Student development quality evaluation method and system based on artificial intelligence

Abstract

The invention discloses a student development quality evaluation method and system based on artificial intelligence, and the method comprises the steps: multi-dimensional data collection, complex feature fusion, multi-level feature calculation, high-order feature generation, association rule mining and a real-time dynamic adjustment mechanism. The development conditions of students in five aspects of morality development, academic development, physical and mental development, aesthetic quality and labor and social practice are comprehensively and objectively evaluated; the method comprises the specific steps that subjective evaluation is replaced with multiple indirect data acquisition, and the influence of human subjective factors is reduced; through multi-level feature calculation and high-order feature generation, the depth and accuracy of data analysis are improved; analyzing the relationship among the high-order features by using an association rule mining technology, and carrying out ultimate feature fusion; calculating a comprehensive development evaluation coefficient through a comprehensive scoring formula, generating comprehensive development evaluation data, and performing personalized feedback and real-time dynamic adjustment; according to the invention, a scientific decision basis is provided for education management and personalized teaching.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence and educational technology, and in particular to a student development quality evaluation method and system based on artificial intelligence. Background Art

[0002] Student development quality evaluation is of great significance for the quality evaluation of student development. It can provide objective, fair and comprehensive student development evaluation through comprehensive data collection and intelligent analysis, helping education administrators and teachers to understand the multi-faceted development of students in a timely manner. However, the current problem is that the existing student development evaluation methods mainly rely on subjective evaluations, such as feedback from teachers, classmates and parents, which may be affected by personal biases, resulting in inaccurate results. In addition, existing technologies usually only consider test scores or single-dimensional data for evaluation, which cannot fully reflect the development of students. The data processing and analysis methods are relatively simple, making it difficult to deeply explore the potential information of the data, lacking real-time monitoring and dynamic adjustment mechanisms, and the evaluation results may lag behind and fail to reflect the development of students in a timely manner. The existence of these problems has led to the current lack of comprehensive and scientific development evaluation.

[0003] The existing technology (Chinese invention patent, publication number: CN115082266B, name: A comprehensive development analysis and evaluation system for student education disciplines) has the following deficiencies or defects when facing these problems. First, the existing technology relies heavily on subjective data and cannot avoid the influence of human subjective factors. Secondly, the data dimension of the existing technology is single and cannot fully reflect the development of students. In addition, the data processing and analysis methods of the existing technology are simple, and it is difficult to deeply explore the potential information of the data. Finally, the existing technology lacks real-time monitoring and dynamic adjustment mechanisms, the evaluation results are delayed, and cannot reflect the development of students in a timely manner. These deficiencies and defects make it difficult for the existing technology to provide a comprehensive and scientific evaluation of the quality of student development. Summary of the invention

[0004] In view of the many problems existing in the above-mentioned prior art, the present invention provides a student development quality evaluation method and system based on artificial intelligence, which comprehensively and objectively evaluates the development of students in five aspects: moral development, academic development, physical and mental development, aesthetic quality, and labor and social practice through multi-dimensional data collection, complex feature fusion, multi-level feature calculation and high-order feature generation, combined with association rule mining and real-time dynamic adjustment mechanism. The effect is to significantly improve the accuracy, comprehensiveness and real-time nature of the evaluation, and provide a scientific decision-making basis for education management and personalized teaching.

[0005] The student development quality evaluation method based on artificial intelligence includes the following steps:

[0006] Collect multi-dimensional data on students' social networks, class interactions, online learning, extracurricular reading, exercise and sleep, mental health, art participation, labor tasks and social practice activities through various channels to generate original data sets;

[0007] The original data set is cleaned, missing values ​​are filled, standardized, feature aligned and data merged to complete data preprocessing, and data dimension reduction is performed through principal component analysis and feature selection methods to generate selected feature data;

[0008] Extracting relevant features of moral development, academic development, physical and mental development, aesthetic quality, and labor and social practice from the selected feature data to generate a feature data set;

[0009] The feature data sets are preliminarily integrated and standardized, and the preliminary scores of various developments are calculated using a multi-level regression analysis method, cross-validation and score adjustment are performed to generate adjusted score data, and high-order features are extracted through a machine learning algorithm, and correlation analysis and ultimate feature integration are performed to finally calculate the final score data including moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice;

[0010] Based on the final scoring data, the comprehensive development assessment coefficient is calculated through the comprehensive scoring formula to complete the comprehensive development assessment, generate comprehensive development assessment data, and classify students into comprehensive development levels. An individualized feedback report is generated, real-time monitoring and dynamic adjustment of model parameters are carried out to optimize the feedback mechanism.

[0011] Preferably, the data collection step includes processing social network data through natural language processing technology and sentiment analysis algorithm to generate social network behavior data, recording class interaction data through a school management system, recording e-learning trajectory data through an online learning platform, recording exercise and sleep data and mental health data through smart devices, recording art participation data through an art course management system, and recording community service data and geographic location data through a community service platform.

[0012] Preferably, the data preprocessing step includes filling missing values ​​in the data using mean filling, interpolation or prediction models, performing standardization to convert different types of data to the same scale, and performing dimensionality reduction through principal component analysis and feature selection methods to generate selected feature data.

[0013] Preferably, the feature extraction step includes extracting social network feature data, class interaction feature data, e-learning trajectory feature data, exercise and sleep feature data, mental health feature data, art participation feature data and community service feature data from the selected feature data.

[0014] Preferably, the steps of feature fusion and calculating final scoring data include:

[0015] Performing preliminary fusion and standardization processing on the feature data set to generate standardized feature data;

[0016] Standardized characteristic data were analyzed using multilevel regression analysis to calculate preliminary scores for each development;

[0017] Perform cross-validation to check the accuracy and stability of the scores, adjust the preliminary scores based on the cross-validation data, and generate adjusted score data;

[0018] High-order features are extracted from the adjusted scoring data through machine learning algorithms, and association rule mining technology is used to analyze the relationship between each high-order feature for ultimate feature fusion. The final scoring data including moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice are finally calculated.

[0019] Preferably, the preliminary scoring data is calculated by the following formula:

[0020] Character Development Score

[0021] Academic development score (A) = log((ELT×W1)+(LRU×W2)+(EEG×W3))

[0022] Physical and mental development score

[0023] Aesthetic quality score (E) = max(ART, MMU, ER)

[0024] Labor and social practice score

[0025] Among them, SNA represents social network activity; CPI represents class interaction score; NLP represents natural language processing sentiment analysis score; ELT represents e-learning trajectory score; LRU represents learning resource usage score; EEG represents brain wave activity score; EX represents exercise volume score; SLP represents sleep quality score; HRV represents heart rate variability score; MH represents mental health score; ART represents artwork score; MMU represents multimedia usage score; ER represents emotion recognition score; TCO represents task completion score; CSV represents community service participation; GEO represents geographic location activity; W1, W2, and W3 represent the weights of different features.

[0026] Preferably, the method of analyzing the relationship between high-order features using association rule mining technology and performing ultimate feature fusion includes the following steps:

[0027] Use the Apriori algorithm to mine frequent item sets from high-order feature data and generate frequent item set data;

[0028] Generate association rules from the frequent item set data by using the FP-Growth algorithm to generate association rule data;

[0029] Fuse high-order feature data with high-order feature relationship data to generate ultimate fused feature data;

[0030] The ultimate fusion feature data were analyzed using a multivariate regression model to calculate the final scoring data.

[0031] Preferably, the comprehensive development assessment step includes:

[0032] Based on the final scoring data, the comprehensive development evaluation coefficient is calculated through a comprehensive scoring formula to complete the comprehensive development evaluation;

[0033] Generate comprehensive development assessment data and classify students into comprehensive development levels;

[0034] Generate personalized feedback reports based on the comprehensive development assessment coefficient, conduct real-time monitoring and dynamic adjustment of model parameters, and optimize the feedback mechanism.

[0035] Preferably, the comprehensive scoring formula is as follows:

[0036] Comprehensive development assessment coefficient

[0037] Among them, M3 represents the final moral development score; A3 represents the final academic development score; P3 represents the final physical and mental development score; E3 represents the final aesthetic literacy score; S3 represents the final labor and social practice score; W represents the sum of the weights of all characteristics.

[0038] A system for implementing the student development quality evaluation method based on artificial intelligence, comprising:

[0039] The data collection module is used to collect multi-dimensional data of students in social networks, class interactions, online learning, extracurricular reading, exercise and sleep, mental health, art participation, labor tasks and social practice activities through various channels to generate original data sets;

[0040] The data preprocessing module is used to clean the original data set, fill in missing values, standardize, align features and merge data to complete data preprocessing, and perform data dimension reduction through principal component analysis and feature selection methods to generate selected feature data;

[0041] A feature extraction module is used to extract relevant features of moral development, academic development, physical and mental development, aesthetic quality, and labor and social practice from the selected feature data to generate a feature data set;

[0042] The feature fusion and complex calculation module is used to perform preliminary fusion and standardization of the feature data set, calculate the preliminary scores of various developments using a multi-level regression analysis method, perform cross-validation and score adjustment, generate adjusted score data, extract high-order features through a machine learning algorithm, perform correlation analysis and ultimate feature fusion, and finally calculate the final score data including moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice;

[0043] The comprehensive development assessment module is used to calculate the comprehensive development assessment coefficient through the comprehensive scoring formula based on the final scoring data, complete the comprehensive development assessment, generate comprehensive development assessment data, and classify students into comprehensive development levels, generate personalized feedback reports, conduct real-time monitoring and dynamically adjust model parameters, and optimize the feedback mechanism.

[0044] Compared with the prior art, the advantages and beneficial effects of the present invention are:

[0045] The present invention achieves the effect of reducing the influence of subjective factors and comprehensively reflecting the development of students through multiple indirect data collection and complex feature fusion technologies;

[0046] The present invention achieves the depth and accuracy of data analysis through multi-level feature calculation, high-order feature generation and association analysis technology;

[0047] The present invention realizes the accuracy and real-time performance of the evaluation results through real-time monitoring and dynamic adjustment technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a flow chart of the method of the present invention;

[0049] Figure 2 It is a structural block diagram of the system of the present invention. DETAILED DESCRIPTION

[0050] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is obvious that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0051] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0052] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0053] In the case of using expressions such as "at least one of A, B, and C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.). In the case of using expressions such as "at least one of A, B, or C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0054] Some block diagrams and / or flow charts are shown in the accompanying drawings. It should be understood that some boxes or combinations thereof in the block diagrams and / or flow charts can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that these instructions can create a device for implementing the functions / operations described in these block diagrams and / or flow charts when executed by the processor. The technology of the present disclosure can be implemented in the form of hardware and / or software (including firmware, microcode, etc.). In addition, the technology of the present disclosure can take the form of a computer program product on a computer-readable storage medium storing instructions, which can be used by an instruction execution system or used in conjunction with an instruction execution system.

[0055] The student development quality evaluation method based on artificial intelligence includes the following steps:

[0056] Collect multi-dimensional data on students' social networks, class interactions, online learning, extracurricular reading, exercise and sleep, mental health, art participation, labor tasks and social practice activities through various channels to generate original data sets;

[0057] Preferably, the data collection step includes processing social network data through natural language processing technology and sentiment analysis algorithm to generate social network behavior data, recording class interaction data through the school management system, recording e-learning trajectory data through the online learning platform, recording exercise and sleep data and mental health data through smart devices, recording art participation data through the art course management system, and recording community service data and geographic location data through the community service platform.

[0058] In the present invention, the data collection step is crucial. Multi-dimensional data of students in social networks, class interactions, online learning, extracurricular reading, exercise and sleep, mental health, art participation, labor tasks and social practice activities are collected through various channels to generate original data sets. This step aims to comprehensively and objectively reflect the development of students in all aspects and provide a basis for subsequent data processing, analysis and evaluation.

[0059] The data collection steps include multiple aspects. First, social network data is processed through natural language processing technology and sentiment analysis algorithms to generate social network behavior data. These technologies parse the text content of students' posts, comments, etc. on social platforms, extract keywords and emotional tendencies, thereby reflecting students' online social behavior and emotional state, which helps to evaluate their moral development, social skills and emotional health. Secondly, the school management system records students' interactive data in classroom and extracurricular activities, including attendance, participation in discussions and collaborative projects, etc., to generate class interaction data to reflect students' social and cooperative abilities in school, and help evaluate their moral development and teamwork ability.

[0060] In terms of online learning, students’ learning behavior data, such as the number of logins, learning time, and online test scores, are recorded through online learning platforms to generate e-learning trajectory data. These data can reflect students’ learning habits, learning progress, and academic performance, and help evaluate their academic development. Extracurricular reading data records students’ borrowing and reading behaviors through library systems and online reading platforms, including borrowed books, reading time, and frequency, to generate extracurricular reading data to reflect students’ autonomous learning ability and reading interest, and help evaluate their academic development and comprehensive quality.

[0061] Exercise and sleep data are recorded through smart devices (such as smart bracelets), including steps, exercise duration, and sleep quality, to generate exercise and sleep data. These data reflect students' physical health and work and rest patterns, and help evaluate their physical and mental development. Mental health data records students' mood swings and psychological assessment results through mental health applications to generate mental health data, which reflects students' mental health status and emotional changes, and helps evaluate their physical and mental development. Art participation data records students' participation in art courses and work submissions through the art course management system to generate art participation data, which reflects students' artistic interests and creativity, and helps evaluate their aesthetic literacy.

[0062] Labor task data records the labor task data completed by students on and off campus through the campus management system, including the type of task, completion status and time, and generates labor task data to reflect students' labor ability and practical experience, helping to evaluate their labor and social practice development. Social practice data records students' social practice activity data through the community service platform, including participation frequency, activity type and performance, and generates social practice data to reflect students' social participation and service awareness, helping to evaluate their labor and social practice development.

[0063] Through the collection and integration of the above multi-dimensional data, the generated original data set provides rich and diverse basic information for subsequent data preprocessing, feature extraction, feature fusion and complex calculation, and comprehensive development evaluation. This comprehensive and objective multi-dimensional data collection method ensures the scientificity and accuracy of the evaluation of student development quality and avoids the one-sidedness of single-dimensional evaluation.

[0064] The original data set is cleaned, missing values ​​are filled, standardized, feature aligned and data merged to complete data preprocessing, and data dimension reduction is performed through principal component analysis and feature selection methods to generate selected feature data;

[0065] Preferably, the data preprocessing step includes filling missing values ​​in the data using mean filling, interpolation or prediction models, performing standardization to convert different types of data to the same scale, and performing dimensionality reduction through principal component analysis and feature selection methods to generate selected feature data.

[0066] In the present invention, the data preprocessing step is a key link to ensure data quality and analysis accuracy. The raw data set is cleaned, missing values ​​are filled, standardized, feature aligned and data merged to complete data preprocessing, and data dimension reduction is performed through principal component analysis and feature selection methods to generate selected feature data. This step aims to improve the consistency, integrity and availability of the data, and provide a high-quality data foundation for subsequent feature extraction and analysis.

[0067] Data preprocessing first involves data cleaning. The purpose of data cleaning is to remove noise and erroneous data from the original data set, such as detecting and deleting outliers to ensure the accuracy and reliability of the data. Next, use mean filling, interpolation, or prediction models to fill in missing values ​​in the data to ensure data integrity. Mean filling replaces missing values ​​with the mean of other values ​​in the data set, interpolation estimates missing values ​​based on the values ​​of adjacent data points, and prediction models predict missing values ​​through training models. Through these methods, data with missing values ​​filled is generated, which improves data integrity and analysis accuracy.

[0068] After data cleaning and missing value filling, standardization is performed. Standardization is the process of converting different types of data to the same scale to eliminate the dimensional differences between different data dimensions. Through standardization, all data will be scaled to the same range, usually scaling the data to between 0 and 1 or standardizing it to a distribution with a mean of 0 and a standard deviation of 1. This step ensures that different features have equal importance in the analysis process and prevents certain features from dominating the model training due to their large dimensions.

[0069] Feature alignment refers to arranging data from different sources in a unified format and structure to ensure that all data have a consistent feature structure. Subsequently, data merging is performed to merge the aligned data sets from different sources to generate a comprehensive data set. This step ensures that all relevant data can be integrated together to provide a comprehensive information basis for subsequent analysis.

[0070] After completing data cleaning, filling missing values, standardization, feature alignment and data merging, data dimensionality reduction is performed through principal component analysis (PCA) and feature selection methods. Principal component analysis is a linear dimensionality reduction technique that reduces data dimensions by projecting high-dimensional data into low-dimensional space and retaining as much variability of the original data as possible. The feature selection method evaluates the importance of each feature, selects the features that contribute most to the analysis, and removes redundant and irrelevant features. Through these methods, the selected feature data is generated, which not only retains the main information of the data, but also reduces the complexity of the data, and improves the efficiency of model training and analysis.

[0071] In summary, the data preprocessing step ensures the integrity, consistency and availability of the data through data cleaning, filling missing values, standardization, feature alignment and data merging; data dimension reduction is performed through principal component analysis and feature selection methods to generate selected feature data, which provides a high-quality data foundation for subsequent feature extraction and complex calculations, and ensures the scientificity and accuracy of the student development quality evaluation. For example, in a specific embodiment, PCA is used to reduce the dimension of the merged data set and extract the first 10 principal components. These principal components retain more than 95% of the variability of the data set, thereby generating high-quality selected feature data, which provides concise and powerful data support for subsequent analysis. Through these preprocessing steps, the efficiency and accuracy of data analysis are guaranteed, and the comprehensiveness and scientificity of the student development quality evaluation are improved.

[0072] Relevant features of moral development, academic development, physical and mental development, aesthetic quality, and labor and social practice are extracted from the selected feature data to generate a feature data set.

[0073] Preferably, the feature extraction step includes extracting social network feature data, class interaction feature data, e-learning trajectory feature data, exercise and sleep feature data, mental health feature data, art participation feature data and community service feature data from the selected feature data.

[0074] In the present invention, extracting relevant features of moral development, academic development, physical and mental development, aesthetic quality, and labor and social practice from the selected feature data to generate a feature data set is a key step in the evaluation process. This step aims to transform the multi-dimensional selected feature data into feature data that can specifically reflect the development of students in all aspects, so as to facilitate further analysis and comprehensive evaluation.

[0075] The feature extraction step first extracts the characteristic data of moral development from the selected characteristic data. This includes generating social network characteristic data by analyzing students' behavior patterns, emotional tendencies and other data in social networks; and generating class interaction characteristic data by analyzing students' performance in cooperation and interaction through class interaction data in the school management system. These characteristic data can comprehensively reflect students' social ability, cooperative spirit and moral development. For example, natural language processing technology is used to analyze students' speeches on social networks, extract keywords and emotional tendency data, and then combine their participation in class interaction to generate comprehensive moral development characteristic data.

[0076] Next, extract characteristic data of academic development from the selected characteristic data. Generate electronic learning trajectory characteristic data through the electronic learning trajectory data of the online learning platform, including the number of students' login times, learning time, test scores, etc.; combine students' extracurricular reading data in the library system and online reading platform, analyze their reading habits and learning interests, and generate comprehensive academic development characteristic data. These characteristic data can accurately reflect students' learning habits, learning effects and academic progress. For example, by analyzing students' learning trajectory data and extracurricular reading data on the online learning platform, comprehensive academic development characteristics can be generated to reflect students' academic investment and performance.

[0077] In terms of physical and mental development, exercise and sleep characteristic data and mental health characteristic data are extracted from the selected characteristic data. The exercise volume and sleep quality data recorded by smart devices are used to generate exercise and sleep characteristic data; the emotional fluctuations and psychological assessment results recorded by mental health applications are used to generate mental health characteristic data. These data reflect the physical health and mental health of students and help to comprehensively evaluate their physical and mental development. For example, the exercise volume and sleep quality data recorded by smart bracelets are combined with the emotional fluctuation data of mental health applications to generate comprehensive physical and mental development characteristic data.

[0078] In terms of aesthetic literacy, art participation feature data is extracted from the selected feature data. Art participation feature data is generated through the data of students participating in art courses and submitting art works recorded by the art course management system. These data can reflect students' interests and abilities in art and help evaluate the development of their aesthetic literacy. For example, by recording students' participation in art courses and submission of works, feature data reflecting their artistic interests and abilities can be generated.

[0079] In terms of labor and social practice, labor task characteristic data and community service characteristic data are extracted from the selected characteristic data. The data of students' participation in labor tasks recorded by the campus management system are used to generate labor task characteristic data; the data of students' participation in social practice activities recorded by the community service platform are used to generate community service characteristic data. These data reflect the students' participation and performance in labor and social practice, which helps to evaluate the development of their labor and social practice. For example, by recording the data of students' participation in campus cleaning and community service activities, characteristic data reflecting their performance in labor and social practice are generated.

[0080] In summary, the feature extraction step generates relevant feature data on moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice by extracting social network feature data, class interaction feature data, e-learning trajectory feature data, exercise and sleep feature data, mental health feature data, art participation feature data, and community service feature data from the selected feature data. These feature data provide a detailed and specific information basis for subsequent feature fusion and complex calculations, ensuring the comprehensiveness and accuracy of the student development quality evaluation. For example, in a specific embodiment, the social network behavior data and class interaction data of students are analyzed by natural language processing technology to generate moral development feature data reflecting their social skills and cooperative spirit, providing reliable data support for the evaluation of their moral development. Through these detailed feature extraction steps, the depth and accuracy of data analysis are guaranteed, and the scientificity and comprehensiveness of the student development quality evaluation are improved.

[0081] The feature data sets are preliminarily integrated and standardized, and the preliminary scores of various developments are calculated using a multi-level regression analysis method, cross-validation and score adjustment are performed to generate adjusted score data, and high-order features are extracted through a machine learning algorithm, and correlation analysis and ultimate feature integration are performed to finally calculate the final score data including moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice;

[0082] Preferably, the steps of feature fusion and calculating final scoring data include:

[0083] Performing preliminary fusion and standardization processing on the feature data set to generate standardized feature data;

[0084] Standardized characteristic data were analyzed using multilevel regression analysis to calculate preliminary scores for each development;

[0085] Perform cross-validation to check the accuracy and stability of the scores, adjust the preliminary scores based on the cross-validation data, and generate adjusted score data;

[0086] High-order features are extracted from the adjusted scoring data through machine learning algorithms, and association rule mining technology is used to analyze the relationship between each high-order feature for ultimate feature fusion. The final scoring data including moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice are finally calculated.

[0087] In the present invention, the steps of feature fusion and calculation of final scoring data are the core links in the evaluation process. The feature data set is initially fused and standardized, and the preliminary scores of various developments are calculated using a multi-level regression analysis method, cross-validation and score adjustment are performed to generate adjusted scoring data, and high-order features are extracted through a machine learning algorithm, and correlation analysis and ultimate feature fusion are performed to finally calculate the final scoring data including moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice.

[0088] First, the feature data set is initially fused and standardized. The purpose of the initial fusion is to integrate feature data from different sources into a unified data set to ensure the integrity and consistency of subsequent analysis. Standardization is to convert different types of data to the same scale, eliminate dimensional differences, and ensure that all features have equal importance in the analysis process. For example, the student's behavior data in social networks, online learning trajectory data, and mental health data are integrated and converted to a range of 0 to 1 through standardization for unified analysis.

[0089] Next, the standardized feature data is analyzed using a multi-level regression analysis method to calculate the preliminary scores for each development. Multi-level regression analysis is a statistical method used to analyze the relationship between multiple variables and can process data with a hierarchical structure. In the present invention, through multi-level regression analysis, the preliminary scores of each student in terms of moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice can be calculated. These preliminary scores reflect the performance of students in various development dimensions and provide basic data for subsequent score adjustments and high-order feature extraction.

[0090] In order to ensure the accuracy and stability of the scoring, cross validation is performed. Cross validation is a method of evaluating model performance. By dividing the data set into a training set and a validation set, the training and validation process is repeated many times to check the stability and generalization ability of the model. Based on the cross validation data, the preliminary scoring is adjusted to generate adjusted scoring data. The adjusted scoring data is more accurate and reliable and can better reflect the actual development of students.

[0091] The key to the next step is to extract high-level features from the adjusted rating data through machine learning algorithms. Machine learning algorithms include but are not limited to random forests, support vector machines, and deep neural networks, which can extract higher-level and more abstract features from complex data. For example, using a deep neural network to train the adjusted rating data can extract high-level features that reflect students' comprehensive abilities and potential development trends.

[0092] Subsequently, the association rule mining technology is used to analyze the relationship between each high-order feature and perform the ultimate feature fusion. Association rule mining technology is a data mining method used to discover interesting relationships between different features in a data set. In the present invention, through the Apriori algorithm and the FP-Growth algorithm, frequent item sets can be mined and association rules can be generated from high-order feature data to analyze the relationship between high-order features in moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice. These association relationships can reveal the mutual influence between different development dimensions and provide an important basis for the final comprehensive score.

[0093] Finally, the ultimate feature fusion is performed, and the ultimate fusion feature data is analyzed through a multiple regression model to calculate the final scoring data including moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice. The multiple regression model can handle the relationship between multiple independent variables and one or more dependent variables, and generate a comprehensive score for each student in each development dimension by analyzing high-order features and their correlation. These final scoring data fully reflect the overall development of students and can provide a scientific and objective evaluation basis for education managers and teachers.

[0094] For example, in a specific embodiment, the social network feature data, class interaction feature data, e-learning trajectory feature data, exercise and sleep feature data, mental health feature data, art participation feature data, and community service feature data of students are initially integrated and standardized, and a preliminary score is calculated using multi-level regression analysis, cross-validation and score adjustment are performed, high-order features are extracted using a deep neural network, and the association rules between high-order features are mined using the Apriori algorithm and the FP-Growth algorithm. Finally, the comprehensive score of the student in each development dimension is calculated using a multivariate regression model, providing a comprehensive and detailed analysis result for the evaluation of the quality of student development. Through these detailed steps, the scientificity, accuracy, and comprehensiveness of the evaluation results are ensured.

[0095] Preferably, the preliminary scoring data is calculated by the following formula:

[0096] Character Development Score

[0097] This formula takes the weighted sum of students’ activity in social networks, their performance in class interactions, and the results of sentiment analysis to reflect their comprehensive performance in moral development. In this way, information from multiple related dimensions can be integrated into a comprehensive score to quantitatively evaluate students’ moral development.

[0098] Academic development score (A) = log((ELT×W1)+(LRU×W2)+(EEG×W3))

[0099] This formula calculates the academic development score by taking the weighted sum of the student's online learning trajectory, learning resource usage, and brain wave activity, and taking the logarithm. The application of the logarithmic function helps to process data with a large numerical range, making the score smoother and easier to interpret. In this way, students' performance in academic development can be accurately quantified, combining multiple learning behaviors and brain wave activity data to provide a more comprehensive assessment.

[0100] Physical and mental development score

[0101] The formula adds up the weighted scores of students' exercise volume, sleep quality, and heart rate variability, and then divides them by their mental health scores to get their physical and mental development scores. This calculation method takes into account students' physical activity, rest, and mental health, and reflects the comprehensive level of physical and mental development through a proportional relationship.

[0102] Aesthetic quality score (E) = max(ART, MMU, ER)

[0103] This formula takes the maximum value of the three scores to reflect the student's best performance in art and aesthetic literacy. In this way, the outstanding performance of students in a specific area can be highlighted, providing a more targeted evaluation.

[0104] Labor and social practice score

[0105] The formula reflects the comprehensive performance of students in labor tasks and social practice by multiplying the ratio of task completion score to community service participation by the activeness of geographical location. This formula can comprehensively consider the completion of students' labor tasks, participation in community services and the activeness of geographical location, providing a more comprehensive evaluation.

[0106] Among them, SNA represents social network activity; CPI represents class interaction score; NLP represents natural language processing sentiment analysis score; ELT represents e-learning trajectory score; LRU represents learning resource usage score; EEG represents brain wave activity score; EX represents exercise volume score; SLP represents sleep quality score; HRV represents heart rate variability score; MH represents mental health score; ART represents artwork score; MMU represents multimedia usage score; ER represents emotion recognition score; TCO represents task completion score; CSV represents community service participation; GEO represents geographic location activity; W1, W2, and W3 represent the weights of different features.

[0107] The present invention can convert multi-dimensional feature data into quantitative scores through calculations of these formulas, reflecting the development of students in various aspects. For example, in a specific embodiment, the above formula is used to calculate that a student's moral development score is 85, the academic development score is 90, the physical and mental development score is 88, the aesthetic quality score is 92, and the labor and social practice score is 87. These scores comprehensively reflect the student's performance in morality, academic, physical and mental, aesthetic and practical aspects, and provide important data support for subsequent comprehensive evaluation and personalized feedback.

[0108] In summary, the preliminary scoring data is calculated through formulas, using various characteristic data and weight relationships to quantitatively evaluate students' performance in different development dimensions. In this way, standardized data processing and comprehensive analysis can be achieved to ensure the scientificity, accuracy and comprehensiveness of the evaluation results, providing strong support for education management and decision-making.

[0109] Preferably, the association rule mining technology is used to analyze the relationship between the high-level features and perform the ultimate feature fusion, including the following steps:

[0110] Use the Apriori algorithm to mine frequent item sets from high-order feature data and generate frequent item set data;

[0111] Generate association rules from the frequent item set data by using the FP-Growth algorithm to generate association rule data;

[0112] Fuse high-order feature data with high-order feature relationship data to generate ultimate fused feature data;

[0113] The ultimate fusion feature data were analyzed using a multivariate regression model to calculate the final scoring data.

[0114] In the present invention, the use of association rule mining technology to analyze the relationship between high-level features and perform ultimate feature fusion is a highly complex and critical step in the evaluation process. The purpose of this step is to discover potential association relationships from high-level feature data and integrate these relationships into a comprehensive feature data set for further scoring and evaluation.

[0115] First, the Apriori algorithm is used to mine frequent item sets from high-order feature data to generate frequent item set data. The Apriori algorithm is a classic association rule mining algorithm that can effectively discover frequently occurring item sets from a large amount of data. High-order feature data contains detailed features of each student in different development dimensions. The Apriori algorithm can identify feature combinations that often appear together in these feature data. For example, a student's high exercise volume (EX) and high sleep quality (SLP) may often appear together. By mining these frequent item sets, we can gain a preliminary understanding of the correlation between the high-order features.

[0116] Next, association rules are generated from the frequent item set data by the FP-Growth algorithm to generate association rule data. The FP-Growth algorithm is an efficient frequent item set mining algorithm that can quickly discover frequent item sets and generate association rules by constructing a frequent pattern tree (FP-tree). These association rules reveal the relationship between different features. For example, if a student's participation in art courses (ART) is high, then his emotion recognition score (ER) may also be high. These association rules provide basic data for further feature fusion.

[0117] The high-order feature data is fused with the high-order feature relationship data to generate the ultimate fused feature data. Feature fusion is to integrate multiple related features into a comprehensive feature to more comprehensively reflect the student's development. In this step, the high-order feature data and the high-order feature relationship data obtained by association rule mining are combined to form a comprehensive feature data set. For example, the student's high exercise (EX), high sleep quality (SLP) and heart rate variability (HRV) data are fused with their corresponding association rules to generate a feature data that comprehensively reflects their physical and mental health status.

[0118] Finally, the ultimate fusion feature data is analyzed using a multiple regression model to calculate the final scoring data. The multiple regression model is a statistical analysis method used to study the impact of multiple independent variables on one or more dependent variables. In the present invention, through the multiple regression model, the various comprehensive features in the ultimate fusion feature data can be analyzed to calculate the final scoring data of students in moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice. For example, by analyzing the fused moral development feature data, the final moral development score of the student can be calculated. These scores combine the influence of multiple related features and provide a more comprehensive and accurate evaluation result.

[0119] For example, in a specific embodiment, the Apriori algorithm is used to find out from the high-order feature data that students' high exercise (EX) and high sleep quality (SLP) often appear together, and then the FP-Growth algorithm is used to generate association rules, and it is found that these students also have high heart rate variability (HRV) scores. These high-order feature data and association rule data are fused to generate a feature data set that comprehensively reflects the physical and mental health status. Finally, the comprehensive feature data is analyzed through a multivariate regression model to calculate the final score of the student's physical and mental development, providing a comprehensive and scientific evaluation basis for education managers.

[0120] In summary, we use association rule mining technology to analyze the relationship between high-order features and perform ultimate feature fusion. We use the Apriori algorithm and FP-Growth algorithm to mine frequent item sets and association rules, fuse high-order feature data with high-order feature relationship data, and use a multivariate regression model to calculate the final score. This complex process not only reveals the potential relationship between students' development dimensions, but also provides more accurate and comprehensive evaluation results through comprehensive analysis, providing solid data support for the scientific evaluation of students' development quality.

[0121] Based on the final scoring data, the comprehensive development assessment coefficient is calculated through the comprehensive scoring formula to complete the comprehensive development assessment, generate comprehensive development assessment data, and classify students into comprehensive development levels. An individualized feedback report is generated, real-time monitoring and dynamic adjustment of model parameters are carried out to optimize the feedback mechanism.

[0122] Preferably, the comprehensive development assessment steps include:

[0123] Based on the final scoring data, the comprehensive development evaluation coefficient is calculated through a comprehensive scoring formula to complete the comprehensive development evaluation;

[0124] Generate comprehensive development assessment data and classify students into comprehensive development levels;

[0125] Generate personalized feedback reports based on the comprehensive development assessment coefficient, conduct real-time monitoring and dynamic adjustment of model parameters, and optimize the feedback mechanism.

[0126] In the present invention, the comprehensive development assessment step is the final stage of the entire evaluation process, which aims to conduct a comprehensive and scientific assessment of the overall development of students and provide personalized feedback and optimization suggestions. This step includes calculating the comprehensive development assessment coefficient based on the final scoring data through a comprehensive scoring formula, generating comprehensive development assessment data, classifying students into comprehensive development levels, generating personalized feedback reports, and performing real-time monitoring and dynamic adjustment of model parameters to optimize the feedback mechanism.

[0127] First, based on the final scoring data, the comprehensive development evaluation coefficient is calculated through a comprehensive scoring formula. The comprehensive scoring formula weights the final scoring data of students in terms of moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice to generate a comprehensive development evaluation coefficient.

[0128] Next, based on the comprehensive development assessment data, students are divided into comprehensive development levels. According to the comprehensive development assessment coefficient, students are divided into different development levels (such as excellent, good, medium, and needs improvement) so that educational administrators and teachers can understand the overall development of each student. This level division can help identify students' strengths and areas that need improvement, and provide a basis for personalized education. For example, students with higher comprehensive development assessment coefficients may be rated as "excellent", while students with lower coefficients may need more attention and support.

[0129] Generate a personalized feedback report based on the comprehensive development assessment coefficient. The feedback report lists in detail the performance of each student in each development dimension and provides targeted suggestions for improvement. For example, the report may point out that a student has outstanding academic development, but needs to improve in physical and mental development, and recommends increasing exercise and sleep time. Through this personalized feedback, students and parents can have a clearer understanding of the student's overall development and take appropriate measures to improve.

[0130] Conduct real-time monitoring and dynamically adjust model parameters to optimize the feedback mechanism. The real-time monitoring system continuously tracks students' development data, detects anomalies and data change trends, and ensures the accuracy and adaptability of the evaluation model. For example, if the physical and mental development scores of a large number of students decline over a period of time, the system can automatically adjust the model parameters to increase the weight of physical and mental development-related features to more accurately reflect the students' actual situation. By dynamically adjusting model parameters, the evaluation system can be continuously optimized and improved to provide more accurate and timely feedback.

[0131] For example, in a specific embodiment, the comprehensive development evaluation coefficient of a student calculated by the comprehensive scoring formula is 85, indicating that the student's overall performance in various development dimensions is good. Based on this coefficient, the student is classified as "good" and a personalized feedback report is generated, indicating that the student has excellent performance in academic development, but needs more attention in terms of mental health, and it is recommended to increase psychological counseling and relaxation training. The real-time monitoring system found that the mental health scores of many students have dropped recently, so it automatically adjusts the model parameters and increases the weight of mental health characteristics to ensure the accuracy and real-time nature of the evaluation results.

[0132] In summary, the comprehensive development assessment steps calculate the comprehensive development assessment coefficient, generate comprehensive development assessment data, divide the comprehensive development level, generate personalized feedback reports, and conduct real-time monitoring and dynamic adjustment of model parameters to ensure the scientificity, accuracy and timeliness of the assessment results. Through this comprehensive assessment method, it can provide students, parents and education managers with a scientific and objective evaluation basis to promote the all-round development of students.

[0133] Preferably, the comprehensive scoring formula is as follows:

[0134] Comprehensive development assessment coefficient

[0135] Among them, M3 represents the final moral development score; A3 represents the final academic development score; P3 represents the final physical and mental development score; E3 represents the final aesthetic literacy score; S3 represents the final labor and social practice score; W represents the sum of the weights of all characteristics.

[0136] The design of the comprehensive scoring formula is based on the principle of multi-dimensional evaluation. By adjusting the weights of different development dimensions, it ensures that each dimension can be properly reflected in the comprehensive evaluation. The selection of weight indexes 1 / 2, 1 / 3, 1 / 4, 1 / 5 and 1 / 6 is based on the evaluation of the importance of different development dimensions. These indexes are used to balance the influence of each dimension in the comprehensive evaluation. Finally, by normalizing the weighted product of the scores of each dimension, a comprehensive evaluation coefficient C is obtained, which makes the comprehensive evaluation results more objective and comprehensive.

[0137] By applying this comprehensive scoring formula, students' performance in moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice can be integrated into a single evaluation index C, which comprehensively reflects the overall development level of students. The effect of this is that a concise numerical value can be used to fully understand the multi-faceted development of students, making it easier for education administrators and teachers to make evaluations and decisions.

[0138] In a specific embodiment, suppose a student's final moral development score M3 is 80, academic development score A3 is 85, physical and mental development score P3 is 90, aesthetic quality score E3 is 70, and labor and social practice score S3 is 75. Calculate according to the formula:

[0139]

[0140] Multiplying the numerator by the weighted value yields 719.94.

[0141] Assuming that the sum of the weights of all features is 10, the final comprehensive development evaluation coefficient CCC is:

[0142]

[0143] Therefore, the comprehensive development assessment coefficient of this student is 71.99, indicating that his overall performance in various development dimensions is good, but there is still room for improvement.

[0144] In the present invention, the comprehensive scoring formula quantifies the performance of students in different development dimensions into a comprehensive evaluation coefficient through scientific and reasonable design. This coefficient not only takes into account the importance and weight of each dimension, but also ensures the objectivity and fairness of the result through normalization. Applying this formula can provide educational managers with a concise and comprehensive indicator to help them better understand and evaluate the overall development of students. At the same time, through personalized feedback and real-time monitoring, the evaluation mechanism is further optimized to ensure that each student can receive a scientific and fair evaluation to promote their all-round development.

[0145] For example, in a specific application scenario, after obtaining a student's comprehensive development evaluation coefficient through the above formula, education administrators can formulate corresponding educational intervention measures based on this value and specific feedback reports to help students make progress in their relatively weak development dimensions and achieve all-round development. This scientific evaluation method not only improves the accuracy and reliability of the evaluation, but also provides solid data support for personalized education.

[0146] like Figure 2 As shown, a system for implementing the student development quality evaluation method based on artificial intelligence includes:

[0147] The data collection module is used to collect multi-dimensional data of students in social networks, class interactions, online learning, extracurricular reading, exercise and sleep, mental health, art participation, labor tasks and social practice activities through various channels to generate original data sets;

[0148] The data collection module is used to collect multi-dimensional data of students in social networks, class interactions, online learning, extracurricular reading, exercise and sleep, mental health, art participation, labor tasks and social practice activities through various channels to generate original data sets. The collected data include students' behavior data on social networks, classroom interaction data, online learning trajectories, extracurricular reading records, exercise and sleep data, mental health data, art participation data, labor task records and social practice participation data. These data are collected through sensors, smart devices, online platforms and management systems to comprehensively reflect the multi-faceted development of students. For example, the students' exercise volume and sleep quality data are recorded through smart bracelets to reflect their physical health; the students' learning trajectory data are recorded through online learning platforms to reflect their academic development.

[0149] The data preprocessing module is used to clean the original data set, fill in missing values, standardize, align features and merge data to complete data preprocessing, and perform data dimension reduction through principal component analysis and feature selection methods to generate selected feature data;

[0150] The data preprocessing module is used to clean the original data set, fill missing values, standardize, align features and merge data to complete data preprocessing, and perform data dimension reduction through principal component analysis and feature selection methods to generate selected feature data. The purpose of data cleaning is to remove noise and erroneous data to ensure the accuracy of the data. Missing values ​​are filled using mean filling, interpolation or prediction models to ensure the integrity of the data. Standardization converts different types of data to the same scale to eliminate dimensional differences. Feature alignment and data merging integrate data from different sources to generate a unified data set. Data dimension reduction is performed through principal component analysis and feature selection methods to reduce the dimension of the data while retaining the main information. For example, through principal component analysis, high-dimensional learning behavior data can be reduced into several main components for subsequent analysis.

[0151] A feature extraction module is used to extract relevant features of moral development, academic development, physical and mental development, aesthetic quality, and labor and social practice from the selected feature data to generate a feature data set;

[0152] The feature extraction module is used to extract relevant features of moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice from the selected feature data to generate a feature data set. Feature extraction is the process of converting multi-dimensional data into feature data that can specifically reflect the development of students in all aspects. For example, social activity is extracted from social network behavior data, learning progress and grades are extracted from online learning trajectory data, health status indicators are extracted from exercise and sleep data, and emotional status is extracted from mental health data. These feature data provide the basis for subsequent complex calculations and analysis.

[0153] The feature fusion and complex calculation module is used to perform preliminary fusion and standardization of the feature data set, calculate the preliminary scores of various developments using a multi-level regression analysis method, perform cross-validation and score adjustment, generate adjusted score data, extract high-order features through a machine learning algorithm, perform correlation analysis and ultimate feature fusion, and finally calculate the final score data including moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice;

[0154] The feature fusion and complex calculation module is used to perform preliminary fusion and standardization on the feature data set, calculate the preliminary scores of each development using the multi-level regression analysis method, perform cross-validation and score adjustment, generate adjusted score data, extract high-order features through machine learning algorithms, perform association analysis and ultimate feature fusion, and finally calculate the final score data including moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice. Preliminary fusion integrates different feature data to generate standardized feature data. Multi-level regression analysis calculates preliminary scores for each development, and cross-validation ensures the accuracy and stability of the scores. Machine learning algorithms extract high-order features, association analysis mines the relationship between features, and ultimate feature fusion calculates the final score data. For example, the moral development score of students is calculated through multi-level regression analysis, and the machine learning algorithm extracts its high-order features, and after association analysis, a comprehensive moral development score is generated.

[0155] The comprehensive development assessment module is used to calculate the comprehensive development assessment coefficient through the comprehensive scoring formula based on the final scoring data, complete the comprehensive development assessment, generate comprehensive development assessment data, and classify students into comprehensive development levels, generate personalized feedback reports, conduct real-time monitoring and dynamically adjust model parameters, and optimize the feedback mechanism.

[0156] The comprehensive development assessment module is used to calculate the comprehensive development assessment coefficient through the comprehensive scoring formula based on the final scoring data, complete the comprehensive development assessment, generate comprehensive development assessment data, and classify students into comprehensive development levels, generate personalized feedback reports, conduct real-time monitoring and dynamically adjust model parameters, and optimize the feedback mechanism. The comprehensive scoring formula weights each score to generate a comprehensive development assessment coefficient to reflect the overall development of the students. Based on the evaluation data, students are graded, such as excellent, good, and need improvement. A personalized feedback report is generated to provide specific improvement suggestions. The real-time monitoring system tracks the development of students, dynamically adjusts model parameters, and ensures the accuracy and real-time nature of the evaluation results. For example, a student's comprehensive evaluation coefficient is 85, which is rated as good. Through a personalized feedback report, it is recommended that he pay more attention to mental health.

[0157] The core principle of this invention is to comprehensively and objectively evaluate the development of students in five aspects: moral development, academic development, physical and mental development, aesthetic quality, and labor and social practice, through multi-dimensional data collection, complex feature fusion, multi-level feature calculation and high-order feature generation, combined with association rule mining and real-time dynamic adjustment mechanism. Through these technical means, the depth and accuracy of data analysis are achieved, the close connection and irreplaceability between data of various dimensions are ensured, and a scientific and comprehensive evaluation of the quality of student development is provided.

[0158] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0159] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0160] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0161] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0162] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0163] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0164] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0165] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0166] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A student development quality evaluation method based on artificial intelligence, characterized in that: The following steps are involved: Data collection: Collect students’ multi-dimensional data on social networks, class interactions, online learning, extracurricular reading, exercise and sleep, mental health, art participation, labor tasks and social practice activities through various channels to generate original data sets; Data preprocessing: cleaning the original data set, filling missing values, standardizing, aligning features and merging data to complete data preprocessing, and reducing data dimension through principal component analysis and feature selection methods to generate selected feature data; Feature extraction, extracting relevant features of moral development, academic development, physical and mental development, aesthetic quality, and labor and social practice from the selected feature data to generate a feature data set; Feature fusion and calculation of final scoring data: preliminary fusion and standardization of the feature data set, calculation of preliminary scores for each development using multi-level regression analysis, cross-validation and score adjustment, generation of adjusted scoring data, extraction of high-order features using machine learning algorithms, correlation analysis and ultimate feature fusion, and final calculation of final scoring data for moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice; Comprehensive development assessment, based on the final scoring data, calculates the comprehensive development assessment coefficient through the comprehensive scoring formula, completes the comprehensive development assessment, generates comprehensive development assessment data, and divides students into comprehensive development levels, generates personalized feedback reports, conducts real-time monitoring and dynamically adjusts model parameters, and optimizes the feedback mechanism.

2. The method for evaluating the quality of student development based on artificial intelligence according to claim 1 is characterized in that: The data collection steps include processing social network data through natural language processing technology and sentiment analysis algorithms to generate social network behavior data, recording class interaction data through the school management system, recording e-learning trajectory data through the online learning platform, recording exercise and sleep data and mental health data through smart devices, recording art participation data through the art course management system, and recording community service data and geographic location data through the community service platform.

3. The method for evaluating the quality of student development based on artificial intelligence according to claim 1 is characterized in that: The data preprocessing steps include filling missing values ​​in the data using mean imputation, interpolation or prediction models, standardization to convert different types of data to the same scale, and dimensionality reduction through principal component analysis and feature selection methods to generate selected feature data.

4. The method for evaluating the quality of student development based on artificial intelligence according to claim 1 is characterized in that: The feature extraction step includes extracting social network feature data, class interaction feature data, e-learning trajectory feature data, exercise and sleep feature data, mental health feature data, art participation feature data and community service feature data from the selected feature data.

5. The method for evaluating the quality of student development based on artificial intelligence according to claim 1 is characterized in that: The steps of feature fusion and calculation of final scoring data include: Performing preliminary fusion and standardization processing on the feature data set to generate standardized feature data; Standardized characteristic data were analyzed using multilevel regression analysis to calculate preliminary scores for each development; Perform cross-validation to check the accuracy and stability of the scores, adjust the preliminary scores based on the cross-validation data, and generate adjusted score data; High-order features are extracted from the adjusted scoring data through machine learning algorithms, and association rule mining technology is used to analyze the relationship between each high-order feature for ultimate feature fusion. The final scoring data including moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice are finally calculated.

6. The method for evaluating the quality of student development based on artificial intelligence according to claim 5 is characterized in that: The preliminary scoring data is calculated using the following formula: Academic development score (A) = log((ELT×W1)+(LRU×W2)+(EEG×W3)) Aesthetic quality score (E) = max(ART, MMU, ER) Among them, SNA represents social network activity; CPI represents class interaction score; NLP represents natural language processing sentiment analysis score; ELT represents e-learning trajectory score; LRU represents learning resource usage score; EEG represents brain wave activity score; EX represents exercise volume score; SLP represents sleep quality score; HRV represents heart rate variability score; MH represents mental health score; ART represents artwork score; MMU represents multimedia usage score; ER represents emotion recognition score; TCO represents task completion score; CSV represents community service participation; GEO represents geographic location activity; W1, W2, and W3 represent the weights of different features.

7. The method for evaluating the quality of student development based on artificial intelligence according to claim 5 is characterized in that: The association rule mining technology is used to analyze the relationship between high-level features and perform the ultimate feature fusion, including the following steps: Use the Apriori algorithm to mine frequent item sets from high-order feature data and generate frequent item set data; Generate association rules from the frequent item set data by using the FP-Growth algorithm to generate association rule data; Fuse high-order feature data with high-order feature relationship data to generate ultimate fused feature data; The ultimate fusion feature data were analyzed using a multivariate regression model to calculate the final scoring data.

8. The method for evaluating the quality of student development based on artificial intelligence according to claim 1 is characterized in that: The steps of comprehensive development assessment include: Based on the final scoring data, the comprehensive development evaluation coefficient is calculated through a comprehensive scoring formula to complete the comprehensive development evaluation; Generate comprehensive development assessment data and classify students into comprehensive development levels; Generate personalized feedback reports based on the comprehensive development assessment coefficient, conduct real-time monitoring and dynamic adjustment of model parameters, and optimize the feedback mechanism.

9. The method for evaluating the quality of student development based on artificial intelligence according to claim 8 is characterized in that: The comprehensive scoring formula is as follows: Among them, M3 represents the final moral development score; A3 represents the final academic development score; P3 represents the final physical and mental development score; E3 represents the final aesthetic literacy score; S3 represents the final labor and social practice score; W represents the sum of the weights of all characteristics.

10. A system for implementing the method for evaluating the quality of student development based on artificial intelligence according to any one of claims 1 to 9, characterized in that: include: The data collection module is used to collect multi-dimensional data of students in social networks, class interactions, online learning, extracurricular reading, exercise and sleep, mental health, art participation, labor tasks and social practice activities through various channels to generate original data sets; The data preprocessing module is used to clean the original data set, fill in missing values, standardize, align features and merge data to complete data preprocessing, and perform data dimension reduction through principal component analysis and feature selection methods to generate selected feature data; A feature extraction module is used to extract relevant features of moral development, academic development, physical and mental development, aesthetic quality, and labor and social practice from the selected feature data to generate a feature data set; The feature fusion and complex calculation module is used to perform preliminary fusion and standardization of the feature data set, calculate the preliminary scores of various developments using a multi-level regression analysis method, perform cross-validation and score adjustment, generate adjusted score data, extract high-order features through a machine learning algorithm, perform correlation analysis and ultimate feature fusion, and finally calculate the final score data including moral development, academic development, physical and mental development, aesthetic literacy, and labor and social practice; The comprehensive development assessment module is used to calculate the comprehensive development assessment coefficient through the comprehensive scoring formula based on the final scoring data, complete the comprehensive development assessment, generate comprehensive development assessment data, and classify students into comprehensive development levels, generate personalized feedback reports, conduct real-time monitoring and dynamically adjust model parameters, and optimize the feedback mechanism.

Images