessment platform 320 determines that the first deviation characteristic value is greater than the preset first deviation threshold or the second deviation characteristic value is greater than the preset second deviation threshold, the data state of the current health assessment data is determined to be the data state to be confirmed.

[0260] Optionally, the active health assessment platform 320 determines the data status of the current health assessment data according to the predicted characteristic value and the current health assessment data, including:

[0261] The active health assessment platform 320 determines a first deviation characteristic value based on the first predicted characteristic value and the current health assessment data;

[0262] The active health assessment platform 320 uses Formula 4 to determine the current health assessment data change rate based on the current health assessment data and the historical health assessment data sequence. Formula 4 is:

[0263]

[0264] in, The rate of change of the current health assessment data;

[0265] The active health assessment platform 320 determines a second deviation characteristic value based on the second predicted characteristic value and the current health assessment data change rate;

[0266] If the active health assessment platform 320 determines that the first deviation characteristic value is greater than the preset first deviation threshold or the second deviation characteristic value is greater than the preset second deviation threshold, the data state of the current health assessment data is determined to be the data state to be confirmed.

[0267] Optionally, after at least one monitoring terminal in the monitoring terminal cluster 330 sends a health assessment data confirmation instruction, the method further includes:

[0268] The monitoring terminal sends a health assessment data confirmation instruction to the active health assessment platform 320 in response to the health assessment data to be confirmed instruction;

[0269] The active health assessment platform 320 generates an updated health assessment data sequence based on the historical health assessment data sequence and the current health assessment data in response to the health assessment data to be confirmed instruction;

[0270] The active health assessment platform 320 updates the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient according to the updated health assessment data sequence to generate a first updated weight coefficient, a second updated weight coefficient, a third updated weight coefficient and a fourth updated weight coefficient, wherein the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient are used to determine the first predicted characteristic value, and the first updated weight coefficient, the second updated weight coefficient, the third updated weight coefficient and the fourth updated weight coefficient are used to determine the predicted characteristic value of the next time node.

[0271] Optionally, after at least one monitoring terminal in the monitoring terminal cluster 330 sends a health assessment data confirmation instruction, the method further includes:

[0272] The monitoring terminal sends a health assessment data confirmation instruction to the active health assessment platform 320 in response to the health assessment data to be confirmed instruction;

[0273] The active health assessment platform 320 generates an updated health assessment data sequence based on the historical health assessment data sequence and the current health assessment data in response to the health assessment data to be confirmed instruction. ;

[0274] The active health assessment platform 320 uses formula 5 and updates the health assessment data sequence according to the The first weight coefficient The second weight coefficient , the third weight coefficient and the fourth weight coefficient Update to generate the first updated weight coefficient , the second updated weight coefficient , the third update weight coefficient And the fourth update weight coefficient , wherein the first update weight coefficient , the second updated weight coefficient , the third updated weight coefficient and the fourth updated weight coefficient For determining the predicted characteristic value of the next time node, the formula 5 is:

[0275]

[0276] in, is the preset adjustment factor.

[0277] Optionally, the assessment system for the children's active health system includes a user terminal cluster 340, each user terminal in the user terminal cluster being communicatively connected to the active health assessment platform 320; after at least one monitoring terminal in the monitoring terminal cluster 330 sends a health assessment data pending confirmation instruction, further comprising:

[0278] The monitoring terminal sends a health assessment data abnormality instruction to the active health assessment platform 320 in response to the health assessment data pending confirmation instruction;

[0279] In response to the health assessment data abnormality instruction, the active health assessment platform 320 sends a health assessment data abnormality report to the target user terminal corresponding to the identity information in the user terminal cluster 340 , where the health assessment data abnormality report includes the updated health assessment data sequence.

[0280] Figure 4 FIG. 1 is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application. Figure 4 As shown, this embodiment provides an electronic device 400 including: a processor 401 and a memory 402; wherein:

[0281] The memory 402 is used to store computer programs. The memory may also be a flash memory.

[0282] The processor 401 is configured to execute the execution instructions stored in the memory to implement each step in the above method. For details, please refer to the relevant description in the above method embodiment.

[0283] Optionally, the memory 402 may be independent or integrated with the processor 401 .

[0284] When the memory 402 is a device independent of the processor 401, the electronic device 400 may further include:

[0285] The bus 403 is used to connect the memory 402 and the processor 401 .

[0286] This embodiment further provides a readable storage medium, in which a computer program is stored. When at least one processor of an electronic device executes the computer program, the electronic device executes the methods provided in the various aforementioned embodiments.

[0287] This embodiment further provides a program product, which includes a computer program stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor can execute the computer program to cause the electronic device to implement the methods provided in the various embodiments described above.

[0288] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered merely as exemplary, and the true scope and spirit of the present application are indicated by the claims.

[0289] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for evaluating a child's active health system, characterized in that: An assessment system for a child's active health system, comprising a physiological sensor cluster, an active health assessment platform, and a monitoring terminal cluster, wherein each physiological sensor in the physiological sensor cluster and each monitoring terminal in the monitoring terminal cluster are respectively communicatively connected to the active health assessment platform; The method comprises: Acquiring current health assessment data of the target child through the physiological sensor cluster, and sending the current health assessment data to the active health assessment platform, wherein the current health assessment data includes identity information of the target child; The active health assessment platform obtains a historical health assessment data sequence of the target child based on the identity information; The active health assessment platform uses a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence. The prediction feature value includes a first prediction feature value and a second prediction feature value. The first prediction feature value is used to characterize the predicted health assessment data based on the historical health assessment data sequence, and the second prediction feature value is used to characterize the change rate of the predicted health assessment data based on the historical health assessment data sequence. The active health assessment platform determines the data state of the current health assessment data based on the predicted characteristic value and the current health assessment data, and sends a health assessment data to-be-confirmed instruction to at least one monitoring terminal in the monitoring terminal cluster when the data state is a data state to be confirmed, wherein the predicted characteristic value is a predicted value, and the current health assessment data is an actual value. By comparing the deviation between the predicted value and the actual value, it is determined whether the current health assessment data has an abnormality to ensure the reliability of the current health assessment data, and the health assessment data to-be-confirmed instruction includes the current health assessment data, the historical health assessment data sequence, and the predicted characteristic value; The active health assessment platform determines the data state of the current health assessment data according to the predicted characteristic value and the current health assessment data, including: The active health assessment platform determines a first deviation characteristic value based on the first predicted characteristic value and the current health assessment data; The active health assessment platform determines the change rate of the current health assessment data based on the current health assessment data and the historical health assessment data sequence; The active health assessment platform determines a second deviation characteristic value based on the second predicted characteristic value and the current health assessment data change rate; If the active health assessment platform determines that the first deviation characteristic value is greater than the preset first deviation threshold, or the second deviation characteristic value is greater than the preset second deviation threshold, the data state of the current health assessment data is determined to be the data state to be confirmed.

2. The method for evaluating the children's active health system according to claim 1, characterized in that: The active health assessment platform utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, including: The active health assessment platform determines a first estimated value based on the historical health assessment data sequence; The active health assessment platform determines a second estimated value based on the historical health assessment data sequence and the first estimated value; The active health assessment platform determines a third estimated value based on the historical health assessment data sequence and the second estimated value; The active health assessment platform determines a fourth estimated value based on the historical health assessment data sequence and the third estimated value; The active health assessment platform determines the first prediction feature value according to the first estimated value, the second estimated value, the third estimated value, and the fourth estimated value.

3. The method for evaluating the children's active health system according to claim 2, characterized in that: Before the active health assessment platform determines the first prediction feature value according to the first estimated value, the second estimated value, the third estimated value, and the fourth estimated value, the further step includes: The active health assessment platform determines a maximum health assessment value and a median health assessment value based on the historical health assessment data sequence. The maximum health assessment value and the median health assessment value are used to input into a preset estimation characteristic function to determine the first estimation value, the second estimation value, the third estimation value and the fourth estimation value.

4. The method for evaluating the children's active health system according to claim 3, characterized in that: The active health assessment platform utilizes a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence, and further includes: The active health assessment determines the second predicted characteristic value according to the historical health assessment data sequence and the preset estimated characteristic function.

5. The method for evaluating a children's active health system according to any one of claims 2 to 4, characterized in that: After at least one monitoring terminal in the monitoring terminal cluster sends a health assessment data to be confirmed instruction, the method further includes: The monitoring terminal sends a health assessment data confirmation instruction to the active health assessment platform in response to the health assessment data to be confirmed instruction; The active health assessment platform generates an updated health assessment data sequence based on the historical health assessment data sequence and the current health assessment data in response to the health assessment data to be confirmed instruction; The active health assessment platform updates the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient according to the updated health assessment data sequence to generate a first updated weight coefficient, a second updated weight coefficient, a third updated weight coefficient and a fourth updated weight coefficient, wherein the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient are used to determine the first predicted characteristic value, and the first updated weight coefficient, the second updated weight coefficient, the third updated weight coefficient and the fourth updated weight coefficient are used to determine the predicted characteristic value of the next time node.

6. The method for evaluating the children's active health system according to claim 5, characterized in that: The evaluation system of the children's active health system includes a user terminal cluster, each user terminal in the user terminal cluster is communicatively connected to the active health evaluation platform; After at least one monitoring terminal in the monitoring terminal cluster sends a health assessment data to be confirmed instruction, the method further includes: The monitoring terminal sends a health assessment data abnormality instruction to the active health assessment platform in response to the health assessment data pending confirmation instruction; In response to the health assessment data abnormality instruction, the active health assessment platform sends a health assessment data abnormality report to the target user terminal corresponding to the identity information in the user terminal cluster, where the health assessment data abnormality report includes the updated health assessment data sequence.

7. An evaluation system for children's active health system, characterized in that: include: A physiological sensor cluster, an active health assessment platform, and a monitoring terminal cluster, wherein each physiological sensor in the physiological sensor cluster and each monitoring terminal in the monitoring terminal cluster are respectively communicatively connected to the active health assessment platform; Acquiring current health assessment data of the target child through the physiological sensor cluster, and sending the current health assessment data to the active health assessment platform, wherein the current health assessment data includes identity information of the target child; The active health assessment platform obtains a historical health assessment data sequence of the target child based on the identity information; The active health assessment platform uses a preset children's active health assessment model and determines a prediction feature value based on the historical health assessment data sequence. The prediction feature value includes a first prediction feature value and a second prediction feature value. The first prediction feature value is used to characterize the predicted health assessment data based on the historical health assessment data sequence, and the second prediction feature value is used to characterize the change rate of the predicted health assessment data based on the historical health assessment data sequence. The active health assessment platform determines the data state of the current health assessment data based on the predicted characteristic value and the current health assessment data, and sends a health assessment data confirmation instruction to at least one monitoring terminal in the monitoring terminal cluster when the data state is a data state to be confirmed, wherein the predicted characteristic value is a predicted value, and the current health assessment data is an actual value. By comparing the deviation between the predicted value and the actual value, it is determined whether the current health assessment data has an abnormality to ensure the reliability of the current health assessment data, and the health assessment data confirmation instruction includes the current health assessment data, the historical health assessment data sequence, and the predicted characteristic value; The active health assessment platform determines the data state of the current health assessment data according to the predicted characteristic value and the current health assessment data, including: The active health assessment platform determines a first deviation characteristic value based on the first predicted characteristic value and the current health assessment data; The active health assessment platform determines the change rate of the current health assessment data based on the current health assessment data and the historical health assessment data sequence; The active health assessment platform determines a second deviation characteristic value based on the second predicted characteristic value and the current health assessment data change rate; If the active health assessment platform determines that the first deviation characteristic value is greater than the preset first deviation threshold, or the second deviation characteristic value is greater than the preset second deviation threshold, the data state of the current health assessment data is determined to be the data state to be confirmed.

8. An electronic device, characterized in that: include: processor; as well as, a memory for storing executable instructions of the processor; The processor is configured to perform the method according to any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

Images