Traditional Chinese medicine child health care system and method based on big data

Abstract

The invention discloses a traditional Chinese medicine child health care system and method based on big data. The system comprises a data acquisition module, a data processing and integration module, a physique identification module and a generation module. Through data processing means such as principal component analysis and clustering analysis, multi-dimensional health data can be efficiently integrated and analyzed, and the accuracy and reliability of data processing are ensured; meanwhile, the physique identification module combines a random forest and a support vector machine algorithm, so that the physique classification and identification process is more accurate and efficient; besides, the generation module can provide health management schemes, including adjustment suggestions of diet, exercise and living habits, for each child according to the identification result, so that dynamic management and continuous optimization of child health are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of TCM child health care, and in particular to a TCM child health care system and method based on big data. Background Art

[0002] With the rapid development of modern society, children's health issues have received more and more attention. Children's physical and psychological development is not yet mature, and they are easily affected by many factors such as environment, diet, and living habits, resulting in complex and diverse physical constitutions. Traditional Chinese medicine child health care usually relies on the doctor's experience, and judges the child's constitution through observation, smell, questioning, and palpation, and gives corresponding health care advice. However, this method is more subjective, and the doctor's professional level and experience directly affect the accuracy of physical constitution identification.

[0003] In the actual process of child health care, parents often find it difficult to obtain scientific and comprehensive health information, resulting in the inability to monitor and adjust children's health status in a timely manner. For example, some children may have hidden metabolic problems. If we only rely on doctors' external observation and traditional medical consultation methods, it is often difficult to discover these potential health risks. In addition, as children grow up, their physical fitness and health status will be dynamically affected by multiple factors. The lack of continuous monitoring of these changes may cause some problems to be ignored in the early stages, thus developing into serious health problems later.

[0004] Based on this, a TCM pediatric health care system and method based on big data is needed. Summary of the invention

[0005] To achieve the above object, the present invention provides the following solution: a TCM child health care system based on big data, comprising:

[0006] Data acquisition module, data processing and integration module, constitution identification module and generation module;

[0007] The data collection module is used to collect genomic data, metabolomics data and life habit data of children, wherein:

[0008] Genomic data are obtained through non-invasive sampling technology, and high-throughput gene sequencing technology is used to analyze gene information. Metabolomics data are obtained through blood or urine samples, and liquid chromatography-mass spectrometry is used to analyze metabolite spectra. Eating habits, exercise volume, sleep quality and living habits data are collected through smart wearable devices and mobile applications.

[0009] The data processing and integration module is connected to the data acquisition module, and is used to clean and standardize the collected data, and integrate different types of data through a data fusion algorithm to build a child health status description model;

[0010] The constitution identification module is connected to the data processing and integration module, and is used to classify the children's constitution types and predict the children's susceptible diseases based on the five-element constitution theory of traditional Chinese medicine and the collected gene and metabolic data;

[0011] The generation module is connected to the physical constitution identification module and is used to generate personalized health suggestions according to the physical constitution identification results, including diet suggestions, exercise suggestions and life habit suggestions.

[0012] Further preferably, the data processing and integration module includes a principal component analysis unit, a cluster analysis unit and a data cleaning unit, wherein: the principal component analysis unit is used to perform dimensionality reduction processing on the collected data to ensure the efficiency and accuracy of data processing; the cluster analysis unit is used to perform cluster analysis on the children's health data by identifying groups of children with similar physical types; the data cleaning unit is used to perform data quality detection and outlier processing on the collected genomics, metabolomics and lifestyle data to ensure the accuracy and consistency of the input data.

[0013] Further preferably, the physical constitution identification module includes a preliminary classification unit and a fine identification unit, wherein: the preliminary classification unit uses a random forest algorithm to preliminarily classify the physical constitution types of children, and the random forest algorithm integrates multiple decision trees to quickly and accurately classify the genomic and metabolomics data of children; the fine identification unit uses a support vector machine algorithm to further refine the preliminary classification results, and the support vector machine algorithm accurately divides different physical constitution types by constructing an optimal classification surface in a high-dimensional space.

[0014] In addition, the present invention also provides a method of a TCM child health care system based on big data, comprising the following steps:

[0015] S1. Collect children's genomic data, metabolomics data and lifestyle data through the data collection module, including:

[0016] Use non-invasive sampling technology to collect children's genomic data, and analyze the collected genetic data through high-throughput gene sequencing technology to obtain children's genetic characteristic information. Obtain metabolomics data by collecting blood or urine samples, and use liquid chromatography-mass spectrometry technology to analyze the types and contents of metabolites to evaluate children's metabolic function and nutritional status. Use smart wearable devices and mobile applications to collect children's living habit data, including eating habits, exercise, and sleep quality, to form a continuous life data record. The collection of living habit data must ensure the authenticity and timeliness of the data, and achieve real-time monitoring and uploading of data through mobile applications;

[0017] S2, inputting the data collected by the data collection module into the data processing and integration module;

[0018] S3. Analyze the integrated data through the constitution identification module, and use the random forest algorithm to perform preliminary constitution classification on the integrated genomics and metabolomics data. The random forest constructs multiple decision trees for integrated learning to quickly obtain preliminary results of children's constitution types. The support vector machine (SVM) algorithm is used to refine the preliminary classification results. SVM ensures accurate division of different constitution types by constructing the optimal classification surface in high-dimensional space.

[0019] S4. Generate personalized health recommendations for each child based on the results of constitution identification;

[0020] S5. Carry out long-term management and continuous optimization of children’s health status.

[0021] Through smart wearable devices, children's health parameters are monitored in real time, including heart rate, body temperature, and activity level physiological indicators. The real-time collected health data is combined with the original data and input into the system for continuous data updating and integration. Feedback is provided to parents through health trend analysis and abnormal warnings generated by the system.

[0022] Further preferably, the genomic data collection in step S1 further includes deep sequencing of specific gene loci, and the deep sequencing selects candidate gene loci that are closely related to TCM constitution, and uses high-throughput sequencing technology to accurately sequence these loci to obtain rich genetic information, more comprehensively evaluate the physical characteristics of children, and identify specific gene markers of physical constitution type.

[0023] Further preferably, in said S2, the data input includes:

[0024] S21. Perform data quality detection and cleaning on the collected data, remove outliers and erroneous data, use automated algorithms to quickly process large-scale data in the data cleaning step, and manually review suspected abnormal data. Use standardization to normalize the data, convert genomics, metabolomics and lifestyle data into a unified scale to facilitate the integrated analysis of cross-domain data. Standardized data can reduce the deviation between different types of data;

[0025] S22. Use principal component analysis (PCA) to reduce the dimensionality of the data, extract the main features in the data, reduce the data dimension and retain important information;

[0026] S23. Use the K-means clustering algorithm to cluster the standardized data and identify groups of children with similar health characteristics. By analyzing the group characteristics, the common characteristics and differences of different physiques can be identified.

[0027] Further preferably, in S4, the health advice includes:

[0028] S41. Recommend appropriate diet plans based on children’s physical type and metabolic status, including specific food selection, nutrient intake and meal schedule, to maintain the balance of yin and yang and the fullness of qi and blood in the body. Dietary recommendations should also take into account the impact of seasonal changes on food ingredients;

[0029] S42. Generate a personalized exercise plan based on the child's physical characteristics and current living habits, including appropriate exercise types, exercise frequency and exercise intensity, aiming to improve the child's physical fitness and immunity, while avoiding the negative impact of excessive exercise on children with weak constitutions;

[0030] S43. Provide suggestions for adjusting work and rest schedules and optimizing indoor temperature and humidity environment based on physical assessment results and children’s living habit data.

[0031] Further preferably, in S3, the physical constitution type is dynamically adjusted and optimized by combining the children's living habit data, and an adaptive algorithm is used to dynamically update the physical constitution assessment results, fully reflecting the health changes of children in their living habits and growth process.

[0032] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0033] 1. The present invention comprehensively collects children's genomic data, metabolomics data and living habits data, and uses data fusion and machine learning to accurately identify children's constitutions and generate personalized health care recommendations, effectively solving the subjectivity and inaccuracy problems in the traditional Chinese medicine constitution identification process;

[0034] 2. The present invention can efficiently integrate and analyze multi-dimensional health data through data processing methods such as principal component analysis and cluster analysis, ensuring the accuracy and reliability of data processing; at the same time, the physical constitution identification module combines random forest and support vector machine algorithms to make the physical constitution classification and identification process more accurate and efficient; in addition, the generation module can provide a health management plan for each child based on the identification results, including suggestions for adjustments to diet, exercise and lifestyle habits, to achieve dynamic management and continuous optimization of children's health. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is a system module diagram of the present invention;

[0037] Figure 2 It is a flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0040] Example

[0041] like Figure 1 As shown, a TCM child health care system based on big data in this embodiment includes:

[0042] Data acquisition module, data processing and integration module, constitution identification module and generation module;

[0043] The data collection module is used to collect children's genomic data, metabolomics data, and lifestyle data to form a multi-dimensional assessment of children's health status, including:

[0044] Genomic data is obtained through non-invasive sampling technology, and high-throughput gene sequencing technology is used to analyze genetic information, ensuring the safety and comfort of children during the data collection process. Metabolomics data is obtained through blood or urine samples, and liquid chromatography-mass spectrometry is used to analyze the metabolite spectrum to accurately understand the metabolism of children, thereby evaluating their nutritional status. Eating habits, exercise volume, sleep quality and living habits data are collected through smart wearable devices and mobile applications. Multi-level and multi-channel data collection makes the acquisition of children's health information more comprehensive and accurate;

[0045] The data processing and integration module is connected to the data acquisition module to clean and standardize the collected data, integrate different types of data through data fusion algorithms, and build a child health status description model;

[0046] The data processing and integration module includes a principal component analysis unit, a cluster analysis unit and a data cleaning unit, which improves the efficiency and quality of data processing. The principal component analysis unit is used to reduce the dimension of the collected data to ensure that the complexity of the data is reduced while retaining the important features of the data, thereby improving the calculation efficiency; the cluster analysis unit is used to cluster the children's health data, and by identifying groups of children with similar physical types, it helps to provide personalized health plans for children with different physical types; the data cleaning unit is used to perform data quality detection and outlier processing on the collected genomics, metabolomics and lifestyle data to ensure the accuracy and consistency of the input data;

[0047] The constitution identification module is connected to the data processing and integration module, and is used to classify children's constitution types and predict children's susceptible diseases based on the five-element constitution theory of traditional Chinese medicine and the collected genetic and metabolic data;

[0048] The constitution identification module includes a preliminary classification unit and a fine identification unit, wherein: the preliminary classification unit uses the random forest algorithm to preliminarily classify the children's constitution types. The random forest algorithm integrates multiple decision trees to quickly and accurately classify the children's genomic and metabolomics data to ensure accurate classification of different constitution types; the fine identification unit uses the support vector machine algorithm to further refine the preliminary classification results. The support vector machine algorithm accurately divides different constitution types by constructing the optimal classification surface in high-dimensional space;

[0049] The generation module analyzes the results of constitution identification and provides tailored health recommendations for each child, including suggestions for adjustments in diet, exercise and lifestyle habits. These recommendations combine the child's constitution type, metabolic status and lifestyle data, and are highly targeted and practical. They help improve the child's overall health status and prevent the occurrence of disease, fully embodying the Chinese medicine concept of "preventing disease before it occurs." In addition, the real-time monitoring function of smart wearable devices enables health recommendations to be dynamically adjusted according to the child's health status, ensuring the continuity and effectiveness of health management.

[0050] In addition, if Figure 2 As shown, the present invention also provides a method of a TCM child health care system based on big data, comprising the following steps:

[0051] S1. Collect children's genomic data, metabolomics data and lifestyle data through the data collection module, including:

[0052] Use non-invasive sampling technology to collect children's genomic data, and analyze the collected genetic data through high-throughput gene sequencing technology to obtain children's genetic characteristic information. Obtain metabolomics data by collecting blood or urine samples, and use liquid chromatography-mass spectrometry technology to analyze the types and contents of metabolites to evaluate children's metabolic function and nutritional status. Use smart wearable devices and mobile applications to collect children's living habit data, including eating habits, exercise, and sleep quality, to form a continuous life data record. The collection of living habit data must ensure the authenticity and timeliness of the data, and achieve real-time monitoring and uploading of data through mobile applications;

[0053] The genomic data collection further includes deep sequencing of specific gene loci. Deep sequencing selects candidate gene loci that are closely related to TCM constitution and uses high-throughput sequencing technology to accurately sequence these loci to obtain rich gene information, more comprehensively evaluate children's physical characteristics, and identify specific gene markers of physical constitution types.

[0054] Through the data collection module, children's genomic data, metabolomics data and lifestyle data are comprehensively collected. Genomic data are obtained using non-invasive sampling technology to ensure the safety and comfort of the sampling process for children. At the same time, deep sequencing of specific gene loci is performed through high-throughput gene sequencing technology to further improve the accuracy of identifying genetic characteristics related to TCM constitution. Metabolomics data are analyzed through liquid chromatography-mass spectrometry technology to understand children's metabolic function and nutritional status in detail. Lifestyle data are collected through smart wearable devices to form a continuous and dynamic life data record, thereby providing comprehensive and real basic data for subsequent health assessment and constitution identification.

[0055] S2. Input the data collected by the data collection module into the data processing and integration module. The data input includes: data quality detection and cleaning of the collected data, elimination of outliers and erroneous data. The data cleaning step uses an automated algorithm to quickly process large-scale data, and manually reviews suspected abnormal data. The data is normalized using standardization processing, and genomics, metabolomics and lifestyle data are converted into a unified scale to facilitate cross-domain data integration and analysis. The standardized data can reduce the deviation between different types of data; principal component analysis PCA is used to reduce the dimensionality of the data, extract the main features in the data, reduce the data dimension and retain important information; the standardized data is clustered using the cluster analysis algorithm K-means clustering to identify groups of children with similar health characteristics, and through the analysis of group characteristics, the common characteristics and differences of different physiques are identified;

[0056] The collected data is input into the data processing and integration module for data cleaning, standardization, dimensionality reduction and cluster analysis. The data quality detection and cleaning steps ensure the accuracy and consistency of the data, remove outliers and manually review suspicious data to ensure the reliability of the analysis results. Standardization allows different types of data to be compared on a unified scale to reduce the deviation between cross-domain data. Dimensionality reduction is performed through principal component analysis to extract the main features in the data, which not only retains important information but also reduces the complexity of the data. The data is further grouped according to cluster analysis to identify groups of children with similar health characteristics, thereby helping to accurately identify physical characteristics and health trends.

[0057] S3. Analyze the integrated data through the constitution identification module, and use the random forest algorithm to perform preliminary constitution classification on the integrated genomics and metabolomics data. The random forest constructs multiple decision trees for integrated learning to quickly obtain the preliminary results of the children's constitution type. The support vector machine (SVM) algorithm is used to finely identify the preliminary classification results. SVM ensures the accurate division of different constitution types by constructing the optimal classification surface in high-dimensional space. Then, by combining the children's living habits data, the constitution type is dynamically adjusted and optimized. The adaptive algorithm is used to dynamically update the constitution assessment results, fully reflecting the health changes of children in their living habits and growth process.

[0058] Through the constitution identification module, the five-element constitution theory of traditional Chinese medicine and modern machine learning algorithms are combined to classify and identify the constitution types of data. By using the random forest algorithm to perform preliminary constitution classification on genomics and metabolomics data, the constitution type of children can be quickly and effectively identified. Next, the support vector machine is used to refine the preliminary classification results to ensure the accuracy and reliability of constitution classification. The effect of the constitution identification module lies in that it combines traditional Chinese medicine theory with modern machine learning technology, which not only inherits the scientific nature of Chinese medicine theory, but also enhances the accuracy of data processing and identification. In addition, through the adaptive algorithm, the constitution assessment results can be dynamically adjusted to adapt to the health changes of children as they grow and develop.

[0059] S4. Generate personalized health recommendations for each child based on the results of constitution identification. The health recommendations include: recommending a suitable diet plan based on the child's constitution type and metabolic status, including specific food selection, nutrient intake and meal schedule to maintain the balance of yin and yang and the fullness of qi and blood in the body. Dietary recommendations also need to consider the impact of seasonal changes on food ingredients; based on the child's constitution characteristics and current living habits data, generate a personalized exercise plan, including appropriate exercise types, exercise frequency and exercise intensity, aiming to improve the child's constitution and immunity, while avoiding the negative impact of excessive exercise on children with weak constitutions; based on the constitution assessment results and the child's living habits data, provide suggestions for adjusting work and rest time, as well as optimizing the indoor temperature and humidity environment;

[0060] S5. Carry out long-term management and continuous optimization of children's health status, monitor children's health parameters in real time through smart wearable devices, including heart rate, body temperature, and activity level physiological indicators, combine the real-time collected health data with the original data, input the data into the system for continuous data update and integration, and provide feedback to parents through health trend analysis and abnormal warnings generated by the system.

[0061] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0062] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A TCM children's health care system based on big data, characterized in that: include: Data acquisition module, data processing and integration module, constitution identification module and generation module; The data collection module is used to collect genomic data, metabolomics data and life habit data of children, wherein: Genomic data are obtained through non-invasive sampling technology, and high-throughput gene sequencing technology is used to analyze gene information. Metabolomics data are obtained through blood or urine samples, and liquid chromatography-mass spectrometry is used to analyze metabolite spectra. Eating habits, exercise volume, sleep quality and living habits data are collected through smart wearable devices and mobile applications. The data processing and integration module is connected to the data acquisition module, and is used to clean and standardize the collected data, and integrate different types of data through a data fusion algorithm to build a child health status description model; The constitution identification module is connected to the data processing and integration module, and is used to classify the children's constitution types and predict the children's susceptible diseases based on the five-element constitution theory of traditional Chinese medicine and the collected gene and metabolic data; The generation module is connected to the physical constitution identification module and is used to generate personalized health suggestions according to the physical constitution identification results, including diet suggestions, exercise suggestions and life habit suggestions.

2. A TCM child health care system and method based on big data according to claim 1, characterized in that: The data processing and integration module includes a principal component analysis unit, a cluster analysis unit and a data cleaning unit, wherein: the principal component analysis unit is used to perform dimensionality reduction processing on the collected data to ensure the efficiency and accuracy of data processing; the cluster analysis unit is used to perform cluster analysis on the children's health data by identifying groups of children with similar physical types; the data cleaning unit is used to perform data quality detection and outlier processing on the collected genomics, metabolomics and lifestyle data to ensure the accuracy and consistency of the input data.

3. A TCM child health care system and method based on big data according to claim 1, characterized in that: The constitution identification module includes a preliminary classification unit and a fine identification unit, wherein: the preliminary classification unit uses a random forest algorithm to preliminarily classify the children's constitution types, and the random forest algorithm integrates multiple decision trees to quickly and accurately classify the children's genomics and metabolomics data; the fine identification unit uses a support vector machine algorithm to further refine the preliminary classification results, and the support vector machine algorithm accurately divides different constitution types by constructing the optimal classification surface in a high-dimensional space.

4. A method of a TCM child health care system based on big data according to any one of claims 1 to 3, characterized in that: The following steps are involved: S1. Collect children's genomic data, metabolomics data and lifestyle data through the data collection module, including: Use non-invasive sampling technology to collect children's genomic data, and analyze the collected genetic data through high-throughput gene sequencing technology to obtain children's genetic characteristic information. Obtain metabolomics data by collecting blood or urine samples, and use liquid chromatography-mass spectrometry technology to analyze the types and contents of metabolites to evaluate children's metabolic function and nutritional status. Use smart wearable devices and mobile applications to collect children's living habit data, including eating habits, exercise, and sleep quality, to form a continuous life data record. The collection of living habit data must ensure the authenticity and timeliness of the data, and use mobile applications to achieve real-time monitoring and uploading of data; S2, inputting the data collected by the data collection module into the data processing and integration module; S3. Analyze the integrated data through the constitution identification module, and use the random forest algorithm to perform preliminary constitution classification on the integrated genomics and metabolomics data. The random forest constructs multiple decision trees for integrated learning to quickly obtain preliminary results of children's constitution types. The support vector machine (SVM) algorithm is used to refine the preliminary classification results. SVM ensures accurate division of different constitution types by constructing the optimal classification surface in high-dimensional space. S4. Generate personalized health recommendations for each child based on the results of constitution identification; S5. Carry out long-term management and continuous optimization of children’s health status. Through smart wearable devices, children's health parameters are monitored in real time, including heart rate, body temperature, and activity level physiological indicators. The real-time collected health data is combined with the original data and input into the system for continuous data updating and integration. Feedback is provided to parents through health trend analysis and abnormal warnings generated by the system.

5. A TCM child health care system and method based on big data according to claim 4, characterized in that: The genomic data collection in step S1 further includes deep sequencing of specific gene loci. The deep sequencing selects candidate gene loci that are closely related to TCM constitution and uses high-throughput sequencing technology to accurately sequence these loci to obtain rich genetic information, more comprehensively evaluate the physical characteristics of children, and identify specific gene markers of physical constitution types.

6. A TCM child health care system and method based on big data as claimed in claim 4, characterized in that: The data input in S2 includes: S21. Perform data quality detection and cleaning on the collected data, remove outliers and erroneous data, use automated algorithms to quickly process large-scale data in the data cleaning step, and manually review suspected abnormal data. Use standardization to normalize the data, convert genomics, metabolomics and lifestyle data into a unified scale to facilitate the integrated analysis of cross-domain data. Standardized data can reduce the deviation between different types of data; S22. Use principal component analysis (PCA) to reduce the dimensionality of the data, extract the main features in the data, reduce the data dimension and retain important information; S23. Use the K-means clustering algorithm to cluster the standardized data and identify groups of children with similar health characteristics. By analyzing the group characteristics, the common characteristics and differences of different physiques can be identified.

7. A TCM child health care system and method based on big data according to claim 4, characterized in that: In S4, health advice includes: S41. Recommend appropriate diet plans based on children’s physical type and metabolic status, including specific food selection, nutrient intake and meal schedule, to maintain the balance of yin and yang and the fullness of qi and blood in the body. Dietary recommendations should also take into account the impact of seasonal changes on food ingredients; S42. Generate a personalized exercise plan based on the child's physical characteristics and current living habits, including appropriate exercise types, exercise frequency and exercise intensity, aiming to improve the child's physical fitness and immunity, while avoiding the negative impact of excessive exercise on children with weak constitutions; S43. Provide suggestions for adjusting work and rest schedules and optimizing indoor temperature and humidity environment based on physical assessment results and children’s living habits data.

8. A TCM child health care system and method based on big data according to claim 4, characterized in that: In S3, the physical constitution type is dynamically adjusted and optimized by combining the children's living habit data, and the physical constitution assessment results are dynamically updated using an adaptive algorithm, fully reflecting the health changes of children in their living habits and growth process.

Images