Method applied to infant health education

Abstract

The invention discloses a method applied to infant health education, which comprises the following steps of: 1, data collection and preprocessing: body development data: collecting physiological data, such as heart rate, body temperature, activity amount, height and weight, of a child in real time by wearing health monitoring equipment; psychological development data: collecting data such as emotional states, attention concentration conditions and cognitive competence of children through intelligent questionnaires, behavior analysis and emotion recognition technologies; social adaptation data: collecting data such as social behaviors, cooperative capabilities and language expressions of children by observing and recording expressions of the children in social interaction; and data cleaning and preprocessing: cleaning the collected data, removing abnormal values and noise data, and performing standardization processing to ensure the quality and consistency of the data. By wearing the health monitoring device, the intelligent questionnaire, behavior analysis and emotion recognition technology, the physical, psychological and social data of children are comprehensively collected, and the diversity and comprehensiveness of the data are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of early childhood education, and in particular to a method applied to early childhood health education. Background Art

[0002] With the development of society and the improvement of living standards, the health education of young children has gradually become the focus of family and society. Traditional early childhood education methods mainly rely on experience and intuition, lack scientific data support and personalized education programs, and are difficult to meet the unique development needs of each child. In recent years, with the rapid development of big data, the Internet of Things and artificial intelligence technologies, new opportunities have been provided for the health education of young children.

[0003] Modern health monitoring equipment can collect children's physiological data in real time, such as heart rate, body temperature, activity level, etc., providing a scientific basis for understanding children's physical condition. The application of intelligent questionnaires, behavioral analysis and emotion recognition technology makes it possible to collect and analyze children's psychological and social data. The combination of these technologies can provide each child with a tailored education program to promote their all-round development.

[0004] Although some existing health education systems can collect some physical or psychological data, the data are isolated and the analysis methods are single, making it difficult to form a comprehensive health education closed loop and achieve comprehensive and dynamic health and education management for children. Therefore, there is an urgent need for a comprehensive health education system and method for children that uses health monitoring, big data analysis, and machine learning technologies to achieve comprehensive monitoring, analysis, and generation of personalized education suggestions for children's physical, psychological, and social adaptability. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the problems existing in the above-mentioned existing methods for preschool health education, the present invention is proposed.

[0007] Therefore, the purpose of the present invention is to provide a method for the general health education of young children, which comprehensively collects children's physical, psychological and social data through wearable health monitoring equipment, intelligent questionnaires, behavioral analysis and emotion recognition technology to ensure the diversity and comprehensiveness of the data.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for preschool health education, comprising the following steps:

[0009] Step 1: Data collection and preprocessing:

[0010] Physical development data: Wearable health monitoring devices collect children's physiological data in real time, such as heart rate, body temperature, activity level, height and weight;

[0011] Psychological development data: Through intelligent questionnaires, behavioral analysis and emotion recognition technology, data on children’s emotional state, concentration, cognitive ability, etc. are collected;

[0012] Social adaptation data: By observing and recording children's performance in social interactions, data on their social behavior, cooperation ability, language expression, etc. are collected;

[0013] Data cleaning and preprocessing: Clean the collected data, remove outliers and noise data, and perform standardization to ensure data quality and consistency;

[0014] Step 2: Big data storage and management:

[0015] Data storage: Use distributed database or cloud storage technology to store large-scale multi-source data;

[0016] Data management: Establish a data management system to classify and store data to facilitate subsequent data analysis and processing;

[0017] Step 3: Data analysis and modeling:

[0018] Feature extraction: Extract key features from physical development data, psychological development data, and social adaptation data, such as average heart rate, mood swings, and social interaction frequency;

[0019] Machine Learning Models: Build and train machine learning models to predict children’s physical, psychological, and social adjustment;

[0020] Physical development prediction model: predicts children's health status and physical development trends based on historical physical data and current monitoring data;

[0021] Psychological development prediction model: predict children's emotional changes and cognitive development based on psychological data;

[0022] Social adaptation prediction model: predict children's social ability and social adaptation level based on social adaptation data;

[0023] Step 4: Personalized suggestion generation:

[0024] Physical development recommendations: Use the physical development prediction model to generate personalized health and exercise recommendations, such as recommending appropriate exercise programs and adjusting diet plans;

[0025] Psychological development suggestions: Use psychological development prediction models to generate personalized mental health and cognitive development suggestions, such as adjusting learning content and recommending psychological games;

[0026] Social adaptation suggestions: Using social adaptation prediction models to generate personalized social activities and cooperation suggestions, such as arranging group activities and recommending social games;

[0027] Step 5: Dynamic adjustment of educational content:

[0028] Real-time adjustment: Dynamically adjust multimedia educational content based on personalized suggestions to ensure that the content is appropriate for children's current physical, psychological and social development status;

[0029] Content difficulty adjustment: Adjust the difficulty level of educational content based on the child’s current state, ensuring that the content is challenging but not too difficult;

[0030] Adjustment of content format: changing the presentation format of educational content according to the psychological and social status of children, such as switching from text reading to animated videos or interactive games;

[0031] Adjustment of study time: Dynamically adjust study and rest time according to health recommendations to ensure that children can study in the best condition;

[0032] Step 6: Feedback and closed-loop optimization:

[0033] Real-time feedback collection: monitor children’s reactions to the adjusted educational content and their physical, psychological, and social states in real time, and collect feedback data;

[0034] Closed-loop mechanism: Form a closed-loop optimization mechanism to continuously improve the effectiveness of personalized health and education management through continuous data collection, analysis, suggestion generation and content adjustment;

[0035] Step 7: Parent-Teacher Interaction:

[0036] Parents and teachers can learn about children’s health, psychological and social status in real time through the interactive platform and obtain personalized suggestions generated by the system;

[0037] Provides regularly generated comprehensive health and learning reports for parents and teachers to refer to, helping them better support the holistic development of children.

[0038] As a preferred solution of the method for applying to infant health education described in the present invention, the intelligent questionnaire technology for psychological development data in step 1 specifically includes:

[0039] Questionnaire design: Design questionnaires that are suitable for children's psychological development, including simple images, animations and sound prompts to help children understand the questions and make choices;

[0040] Questionnaire platform: Develop an intelligent questionnaire platform to display the questionnaire through a tablet or smartphone and record the children’s responses;

[0041] Data Collection: Children’s responses to each question, including the answer chosen and the time taken to answer, were recorded to generate preliminary data on emotional state, attention, and cognitive abilities;

[0042] Data Analysis: Questionnaire responses were analyzed using pre-set scoring criteria and algorithms to assess children’s emotional states such as happiness, anxiety, concentration, and cognitive ability levels.

[0043] As a preferred solution of the method for preschool health education described in the present invention, the behavior analysis technology of psychological development data in step 1 specifically includes:

[0044] Behavior monitoring devices: Install cameras, microphones and motion sensors to monitor children’s behavior and activities in real time;

[0045] Behavior recognition algorithm: Use computer vision and audio processing technology to analyze video and audio data to identify children's behavioral characteristics, such as facial expressions, voice changes, and movement frequency;

[0046] Feature extraction: Extract key behavioral features from monitoring data, such as the number of smiles, voice tone changes, eye movement trajectories, and hand movements;

[0047] Data Analysis: Based on behavioral characteristics, children’s emotional states such as happiness, frustration, concentration such as focus, distraction, and cognitive abilities such as comprehension and reaction speed were assessed.

[0048] As a preferred solution of the method for preschool health education described in the present invention, the emotion recognition technology of psychological development data in step 1 specifically includes:

[0049] Facial Expression Recognition:

[0050] Image acquisition: The facial image of the child is collected in real time through the camera;

[0051] Facial feature detection: Use deep learning algorithms to detect and extract facial key points and expression features, such as changes in eyebrows, eyes, and mouth;

[0052] Emotion classification: Based on facial expression features, classify and identify children’s emotional states, such as happiness, sadness, surprise, and anger;

[0053] Speech emotion recognition:

[0054] Voice collection: collect children’s voice data in real time through microphone;

[0055] Acoustic feature extraction: Use speech processing technology to extract acoustic features in speech, such as fundamental frequency, volume, speaking speed, and intonation;

[0056] Emotion classification: Based on acoustic features, a machine learning model is used to classify and identify children’s emotional states, such as happiness, tension, and calmness;

[0057] Multimodal Emotion Recognition:

[0058] Data fusion: Fusion of facial expressions and voice features to form multimodal emotion data;

[0059] Comprehensive analysis: Utilizes multimodal emotion recognition algorithms to comprehensively analyze facial expressions and voice data to provide a more accurate assessment of emotional state.

[0060] As a preferred embodiment of the method for preschool health education of the present invention, the physical development prediction model in step 3 is used to predict the health status and physical development trend of children; by analyzing historical physical data and current monitoring data, a personalized health recommendation and exercise plan is generated, including:

[0061] 1) Input data

[0062] Physiological data: heart rate, body temperature, blood pressure, blood oxygen saturation;

[0063] Activity data: daily steps, amount of exercise, type of exercise and duration;

[0064] Dietary data: daily nutrients and calories consumed;

[0065] Historical health data: height, weight, growth records, medical history;

[0066] 2) Output results

[0067] Health status assessment: a score of current health status, such as good, fair, or poor;

[0068] Physical development prediction: physical development trends in the future, such as expected height and weight changes;

[0069] Personalized health advice: advice on current health status, such as increasing exercise and adjusting diet;

[0070] 3) Algorithm Implementation

[0071] Data preprocessing: cleaning, standardization and normalization of input data;

[0072] Feature extraction: Extract key features such as average heart rate, activity level, and nutritional intake;

[0073] Machine Learning Models:

[0074] Regression models: such as linear regression and random forest regression, used to predict continuous variables such as height and weight;

[0075] Classification models: such as decision trees and support vector machines, used to assess health status;

[0076] Time series models: such as long short-term memory networks, are used to analyze and predict time series data.

[0077] As a preferred solution of the method for applying to infant health education of the present invention, the specific algorithm formula of the regression model in the machine learning model is as follows:

[0078] (1) Data preprocessing:

[0079] Clean, standardize and normalize input data to ensure data quality and consistency, Where X is the original data, μ is the mean of the data, and σ is the standard deviation of the data;

[0080] (2) Feature extraction:

[0081] Extract key features from input data, such as average heart rate, daily steps, and nutritional intake;

[0082] (3) Random Forest Regression Model:

[0083] Decision tree construction: Each decision tree is constructed by randomly selecting features and samples, and the node splitting of the decision tree is based on minimizing the mean square error MSE

[0084]

[0085] Where N is the number of samples, y i is the true value, is the predicted value;

[0086] Random forest generation: build multiple decision trees, each of which is trained on a different random subsample. Suppose we build T decision trees, and the prediction result of each tree is

[0087] Prediction results summary:

[0088] Take the average of the prediction results of all decision trees to get the final prediction result:

[0089]

[0090] As a preferred embodiment of the method for preschool health education described in the present invention, the psychological development prediction model is used to evaluate and predict the emotional state, concentration and cognitive ability of children; through intelligent questionnaires, behavior analysis and emotion recognition technology, personalized psychological health and cognitive development suggestions are generated, specifically including:

[0091] A1. Input data:

[0092] Intelligent questionnaire data: children’s responses to the psychological questionnaire and the time they responded;

[0093] Behavioral analysis data: facial expressions, voice intonation, behavioral movements;

[0094] Emotion recognition data: emotional states, such as happiness, sadness, and concentration;

[0095] A2. Output results

[0096] Emotional state assessment: rating of current emotional state, such as happy, depressed;

[0097] Attention assessment: Rating of current attention status, such as concentration and distraction;

[0098] Cognitive assessment: Scoring of cognitive ability levels, such as comprehension and memory;

[0099] A3. Algorithm Implementation

[0100] Data preprocessing: cleaning, standardization and normalization of input data;

[0101] Feature extraction: extract key features, such as facial expression features, voice features, and behavioral features;

[0102] Machine Learning Models:

[0103] Emotion recognition model: Convolutional neural network is used for facial expression recognition;

[0104] Speech emotion recognition model: Long short-term memory network (LSTM) is used for speech emotion recognition.

[0105] As a preferred embodiment of the method for preschool health education of the present invention, the social adaptation prediction model is used to evaluate and predict children's social ability and social adaptation level, and to generate personalized social activities and cooperation suggestions by observing and recording children's social behaviors, including:

[0106] B1. Input data

[0107] Social behavior data: children’s performance in social interactions, such as the number of conversations, the number of collaborations, and the length of interaction.

[0108] Language expression data: children’s language expression ability, such as vocabulary, sentence complexity, language fluency, etc.

[0109] Social feedback data: Teacher and parent ratings of children's social behavior.

[0110] B2. Output results

[0111] Social skills assessment: Rating of current social skills, such as good, medium, or poor;

[0112] Social adaptation assessment: score of current social adaptation level, such as high, medium, or low;

[0113] Personalized social suggestions: suggestions for current social abilities, such as participating in group activities and conducting social training;

[0114] B3. Algorithm Implementation

[0115] Data preprocessing: cleaning, standardization and normalization of input data;

[0116] Feature extraction: extract key features, such as the number of conversations, interaction duration, and language complexity;

[0117] Machine Learning Models:

[0118] Behavior classification model: Random forest is used for social behavior classification;

[0119] Language analysis model: The natural language processing (NLP) model is used to analyze language expression ability.

[0120] Beneficial effects of the present invention:

[0121] 1. Comprehensive data collection and preprocessing:

[0122] Through wearable health monitoring devices, smart questionnaires, behavioral analysis and emotion recognition technology, we can comprehensively collect children's physical, psychological and social data to ensure the diversity and comprehensiveness of the data;

[0123] 2. Advanced data analysis and modeling:

[0124] Through feature extraction technology, key features are extracted from physical development data, psychological development data, and social adaptation data to improve the accuracy and efficiency of data analysis. Build and train machine learning models, including physical development prediction models, psychological development prediction models, and social adaptation prediction models, which are used to predict children's health status, emotional changes, cognitive development, and social skills, respectively, and provide scientific, accurate, and personalized prediction results;

[0125] 3. Personalized suggestion generation:

[0126] Based on the results of the prediction model, personalized physical development suggestions, psychological development suggestions, and social adaptation suggestions are generated to help children develop comprehensively in health, psychology, and social aspects. Scientific and personalized health and education suggestions are provided, such as recommending appropriate sports programs, adjusting diet plans, adjusting learning content, recommending psychological games, and arranging group activities. BRIEF DESCRIPTION OF THE DRAWINGS

[0127] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative labor. Among them:

[0128] Figure 1 The figure is a schematic diagram of the method of applying the present invention to early childhood health education. DETAILED DESCRIPTION

[0129] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0130] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0131] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0132] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0133] Reference Figure 1 , provides a method for applying to early childhood health education, comprising the following steps:

[0134] Step 1: Data collection and preprocessing:

[0135] Physical development data: The physiological data of children, such as heart rate, body temperature, activity level, height and weight, are collected in real time by wearing health monitoring equipment. Among them, the monitoring equipment is a prior art product that can obtain the development data of young children, which will not be described in detail here;

[0136] Psychological development data: Through intelligent questionnaires, behavioral analysis and emotion recognition technology, data on children’s emotional state, concentration, cognitive ability, etc. are collected;

[0137] Social adaptation data: By observing and recording children's performance in social interactions, data on their social behavior, cooperation ability, language expression, etc. are collected;

[0138] Data cleaning and preprocessing: Clean the collected data, remove outliers and noise data, and perform standardization to ensure data quality and consistency;

[0139] Step 2: Big data storage and management:

[0140] Data storage: Use distributed database or cloud storage technology to store large-scale multi-source data;

[0141] Data management: Establish a data management system to classify and store data to facilitate subsequent data analysis and processing;

[0142] Step 3: Data analysis and modeling:

[0143] Feature extraction: Extract key features from physical development data, psychological development data, and social adaptation data, such as average heart rate, mood swings, and social interaction frequency;

[0144] Machine Learning Models: Build and train machine learning models to predict children’s physical, psychological, and social adjustment;

[0145] Physical development prediction model: predicts children's health status and physical development trends based on historical physical data and current monitoring data;

[0146] Psychological development prediction model: predict children's emotional changes and cognitive development based on psychological data;

[0147] Social adaptation prediction model: predict children's social ability and social adaptation level based on social adaptation data;

[0148] Step 4: Personalized suggestion generation:

[0149] Physical development recommendations: Use the physical development prediction model to generate personalized health and exercise recommendations, such as recommending appropriate exercise programs and adjusting diet plans;

[0150] Psychological development suggestions: Use psychological development prediction models to generate personalized mental health and cognitive development suggestions, such as adjusting learning content and recommending psychological games;

[0151] Social adaptation suggestions: Using social adaptation prediction models to generate personalized social activities and cooperation suggestions, such as arranging group activities and recommending social games;

[0152] Step 5: Dynamic adjustment of educational content:

[0153] Real-time adjustment: Dynamically adjust multimedia educational content based on personalized suggestions to ensure that the content is appropriate for children's current physical, psychological and social development status;

[0154] Content difficulty adjustment: Adjust the difficulty level of educational content based on the child’s current state, ensuring that the content is challenging but not too difficult;

[0155] Adjustment of content format: changing the presentation format of educational content according to the psychological and social status of children, such as switching from text reading to animated videos or interactive games;

[0156] Adjustment of study time: Dynamically adjust study and rest time according to health recommendations to ensure that children can study in the best condition;

[0157] Step 6: Feedback and closed-loop optimization:

[0158] Real-time feedback collection: monitor children’s reactions to the adjusted educational content and their physical, psychological, and social states in real time, and collect feedback data;

[0159] Closed-loop mechanism: Form a closed-loop optimization mechanism to continuously improve the effectiveness of personalized health and education management through continuous data collection, analysis, suggestion generation and content adjustment;

[0160] Step 7: Parent-Teacher Interaction:

[0161] Parents and teachers can learn about children’s health, psychological and social status in real time through the interactive platform and obtain personalized suggestions generated by the system;

[0162] Provides regularly generated comprehensive health and learning reports for parents and teachers to refer to, helping them better support the holistic development of children.

[0163] The intelligent questionnaire technology for psychological development data in step 1 specifically includes:

[0164] Questionnaire design: Design questionnaires that are suitable for children's psychological development, including simple images, animations and sound prompts to help children understand the questions and make choices;

[0165] Questionnaire platform: Develop an intelligent questionnaire platform to display the questionnaire through a tablet or smartphone and record the children’s responses;

[0166] Data Collection: Children’s responses to each question, including the answer chosen and the time taken to answer, were recorded to generate preliminary data on emotional state, attention, and cognitive abilities;

[0167] Data Analysis: Questionnaire responses were analyzed using pre-set scoring criteria and algorithms to assess children’s emotional states such as happiness, anxiety, concentration, and cognitive ability levels.

[0168] Furthermore, the behavior analysis technology of the psychological development data in step 1 specifically includes:

[0169] Behavior monitoring devices: Install cameras, microphones and motion sensors to monitor children’s behavior and activities in real time;

[0170] Behavior recognition algorithm: Use computer vision and audio processing technology to analyze video and audio data to identify children's behavioral characteristics, such as facial expressions, voice changes, and movement frequency;

[0171] Feature extraction: Extract key behavioral features from monitoring data, such as the number of smiles, voice tone changes, eye movement trajectories, and hand movements;

[0172] Data Analysis: Based on behavioral characteristics, children’s emotional states such as happiness, frustration, concentration such as focus, distraction, and cognitive abilities such as comprehension and reaction speed were assessed.

[0173] Furthermore, the emotion recognition technology of the psychological development data in step 1 specifically includes:

[0174] Facial Expression Recognition:

[0175] Image acquisition: The facial image of the child is collected in real time through the camera;

[0176] Facial feature detection: Use deep learning algorithms to detect and extract facial key points and expression features, such as changes in eyebrows, eyes, and mouth;

[0177] Emotion classification: Based on facial expression features, classify and identify children’s emotional states, such as happiness, sadness, surprise, and anger;

[0178] Speech emotion recognition:

[0179] Voice collection: collect children’s voice data in real time through microphone;

[0180] Acoustic feature extraction: Use speech processing technology to extract acoustic features in speech, such as fundamental frequency, volume, speaking speed, and intonation;

[0181] Emotion classification: Based on acoustic features, a machine learning model is used to classify and identify children’s emotional states, such as happiness, tension, and calmness;

[0182] Multimodal Emotion Recognition:

[0183] Data fusion: Fusion of facial expressions and voice features to form multimodal emotion data;

[0184] Comprehensive analysis: Utilizes multimodal emotion recognition algorithms to comprehensively analyze facial expressions and voice data to provide a more accurate assessment of emotional state.

[0185] Specific examples:

[0186] Example 1: Exercise recommendations based on physical development data

[0187] Data collection: Health monitoring devices collect children’s heart rate, activity level and body temperature data in real time and transmit them to the cloud storage system.

[0188] Data analysis: The physical development prediction model analyzes physical data to determine whether the amount of exercise for children is appropriate.

[0189] Personalized suggestion generation: The system generates health suggestions and recommends appropriate sports, such as running, skipping rope, etc.

[0190] Dynamic adjustment of educational content: The educational content platform arranges appropriate exercise time and events based on suggestions.

[0191] Real-time feedback: monitor the changes in children's heart rate and activity after exercise, and evaluate the effect of exercise. Closed-loop optimization: optimize the physical development prediction model and exercise suggestion generation algorithm based on feedback data. The sports activity table for each age group is as follows:

[0192]

[0193]

[0194]

[0195]

[0196]

[0197] Example 2: Adjusting learning content based on psychological development data

[0198] Data collection: Children’s emotional state and attention data were collected through intelligent questionnaires and emotion recognition technology.

[0199] Data Analysis: The psychological development prediction model analyzes psychological data to determine the emotional and cognitive state of children.

[0200] Personalized suggestion generation: The system generates mental health suggestions and adjusts the difficulty and format of learning content.

[0201] Dynamic adjustment of educational content: The educational content platform replaces the current difficult math problems with interesting psychological games based on suggestions.

[0202] Real-time feedback: monitor children’s mood changes and concentration after playing games, and evaluate the effect of adjustments.

[0203] Closed-loop optimization: Optimize the psychological development prediction model and learning content suggestion generation algorithm based on feedback data.

[0204] Example 3: Scheduling social events based on social adaptation data

[0205] Data Collection: Data on social behavior and cooperation were collected by observing and recording children in social interactions.

[0206] Data Analysis: The social adaptation prediction model analyzes social data to determine children's social ability and adaptation level.

[0207] Personalized suggestion generation: The system generates social activity suggestions and arranges appropriate group activities or social games.

[0208] Dynamic adjustment of educational content: The educational content platform arranges social activities and cooperation projects based on suggestions.

[0209] Real-time feedback: monitor children’s performance and feedback in social activities and evaluate the effectiveness of activities.

[0210] Closed-loop optimization: Optimize the social adaptation prediction model and social activity suggestion generation algorithm based on feedback data.

[0211] The physical development prediction model in step 3 is used to predict the health status and physical development trend of children; by analyzing historical physical data and current monitoring data, personalized health advice and exercise plans are generated, including:

[0212] 1) Input data

[0213] Physiological data: heart rate, body temperature, blood pressure, blood oxygen saturation;

[0214] Activity data: daily steps, amount of exercise, type of exercise and duration;

[0215] Dietary data: daily nutrients and calories consumed;

[0216] Historical health data: height, weight, growth records, medical history;

[0217] 2) Output results

[0218] Health status assessment: a score of current health status, such as good, fair, or poor;

[0219] Physical development prediction: physical development trends in the future, such as expected height and weight changes;

[0220] Personalized health advice: advice on current health status, such as increasing exercise and adjusting diet;

[0221] 3) Algorithm Implementation

[0222] Data preprocessing: cleaning, standardization and normalization of input data;

[0223] Feature extraction: Extract key features such as average heart rate, activity level, and nutritional intake;

[0224] Machine Learning Models:

[0225] Regression models: such as linear regression and random forest regression, used to predict continuous variables such as height and weight;

[0226] Classification models: such as decision trees and support vector machines, used to assess health status;

[0227] Time series models: such as long short-term memory networks, are used to analyze and predict time series data.

[0228] Specifically, the specific algorithm formula of the regression model in the machine learning model is as follows:

[0229] (1) Data preprocessing:

[0230] Clean, standardize and normalize input data to ensure data quality and consistency, Where X is the original data, μ is the mean of the data, and σ is the standard deviation of the data;

[0231] (2) Feature extraction:

[0232] Extract key features from input data, such as average heart rate, daily steps, and nutritional intake;

[0233] (3) Random Forest Regression Model:

[0234] Decision tree construction: Each decision tree is constructed by randomly selecting features and samples, and the node splitting of the decision tree is based on minimizing the mean square error MSE

[0235]

[0236] Where N is the number of samples, y i is the true value, is the predicted value;

[0237] Random forest generation: build multiple decision trees, each of which is trained on a different random subsample. Suppose we build T decision trees, and the prediction result of each tree is

[0238] Prediction results summary:

[0239] Take the average of the prediction results of all decision trees to get the final prediction result:

[0240]

[0241] Furthermore, the psychological development prediction model is used to evaluate and predict children's emotional state, concentration and cognitive ability; through intelligent questionnaires, behavioral analysis and emotion recognition technology, personalized psychological health and cognitive development suggestions are generated, including:

[0242] A1. Input data:

[0243] Intelligent questionnaire data: children’s responses to the psychological questionnaire and the time they responded;

[0244] Behavioral analysis data: facial expressions, voice intonation, behavioral movements;

[0245] Emotion recognition data: emotional states, such as happiness, sadness, and concentration;

[0246] A2. Output results

[0247] Emotional state assessment: rating of current emotional state, such as happy, depressed;

[0248] Attention assessment: Rating of current attention status, such as concentration and distraction;

[0249] Cognitive assessment: Scoring of cognitive ability levels, such as comprehension and memory;

[0250] A3. Algorithm Implementation

[0251] Data preprocessing: cleaning, standardization and normalization of input data;

[0252] Feature extraction: extract key features, such as facial expression features, voice features, and behavioral features;

[0253] Machine Learning Models:

[0254] Emotion recognition model: Convolutional neural network is used for facial expression recognition;

[0255] Speech emotion recognition model: Long short-term memory network (LSTM) is used for speech emotion recognition.

[0256] Specific examples:

[0257] Example 1: Collecting psychological development data through smart questionnaires

[0258] Questionnaire design: Design a questionnaire containing emotion recognition questions, such as “How do you feel today?” accompanied by emoticon icons (happy, calm, sad).

[0259] Questionnaire presentation: The questionnaire was presented on a tablet computer, and children selected emoticon icons to answer.

[0260] Data collection: Children’s choices and answer times are recorded, and the system automatically generates emotional state data.

[0261] Data analysis: Analyze the responses to assess the children’s emotional state and attention span.

[0262] Example 2: Identifying emotions and attention through behavioral analysis

[0263] Behavior monitoring equipment: Install cameras and microphones to monitor children's behavior in the classroom in real time.

[0264] Behavior recognition algorithm: The camera captures the child’s facial expressions and the microphone records the child’s voice.

[0265] Feature extraction: Extract children’s facial expression features and voice features, such as the number of smiles and changes in voice intonation.

[0266] Data analysis: Based on behavioral characteristics, assess the children’s emotional state (e.g., happy, focused) and attention span (e.g., distracted).

[0267] Example 3: Assessing emotional state through emotion recognition technology

[0268] Facial Expression Recognition:

[0269] Image acquisition: The camera captures the child’s facial image in real time.

[0270] Facial feature detection: The algorithm detects key facial points, such as raised corners of the mouth and raised eyebrows.

[0271] Emotion classification: Recognizing a child’s expression as happy.

[0272] Speech emotion recognition:

[0273] Voice collection: The microphone collects the child's voice.

[0274] Acoustic feature extraction: extract the fundamental frequency and speaking rate of speech.

[0275] Emotion classification: Identify the tone of speech as happy.

[0276] Multimodal Emotion Recognition:

[0277] Data fusion: Combining facial expressions and voice features.

[0278] Comprehensive analysis: After comprehensive analysis, it was confirmed that the children were in a happy state.

[0279] Furthermore, the social adaptation prediction model is used to evaluate and predict children's social ability and social adaptation level, and to generate personalized social activities and cooperation suggestions by observing and recording children's social behaviors, including:

[0280] B1. Input data

[0281] Social behavior data: children’s performance in social interactions, such as the number of conversations, the number of collaborations, and the length of interaction.

[0282] Language expression data: children’s language expression ability, such as vocabulary, sentence complexity, language fluency, etc.

[0283] Social feedback data: Teacher and parent ratings of children's social behavior.

[0284] B2. Output results

[0285] Social skills assessment: Rating of current social skills, such as good, medium, or poor;

[0286] Social adaptation assessment: score of current social adaptation level, such as high, medium, or low;

[0287] Personalized social suggestions: suggestions for current social abilities, such as participating in group activities and conducting social training;

[0288] B3. Algorithm Implementation

[0289] Data preprocessing: cleaning, standardization and normalization of input data;

[0290] Feature extraction: extract key features, such as the number of conversations, interaction duration, and language complexity;

[0291] Machine Learning Models:

[0292] Behavior classification model: Random forest is used for social behavior classification;

[0293] Language analysis model: The natural language processing (NLP) model is used to analyze language expression ability.

[0294] Specific examples:

[0295] Example 1: Physical Development Prediction Model

[0296] Data preprocessing: standardize heart rate, body temperature, and activity data.

[0297] Feature extraction: Calculate features such as average heart rate and daily steps.

[0298] Machine learning model: Use random forest regression to predict future height and weight changes.

[0299] Example 2: Psychological Development Prediction Model

[0300] Data preprocessing: cleaning and standardizing intelligent questionnaire data and behavioral data.

[0301] Feature extraction: extract facial expression features and voice intonation features.

[0302] Machine learning model: CNN is used for facial expression recognition and LSTM is used for speech emotion recognition.

[0303] Example 3: Social Adaptation Prediction Model

[0304] Data preprocessing: standardize social behavior data and language expression data.

[0305] Feature extraction: Extract features such as number of conversations and language complexity.

[0306] Machine learning model: Use random forest to classify social behaviors and use NLP model to analyze language expression ability.

[0307] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for preschool health education, characterized in that: The following steps are involved: Step 1: Data collection and preprocessing: Physical development data: Wearable health monitoring devices collect children's physiological data in real time, such as heart rate, body temperature, activity level, height and weight; Psychological development data: Through intelligent questionnaires, behavioral analysis and emotion recognition technology, data on children’s emotional state, concentration, cognitive ability, etc. are collected; Social adaptation data: By observing and recording children's performance in social interactions, data on their social behavior, cooperation ability, language expression, etc. are collected; Data cleaning and preprocessing: Clean the collected data, remove outliers and noise data, and perform standardization to ensure data quality and consistency; Step 2: Big data storage and management: Data storage: Use distributed database or cloud storage technology to store large-scale multi-source data; Data management: Establish a data management system to classify and store data to facilitate subsequent data analysis and processing; Step 3: Data analysis and modeling: Feature extraction: Extract key features from physical development data, psychological development data, and social adaptation data, such as average heart rate, mood swings, and social interaction frequency; Machine Learning Models: Build and train machine learning models to predict children’s physical, psychological, and social adjustment; Physical development prediction model: predicts children's health status and physical development trends based on historical physical data and current monitoring data; Psychological development prediction model: predict children's emotional changes and cognitive development based on psychological data; Social adaptation prediction model: predict children's social ability and social adaptation level based on social adaptation data; Step 4: Personalized suggestion generation: Physical development recommendations: Use the physical development prediction model to generate personalized health and exercise recommendations, such as recommending appropriate exercise programs and adjusting diet plans; Psychological development suggestions: Use psychological development prediction models to generate personalized mental health and cognitive development suggestions, such as adjusting learning content and recommending psychological games; Social adaptation suggestions: Using social adaptation prediction models to generate personalized social activities and cooperation suggestions, such as arranging group activities and recommending social games; Step 5: Dynamic adjustment of educational content: Real-time adjustment: Dynamically adjust multimedia educational content based on personalized suggestions to ensure that the content is appropriate for children's current physical, psychological and social development status; Content difficulty adjustment: Adjust the difficulty level of educational content based on the child’s current state, ensuring that the content is challenging but not too difficult; Adjustment of content format: changing the presentation format of educational content according to the psychological and social status of children, such as switching from text reading to animated videos or interactive games; Adjustment of study time: Dynamically adjust study and rest time according to health recommendations to ensure that children can study in the best condition; Step 6: Feedback and closed-loop optimization: Real-time feedback collection: monitor children’s reactions to the adjusted educational content and their physical, psychological, and social states in real time, and collect feedback data; Closed-loop mechanism: Form a closed-loop optimization mechanism to continuously improve the effectiveness of personalized health and education management through continuous data collection, analysis, suggestion generation and content adjustment; Step 7: Parent-Teacher Interaction: Parents and teachers can learn about children’s health, psychological and social status in real time through the interactive platform and obtain personalized suggestions generated by the system; Provides regularly generated comprehensive health and learning reports for parents and teachers to refer to, helping them better support the holistic development of children.

2. The method for preschool health education according to claim 1, characterized in that: The intelligent questionnaire technology for psychological development data in step 1 specifically includes: Questionnaire design: Design questionnaires that are suitable for children's psychological development, including simple images, animations and sound prompts to help children understand the questions and make choices; Questionnaire platform: Develop an intelligent questionnaire platform to display the questionnaire through a tablet or smartphone and record the children’s responses; Data Collection: Children’s responses to each question, including the answer chosen and the time taken to answer, were recorded to generate preliminary data on emotional state, attention, and cognitive abilities; Data Analysis: Questionnaire responses were analyzed using pre-set scoring criteria and algorithms to assess children’s emotional states such as happiness, anxiety, concentration, and cognitive ability levels.

3. The method for preschool health education according to claim 2, characterized in that: The behavior analysis technology of psychological development data in step 1 specifically includes: Behavior monitoring devices: Install cameras, microphones and motion sensors to monitor children’s behavior and activities in real time; Behavior recognition algorithm: Use computer vision and audio processing technology to analyze video and audio data to identify children's behavioral characteristics, such as facial expressions, voice changes, and movement frequency; Feature extraction: Extract key behavioral features from monitoring data, such as the number of smiles, voice tone changes, eye movement trajectories, and hand movements; Data Analysis: Based on behavioral characteristics, children’s emotional states such as happiness, frustration, concentration such as focus, distraction, and cognitive abilities such as comprehension and reaction speed were assessed.

4. The method for preschool health education according to claim 3, characterized in that: The emotion recognition technology of the psychological development data in step 1 specifically includes: Facial Expression Recognition: Image acquisition: The facial image of the child is collected in real time through the camera; Facial feature detection: Use deep learning algorithms to detect and extract facial key points and expression features, such as changes in eyebrows, eyes, and mouth; Emotion classification: Based on facial expression features, classify and identify children’s emotional states, such as happiness, sadness, surprise, and anger; Speech emotion recognition: Voice collection: collect children’s voice data in real time through microphone; Acoustic feature extraction: Use speech processing technology to extract acoustic features in speech, such as fundamental frequency, volume, speaking speed, and intonation; Emotion classification: Based on acoustic features, a machine learning model is used to classify and identify children’s emotional states, such as happiness, tension, and calmness; Multimodal Emotion Recognition: Data fusion: Fusion of facial expressions and voice features to form multimodal emotion data; Comprehensive analysis: Utilizes multimodal emotion recognition algorithms to comprehensively analyze facial expressions and voice data to provide a more accurate assessment of emotional state.

5. The method for preschool health education according to claim 1, characterized in that: The physical development prediction model in step 3 is used to predict the health status and physical development trend of children; by analyzing historical physical data and current monitoring data, a personalized health recommendation and exercise plan is generated, including: 1) Input data Physiological data: heart rate, body temperature, blood pressure, blood oxygen saturation; Activity data: daily steps, amount of exercise, type of exercise and duration; Dietary data: daily nutrients and calories consumed; Historical health data: height, weight, growth records, medical history; 2) Output results Health status assessment: a score of current health status, such as good, fair, or poor; Physical development prediction: physical development trends in the future, such as expected height and weight changes; Personalized health advice: advice on current health status, such as increasing exercise and adjusting diet; 3) Algorithm Implementation Data preprocessing: cleaning, standardization and normalization of input data; Feature extraction: Extract key features such as average heart rate, activity level, and nutritional intake; Machine Learning Models: Regression models: such as linear regression and random forest regression, used to predict continuous variables such as height and weight; Classification models: such as decision trees and support vector machines, used to assess health status; Time series models: such as long short-term memory networks, are used to analyze and predict time series data.

6. The method for preschool health education according to claim 5, characterized in that: The specific algorithm formula of the regression model in the machine learning model is as follows: (1) Data preprocessing: Clean, standardize and normalize input data to ensure data quality and consistency, Where X is the original data, μ is the mean of the data, and σ is the standard deviation of the data; (2) Feature extraction: Extract key features from input data, such as average heart rate, daily steps, and nutritional intake; (3) Random Forest Regression Model: Decision tree construction: Each decision tree is constructed by randomly selecting features and samples, and the node splitting of the decision tree is based on minimizing the mean square error MSE Where N is the number of samples, y i is the true value, is the predicted value; Random forest generation: build multiple decision trees, each of which is trained on a different random subsample. Suppose we build T decision trees, and the prediction result of each tree is Prediction results summary: Take the average of the prediction results of all decision trees to get the final prediction result:

7. The method for preschool health education according to claim 1, characterized in that: The psychological development prediction model is used to evaluate and predict children's emotional state, concentration and cognitive ability; through intelligent questionnaires, behavioral analysis and emotion recognition technology, it generates personalized psychological health and cognitive development suggestions, including: A1. Input data: Intelligent questionnaire data: children’s responses to the psychological questionnaire and the time they responded; Behavioral analysis data: facial expressions, voice intonation, behavioral movements; Emotion recognition data: emotional states, such as happiness, sadness, and concentration; A2. Output results Emotional state assessment: rating of current emotional state, such as happy, depressed; Attention assessment: Rating of current attention status, such as concentration and distraction; Cognitive assessment: Scoring of cognitive ability levels, such as comprehension and memory; A3. Algorithm Implementation Data preprocessing: cleaning, standardization and normalization of input data; Feature extraction: extract key features, such as facial expression features, voice features, and behavioral features; Machine Learning Models: Emotion recognition model: Convolutional neural network is used for facial expression recognition; Speech emotion recognition model: Long short-term memory network (LSTM) is used for speech emotion recognition.

8. The method for preschool health education according to claim 1, characterized in that: The social adaptation prediction model is used to evaluate and predict children's social ability and social adaptation level, and generates personalized social activities and cooperation suggestions by observing and recording children's social behaviors, including: B1. Input data Social behavior data: children’s performance in social interactions, such as the number of conversations, the number of collaborations, and the length of interaction. Language expression data: children’s language expression ability, such as vocabulary, sentence complexity, language fluency, etc. Social feedback data: Teacher and parent ratings of children's social behavior. B2. Output results Social skills assessment: Rating of current social skills, such as good, medium, or poor; Social adaptation assessment: score of current social adaptation level, such as high, medium, or low; Personalized social suggestions: suggestions for current social abilities, such as participating in group activities and conducting social training; B3. Algorithm Implementation Data preprocessing: cleaning, standardization and normalization of input data; Feature extraction: extract key features, such as the number of conversations, interaction duration, and language complexity; Machine Learning Models: Behavior classification model: Random forest is used for social behavior classification; Language analysis model: The natural language processing (NLP) model is used to analyze language expression ability.

Images