Multi-dimensional data determination method for active health of children

Abstract

The invention provides a multi-dimensional data determination method for active health of children. The method comprises the following steps: acquiring original multi-source active health data of a target child object, and generating a to-be-processed active health data sequence according to the original multi-source active health data by using a time label; the method comprises the following steps of: extracting a first index parameter sequence of a first physiological index and a second index parameter sequence of a second physiological index in a to-be-processed active health data sequence, and determining an index parameter correlation characteristic value according to the first index parameter sequence and the second index parameter sequence; and only when the index parameter association feature value meets the preset parameter association condition, determining that the original multi-source active health data is the to-be-evaluated active health data of the target child object, thereby checking and verifying the original data to ensure the quality and reliability of subsequent data input into a related model.

Description

Technical Field

[0001] The present application relates to data processing technology, and more particularly to a method for determining multi-dimensional data for children's active health. Background Art

[0002] With the continuous improvement of health awareness, children's health management has become the focus of attention of families, schools and all sectors of society. Therefore, how to scientifically and comprehensively evaluate children's health status, timely discover potential health problems and take effective measures to intervene has become an urgent problem to be solved in the current field of children's health management.

[0003] Traditional child health assessment methods mostly rely on single physiological indicators, such as height, weight, heart rate, etc. Although these methods can reflect children's health status to a certain extent, they have many limitations. First, a single physiological indicator is difficult to fully reflect the health status of children, ignoring the impact of multi-dimensional factors such as psychology and behavior on health. Secondly, traditional assessment methods often lack dynamism and continuity, and cannot monitor and track changes in children's health status in real time. In addition, there are problems such as inconsistent formats and inconsistent time sequences between health data from different sources, which brings difficulties to data integration and analysis.

[0004] In recent years, with the rapid development of technologies such as big data and artificial intelligence, new ideas and methods have been provided for children's health management. In particular, the concept of active health has been proposed, which emphasizes long-term continuous dynamic tracking of the behavioral system of individuals throughout their life cycle, comprehensive assessment of their own status, and selection of appropriate lifestyle intervention measures to improve their health status. This concept provides a new perspective for children's health management, that is, from single physiological indicator detection to multi-dimensional data comprehensive analysis, and from static evaluation to dynamic tracking.

[0005] However, to achieve child health management based on the concept of active health, we first need to solve the problem of integrating, processing and analyzing multi-dimensional data. How to effectively obtain, integrate and analyze child health data from different channels and provide reliable data for subsequent data processing has become a major challenge facing the current field of child health management. Summary of the invention

[0006] The present application provides a method and system for determining multi-dimensional data for children's active health, so as to ensure the quality and reliability of data subsequently used for input into relevant models.

[0007] In a first aspect, the present application provides a method for determining multi-dimensional data for active health of children, characterized by comprising:

[0008] Acquire original multi-source active health data of the target child object, and generate a sequence of active health data to be processed based on the original multi-source active health data using a time tag, wherein the active health data to be processed in the sequence of active health data to be processed includes a multi-dimensional data framework and indicator parameters for filling each physiological indicator in the multi-dimensional data framework;

[0009] Extracting a first indicator parameter sequence of a first physiological indicator and a second indicator parameter sequence of a second physiological indicator from the active health data sequence to be processed, wherein the first physiological indicator and the second physiological indicator are two physiological indicators having a preset association relationship;

[0010] Determine an indicator parameter association characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence, wherein the indicator parameter association characteristic value is used to characterize the degree of matching between the first indicator parameter sequence and the second indicator parameter sequence;

[0011] Only when the indicator parameter-associated characteristic value satisfies the preset parameter-associated condition, the original multi-source active health data is determined to be the active health data to be evaluated of the target child object.

[0012] In the above scheme, the original multi-source active health data of the target child object is first obtained, and the active health data sequence to be processed is generated using time tags. This process realizes the comprehensive integration of children's health data, unifies data from different channels (such as wearable devices, medical records, etc.) on a timeline, and ensures the integrity and timeliness of the data. At the same time, the construction of a multi-dimensional data framework and the filling of indicator parameters make the data more standardized in structure, which is convenient for subsequent processing and analysis.

[0013] On the basis of data integration, the above scheme further extracts the indicator parameter sequence of two physiological indicators (the first physiological indicator and the second physiological indicator) with a preset correlation relationship in the active health data sequence to be processed. By calculating the correlation characteristic value between the two indicator parameter sequences, the degree of matching between them can be quantified, so that the data in the two indicator parameter sequences can be mutually verified. Only when the indicator parameter correlation characteristic value meets the preset parameter correlation condition, the original multi-source active health data is determined as the active health data to be evaluated, thereby playing a role in data quality verification. By setting reasonable correlation conditions, data whose correlation characteristic values ​​do not meet the conditions due to data anomalies, missing or inconsistencies can be filtered out, thereby ensuring the effectiveness and reliability of subsequent data input into the recognition model for analysis.

[0014] Optionally, there is a preset association relationship between the first physiological indicator and the second physiological indicator in a preset physiological indicator association list, and the preset physiological indicator association list is used to establish a preset association relationship between different physiological indicators;

[0015] Correspondingly, determining the indicator parameter associated characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence includes:

[0016] Traversing any two indicator parameters in the preset physiological indicator association list, determining the indicator parameter association characteristic value between two different indicator parameters to form an indicator parameter association characteristic value set, wherein the two different indicator parameters correspond to two different indicator parameter sequences in the active health data sequence to be processed;

[0017] Determining the comprehensive indicator parameter associated characteristic value corresponding to the original multi-source active health data according to the indicator parameter associated characteristic value set;

[0018] The determining that the original multi-source active health data is the active health data to be evaluated of the target child object only when the indicator parameter associated characteristic value satisfies the preset parameter associated condition includes:

[0019] Only when the comprehensive indicator parameter associated characteristic value is greater than the preset indicator parameter associated characteristic threshold value, the original multi-source active health data is determined to be the active health data to be evaluated of the target child object.

[0020] In the above scheme, when processing the active health data to be evaluated, the preset physiological indicator association list is first traversed, and for any two physiological indicators in the list that have an associated relationship, the corresponding indicator parameter sequences in the active health data sequence to be processed are extracted respectively. For each pair of extracted indicator parameter sequences, the indicator parameter association characteristic value between them is calculated, and the characteristic value is used to quantify the matching degree and correlation of the two physiological indicators in the time series. By traversing the entire preset physiological indicator association list, a series of indicator parameter association characteristic values ​​can be calculated, and an indicator parameter association characteristic value set is formed, which provides a rich data basis for subsequent comprehensive evaluation. After forming the indicator parameter association characteristic value set, the comprehensive indicator parameter association characteristic value of these characteristic values ​​is further calculated. This step realizes an overall evaluation of the credibility or reliability of the data by comprehensively considering the correlation between multiple physiological indicators. In addition, in order to judge the quality of the original multi-source active health data, a preset indicator parameter association characteristic threshold is also set. Only when the comprehensive indicator parameter association characteristic value is greater than the threshold, the original data is determined as the active health data to be evaluated. This mechanism ensures the accuracy and effectiveness of subsequent health evaluation.

[0021] Optionally, determining the indicator parameter associated characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence includes:

[0022] Using formula 1, and according to the first indicator parameter sequence P = {p1, p2, ..., p i ,…,p n} and the second indicator parameter sequence Q={q1,q2,…,q i ,…,q n}Determine the indicator parameter associated characteristic value K, the formula 1 is:

[0023]

[0024] Among them, p i is the i-th indicator parameter in the first indicator parameter sequence P, q i is the i-th indicator parameter in the second indicator parameter sequence Q, is the average value of the indicator parameters of the first indicator parameter sequence P, is the average value of the indicator parameters of the second indicator parameter sequence Q.

[0025] In the above scheme, Formula 1 calculates the covariance between the two physiological indicator parameter sequences and standardizes it to obtain the indicator parameter association eigenvalue. This process effectively quantifies the matching degree and correlation of the two physiological indicators in the time series. The size of the indicator parameter association eigenvalue directly reflects the strength of the correlation between the two indicators. When using Formula 1 to calculate the indicator parameter association eigenvalue, the deviation of each indicator parameter from its average value is taken into account, which helps to eliminate the influence of individual differences on the data and make the processing results more accurate. At the same time, by performing square and square root operations on the deviation, the stability and noise resistance of the data are further enhanced, and the accuracy of data processing is improved.

[0026] Optionally, determining the indicator parameter associated characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence includes:

[0027] The indicator parameter association characteristic value is determined according to the first indicator parameter sequence, the second indicator parameter sequence and the time delay step number, and the time delay step number is used to characterize the delay association relationship between the first indicator parameter and the second indicator parameter.

[0028] In the above scheme, children's physiological indicators often show the characteristics of dynamic changes in the time dimension, and there may be a certain delayed correlation between different indicators. By introducing the time delay step, this delayed correlation can be captured, thereby more comprehensively revealing the dynamic interaction between physiological indicators. Time delay correlation analysis allows us to consider the non-immediate effects between physiological indicators, which helps to more accurately determine the linkage relationship between two physiological indicator data. For example, changes in some physiological indicators may lag behind other indicators. By considering time delays, we can capture these changes more promptly. In addition, by adjusting the time delay step, it can also adapt to different delayed correlation patterns between different physiological indicators, so that it can be applied to a wider range of children's health data analysis scenarios, whether it is short-term physiological fluctuations or long-term trend predictions, more accurate and reliable results can be obtained.

[0029] Optionally, after determining the indicator parameter associated characteristic value according to the first indicator parameter sequence, the second indicator parameter sequence and the time delay step number, the method further includes:

[0030] The indicator parameter associated characteristic value is updated by using weight values ​​corresponding to different time delay steps to generate updated indicator parameter associated characteristic value, and the updated indicator parameter associated characteristic value is used to replace the indicator parameter associated characteristic value.

[0031] In the above scheme, the correlation eigenvalues ​​of the indicator parameters under different time delay steps reflect the correlation between the physiological indicators under different time delays. However, the importance of these correlations may vary depending on the number of delay steps. By assigning corresponding weight values ​​to different time delay steps and updating the correlation eigenvalues, the actual contribution of the correlation under each time delay can be more accurately reflected, thereby improving the accuracy of the overall correlation eigenvalue, which helps to more accurately evaluate the dynamic correlation pattern between children's physiological indicators. Among them, the physiological state of children is a dynamically changing process, and the correlation between different physiological indicators may also change over time. By introducing a time delay weight update mechanism, this method can dynamically adjust the calculation method of the correlation eigenvalue to adapt to changes in the correlation between physiological indicators.

[0032] Optionally, after extracting the first indicator parameter sequence of the first physiological indicator and the second indicator parameter sequence of the second physiological indicator in the active health data sequence to be processed, the method further includes:

[0033] If it is determined that the target object exists in the first indicator parameter sequence, determining the indicator estimation value of the target object according to the first indicator parameter sequence and the second indicator parameter sequence, wherein the indicator parameter corresponding to the target object in the first indicator parameter sequence is empty or abnormal;

[0034] The indicator estimate is added to the first indicator parameter sequence.

[0035] In the above scheme, in the active health data collection of children, due to various reasons (such as equipment failure, data loss, etc.), there may be null values ​​or outliers in some physiological indicator parameter sequences. These missing or abnormal data points will seriously affect the accuracy and reliability of subsequent data analysis. By introducing the indicator estimation value filling mechanism, these missing or abnormal data points can be automatically detected and filled, thereby significantly improving the integrity and availability of the data. This is crucial for subsequent data analysis, model training, and health status assessment. Among them, in the data analysis process, the presence of null values ​​or outliers often leads to deviations or distortions in the analysis results. By filling in reasonable indicator estimates, this deviation can be reduced and the accuracy and reliability of data analysis can be improved. Especially in the analysis of children's health data, small data deviations may also have a significant impact on health status assessment. Therefore, the introduction of the indicator estimation value filling mechanism is of great significance to ensure the accuracy of data analysis results.

[0036] Optionally, determining the indicator estimation value of the target object according to the first indicator parameter sequence and the second indicator parameter sequence includes:

[0037] Acquire a first indicator parameter and a second indicator parameter, wherein the first indicator parameter and the second indicator parameter are respectively the previous data and the next data of the target object in the first indicator parameter sequence;

[0038] Obtaining a third indicator parameter, a fourth indicator parameter, and a fifth indicator parameter in the second indicator parameter sequence, wherein the third indicator parameter and the first indicator parameter have the same time tag, the fourth indicator parameter and the target object have the same time tag, and the fifth indicator parameter and the second indicator parameter have the same time tag;

[0039] The indicator estimation value is determined according to the first indicator parameter, the second indicator parameter, the third indicator parameter, the fourth indicator parameter and the fifth indicator parameter.

[0040] In the above scheme, during the collection of children's health data, some data points may be missing or abnormal due to various reasons (such as equipment failure, data recording errors, etc.). Traditional data repair methods may not be able to accurately estimate these missing or abnormal values, thereby affecting the accuracy of subsequent data analysis. The above scheme can more accurately estimate missing or abnormal data points by comprehensively considering the data points before and after the target object and the data values ​​of the associated indicators at the same time point. This accuracy is essential for maintaining the continuity and consistency of children's health data. Among them, children's physiological indicators often fluctuate over time, and there may be a certain time correlation between different indicators. The above scheme can make full use of the time correlation of the data by obtaining the relevant indicator parameters (third indicator parameters, fourth indicator parameters) with the same time label as the target object, so as to more accurately estimate the indicator value of the target object. The use of this time correlation helps to capture the dynamic change characteristics of children's physiological indicators and provide more comprehensive information for health status assessment.

[0041] In a second aspect, the present application provides a multi-dimensional data determination system for children's active health, comprising:

[0042] An acquisition module, used to acquire original multi-source active health data of a target child object, and generate a sequence of active health data to be processed according to the original multi-source active health data using a time tag, wherein the active health data to be processed in the sequence of active health data to be processed includes a multi-dimensional data framework and indicator parameters for filling each physiological indicator in the multi-dimensional data framework;

[0043] An extraction module, used to extract a first indicator parameter sequence of a first physiological indicator and a second indicator parameter sequence of a second physiological indicator from the active health data sequence to be processed, wherein the first physiological indicator and the second physiological indicator are two physiological indicators having a preset association relationship;

[0044] a processing module, configured to determine an indicator parameter association characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence, wherein the indicator parameter association characteristic value is used to characterize a matching degree between the first indicator parameter sequence and the second indicator parameter sequence;

[0045] The processing module is further configured to determine that the original multi-source active health data is the active health data to be evaluated of the target child object only when the indicator parameter associated characteristic value satisfies a preset parameter associated condition.

[0046] Optionally, there is a preset association relationship between the first physiological indicator and the second physiological indicator in a preset physiological indicator association list, and the preset physiological indicator association list is used to establish a preset association relationship between different physiological indicators;

[0047] The processing module is specifically used for:

[0048] Traversing any two indicator parameters in the preset physiological indicator association list, determining the indicator parameter association characteristic value between two different indicator parameters to form an indicator parameter association characteristic value set, wherein the two different indicator parameters correspond to two different indicator parameter sequences in the active health data sequence to be processed;

[0049] Determining the comprehensive indicator parameter associated characteristic value corresponding to the original multi-source active health data according to the indicator parameter associated characteristic value set;

[0050] Only when the comprehensive indicator parameter associated characteristic value is greater than the preset indicator parameter associated characteristic threshold value, the original multi-source active health data is determined to be the active health data to be evaluated of the target child object.

[0051] Optionally, the processing module is specifically used to:

[0052] Using formula 1, and according to the first indicator parameter sequence P = {p1, p2, ..., p i ,…,p n} and the second indicator parameter sequence Q={q1,q2,…,q i ,…,q n}Determine the indicator parameter associated characteristic value K, the formula 1 is:

[0053]

[0054] Among them, p i is the i-th indicator parameter in the first indicator parameter sequence P, q i is the i-th indicator parameter in the second indicator parameter sequence Q, is the average value of the indicator parameters of the first indicator parameter sequence P, is the average value of the indicator parameters of the second indicator parameter sequence Q.

[0055] Optionally, the processing module is specifically used to:

[0056] The indicator parameter association characteristic value is determined according to the first indicator parameter sequence, the second indicator parameter sequence and the time delay step number, and the time delay step number is used to characterize the delay association relationship between the first indicator parameter and the second indicator parameter.

[0057] Optionally, the processing module is specifically used to:

[0058] The indicator parameter associated characteristic value is updated by using weight values ​​corresponding to different time delay steps to generate updated indicator parameter associated characteristic value, and the updated indicator parameter associated characteristic value is used to replace the indicator parameter associated characteristic value.

[0059] Optionally, the processing module is specifically used to:

[0060] If it is determined that the target object exists in the first indicator parameter sequence, determining the indicator estimation value of the target object according to the first indicator parameter sequence and the second indicator parameter sequence, wherein the indicator parameter corresponding to the target object in the first indicator parameter sequence is empty or abnormal;

[0061] The indicator estimate is added to the first indicator parameter sequence.

[0062] Optionally, the processing module is specifically used to:

[0063] Acquire a first indicator parameter and a second indicator parameter, wherein the first indicator parameter and the second indicator parameter are respectively the previous data and the next data of the target object in the first indicator parameter sequence;

[0064] Obtaining a third indicator parameter, a fourth indicator parameter, and a fifth indicator parameter in the second indicator parameter sequence, wherein the third indicator parameter and the first indicator parameter have the same time tag, the fourth indicator parameter and the target object have the same time tag, and the fifth indicator parameter and the second indicator parameter have the same time tag;

[0065] The indicator estimation value is determined according to the first indicator parameter, the second indicator parameter, the third indicator parameter, the fourth indicator parameter and the fifth indicator parameter.

[0066] In a third aspect, the present application provides an electronic device, including:

[0067] processor; and,

[0068] A memory, configured to store executable instructions of the processor;

[0069] The processor is configured to perform any possible method described in the first aspect by executing the executable instructions.

[0070] 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.

[0071] The multi-dimensional data determination method and system for children's active health provided in the present application obtains the original multi-source active health data of the target child object, and uses time tags to generate a sequence of active health data to be processed based on the original multi-source active health data, then extracts the first indicator parameter sequence of the first physiological indicator and the second indicator parameter sequence of the second physiological indicator in the sequence of active health data to be processed, and then determines the indicator parameter associated characteristic value based on the first indicator parameter sequence and the second indicator parameter sequence, and only when the indicator parameter associated characteristic value meets the preset parameter association condition, determines the original multi-source active health data as the active health data to be evaluated of the target child object, thereby checking and verifying the original data to ensure the quality and reliability of the data subsequently used for input into the relevant model. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] 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.

[0073] Figure 1 is a flowchart of a method for determining multi-dimensional data for active health of children according to an exemplary embodiment of the present application;

[0074] Figure 2 is a flowchart of a method for determining multi-dimensional data for active health of children according to another exemplary embodiment of the present application;

[0075] Figure 3 is a structural schematic diagram of a multi-dimensional data determination system for active health of children according to an exemplary embodiment of the present application;

[0076] Figure 4 It is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application.

[0077] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0078] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0079] Figure 1 FIG. 1 is a flow chart of a method for determining multi-dimensional data for active health of children according to an exemplary embodiment of the present application. Figure 1 As shown, the method provided in this embodiment includes:

[0080] S101. Acquire original multi-source active health data of a target child object, and generate a sequence of active health data to be processed based on the original multi-source active health data using a time tag.

[0081] In this step, the original multi-source active health data of the target child object is obtained, and a sequence of active health data to be processed is generated based on the original multi-source active health data using time tags. The active health data to be processed in the sequence of active health data to be processed includes a multi-dimensional data framework and indicator parameters for filling in each physiological indicator in the multi-dimensional data framework.

[0082] Specifically, it is necessary to first obtain the original multi-source active health data of the target child through multiple channels. These data sources include but are not limited to medical record systems, health applications, etc. The acquired data should include the child's multi-dimensional physiological indicators, such as height, weight, bone density, degree of bone closure, etc. To ensure the accuracy and consistency of the data, all acquired data must be accompanied by clear time tags for subsequent data integration and processing.

[0083] After obtaining the original multi-source active health data, the time tags are used to integrate the data into a unified timeline to generate a sequence of active health data to be processed. The key to this step is to build a multi-dimensional data framework to fill and organize physiological indicator data from different sources. Each column of the data framework represents a physiological indicator, and each row corresponds to a specific time point. For missing or abnormal data points, preliminary data cleaning and preprocessing will be performed to ensure the integrity and reliability of the data.

[0084] S102: extracting a first indicator parameter sequence of a first physiological indicator and a second indicator parameter sequence of a second physiological indicator from the active health data sequence to be processed.

[0085] In this step, a first indicator parameter sequence of a first physiological indicator and a second indicator parameter sequence of a second physiological indicator in the active health data sequence to be processed are extracted, and the first physiological indicator and the second physiological indicator are two physiological indicators with a preset association relationship.

[0086] Specifically, in the active health data sequence to be processed, a first indicator parameter sequence and a second indicator parameter sequence of two physiological indicators with a preset association relationship are extracted. The preset association relationship can be established based on physiological and medical knowledge, such as height and weight. By traversing the data sequence, the parameter sequences corresponding to the two physiological indicators are found to prepare for subsequent analysis and calculation.

[0087] S103: Determine an indicator parameter associated characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence.

[0088] In this step, an indicator parameter association characteristic value is determined according to the first indicator parameter sequence and the second indicator parameter sequence, and the indicator parameter association characteristic value is used to characterize the matching degree between the first indicator parameter sequence and the second indicator parameter sequence.

[0089] Specifically, in order to quantify the degree of matching between the first indicator parameter sequence and the second indicator parameter sequence, the indicator parameter correlation characteristic value can be calculated using statistical or machine learning methods, and the specific methods include but are not limited to covariance analysis, Pearson correlation coefficient calculation, etc. In addition, considering the dynamic change characteristics of children's physiological indicators, time delay steps can also be introduced to capture the delayed correlation relationship between indicators. By comprehensively considering these factors, the characteristic value that can accurately reflect the degree of correlation between indicators is calculated.

[0090] Optionally, the first physiological indicator and the second physiological indicator have a preset association relationship in a preset physiological indicator association list, and the preset physiological indicator association list is used to establish a preset association relationship between different physiological indicators. Correspondingly, determining the indicator parameter association characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence includes:

[0091] Traverse any two indicator parameters in the preset physiological indicator association list, determine the indicator parameter association characteristic value between two different indicator parameters, and form an indicator parameter association characteristic value set, wherein the two different indicator parameters correspond to two different indicator parameter sequences in the active health data sequence to be processed. Determine the comprehensive indicator parameter association characteristic value corresponding to the original multi-source active health data according to the indicator parameter association characteristic value set. Only when the comprehensive indicator parameter association characteristic value is greater than the preset indicator parameter association characteristic threshold value, the original multi-source active health data is determined to be the active health data to be evaluated for the target child object.

[0092] Specifically, a preset physiological indicator association list may first be established. The list is used to clarify the preset association relationships between different physiological indicators, which are pre-set based on physiological and medical knowledge. The preset physiological indicator association list is presented in a table format, where each row represents an association pair, including two physiological indicators and their association relationship descriptions.

[0093] After obtaining the active health data sequence to be processed, the preset physiological index association list is traversed. For each association pair in the list, the first index parameter sequence and the second index parameter sequence corresponding to the two physiological indexes in the data sequence to be processed are extracted.

[0094] For each pair of extracted indicator parameter sequences, the correlation eigenvalues ​​between them are calculated using statistical or machine learning methods. The specific method can be selected according to the actual situation, such as covariance analysis, Pearson correlation coefficient calculation, etc. The calculated correlation eigenvalues ​​reflect the matching degree and correlation of the two physiological indicators in the time series. All these correlation eigenvalues ​​are combined into an indicator parameter correlation eigenvalue set to provide a data basis for subsequent comprehensive evaluation.

[0095] After obtaining the set of indicator parameter associated eigenvalues, it is necessary to further calculate the integrated indicator parameter associated eigenvalues ​​corresponding to the original multi-source active health data. This can be achieved by weighted averaging, summing or other statistical methods for all associated eigenvalues ​​in the set. The integrated indicator parameter associated eigenvalue is a quantitative assessment of the overall correlation of the original data, reflecting the coordination and consistency between multiple physiological indicators within the data.

[0096] Finally, the calculated comprehensive indicator parameter associated characteristic value is compared with the preset indicator parameter associated characteristic threshold. The preset threshold is set based on a large amount of historical data and medical knowledge, and is used to judge the quality and reliability of the data. When the comprehensive indicator parameter associated characteristic value is greater than the preset threshold, the original multi-source active health data is considered to be valid and reliable, and can be determined as the active health data to be evaluated for the target child object. On the contrary, if the comprehensive characteristic value is less than or equal to the threshold, the original data needs to be further checked, verified, or the abnormal data points need to be excluded and the comprehensive characteristic value needs to be recalculated.

[0097] In a possible implementation, the determining of the indicator parameter associated characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence may include:

[0098] Using formula 1, and according to the first indicator parameter sequence P = {p1, p2, ..., p i ,…,p n} and the second index parameter sequence Q={q1,q2,…,q i ,…,q n}Determine the indicator parameter associated characteristic value K, formula 1 is:

[0099]

[0100] Among them, p i is the i-th indicator parameter in the first indicator parameter sequence P, qi is the i-th index parameter in the second index parameter sequence Q, is the average value of the indicator parameters of the first indicator parameter sequence P, is the average value of the indicator parameters of the second indicator parameter sequence Q.

[0101] In the above scheme, Formula 1 calculates the covariance between the two physiological indicator parameter sequences and standardizes it to obtain the indicator parameter association eigenvalue. This process effectively quantifies the matching degree and correlation of the two physiological indicators in the time series. The size of the indicator parameter association eigenvalue directly reflects the strength of the correlation between the two indicators. When using Formula 1 to calculate the indicator parameter association eigenvalue, the deviation of each indicator parameter from its average value is taken into account, which helps to eliminate the influence of individual differences on the data and make the processing results more accurate. At the same time, by performing square and square root operations on the deviation, the stability and noise resistance of the data are further enhanced, and the accuracy of data processing is improved.

[0102] In another possible implementation, the determining of the indicator parameter associated characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence may further include:

[0103] Using formula 2, and according to the first indicator parameter sequence P = {p1, p2, ..., p i ,…,p n} and the second index parameter sequence Q={q1,q2,…,q i ,…,q n}Determine the indicator parameter associated characteristic value K, formula 2 is:

[0104]

[0105] Among them, p i is the i-th indicator parameter in the first indicator parameter sequence P, q i is the i-th index parameter in the second index parameter sequence Q, is the average value of the indicator parameters of the first indicator parameter sequence P, is the average value of the indicator parameters of the second indicator parameter sequence Q, m is the preset maximum time delay step number, and τ is the time delay step number.

[0106] In the above scheme, children's physiological indicators often show the characteristics of dynamic changes in the time dimension, and there may be a certain delayed correlation between different indicators. By introducing the time delay step, this delayed correlation can be captured, thereby more comprehensively revealing the dynamic interaction between physiological indicators. Time delay correlation analysis allows us to consider the non-immediate effects between physiological indicators, which helps to more accurately determine the linkage relationship between two physiological indicator data. For example, changes in some physiological indicators may lag behind other indicators. By considering time delays, we can capture these changes more promptly. In addition, by adjusting the time delay step, it can also adapt to different delayed correlation patterns between different physiological indicators, so that it can be applied to a wider range of children's health data analysis scenarios, whether it is short-term physiological fluctuations or long-term trend predictions, more accurate and reliable results can be obtained.

[0107] Specifically, Formula 2 can accurately quantify the dynamic relationship between the first indicator parameter sequence and the second indicator parameter sequence by introducing the time delay step number. In the monitoring of children's physiological indicators, there may be a certain time lag between different indicators. By adjusting the time delay step number, Formula 2 can capture this time lag relationship, thereby more comprehensively reflecting the true relationship between physiological indicators.

[0108] In addition, the setting of the preset maximum time delay step number enables higher flexibility and adaptability in processing the association of different physiological indicators. For the association pattern between different physiological indicators, the value of the preset maximum time delay step number can be adjusted to adapt to different time delay ranges. This flexibility enables the method to be widely used in various child health data processing scenarios, whether it is short-term physiological fluctuations or long-term trend predictions, accurate and reliable results can be obtained.

[0109] When calculating the indicator parameter association eigenvalue, Formula 2 obtains a dimensionless association eigenvalue by calculating the covariance between the two sequences and standardizing them. The size of this eigenvalue directly reflects the strength of the correlation between the two physiological indicators, providing a reliable quantitative indicator for data quality verification. When the indicator parameter association eigenvalue is greater than the preset threshold, the original multi-source active health data can be considered to be valid and reliable, thereby ensuring the accuracy of subsequent health assessments.

[0110] In addition, by traversing the preset physiological index association list and calculating the association characteristic value of each pair of associated indicators using Formula 2, a set of multiple association characteristic values ​​can be obtained. These characteristic values ​​not only reflect the correlation between different physiological indicators, but also provide a rich data foundation for subsequent multi-dimensional data analysis and health assessment.

[0111] Furthermore, Formula 3 can be used to update the indicator parameter associated characteristic value K to generate an updated indicator parameter associated characteristic value K ′ , update the index parameter associated eigenvalue K ′ Used to replace the indicator parameter associated eigenvalue K, formula 3 is:

[0112]

[0113] Among them, ω(τ) is the weight value corresponding to the time delay step τ.

[0114] In the above scheme, the correlation eigenvalues ​​of the indicator parameters under different time delay steps reflect the correlation between the physiological indicators under different time delays. However, the importance of these correlations may vary depending on the number of delay steps. By assigning corresponding weight values ​​to different time delay steps and updating the correlation eigenvalues, the actual contribution of the correlation under each time delay can be more accurately reflected, thereby improving the accuracy of the overall correlation eigenvalue, which helps to more accurately evaluate the dynamic correlation pattern between children's physiological indicators. Among them, the physiological state of children is a dynamically changing process, and the correlation between different physiological indicators may also change over time. By introducing a time delay weight update mechanism, this method can dynamically adjust the calculation method of the correlation eigenvalue to adapt to changes in the correlation between physiological indicators.

[0115] Specifically, the indicator parameter association eigenvalue is updated through formula 3, and the weight value corresponding to the time delay step is introduced. This weight value reflects the importance of the association eigenvalue under different time delays. In the monitoring of children's physiological indicators, the correlation under different time delays may have different meanings. For example, recent data may better reflect the current physiological state, while more distant data may reflect the long-term trend more. By assigning reasonable weights to different time delay steps, formula 3 can more accurately reflect the actual contribution of the correlation under each time delay, thereby improving the accuracy and robustness of the overall association eigenvalue.

[0116] The physiological state of children is a dynamic process, and the correlation between different physiological indicators may also change over time. By introducing a time-delayed weight update mechanism, the calculation method of the associated eigenvalue can be dynamically adjusted to adapt to the changes in the correlation between physiological indicators. This adaptability makes this method more flexible and effective in processing complex and changeable children's health data.

[0117] S104. Determine the original multi-source active health data as the active health data to be evaluated for the target child object.

[0118] In this step, only when the indicator parameter-associated characteristic value satisfies the preset parameter-associated condition, the original multi-source active health data is determined as the active health data to be evaluated of the target child object.

[0119] Specifically, the calculated indicator parameter-associated characteristic value is compared with the preset parameter-associated condition. The preset condition can be set based on historical data and medical knowledge to judge the quality and reliability of the data. When the characteristic value meets the preset condition, the original multi-source active health data is considered to be valid and reliable, and can be used as the active health data to be evaluated for the target child object. On the contrary, if the characteristic value does not meet the condition, it is necessary to further check and verify the original data, or recalculate the characteristic value after excluding abnormal data points.

[0120] In this embodiment, the original multi-source active health data of the target child object is obtained, and a sequence of active health data to be processed is generated according to the original multi-source active health data using time tags. Then, the first indicator parameter sequence of the first physiological indicator and the second indicator parameter sequence of the second physiological indicator in the sequence of active health data to be processed are extracted, and then the indicator parameter associated characteristic values ​​are determined according to the first indicator parameter sequence and the second indicator parameter sequence. Moreover, only when the indicator parameter associated characteristic values ​​meet the preset parameter association conditions, the original multi-source active health data is determined as the active health data to be evaluated of the target child object, thereby checking and verifying the original data to ensure the quality and reliability of the data subsequently used for input into the relevant model.

[0121] Figure 2 FIG. 1 is a flow chart of a method for determining multi-dimensional data for active health of children according to another exemplary embodiment of the present application. Figure 2 As shown, the method provided in this embodiment includes:

[0122] S201. Acquire original multi-source active health data of a target child object, and generate a sequence of active health data to be processed based on the original multi-source active health data using time tags.

[0123] In this step, the original multi-source active health data of the target child object is obtained, and a sequence of active health data to be processed is generated based on the original multi-source active health data using time tags. The active health data to be processed in the sequence of active health data to be processed includes a multi-dimensional data framework and indicator parameters for filling in each physiological indicator in the multi-dimensional data framework.

[0124] Specifically, it is necessary to first obtain the original multi-source active health data of the target child through multiple channels. These data sources include but are not limited to medical record systems, health applications, etc. The acquired data should include the child's multi-dimensional physiological indicators, such as height, weight, bone density, degree of bone closure, etc. To ensure the accuracy and consistency of the data, all acquired data must be accompanied by clear time tags for subsequent data integration and processing.

[0125] After obtaining the original multi-source active health data, the time tags are used to integrate the data into a unified timeline to generate a sequence of active health data to be processed. The key to this step is to build a multi-dimensional data framework to fill and organize physiological indicator data from different sources. Each column of the data framework represents a physiological indicator, and each row corresponds to a specific time point. For missing or abnormal data points, preliminary data cleaning and preprocessing will be performed to ensure the integrity and reliability of the data.

[0126] S202: extracting a first indicator parameter sequence of a first physiological indicator and a second indicator parameter sequence of a second physiological indicator from the active health data sequence to be processed.

[0127] In this step, a first indicator parameter sequence of a first physiological indicator and a second indicator parameter sequence of a second physiological indicator in the active health data sequence to be processed are extracted, and the first physiological indicator and the second physiological indicator are two physiological indicators with a preset association relationship.

[0128] Specifically, in the active health data sequence to be processed, a first indicator parameter sequence and a second indicator parameter sequence of two physiological indicators with a preset association relationship are extracted. The preset association relationship can be established based on physiological and medical knowledge, such as height and weight. By traversing the data sequence, the parameter sequences corresponding to the two physiological indicators are found to prepare for subsequent analysis and calculation.

[0129] S203: Determine that a target object exists in the first indicator parameter sequence, and determine an indicator estimation value of the target object according to the first indicator parameter sequence and the second indicator parameter sequence.

[0130] If it is determined that the target object exists in the first indicator parameter sequence, an indicator estimation value of the target object is determined according to the first indicator parameter sequence and the second indicator parameter sequence, wherein the indicator parameter corresponding to the target object in the first indicator parameter sequence is empty or abnormal.

[0131] Specifically, the system will traverse and check the extracted first indicator parameter sequence to determine whether there is a target object. The "target object" here refers to the data point whose corresponding indicator parameter is empty or abnormal in the first indicator parameter sequence. These empty values ​​or abnormal values ​​may be caused by equipment failure, data loss or recording errors, which will seriously affect the accuracy and reliability of subsequent data analysis.

[0132] For determining the index estimation value of the target object according to the first index parameter sequence and the second index parameter sequence, the first index parameter and the second index parameter may be obtained, wherein the first index parameter and the second index parameter are respectively the previous data and the next data of the target object in the first index parameter sequence. The third index parameter, the fourth index parameter and the fifth index parameter in the second index parameter sequence are obtained, wherein the third index parameter and the first index parameter have the same time tag, the fourth index parameter and the target object have the same time tag, and the fifth index parameter and the second index parameter have the same time tag. Then, the index estimation value is determined according to the first index parameter, the second index parameter, the third index parameter, the fourth index parameter and the fifth index parameter.

[0133] Specifically, once the target object is identified, the system will determine the target object's index estimation value based on the first index parameter sequence and the second index parameter sequence. The specific implementation of this step is as follows:

[0134] First, the system will obtain the previous data (recorded as the first indicator parameter) and the next data (recorded as the second indicator parameter) of the target object in the first indicator parameter sequence. These two data points will serve as the basis for estimating the target object's indicator value.

[0135] Next, the system will obtain the data of the time points related to the target object in the second indicator parameter sequence. Specifically, it will obtain the third indicator parameter (recorded as the fourth indicator parameter) with the same time tag as the target object, and the fifth indicator parameter with the same time tag as the data points before and after the target object (recorded as the third indicator parameter and the sixth indicator parameter, respectively).

[0136] Finally, the system will calculate the target object's estimated index value based on the obtained index parameters using appropriate algorithms (such as linear interpolation, regression analysis, etc.). This estimated value should be as close as possible to the target object's normal index value.

[0137] After the indicator estimate is calculated, the system will add it to the first indicator parameter sequence to replace the original null value or abnormal value. In this way, the first indicator parameter sequence is completely filled, providing a reliable data basis for subsequent data analysis and health assessment.

[0138] In a possible implementation, Formula 4 may be used to determine the indicator estimation value w according to the first indicator parameter w1, the second indicator parameter w2, the third indicator parameter w3, the fourth indicator parameter w4, and the fifth indicator parameter w5. Formula 4 is:

[0139]

[0140] Among them, w is the estimated value of the indicator.

[0141] In the above scheme, during the collection of children's active health data, due to various reasons (such as equipment failure, data loss, etc.), there may be null values ​​or abnormal values ​​in some physiological indicator parameter sequences. These missing or abnormal data points will seriously affect the accuracy and reliability of subsequent data analysis. By using formula 4 to calculate the indicator estimate, we can automatically detect and fill these missing or abnormal data points, thereby significantly improving the integrity and availability of the data. This is crucial for subsequent data analysis, model training, and health status assessment.

[0142] Formula 4 can estimate missing or abnormal data points by comprehensively considering the data points before and after the target object and the data values ​​of related indicators at the same time point. It not only considers the continuity in time, but also the correlation between different physiological indicators, thereby improving the accuracy of the estimated value. The above estimated values ​​help maintain the continuity and consistency of children's health data and provide more comprehensive information for health status assessment.

[0143] S204: Add the indicator estimation value to the first indicator parameter sequence.

[0144] After filling in the indicator estimates, the system can also verify these estimates to ensure their rationality and accuracy. The verification process may include checking the correlation with other physiological indicators, comparing with historical data, etc. If the estimated value is found to be obviously unreasonable or significantly inconsistent with other data, the system can also recalculate or use other methods to fill it in.

[0145] S205. Determine an indicator parameter associated characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence.

[0146] In this step, an indicator parameter association characteristic value is determined according to the first indicator parameter sequence and the second indicator parameter sequence, and the indicator parameter association characteristic value is used to characterize the matching degree between the first indicator parameter sequence and the second indicator parameter sequence.

[0147] Specifically, in order to quantify the degree of matching between the first indicator parameter sequence and the second indicator parameter sequence, the indicator parameter correlation characteristic value can be calculated using statistical or machine learning methods, and the specific methods include but are not limited to covariance analysis, Pearson correlation coefficient calculation, etc. In addition, considering the dynamic change characteristics of children's physiological indicators, time delay steps can also be introduced to capture the delayed correlation relationship between indicators. By comprehensively considering these factors, the characteristic value that can accurately reflect the degree of correlation between indicators is calculated.

[0148] Optionally, the first physiological indicator and the second physiological indicator have a preset association relationship in a preset physiological indicator association list, and the preset physiological indicator association list is used to establish a preset association relationship between different physiological indicators. Correspondingly, determining the indicator parameter association characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence includes:

[0149] Traverse any two indicator parameters in the preset physiological indicator association list, determine the indicator parameter association characteristic value between two different indicator parameters, and form an indicator parameter association characteristic value set, wherein the two different indicator parameters correspond to two different indicator parameter sequences in the active health data sequence to be processed. Determine the comprehensive indicator parameter association characteristic value corresponding to the original multi-source active health data according to the indicator parameter association characteristic value set. Only when the comprehensive indicator parameter association characteristic value is greater than the preset indicator parameter association characteristic threshold value, the original multi-source active health data is determined to be the active health data to be evaluated for the target child object.

[0150] Specifically, a preset physiological indicator association list may first be established. The list is used to clarify the preset association relationships between different physiological indicators, which are pre-set based on physiological and medical knowledge. The preset physiological indicator association list is presented in a table format, where each row represents an association pair, including two physiological indicators and their association relationship descriptions.

[0151] After obtaining the active health data sequence to be processed, the preset physiological index association list is traversed. For each association pair in the list, the first index parameter sequence and the second index parameter sequence corresponding to the two physiological indexes in the data sequence to be processed are extracted.

[0152] For each pair of extracted indicator parameter sequences, the correlation eigenvalues ​​between them are calculated using statistical or machine learning methods. The specific method can be selected according to the actual situation, such as covariance analysis, Pearson correlation coefficient calculation, etc. The calculated correlation eigenvalues ​​reflect the matching degree and correlation of the two physiological indicators in the time series. All these correlation eigenvalues ​​are combined into an indicator parameter correlation eigenvalue set to provide a data basis for subsequent comprehensive evaluation.

[0153] After obtaining the set of indicator parameter associated eigenvalues, it is necessary to further calculate the integrated indicator parameter associated eigenvalues ​​corresponding to the original multi-source active health data. This can be achieved by weighted averaging, summing or other statistical methods for all associated eigenvalues ​​in the set. The integrated indicator parameter associated eigenvalue is a quantitative assessment of the overall correlation of the original data, reflecting the coordination and consistency between multiple physiological indicators within the data.

[0154] Finally, the calculated comprehensive indicator parameter associated characteristic value is compared with the preset indicator parameter associated characteristic threshold. The preset threshold is set based on a large amount of historical data and medical knowledge, and is used to judge the quality and reliability of the data. When the comprehensive indicator parameter associated characteristic value is greater than the preset threshold, the original multi-source active health data is considered to be valid and reliable, and can be determined as the active health data to be evaluated for the target child object. On the contrary, if the comprehensive characteristic value is less than or equal to the threshold, the original data needs to be further checked, verified, or the abnormal data points need to be excluded and the comprehensive characteristic value needs to be recalculated.

[0155] S206: Determine the original multi-source active health data as the active health data to be evaluated for the target child object.

[0156] In this step, only when the indicator parameter-associated characteristic value satisfies the preset parameter-associated condition, the original multi-source active health data is determined as the active health data to be evaluated of the target child object.

[0157] Specifically, the calculated indicator parameter-associated characteristic value is compared with the preset parameter-associated condition. The preset condition can be set based on historical data and medical knowledge to judge the quality and reliability of the data. When the characteristic value meets the preset condition, the original multi-source active health data is considered to be valid and reliable, and can be used as the active health data to be evaluated for the target child object. On the contrary, if the characteristic value does not meet the condition, it is necessary to further check and verify the original data, or recalculate the characteristic value after excluding abnormal data points.

[0158] Figure 3 FIG. 1 is a schematic diagram of a multi-dimensional data determination system for children's active health according to an exemplary embodiment of the present application. Figure 3 As shown, the multi-dimensional data determination system 300 for active health of children provided in this embodiment includes:

[0159] An acquisition module 310 is used to acquire original multi-source active health data of a target child object, and generate a sequence of active health data to be processed according to the original multi-source active health data using a time tag, wherein the active health data to be processed in the sequence of active health data to be processed includes a multi-dimensional data framework and indicator parameters for filling each physiological indicator in the multi-dimensional data framework;

[0160] An extraction module 320 is used to extract a first indicator parameter sequence of a first physiological indicator and a second indicator parameter sequence of a second physiological indicator from the active health data sequence to be processed, wherein the first physiological indicator and the second physiological indicator are two physiological indicators having a preset association relationship;

[0161] A processing module 330, configured to determine an indicator parameter association characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence, wherein the indicator parameter association characteristic value is used to characterize a matching degree between the first indicator parameter sequence and the second indicator parameter sequence;

[0162] The processing module 330 is further configured to determine that the original multi-source active health data is the active health data to be evaluated of the target child object only when the indicator parameter associated characteristic value satisfies a preset parameter associated condition.

[0163] Optionally, there is a preset association relationship between the first physiological indicator and the second physiological indicator in a preset physiological indicator association list, and the preset physiological indicator association list is used to establish a preset association relationship between different physiological indicators;

[0164] The processing module 330 is specifically used for:

[0165] Traversing any two indicator parameters in the preset physiological indicator association list, determining the indicator parameter association characteristic value between two different indicator parameters to form an indicator parameter association characteristic value set, wherein the two different indicator parameters correspond to two different indicator parameter sequences in the active health data sequence to be processed;

[0166] Determining the comprehensive indicator parameter associated characteristic value corresponding to the original multi-source active health data according to the indicator parameter associated characteristic value set;

[0167] Only when the comprehensive indicator parameter associated characteristic value is greater than the preset indicator parameter associated characteristic threshold value, the original multi-source active health data is determined to be the active health data to be evaluated of the target child object.

[0168] Optionally, the processing module 330 is specifically configured to:

[0169] Using formula 1, and according to the first indicator parameter sequence P = {p1, p2, ..., p i ,…,p n} and the second indicator parameter sequence Q={q1,q2,…,q i ,…,q n}Determine the indicator parameter associated characteristic value K, the formula 1 is:

[0170]

[0171] Among them, p i is the i-th indicator parameter in the first indicator parameter sequence P, q i is the i-th indicator parameter in the second indicator parameter sequence Q, is the average value of the indicator parameters of the first indicator parameter sequence P, is the average value of the indicator parameters of the second indicator parameter sequence Q.

[0172] Optionally, the processing module 330 is specifically configured to:

[0173] The indicator parameter association characteristic value is determined according to the first indicator parameter sequence, the second indicator parameter sequence and the time delay step number, and the time delay step number is used to characterize the delay association relationship between the first indicator parameter and the second indicator parameter.

[0174] Optionally, the processing module 330 is specifically configured to:

[0175] The indicator parameter associated characteristic value is updated by using weight values ​​corresponding to different time delay steps to generate updated indicator parameter associated characteristic value, and the updated indicator parameter associated characteristic value is used to replace the indicator parameter associated characteristic value.

[0176] Optionally, the processing module 330 is specifically configured to:

[0177] If it is determined that the target object exists in the first indicator parameter sequence, determining the indicator estimation value of the target object according to the first indicator parameter sequence and the second indicator parameter sequence, wherein the indicator parameter corresponding to the target object in the first indicator parameter sequence is empty or abnormal;

[0178] The indicator estimate is added to the first indicator parameter sequence.

[0179] Optionally, the processing module 330 is specifically configured to:

[0180] Acquire a first indicator parameter and a second indicator parameter, wherein the first indicator parameter and the second indicator parameter are respectively the previous data and the next data of the target object in the first indicator parameter sequence;

[0181] Obtaining a third indicator parameter, a fourth indicator parameter, and a fifth indicator parameter in the second indicator parameter sequence, wherein the third indicator parameter and the first indicator parameter have the same time tag, the fourth indicator parameter and the target object have the same time tag, and the fifth indicator parameter and the second indicator parameter have the same time tag;

[0182] The indicator estimation value is determined according to the first indicator parameter, the second indicator parameter, the third indicator parameter, the fourth indicator parameter and the fifth indicator parameter.

[0183] Figure 4 is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application. Figure 4 As shown, an electronic device 400 provided in this embodiment includes: a processor 401 and a memory 402; wherein:

[0184] The memory 402 is used to store computer programs, and the memory may also be a flash memory.

[0185] The processor 401 is used 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.

[0186] Optionally, the memory 402 may be independent or integrated with the processor 401 .

[0187] When the memory 402 is a device independent of the processor 401, the electronic device 400 may further include:

[0188] The bus 403 is used to connect the memory 402 and the processor 401 .

[0189] 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 above-mentioned various implementation modes.

[0190] This embodiment also provides a program product, which includes a computer program stored in a readable storage medium. At least one processor of the electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device implements the methods provided in the above various embodiments.

[0191] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

[0192] It should be understood that the present application is not limited to the precise structures that have been 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 determining multi-dimensional data for children's active health, characterized in that: include: Acquire original multi-source active health data of the target child object, and generate a sequence of active health data to be processed based on the original multi-source active health data using a time tag, wherein the active health data to be processed in the sequence of active health data to be processed includes a multi-dimensional data framework and indicator parameters for filling each physiological indicator in the multi-dimensional data framework; Extracting a first indicator parameter sequence of a first physiological indicator and a second indicator parameter sequence of a second physiological indicator from the active health data sequence to be processed, wherein the first physiological indicator and the second physiological indicator are two physiological indicators having a preset association relationship; Determine an indicator parameter association characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence, wherein the indicator parameter association characteristic value is used to characterize the degree of matching between the first indicator parameter sequence and the second indicator parameter sequence; Only when the indicator parameter-associated characteristic value satisfies the preset parameter-associated condition, the original multi-source active health data is determined to be the active health data to be evaluated of the target child object.

2. The method for determining multi-dimensional data for active health of children according to claim 1, characterized in that: There is a preset association relationship between the first physiological indicator and the second physiological indicator in a preset physiological indicator association list, and the preset physiological indicator association list is used to establish a preset association relationship between different physiological indicators; Correspondingly, determining the indicator parameter associated characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence includes: Traversing any two indicator parameters in the preset physiological indicator association list, determining the indicator parameter association characteristic value between two different indicator parameters to form an indicator parameter association characteristic value set, wherein the two different indicator parameters correspond to two different indicator parameter sequences in the active health data sequence to be processed; Determining the comprehensive indicator parameter associated characteristic value corresponding to the original multi-source active health data according to the indicator parameter associated characteristic value set; The determining that the original multi-source active health data is the active health data to be evaluated of the target child object only when the indicator parameter associated characteristic value satisfies the preset parameter associated condition includes: Only when the comprehensive indicator parameter associated characteristic value is greater than the preset indicator parameter associated characteristic threshold value, the original multi-source active health data is determined to be the active health data to be evaluated of the target child object.

3. The method for determining multi-dimensional data for active health of children according to claim 2, characterized in that: The determining the indicator parameter associated characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence includes: Using formula 1, and according to the first indicator parameter sequence P = {p1, p2, ..., p i ,…,p n } and the second indicator parameter sequence Q={q1,q2,…,q i ,…,q n }Determine the indicator parameter associated characteristic value K, the formula 1 is: Among them, p i is the i-th indicator parameter in the first indicator parameter sequence P, q i is the i-th indicator parameter in the second indicator parameter sequence Q, is the average value of the indicator parameters of the first indicator parameter sequence P, is the average value of the indicator parameters of the second indicator parameter sequence Q.

4. The method for determining multi-dimensional data for active health of children according to claim 2, characterized in that: The determining the indicator parameter associated characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence includes: The indicator parameter association characteristic value is determined according to the first indicator parameter sequence, the second indicator parameter sequence and the time delay step number, and the time delay step number is used to characterize the delay association relationship between the first indicator parameter and the second indicator parameter.

5. The method for determining multi-dimensional data for active health of children according to claim 4, characterized in that: After determining the indicator parameter associated characteristic value according to the first indicator parameter sequence, the second indicator parameter sequence and the time delay step number, the method further includes: The indicator parameter associated characteristic value is updated by using weight values ​​corresponding to different time delay steps to generate updated indicator parameter associated characteristic value, and the updated indicator parameter associated characteristic value is used to replace the indicator parameter associated characteristic value.

6. The method for determining multi-dimensional data for active health of children according to any one of claims 1 to 5, characterized in that: After extracting the first indicator parameter sequence of the first physiological indicator and the second indicator parameter sequence of the second physiological indicator from the active health data sequence to be processed, the method further includes: If it is determined that the target object exists in the first indicator parameter sequence, determining the indicator estimation value of the target object according to the first indicator parameter sequence and the second indicator parameter sequence, wherein the indicator parameter corresponding to the target object in the first indicator parameter sequence is empty or abnormal; The indicator estimate is added to the first indicator parameter sequence.

7. The method for determining multi-dimensional data for active health of children according to claim 6, characterized in that: The step of determining the indicator estimation value of the target object according to the first indicator parameter sequence and the second indicator parameter sequence includes: Acquire a first indicator parameter and a second indicator parameter, wherein the first indicator parameter and the second indicator parameter are respectively the previous data and the next data of the target object in the first indicator parameter sequence; Obtaining a third indicator parameter, a fourth indicator parameter, and a fifth indicator parameter in the second indicator parameter sequence, wherein the third indicator parameter and the first indicator parameter have the same time tag, the fourth indicator parameter and the target object have the same time tag, and the fifth indicator parameter and the second indicator parameter have the same time tag; The indicator estimation value is determined according to the first indicator parameter, the second indicator parameter, the third indicator parameter, the fourth indicator parameter and the fifth indicator parameter.

8. A multi-dimensional data determination system for children's active health, characterized in that: include: An acquisition module, used to acquire original multi-source active health data of a target child object, and generate a sequence of active health data to be processed according to the original multi-source active health data using a time tag, wherein the active health data to be processed in the sequence of active health data to be processed includes a multi-dimensional data framework and indicator parameters for filling each physiological indicator in the multi-dimensional data framework; An extraction module, used to extract a first indicator parameter sequence of a first physiological indicator and a second indicator parameter sequence of a second physiological indicator from the active health data sequence to be processed, wherein the first physiological indicator and the second physiological indicator are two physiological indicators having a preset association relationship; a processing module, configured to determine an indicator parameter association characteristic value according to the first indicator parameter sequence and the second indicator parameter sequence, wherein the indicator parameter association characteristic value is used to characterize a matching degree between the first indicator parameter sequence and the second indicator parameter sequence; The processing module is further configured to determine that the original multi-source active health data is the active health data to be evaluated of the target child object only when the indicator parameter associated characteristic value satisfies a preset parameter associated condition.

9. An electronic device, characterized in that: include: processor; as well as, A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

10. 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 7 when executed by a processor.

Images