Construction method and system of health database and nutritional requirement database

By building a personalized health database and nutritional requirements database, using machine learning and statistical analysis, the problem of lack of personalization and incomplete database in the existing system is solved, precise health management and nutrition intervention suggestions are achieved, and the system is improved Real-time and user experience.

CN119066045AActive Publication Date: 2024-12-03贵港新食记食品有限公司 +1

Patent Information

Application Number
CN202410975639.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-12-03
Estimated Expiration
2044-07-19

AI Technical Summary

Technical Problem

The existing health management and nutrient intake recommendation systems lack personalization, the database is not comprehensive enough, modeling and algorithms cannot accurately capture population differences and data sparsity, cannot provide real-time feedback and adjustment suggestions, and the user interface is not friendly.

Method used

Build health databases and nutritional needs databases for different groups of people, establish a correlation database between health indicators and nutrient needs through data collection, sorting and analysis, develop personalized health assessment and nutrient intervention models, and use machine learning algorithms and statistical analysis to optimize users Interface and system real-time.

Benefits of technology

Personalized health management and nutrient intervention suggestions are realized, the accuracy and user experience of recommendations are improved, the latest research results and data changes can be reflected in real time, human errors and operational costs are reduced, and the effectiveness of health management and user satisfaction are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066045A_ABST
    Figure CN119066045A_ABST
Patent Text Reader

Abstract

The invention belongs to the field of health management and nutriology, and discloses a method for constructing a health database and a nutritional requirement database for different people, and the method comprises the steps: constructing a health index and nutrient requirement database for different healthy people and sub-healthy people; constructing a health index and nutrient demand correlation database; formulating health state assessment schemes for different people; and formulating a precise personalized nutrient intervention scheme for specific crowds. According to the method, the health database and the nutrient demand database of different crowds are constructed, personalized health assessment and nutrient intervention based on data analysis are realized, and accurate health management and nutrient intervention suggestions are provided for different crowds, so that the overall health level of different crowds is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to but is not limited to the field of health management and nutrition, and in particular relates to a method and system for constructing a health database and a nutritional requirement database for different groups of people. Background Art

[0002] Existing health management and nutrient intake recommendations are mainly targeted at the general population, without fully considering the special needs of different groups (such as pregnant women, infants, the elderly, etc.). People of different ages, genders, health levels, and lifestyles have different health indicators and nutrient requirements. In order to provide more accurate health management and nutrient intake guidance, it is necessary to build a health database and nutrient requirement database for different groups of people, and develop corresponding modeling and algorithms to achieve personalized health assessment and intervention measures.

[0003] The technical problems existing in the existing technologies in health management and nutrient intake recommendation mainly include the following points:

[0004] 1. Lack of personalized recommendations: The current system mainly makes recommendations based on broad population data, without fully considering individual differences. Everyone’s physical condition, nutritional needs, and health status are unique, so a more personalized recommendation system is needed.

[0005] 2. Incomplete database: The existing health database and nutrient requirement database may not be comprehensive enough, especially for specific groups (such as pregnant women, infants, the elderly, etc.), the data collection and analysis are insufficient. This leads to the possibility that the recommendations for these groups may not be accurate enough.

[0006] 3. Limitations of modeling and algorithms: Existing modeling and algorithms may not adequately capture all variables that affect health and nutrient requirements, or accurately make predictions and recommendations based on these variables. In addition, these algorithms may not be able to handle the sparsity and imbalance of data well.

[0007] 4. Lack of real-time feedback and adjustment: People’s physical conditions and nutritional needs change over time. Existing systems may not be able to provide real-time feedback and adjustment suggestions to meet users’ changing needs.

[0008] 5. Unfriendly user interface: The user interfaces of some existing health management and nutrient intake recommendation systems may not be intuitive and user-friendly enough, making it difficult for users to use them, thereby reducing the practicality and acceptance of the system.

[0009] To solve these problems, future technological development directions may include: building a more comprehensive and detailed database, developing more advanced modeling and algorithms to provide more accurate personalized recommendations, realizing real-time feedback and adjustment functions of the system, and optimizing the user interface. Summary of the invention

[0010] In view of the problems existing in the prior art, the present invention provides a method for constructing a health database and a nutritional requirement database for different groups of people.

[0011] The present invention is implemented as follows: a method for constructing a health database and a nutritional requirement database for different groups of people, the method comprising:

[0012] S1: Construct a database of health indicators and nutrient requirements for different healthy and sub-healthy populations;

[0013] S2: Construct a database on the correlation between health indicators and nutrient requirements;

[0014] S3: Develop health status assessment programs for different populations;

[0015] S4: Develop precise and personalized nutrient intervention plans for specific populations.

[0016] Furthermore, said S1 includes data collection and database construction;

[0017] The data collection specifically includes:

[0018] Data source:

[0019] (1) Medical institutions, health management platforms, questionnaires, personal health records, etc.;

[0020] (2) Literature from domestic and foreign journals and databases such as CNKI, Wanfang, VIP, ScienceDirect, PubMed, Web of Science, and WILEY;

[0021] (3) Relevant information on major official information platforms such as the National Health Commission and the Chinese Nutrition Society;

[0022] Data types: including health indicators such as weight, blood pressure, blood sugar, physical activity, sleep, and nutrient requirement data;

[0023] Target population: Healthy people: women preparing for pregnancy, pregnant women (early / mid-term / late), breastfeeding women, infants, children, teenagers, middle-aged people, and the elderly.

[0024] Sub-healthy people: obese people, people with hypertension, people with diabetes, people with tumors, people with cardiovascular diseases, etc.

[0025] Further, the S2 specifically includes:

[0026] (1) Data collection and organization: Statistics and analysis of the types and intake of nutrients that affect health status among people with different health levels;

[0027] (2) Data analysis and processing: Use regression analysis, correlation analysis, and machine learning algorithms to evaluate the correlation between nutrients and health levels;

[0028] (3) Database construction: Establish a database containing data related to health indicators and nutrient requirements.

[0029] Furthermore, the database construction specifically includes:

[0030] (1) Demand Analysis

[0031] Determine the data types and structures that the database needs to store, such as health indicators, nutrient types and intake, collection time, data sources, etc.;

[0032] (2) Database design: table structure design; field definition;

[0033] (3) Database implementation: Select a suitable database management system (such as MySQL, MongoDB), create a database and table;

[0034] (4) Data import: Import the cleaned and processed data into the database.

[0035] Further, the S3 specifically includes:

[0036] (1) Correlation analysis of health indicators: Using statistical analysis and machine learning methods, explore the correlation between different health indicator levels and health status, aiming to understand the intrinsic relationship between the indicators and provide a basis for the subsequent construction of personalized assessment models;

[0037] (2) Personalized assessment model, which is mainly used to achieve: based on the analysis results, build a health status assessment model suitable for different groups of people; the assessment model inputs different health indicator data and outputs health assessment results; the personalized assessment model aims to build a customized health status assessment model for different groups of people based on the analysis results of health indicators. By inputting different health indicator data, the model can output health assessment results and provide a scientific basis for personalized health management.

[0038] Furthermore, the implementation process of the correlation analysis of the health indicators specifically includes:

[0039] (1) Feature selection

[0040] LASSO regression: By introducing L1 regularization, important features are screened;

[0041] Random Forest: Use feature importance to evaluate the importance of each indicator;

[0042] (2) Modeling and Verification

[0043] Model selection: Choose an appropriate model (e.g. linear regression, decision tree, support vector machine);

[0044] Cross-validation: Split the data set for model training and validation to ensure the generalization ability of the model;

[0045] (3) Hyperparameter Tuning

[0046] Optimize model parameters using grid search or random search;

[0047] (4) Result analysis and reporting

[0048] Correlation report: Comprehensively describe the correlation between various health indicators;

[0049] Feature Importance: Using methods such as LASSO and random forest, key health indicators are listed and ranked in order of importance;

[0050] Model performance: Evaluate the performance of different models in predicting health indicators.

[0051] Furthermore, the implementation process of the personalized evaluation model is as follows:

[0052] (1) Data Grouping

[0053] Group data according to population characteristics (such as age, gender, health status, etc.) to ensure the model is targeted;

[0054] (2) Model selection

[0055] Model type: linear regression, decision tree, random forest, support vector machine, neural network, etc.

[0056] Model selection basis: Select the appropriate model type based on the data characteristics of health indicators and health levels;

[0057] (3) Model training

[0058] Divide the training set and test set; train the model and evaluate its performance;

[0059] (4) Model evaluation

[0060] Use evaluation indicators (such as accuracy, AUC, F1-score, etc.) to evaluate model performance;

[0061] Ensure the generalization ability of the model through cross-validation;

[0062] (5) Hyperparameter Tuning

[0063] Use grid search and random search to tune the model's hyperparameters to improve model performance.

[0064] Further, the S4 specifically includes:

[0065] Data integration: Integrate health data and nutrient requirement data from different sources and types to establish a complete and unified data set, providing a basis for subsequent algorithm model development;

[0066] Algorithmic model: Develop algorithms based on machine learning and statistical models to predict the impact of different nutrient intakes on health levels and generate personalized nutrient intervention recommendations.

[0067] Furthermore, the algorithm model algorithm steps are as follows:

[0068] (1) Feature selection

[0069] Select key health indicators and nutrient data: select important features through correlation analysis;

[0070] Feature engineering: creating new features to improve the predictive power of the model;

[0071] (2) Training Model

[0072] Choose a machine learning algorithm: such as linear regression, decision tree, random forest, support vector machine, neural network, etc.

[0073] Data segmentation: divided into training set and test set;

[0074] Model training: training the selected machine learning model;

[0075] (3) Model evaluation

[0076] Performance evaluation: using mean square error (MSE), R 2 Evaluate model performance using indicators such as

[0077] Cross-validation: K-fold cross-validation is used to evaluate the stability and generalization ability of the model;

[0078] (4) Generate personalized nutrient intervention recommendations

[0079] Rule engine: Establish a rule engine to provide personalized nutrient intervention recommendations based on model prediction results, such as increasing the intake of a certain nutrient;

[0080] Nutrient intervention optimization algorithm: Use linear programming or other optimization algorithms to recommend the best nutrient intervention plan for users.

[0081] Another object of the present invention is to provide a system for constructing a health database and a nutritional requirement database for different groups of people and a modeling system thereof, which implements the method for constructing a health database and a nutritional requirement database for different groups of people, and the system comprises:

[0082] Database construction module, obtain health data and nutrient requirement data from hospitals, health management platforms, etc.; remove duplicate and abnormal data to ensure data quality; use MySQL database to store structured data to realize health indicators and nutrient requirement database for different groups;

[0083] The data collection and import module collects data through questionnaires, medical records, health management platforms and other channels; cleans and organizes the collected data and imports it into the database;

[0084] The data analysis and modeling module uses statistical and machine learning methods based on the collected health data to establish health assessment models for different populations; analyzes the relationship between nutrients and health levels, and establishes a personalized nutrient demand model;

[0085] The system implements the module and develops a front-end interface to display the health assessment results and nutrient requirement recommendations for different groups of people; builds back-end services to provide API interfaces for health assessment and nutrient requirement prediction; and continuously optimizes algorithms to improve the accuracy of health assessment and nutrient requirement prediction.

[0086] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0087] First, use methods such as literature query, web crawler, and information platform search to obtain original data and establish a database related to food nutrition and human health; design a dynamic and process-based database construction algorithm model.

[0088] The advantages and innovations of the dynamic and process-based database construction method are as follows:

[0089] (1) Dynamic

[0090] Real-time update: Dynamic databases can reflect the latest research results and data changes in real time, ensuring the timeliness and accuracy of data. This is especially important in the fields of nutrition and health sciences, because research in these fields progresses rapidly and new discoveries and data continue to emerge.

[0091] Automatic expansion: As new data is continuously added, the database can automatically expand its storage capacity and structure without manual intervention. This greatly improves the flexibility and scalability of the database and can adapt to growing data needs.

[0092] (2) Process

[0093] Standardized operations: The process-based database construction algorithm model standardizes the steps of data acquisition, processing, storage, and update, ensuring that each step is carried out in accordance with established rules and processes. This helps improve the efficiency and consistency of database construction.

[0094] Reduce human errors: Through process-based operations, the possibility of human intervention and errors is reduced, and the accuracy and reliability of data are improved. This is especially important for scientific research and data analysis, because incorrect data may lead to wrong conclusions and decisions.

[0095] (3) Innovation

[0096] Technology integration: The present invention achieves comprehensiveness and diversity of data by integrating multiple data acquisition methods such as literature query, web crawler, information platform search, etc. This technology integration is an innovative attempt in the field of database construction, which can more comprehensively cover relevant nutrition and health information.

[0097] Algorithm optimization: The dynamic and process-oriented database construction algorithm model designed optimizes the data processing and storage process and improves the operating efficiency and stability of the database. This algorithm optimization is an innovation in the field of database technology and helps promote the development of related technologies.

[0098] User experience: Dynamic and process-based database construction not only improves the accuracy and reliability of data, but also improves user experience. Users can more conveniently obtain the latest data and information, which improves the practicality of the database and user satisfaction.

[0099] Second, by segmenting different populations, personalized health assessments and personalized nutrient intervention strategies are conducted to provide more accurate health management and dietary recommendations.

[0100] The advantages and innovations of segmenting different populations, personalized health assessment and personalized nutritional intervention are as follows:

[0101] (1) Segmentation of different groups

[0102] By segmenting different groups of people, such as age, gender, weight, height, living habits, medical history, etc., the present invention can more accurately identify individual health needs and risks. This segmentation makes health assessment and nutritional advice more personalized, avoiding "one-size-fits-all" universal advice, thereby improving the pertinence and effectiveness of health management.

[0103] (2) Personalized health assessment

[0104] Real-time monitoring: Using modern technology, such as wearable devices and mobile applications, the present invention can monitor the user's health status in real time, such as heart rate, blood pressure, activity level, etc. This dynamic assessment makes health management more timely and accurate, and can detect health problems in time and take corresponding intervention measures.

[0105] Scientific analysis: Based on a large amount of health and nutrition data, scientific analysis and prediction are carried out using statistical and machine learning methods. This data-driven evaluation method can provide more objective and accurate health assessment results, ensuring the scientificity and effectiveness of nutritional recommendations.

[0106] (3) Personalized nutrient intervention

[0107] Customized nutritional advice: Considering that everyone's nutritional needs and health conditions are different, the present invention can provide customized nutritional advice based on the individual's specific situation. This personalized nutritional advice is more in line with the individual's actual needs and helps achieve better health management results.

[0108] Third, personalization: By segmenting different populations, we develop personalized health evaluation standards and nutrient requirements to provide more accurate health management and dietary recommendations.

[0109] Data-driven: Analyze and model based on a large amount of real data to ensure the scientificity and effectiveness of health assessment and nutrient requirement intervention recommendations.

[0110] Scalability: The database and algorithm model design have good scalability and can be continuously optimized and upgraded according to user needs and the development of new technologies.

[0111] The objects of the present invention are:

[0112] (1) Providing a database of health indicators and nutrient requirements for different populations (including healthy and sub-healthy people), thereby providing data support for personalized health management and nutrient intake guidance.

[0113] (2) Develop health status assessment plans and nutrient intervention measures for different populations through statistical analysis and modeling.

[0114] The present invention constructs a health database and a nutrient requirement database for different populations to achieve personalized health assessment and nutrient intervention based on data analysis, providing accurate health management and nutrient intervention recommendations for different populations, thereby improving the overall health level of different populations.

[0115] Fourth, as auxiliary evidence of the inventiveness of the claims of the present invention, it is also reflected in the following important aspects:

[0116] (1) The expected benefits and commercial value of the technical solution of the present invention after transformation are:

[0117] The predicted benefits and commercial value of "dynamic and process-based database construction method"

[0118] Scientific research supports:

[0119] The dynamic and process-oriented database provides a rich data resource for research in the fields of nutrition and health sciences, which helps promote scientific research and technological innovation in related fields. Researchers can obtain the required data more conveniently and accelerate the research process.

[0120] Health Assessment and Disease Prevention:

[0121] The database can be used for health assessment and disease prevention, providing scientific data support. By analyzing the relationship between food nutrition and human health, it can provide decision-making basis for health managers and policy makers and improve the level of public health.

[0122] Economic benefits:

[0123] By optimizing the database construction process, manual intervention and errors are reduced, and operating costs are reduced. At the same time, the high efficiency and reliability of the database also provide economic value to related enterprises and institutions and improve their competitiveness.

[0124] Sustainability:

[0125] The dynamic and process-oriented database construction model has the characteristics of sustainable development. As time goes by and technology advances, the database can be continuously updated and expanded to adapt to changing needs and challenges, maintaining its long-term value and application potential.

[0126] Predicted benefits and commercial value of "personalized health assessment and personalized nutrient intervention strategies by segmenting different populations"

[0127] Improve health management effects:

[0128] Through personalized health assessment and nutrient intervention, health risks can be more accurately identified and managed, improving the overall effectiveness of health management, which helps prevent disease, promote health, and improve quality of life.

[0129] Promotes nutritional balance:

[0130] Personalized nutritional advice helps users achieve nutritional balance and avoid nutritional excess or deficiency, which is important for maintaining good health and preventing chronic diseases.

[0131] Improve user satisfaction:

[0132] Personalized health assessments and nutritional recommendations can better meet user needs and improve user satisfaction and trust. Users are more willing to accept and follow these recommendations, thereby improving compliance with health management.

[0133] Support scientific research:

[0134] The implementation and optimization of personalized health assessment and nutrient intervention models provide rich data and cases for scientific research, which helps to promote research in the fields of health science and nutrition and promote the development and application of related theories.

[0135] Economic benefits:

[0136] By improving the effectiveness of health management and user satisfaction, personalized health assessment and nutrient intervention models can bring significant economic benefits, including not only reducing medical expenses and improving work efficiency, but also improving the overall quality of life of users.

[0137] (2) The technical solution of the present invention solves a technical problem that people have been eager to solve but have never been able to solve successfully:

[0138] The present invention provides a real-time, personalized and systematic solution for building and modeling health databases and nutrient requirement databases for different groups of people.

[0139] The present invention realizes the dynamic and process-based construction of a health indicator-nutrient requirement correlation database, and provides customized nutrition recommendations through personalized health assessment models and nutrient intervention models. Users monitor their health conditions in real time, such as heart rate, blood pressure, activity level, etc. The present invention can more accurately identify and manage health risks based on these health data of users, and provide personalized nutrient recommendations.

[0140] The above solutions apply the latest research results of nutrition and health to health assessment and disease prevention. At the same time, personalized health assessment and nutrition suggestions can better meet the needs of users and improve user satisfaction and trust. Users are more willing to accept and follow these suggestions, thereby improving compliance with health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0141] Figure 1 It is a logic diagram of the overall process provided by an embodiment of the present invention;

[0142] Figure 2 It is a logical structure diagram of a database provided by an embodiment of the present invention;

[0143] Figure 3It is a process logic diagram of the health assessment model and nutrient intervention recommendation model provided by the embodiment of the present invention;

[0144] Figure 4 It is a schematic diagram of collecting health data (partial data) of a group of people in the early pregnancy period provided by an embodiment of the present invention;

[0145] Figure 5 is a schematic diagram of establishing a health index and nutrient requirement database provided by an embodiment of the present invention;

[0146] Figure 6 It is a schematic diagram of weight health data (partial data) of a group of people in the early pregnancy period provided by an embodiment of the present invention;

[0147] Figure 7 is a schematic diagram of web page display provided by an embodiment of the present invention;

[0148] Figure 8 It is a schematic diagram of implementing the disease population classification algorithm model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0149] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0150] like Figure 1 As shown, an embodiment of the present invention provides a method for constructing a health database and a nutritional requirement database for different groups of people, the method comprising:

[0151] S1: Construct a database of health indicators and nutrient requirements for different healthy and sub-healthy populations;

[0152] S2: Construct a database on the correlation between health indicators and nutrient requirements;

[0153] S3: Develop health status assessment programs for different populations;

[0154] S4: Develop precise and personalized nutrient intervention plans for specific populations.

[0155] like Figure 2 As shown, S1 includes data collection and database construction;

[0156] The data collection specifically includes:

[0157] Data source:

[0158] (1) Medical institutions, health management platforms, questionnaires, personal health records, etc.;

[0159] (2) Literature from domestic and foreign journals and databases such as CNKI, Wanfang, VIP, ScienceDirect, PubMed, Web of Science, and WILEY;

[0160] (3) Relevant information on major official information platforms such as the National Health Commission and the Chinese Nutrition Society;

[0161] Data types: including health indicators such as weight, blood pressure, blood sugar, physical activity, sleep, and nutrient requirement data;

[0162] Target population: Healthy people: women preparing for pregnancy, pregnant women (early / mid-term / late), breastfeeding women, infants, children, teenagers, middle-aged people, and the elderly.

[0163] Sub-healthy people: obese people, people with hypertension, people with diabetes, people with tumors, people with cardiovascular diseases, etc.

[0164] Further, the S2 specifically includes:

[0165] (1) Data collection and organization: Statistics and analysis of the types and intake of nutrients that affect health status among people with different health levels;

[0166] (2) Data analysis and processing: Use regression analysis, correlation analysis, and machine learning algorithms to evaluate the correlation between nutrients and health levels;

[0167] (3) Database construction: Establish a database containing data related to health indicators and nutrient requirements.

[0168] Furthermore, the database construction specifically includes:

[0169] (1) Demand Analysis

[0170] Determine the data types and structures that the database needs to store, such as health indicators, nutrient types and intake, collection time, data sources, etc.;

[0171] (2) Database design: table structure design; field definition;

[0172] (3) Database implementation: Select a suitable database management system (such as MySQL, MongoDB), create a database and table;

[0173] (4) Data import: Import the cleaned and processed data into the database.

[0174] Further, the S3 specifically includes:

[0175] (1) Correlation analysis of health indicators: Using statistical analysis and machine learning methods, explore the correlation between different health indicator levels and health status, aiming to understand the intrinsic relationship between the indicators and provide a basis for the subsequent construction of personalized assessment models;

[0176] (2) Personalized assessment model, which is mainly used to achieve: based on the analysis results, build a health status assessment model suitable for different groups of people; the assessment model inputs different health indicator data and outputs health assessment results; the personalized assessment model aims to build a customized health status assessment model for different groups of people based on the analysis results of health indicators. By inputting different health indicator data, the model can output health assessment results and provide a scientific basis for personalized health management.

[0177] Furthermore, the implementation process of the correlation analysis of the health indicators specifically includes:

[0178] (1) Feature selection

[0179] LASSO regression: By introducing L1 regularization, important features are screened;

[0180] Random Forest: Use feature importance to evaluate the importance of each indicator;

[0181] (2) Modeling and Verification

[0182] Model selection: Choose an appropriate model (e.g. linear regression, decision tree, support vector machine);

[0183] Cross-validation: Split the data set for model training and validation to ensure the generalization ability of the model;

[0184] (3) Hyperparameter Tuning

[0185] Optimize model parameters using grid search or random search;

[0186] (4) Result analysis and reporting

[0187] Correlation report: Comprehensively describe the correlation between various health indicators;

[0188] Feature Importance: Using methods such as LASSO and random forest, key health indicators are listed and ranked in order of importance;

[0189] Model performance: Evaluate the performance of different models in predicting health indicators.

[0190] Furthermore, the implementation process of the personalized evaluation model is as follows:

[0191] (1) Data Grouping

[0192] Group data according to population characteristics (such as age, gender, health status, etc.) to ensure the model is targeted;

[0193] (2) Model selection

[0194] Model type: linear regression, decision tree, random forest, support vector machine, neural network, etc.

[0195] Model selection basis: Select the appropriate model type based on the data characteristics of health indicators and health levels;

[0196] (3) Model training

[0197] Divide the training set and test set; train the model and evaluate its performance;

[0198] (4) Model evaluation

[0199] Use evaluation indicators (such as accuracy, AUC, F1-score, etc.) to evaluate model performance;

[0200] Ensure the generalization ability of the model through cross-validation;

[0201] (5) Hyperparameter Tuning

[0202] like Figure 3 As shown in the figure, grid search and random search are used to tune the model's hyperparameters to improve model performance.

[0203] Further, the S4 specifically includes:

[0204] Data integration: Integrate health data and nutrient requirement data from different sources and types to establish a complete and unified data set, providing a basis for subsequent algorithm model development;

[0205] Algorithmic model: Develop algorithms based on machine learning and statistical models to predict the impact of different nutrient intakes on health levels and generate personalized nutrient intervention recommendations.

[0206] Furthermore, the algorithm model algorithm steps are as follows:

[0207] (1) Feature selection

[0208] Select key health indicators and nutrient data: select important features through correlation analysis;

[0209] Feature engineering: creating new features to improve the predictive power of the model;

[0210] (2) Training Model

[0211] Choose a machine learning algorithm: such as linear regression, decision tree, random forest, support vector machine, neural network, etc.

[0212] Data segmentation: divided into training set and test set;

[0213] Model training: training the selected machine learning model;

[0214] (3) Model evaluation

[0215] Performance evaluation: using mean square error (MSE), R 2 Evaluate model performance using indicators such as

[0216] Cross-validation: K-fold cross-validation is used to evaluate the stability and generalization ability of the model;

[0217] (4) Generate personalized nutrient intervention recommendations

[0218] Rule engine: Establish a rule engine to provide personalized nutrient intervention recommendations based on model prediction results, such as increasing the intake of a certain nutrient;

[0219] Nutrient intervention optimization algorithm: Use linear programming or other optimization algorithms to recommend the best nutrient intervention plan for users.

[0220] The embodiment of the present invention provides a system for constructing a health database and a nutritional requirement database for different groups of people and a modeling system thereof, which implements the method for constructing a health database and a nutritional requirement database for different groups of people. The system includes:

[0221] Database construction module, obtain health data and nutrient requirement data from hospitals, health management platforms, etc.; remove duplicate and abnormal data to ensure data quality; use MySQL database to store structured data to realize health indicators and nutrient requirement database for different groups;

[0222] The data collection and import module collects data through questionnaires, medical records, health management platforms and other channels; cleans and organizes the collected data and imports it into the database;

[0223] The data analysis and modeling module uses statistical and machine learning methods based on the collected health data to establish health assessment models for different populations; analyzes the relationship between nutrients and health levels, and establishes a personalized nutrient demand model;

[0224] The system implements the module and develops a front-end interface to display the health assessment results and nutrient requirement recommendations for different groups of people; builds back-end services to provide API interfaces for health assessment and nutrient requirement prediction; and continuously optimizes algorithms to improve the accuracy of health assessment and nutrient requirement prediction.

[0225] Example 1: Database-based health assessment

[0226] Suppose we have collected a large amount of health checkup data from people of different ages, including blood pressure, blood sugar, blood lipids and other indicators. Through data cleaning and analysis, we can establish health evaluation standards for different age groups. When a user uploads his health checkup data to the system, the system automatically evaluates his health status according to his age group and provides personalized health advice.

[0227] Example 2: Personalized nutrient intervention recommendations

[0228] By analyzing the dietary records and health status of people at a certain health level, it is found that certain nutrients (such as vitamin D and unsaturated fatty acids) have a significant impact on their health status. Based on this, a nutrient intervention recommendation algorithm is established. When users provide their daily dietary records and health goals, the system can provide personalized nutrient intervention recommendations based on the analysis results.

[0229] First, we obtain data materials related to health indicators and nutrient requirements through data sources such as different domestic and international journals, databases, and various health data platforms. Figure 4 It is the collection content of (partial) health data of the population in the early stages of pregnancy.

[0230] Then, through the process of data acquisition, data cleaning, data structure design, and data storage through text mining algorithms, a database of health indicators and nutrient requirements for different healthy and sub-healthy people is constructed in a dynamic and process-based manner. Figure 5 It is a database interface for health indicators and nutrient requirements. Figure 6 It is the weight health data (partial data) of the pre-pregnancy population in this database.

[0231] Figure 7 The data display module includes a web page display interface. The user inputs personal data through the health index collector and the disease condition collector, and the data processing module generates a personalized nutrient intake plan based on the input data and displays the intake plan to the user through the web page display interface.

[0232] Figure 8 Decision trees and logistic regression are used for multi-label classification to classify disease populations: training is performed based on the collected diabetes dataset, inputting some of the patient's physical examination indicators such as triglycerides, and outputting whether the patient suffers from diabetes and hypertension.

[0233] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. It can be understood by a person of ordinary skill in the art that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0234] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. A method for constructing a health database and a nutritional requirement database for different groups of people, characterized in that: The method includes: S1: Construct a database of health indicators and nutrient requirements for different healthy and sub-healthy populations; S2: Construct a database on the correlation between health indicators and nutrient requirements; S3: Develop health status assessment programs for different populations; S4: Develop precise and personalized nutrient intervention plans for specific populations.

2. The method for constructing a health database and a nutritional requirement database for different groups of people according to claim 1, characterized in that: Said S1 includes data collection and database construction; The data collection specifically includes: Data source: (1) Medical institutions, health management platforms, questionnaires, and personal health records; (2) Literature from domestic and foreign journals and databases such as CNKI, Wanfang, VIP, ScienceDirect, PubMed, Web of Science, and WILEY; (3) Relevant information on the official information platforms of the National Health Commission and the Chinese Nutrition Society; Data types: including weight, blood pressure, blood sugar, physical activity, sleep health indicators, and nutrient requirements data; Target population: Healthy people: women preparing for pregnancy, pregnant women, breastfeeding women, infants, children, teenagers, middle-aged people, and the elderly. Sub-healthy people: obese people, people with hypertension, people with diabetes, people with cancer, and people with cardiovascular diseases.

3. The method for constructing a health database and a nutritional requirement database for different groups of people as claimed in claim 1, characterized in that: The S2 specifically includes: (1) Data collection and organization: Statistics and analysis of the types and intake of nutrients that affect health status among people with different health levels; (2) Data analysis and processing: Use regression analysis, correlation analysis, and machine learning algorithms to evaluate the correlation between nutrients and health levels; (3) Database construction: Establish a database containing data related to health indicators and nutrient requirements.

4. The method for constructing a health database and a nutritional requirement database for different groups of people as claimed in claim 3, characterized in that: The database construction specifically includes: (1) Demand Analysis Determine the data types and structures that the database needs to store, such as health indicators, nutrient types and intake, collection time, and data sources; (2) Database design: table structure design; field definition; (3) Database implementation: select a suitable database management system and create databases and tables; (4) Data import: Import the cleaned and processed data into the database.

5. The method for constructing a health database and a nutritional requirement database for different groups of people as claimed in claim 1, characterized in that: The S3 specifically includes: (1) Correlation analysis of health indicators: Using statistical analysis and machine learning methods, explore the correlation between different health indicator levels and health status, aiming to understand the intrinsic relationship between the indicators and provide a basis for the subsequent construction of personalized assessment models; (2) Personalized assessment model, which is mainly used to achieve: based on the analysis results, build a health status assessment model suitable for different groups of people; the assessment model inputs different health indicator data and outputs health assessment results; the personalized assessment model aims to build a customized health status assessment model for different groups of people based on the analysis results of health indicators. By inputting different health indicator data, the model can output health assessment results and provide a scientific basis for personalized health management.

6. The method for constructing a health database and a nutritional requirement database for different groups of people as claimed in claim 5, characterized in that: The implementation process of the correlation analysis of the health indicators specifically includes: (1) Feature selection LASSO regression: By introducing L1 regularization, important features are screened; Random Forest: Use feature importance to evaluate the importance of each indicator; (2) Modeling and Verification Model selection: Selecting an appropriate model; Cross-validation: Split the data set for model training and validation to ensure the generalization ability of the model; (3) Hyperparameter Tuning Optimize model parameters using grid search or random search; (4) Result analysis and reporting Correlation report: Comprehensively describe the correlation between various health indicators; Feature Importance: Using LASSO and random forest methods, key health indicators are listed and ranked in order of importance; Model performance: Evaluate the performance of different models in predicting health indicators.

7. The method for constructing a health database and a nutritional requirement database for different groups of people as claimed in claim 5, characterized in that: The implementation process of the personalized evaluation model is as follows: (1) Data Grouping Group data according to population characteristics to ensure the model is targeted; (2) Model selection Model types: linear regression, decision tree, random forest, support vector machine, neural network; Model selection basis: Select the appropriate model type based on the data characteristics of health indicators and health levels; (3) Model training Divide the training set and test set; train the model and evaluate its performance; (4) Model evaluation Use evaluation metrics to assess model performance; Ensure the generalization ability of the model through cross-validation; (5) Hyperparameter Tuning Use grid search and random search to tune the model's hyperparameters to improve model performance.

8. The method for constructing a health database and a nutritional requirement database for different groups of people as claimed in claim 1, characterized in that: The S4 specifically includes: Data integration: Integrate health data and nutrient requirement data from different sources and types to establish a complete and unified data set, providing a basis for subsequent algorithm model development; Algorithmic model: Develop algorithms based on machine learning and statistical models to predict the impact of different nutrient intakes on health levels and generate personalized nutrient intervention recommendations.

9. The method for constructing a health database and a nutritional requirement database for different groups of people as claimed in claim 8, characterized in that: The algorithm model algorithm steps are as follows: (1) Feature selection Select key health indicators and nutrient data: select important features through correlation analysis; Feature engineering: creating new features to improve the predictive power of the model; (2) Training Model Choose a machine learning algorithm: such as linear regression, decision tree, random forest, support vector machine, neural network; Data segmentation: divided into training set and test set; Model training: training the selected machine learning model; (3) Model evaluation Performance evaluation: Use indicators such as mean square error and R2 to evaluate model performance; Cross-validation: K-fold cross-validation is used to evaluate the stability and generalization ability of the model; (4) Generate personalized nutrient intervention recommendations Rule engine: Establish a rule engine to provide personalized nutrient intervention recommendations based on model prediction results, such as increasing the intake of a certain nutrient; Nutrient intervention optimization algorithm: Use linear programming or other optimization algorithms to recommend the best nutrient intervention plan for users.

10. A system for constructing a health database and a nutritional requirement database for different groups of people and a modeling system thereof for implementing the method for constructing a health database and a nutritional requirement database for different groups of people as claimed in any one of claims 1 to 9, characterized in that: The system includes: Database construction module, obtain health data and nutrient requirement data from hospitals and health management platforms; remove duplicate and abnormal data to ensure data quality; use MySQL database to store structured data to realize health indicators and nutrient requirement database for different groups; The data collection and import module collects data through questionnaires, medical records, and health management platform channels; cleans and organizes the collected data and imports it into the database; The data analysis and modeling module uses statistical and machine learning methods based on the collected health data to establish health assessment models for different populations; analyzes the relationship between nutrients and health levels, and establishes a personalized nutrient demand model; The system implements the module and develops a front-end interface to display the health assessment results and nutrient requirement recommendations for different groups of people; builds back-end services to provide API interfaces for health assessment and nutrient requirement prediction; and continuously optimizes algorithms to improve the accuracy of health assessment and nutrient requirement prediction.

Citation Information

Patent Citations

  • Health information processing method and system based on healthy big data

    CN108573752A

  • Individual sub-health intervention method and system based on big data and artificial intelligence

    CN109545328A

  • Old people nutrition and health state assessment and risk prediction system based on machine learning

    CN114974570A

  • Method and device for evaluating and managing human nutrition of whole population

    CN116312964A

  • Real-time method of bio big data automatic collection for personalized lifespan prediction

    US20230187041A1

Cited By

  • Method and system for constructing nutrition state outcome prediction model based on dynamic body weight

    CN119833108A