College student German education intelligent evaluation system and method based on artificial intelligence

Abstract

The invention discloses an artificial intelligence-based college student gordon wisdom evaluation system and method, and the method comprises the steps: S1, building a multi-dimensional data set through a data collection module; s2, performing semantic analysis on the student text data by using natural language processing and sentiment analysis technologies; s3, performing data mining on the student behavior data, identifying and extracting a behavior mode, and performing classification and clustering analysis; s4, establishing a German education evaluation model, and performing quantitative evaluation according to moral cognition, moral emotion and moral behaviors; s5, through an intelligent evaluation system, personalized German education feedback and suggestions are automatically generated and provided for students to perform self-reflection and improvement; and S6, in the data processing and storage process, data encryption and access control technologies are adopted. The method has the advantages of comprehensiveness, objectivity, dynamism and high safety.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based moral education wisdom evaluation system and method for college students. Background Art

[0002] With the rapid development of artificial intelligence and big data technology, the evaluation of college students' moral education has gradually become an important focus in the field of education. In the modern education system, moral education is not only a supplement to students' academic performance, but also an important part of comprehensively cultivating students' moral literacy, emotional cognition and behavioral norms. However, traditional moral education evaluation methods have many shortcomings and it is difficult to comprehensively, objectively and timely evaluate students' moral education performance.

[0003] In the existing technology, the traditional moral education evaluation method mainly relies on the subjective judgment of teachers and static evaluation criteria. Specifically, the traditional method has obvious shortcomings in the following aspects:

[0004] 1. Lack of dynamic adaptability: Traditional moral education evaluation is usually based on fixed evaluation standards and teachers' subjective impressions, which makes it difficult to timely reflect students' growth changes and dynamic changes in moral education performance.

[0005] 2. The evaluation process is not objective enough: Since moral education performance involves subjective factors such as students' emotions and behaviors, teachers' personal biases and limited observation scope may lead to evaluation results that are not comprehensive and objective enough.

[0006] 3. Low data processing efficiency: Traditional evaluation methods rely heavily on manual recording and analysis, which makes it difficult to process large amounts of student data, especially when it comes to multi-dimensional data (such as text, behavior, grades, etc.), and lack effective data integration and analysis methods.

[0007] 4. Imperfect feedback mechanism: Traditional feedback methods are usually one-way and static, lacking personalized guidance and dynamic adjustment, making it difficult to provide targeted suggestions and improvement measures based on students’ actual conditions.

[0008] Therefore, how to provide an artificial intelligence-based moral education wisdom evaluation system and method for college students is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0009] One purpose of the present invention is to propose an intelligent evaluation system and method for college students' moral education based on artificial intelligence. The present invention makes full use of natural language processing, sentiment analysis, machine learning and big data technology, and describes in detail a method for realizing intelligent and automated evaluation of college students' moral education, which has the advantages of comprehensiveness, objectivity, dynamism and high security.

[0010] According to an embodiment of the present invention, a method for evaluating college students' moral education wisdom based on artificial intelligence is characterized by comprising the following steps:

[0011] S1. Through the data collection module, comprehensively collect students' text data, behavioral data and academic performance information to establish a multi-dimensional data set;

[0012] S2. Use natural language processing and sentiment analysis techniques to conduct semantic analysis on student text data, extract keywords, classify sentiment tendencies, and identify positive, negative, and neutral sentiments;

[0013] S3, conduct data mining on student behavior data, identify and extract behavior patterns, and conduct classification and cluster analysis;

[0014] S4. Establish a moral education evaluation model, conduct quantitative evaluation based on moral cognition, moral emotion and moral behavior, and generate comprehensive moral education evaluation results;

[0015] S5. Through the intelligent evaluation system, personalized moral education feedback and suggestions are automatically generated to provide students with self-reflection and improvement, and provide guidance for teachers;

[0016] S6. During data processing and storage, data encryption and access control technologies are used to ensure the privacy and security of student data.

[0017] Optionally, the S1 specifically includes:

[0018] S11. Collect student text data, including students’ essays, papers, social media posts, and other written expressions, through web crawler technology and student management system interfaces:

[0019] T={t1,t2,…,t n};

[0020] Among them, t i Represents the i-th text data;

[0021] S12. Obtain student behavior data through a behavior data collection device, including library borrowing records, class attendance records, extracurricular activity participation records, and volunteer service records:

[0022] B={b1,b2,…,b m};

[0023] Among them, b j represents the jth behavior data;

[0024] S13. Obtain students’ academic performance information through the academic information collection module, including subject performance, course selection, academic competition results and scientific research achievements:

[0025] A={a1,a2,…,a k};

[0026] Among them, a l represents the lth academic achievement data;

[0027] S14. During the data collection process, pre-process the data:

[0028]

[0029] Among them, d i,j Represents the original data, Represents the normalized data, min(d i ) and max(d i ) represent the minimum and maximum values ​​of the i-th category data respectively;

[0030] S15. Store the processed text data, behavior data and academic performance information in the database and use big data technology to perform structured storage and management of the data:

[0031] D={(T i ,B i ,A i )|i=1,2,…,N};

[0032] Where D represents the database, N represents the number of students, and T i ,B i ,A i Respectively represent the text data, behavior data and academic performance data of the i-th student;

[0033] S16. Label the data and build a multi-dimensional data set. The data of each student is represented as a vector And define the tag collection:

[0034] L={l1,l2,…,l p};

[0035] Among them, l p represents the pth label;

[0036] S17. In the process of data storage and transmission, data encryption technology is adopted, using symmetric encryption algorithms and asymmetric encryption algorithms:

[0037] C=E K (M);

[0038] Among them, M represents plaintext data, K represents the key, and E K represents the encryption function, and C represents the ciphertext data.

[0039] Optionally, the S2 specifically includes:

[0040] S21, for the student text data set T = {t1, t2, ..., t n}, the processed text data is represented by T′={t′1,t′2,…,t′ n};

[0041] Among them, t′ i Represents the i-th processed text data;

[0042] S22. Use natural language processing technology to perform semantic analysis on the pre-processed text data and extract a set of keywords:

[0043] K={k1,k2,…,k m};

[0044] Among them, k j represents the jth keyword;

[0045] Keyword extraction is performed by calculating term frequency-inverse document frequency TF-IDF:

[0046]

[0047] Among them, DF(k j ) indicates keyword k j In the text t' i The word frequency in, N represents the total number of text data, DF(k j ) means it contains the keyword k j The number of texts;

[0048] S23. Perform sentiment analysis to classify text data into positive, negative, and neutral sentiments:

[0049] S(t' i ) = argmax c∈{pos,neg,neu} P(c|t' i );

[0050] Among them, S(t' i ) represents the text t' i The sentiment classification result of , c represents the sentiment category, including positive pos, negative neg and neutral neu, P(c|t′ i ) represents the text t′ i The probability of belonging to sentiment category c;

[0051] S24. Calculate the overall sentiment tendency score of each student:

[0052]

[0053] Among them, Ei represents the overall sentiment score of the i-th student, n i represents the number of texts of the student, S(t j ′) represents the sentiment score of the jth text, and the sentiment score is assigned 1, -1 and 0 according to positive, negative and neutral respectively;

[0054] S25. Generate a student sentiment analysis report based on the sentiment analysis results. The report content includes keyword extraction results, sentiment classification results and sentiment tendency scores, and is stored in the database:

[0055] R i =(K,{S(t′1),S(t′2),…,S(t′ n )},E i );

[0056] Among them, R i represents the sentiment analysis report of the i-th student, K represents the keyword set, {S(t′1), S(t′2),…, S(t′ n )} represents the sentiment classification result of each text of the student, E i Represents the overall sentiment tendency score.

[0057] Optionally, the S3 specifically includes:

[0058] S31, for the student behavior data set B = {b1, b2, ..., b m} is preprocessed, and the processed behavior data is expressed as B′={b′1,b′2,…,b′ m};

[0059] Among them, b j ′ represents the jth preprocessed behavior data;

[0060] S32, extracting features from the preprocessed behavior data to extract feature vectors:

[0061] F j ={f j1 ,f j2 ,…,f jn};

[0062] Among them, F j represents the feature vector of the jth behavior data, f jk represents the kth eigenvalue;

[0063] S33. Use cluster analysis to perform cluster analysis on feature vectors and identify behavior patterns:

[0064]

[0065] Among them, m represents the total number of behavioral data, c j represents the cluster label of the jth eigenvector, Indicates the c j The centers of the clusters, Denotes the eigenvector F j The cluster center The Euclidean distance between

[0066] S34. Based on the clustering results, identify the typical behavior patterns of students:

[0067] P={p1,p2,…,p q};

[0068] Among them, p q represents the qth identified behavior pattern;

[0069] S35. Calculate the behavior pattern score for each student:

[0070]

[0071] Among them, M i represents the behavior pattern score of the i-th student, Q represents the total number of identified behavior patterns, and w q represents the weight of the qth behavior pattern, I(p q |F i ) represents the i-th student and behavior pattern p q The matching function of

[0072] S36. Generate a student behavior pattern report based on the behavior pattern analysis results. The report content includes feature extraction results, behavior pattern classification results and behavior pattern scores, and is stored in the database:

[0073] R i =(F,{P},M i );

[0074] Among them, R i represents the behavior pattern report of the i-th student, F represents the feature vector set, {P} represents the behavior pattern set, M i Indicates the behavioral pattern score.

[0075] Optionally, the S4 specifically includes:

[0076] S41. Based on the multi-dimensional data of students, a moral education evaluation model is established and a moral education evaluation index system is defined, including three dimensions: moral cognition, moral emotion and moral behavior:

[0077]

[0078] Among them, Ii represents the i-th evaluation index;

[0079] S42. Convert text data, behavior data and academic performance data into evaluation index vectors:

[0080]

[0081] in, represents the text data evaluation index vector of the i-th student, represents the evaluation index vector of the behavior data of the i-th student, represents the evaluation index vector of the academic performance data of the i-th student, x i is the eigenvalue, min(x) and max(x) are the minimum and maximum values ​​of the eigenvalue respectively;

[0082] S43. Use the support vector machine algorithm to quantitatively evaluate students' moral education performance and build an evaluation model:

[0083]

[0084] in, represents the weight vector, b represents the bias, C represents the penalty parameter, N represents the number of samples, and y i represents the true label of the sample, Represents the feature vector of the i-th sample. By optimizing the objective function, the optimal weight vector is obtained. and bias b;

[0085] S44. Substitute each student's multi-dimensional data into the evaluation model to calculate the moral education performance score:

[0086]

[0087] Among them, S i represents the moral education performance score of the i-th student, represents the evaluation index vector of the i-th student, and the moral education performance score S i The value of represents the comprehensive performance of the student in all aspects of moral education;

[0088] S45. According to the scoring results, students are divided into different moral education performance levels:

[0089] G = {g1, g2, ..., gm};

[0090] Among them, g m represents the mth level of moral education performance;

[0091] S46. Generate a moral education evaluation report, the content of which includes an evaluation index vector, a moral education performance score and a moral education performance grade, and store it in a database:

[0092]

[0093] Among them, R i represents the moral education evaluation report of the i-th student, represents the evaluation index vector, S i represents the moral education performance score, g i Indicates the level of moral education performance.

[0094] Optionally, the S5 specifically includes:

[0095] S51. Score based on moral education performance i Generate personalized moral education feedback and suggestions, conduct detailed analysis of students' moral education performance, and calculate the impact of each evaluation indicator's weight on the student's overall score:

[0096]

[0097] Among them, W i,j represents the weight influence of the jth evaluation index of the i-th student, V i,j represents the jth evaluation index value of the i-th student, w j represents the weight of the jth evaluation index, and n represents the total number of evaluation indicators;

[0098] S52. Generate a personalized feedback report based on the impact analysis results. The report includes the student's strengths, areas for improvement, and specific suggestions. The suggestions are generated based on the student's performance on various evaluation indicators:

[0099] R suggestion (i) = f(W i,1 ,W i,2 ,…,W i,n );

[0100] Among them, R suggestion (i) represents the feedback suggestions of the i-th student, and the function f affects the value W according to the student’s weight i,j Generate specific recommendations;

[0101] S53. Provide personalized moral education guidance and improvement plans, which are presented to students and teachers through intelligent systems. Personalized guidance includes behavioral suggestions and emotional development suggestions, which are stored in the database for easy access by students and teachers:

[0102] G i =(S i ,R suggestion (i));

[0103] Among them, G iRepresents the personalized moral education guidance content of the i-th student, including the moral education performance score S i and personalized feedback suggestions R suggestion (i);

[0104] S54. Regularly update feedback and suggestions, and dynamically adjust according to students’ latest performance:

[0105]

[0106] Among them, ΔS i represents the change rate of the moral education performance score of the i-th student, Indicates the latest rating. represents the previous score, and T represents the time interval.

[0107] Optionally, the S6 specifically includes:

[0108] S61. In the process of data processing and storage, data encryption technology is used to protect the privacy and security of students' personal data. The data is encrypted using a symmetric encryption algorithm:

[0109] C i =E K (D i );

[0110] Among them, C i Indicates the encrypted data, E K Denotes the symmetric encryption algorithm, D i represents the original data, K represents the symmetric encryption key;

[0111] S62. During data transmission, an asymmetric encryption algorithm is used to encrypt and decrypt data:

[0112] C i =E pub (D i );

[0113] D i =D priv (C i );

[0114] Among them, E pub represents the public key encryption algorithm, D priv Denotes the private key decryption algorithm, D i represents the original data, C i Indicates encrypted data, pub indicates public key, and priv indicates private key;

[0115] S63. Perform access control on stored data, define access control policies, and implement them through the role-based access control model:

[0116] P = (U, R, PA, UA);

[0117] Among them, P represents the access control policy, U represents the user set, R represents the role set, PA represents the permission allocation set, and UA represents the user allocation set;

[0118] S64. Authenticate and authorize data access requests. The authentication process uses a hash function:

[0119] H i =H(U i +T);

[0120] Among them, H i represents the hash value, H represents the hash function, and U i represents user information, T represents timestamp;

[0121] S65. Audit and monitor data access records to promptly detect and handle abnormal access behaviors. The audit and monitoring process includes recording the user ID, access time, and access operations for each access:

[0122] A={(U i ,T i ,O i )|i=1,2,…,n};

[0123] Among them, A represents the audit log, U i Indicates user ID, T i Indicates the access time, O i Represents an access operation.

[0124] A college student moral education wisdom evaluation system based on an artificial intelligence college student moral education wisdom evaluation method, characterized by comprising:

[0125] The data collection module is used to collect students' text data, behavior data and academic performance data, including a web crawler interface, a student management system interface and a behavior data collection device;

[0126] The data processing module is used to preprocess and extract features from the collected data, including data cleaning, deduplication, missing value processing and formatting, as well as text segmentation, sentiment analysis and behavioral feature extraction;

[0127] The moral education evaluation module uses machine learning algorithms to conduct quantitative evaluation of processed data, establish a moral education evaluation model, and evaluate students' moral education performance, including the establishment of an evaluation index system, the calculation of moral education performance scores, and the classification of moral education performance levels;

[0128] The feedback generation module is used to generate personalized feedback and suggestions based on the moral education performance score, and generate a detailed moral education feedback report based on the student's specific performance, including strengths, areas for improvement and specific suggestions;

[0129] A data storage module is used to store processed data, evaluation results and feedback reports, including text data, behavior data, academic performance data, evaluation index vectors, moral education performance scores, moral education performance levels and feedback suggestions;

[0130] Data encryption and security module, responsible for encrypting and protecting data in the system and controlling access, including symmetric encryption algorithms, asymmetric encryption algorithms and role-based access control models;

[0131] The user interaction module provides an interactive interface for students and teachers to display moral education evaluation results and personalized feedback, supports querying and downloading feedback reports, and includes user authentication, permission control, and log auditing functions;

[0132] The system management module is responsible for the overall management and maintenance of the system, including user management, permission configuration, data backup and recovery, as well as system monitoring and troubleshooting.

[0133] The beneficial effects of the present invention are:

[0134] (1) The present invention realizes a comprehensive analysis and dynamic evaluation of college students' moral education performance by combining natural language processing, sentiment analysis, machine learning and big data technology. The system can comprehensively process students' text data, behavior data and academic performance data, quantify students' moral education performance from multiple dimensions, provide objective moral education evaluation results, and avoid the deviation caused by subjective judgment in traditional methods.

[0135] (2) The present invention generates personalized moral education feedback and suggestions for each student through an intelligent feedback generation module. Based on the specific performance of the students, the system can provide targeted guidance and improvement plans to help students reflect on themselves and improve themselves. This dynamic and personalized feedback mechanism greatly improves the pertinence and effectiveness of education.

[0136] (3) The present invention adopts advanced data encryption and access control technologies to ensure the privacy and security of student data. By symmetric and asymmetric encryption of data, combined with the role access control model, the system can effectively prevent data leakage and unauthorized access, and ensure the confidentiality and integrity of data.

[0137] (4) The present invention provides teachers and students with a convenient query and feedback channel through the intelligent evaluation system and user interaction module. The system can update students' moral education performance in real time, and teachers can adjust teaching methods in time according to students' latest performance, thereby improving the flexibility and responsiveness of education. BRIEF DESCRIPTION OF THE DRAWINGS

[0138] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0139] Figure 1 This is a general framework diagram of an artificial intelligence-based college students' moral education wisdom evaluation system and method proposed by the present invention;

[0140] Figure 2 This is a workflow diagram of a data acquisition module of an artificial intelligence-based college student moral education wisdom evaluation system and method proposed by the present invention;

[0141] Figure 3 A flowchart of the generation and display of personalized feedback for the college students' moral education wisdom evaluation system and method based on artificial intelligence proposed by the present invention;

[0142] Figure 4 This is a flow chart for implementing data encryption and access control of an artificial intelligence-based college student moral education wisdom evaluation system and method proposed by the present invention. DETAILED DESCRIPTION

[0143] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0144] refer to Figure 1-Figure 4 , a method for evaluating college students' moral education wisdom based on artificial intelligence, characterized by comprising the following steps:

[0145] S1. Through the data collection module, comprehensively collect students' text data, behavioral data and academic performance information to establish a multi-dimensional data set;

[0146] In this implementation, S1 specifically includes:

[0147] S11. Collect student text data, including students’ essays, papers, social media posts, and other written expressions, through web crawler technology and student management system interfaces:

[0148] T={t1,t2,…,t n};

[0149] Among them, t i Represents the i-th text data;

[0150] S12. Obtain student behavior data through a behavior data collection device, including library borrowing records, class attendance records, extracurricular activity participation records, and volunteer service records:

[0151] B={b1,b2,…,b m};

[0152] Among them, b j represents the jth behavior data;

[0153] S13. Obtain students’ academic performance information through the academic information collection module, including subject performance, course selection, academic competition results and scientific research achievements:

[0154] A={a1,a2,…,a k};

[0155] Among them, a l represents the lth academic achievement data;

[0156] S14. During the data collection process, pre-process the data:

[0157]

[0158] Among them, d i,j Represents the original data, Represents the normalized data, min(d i ) and max(d i ) represent the minimum and maximum values ​​of the i-th category data respectively;

[0159] S15. Store the processed text data, behavior data and academic performance information in the database and use big data technology to perform structured storage and management of the data:

[0160] D={(T i ,B i ,A i )|i=1,2,…,N};

[0161] Where D represents the database, N represents the number of students, and T i ,B i ,A i Respectively represent the text data, behavior data and academic performance data of the i-th student;

[0162] S16. Label the data and build a multi-dimensional data set. The data of each student is represented as a vector And define the tag collection:

[0163] L={l1,l2,…,l p};

[0164] Among them, l p represents the pth label;

[0165] S17. In the process of data storage and transmission, data encryption technology is adopted, using symmetric encryption algorithms and asymmetric encryption algorithms:

[0166] C=E K (M);

[0167] Among them, M represents plaintext data, K represents the key, and E K represents the encryption function, and C represents the ciphertext data.

[0168] S2. Use natural language processing and sentiment analysis techniques to conduct semantic analysis on student text data, extract keywords, classify sentiment tendencies, and identify positive, negative, and neutral sentiments;

[0169] In this implementation, S2 specifically includes:

[0170] S21, for the student text data set T = {t1, t2, ..., t n}, the processed text data is represented by T′={t′1,t′2,…,t′ n};

[0171] Among them, t′ i Represents the i-th processed text data;

[0172] S22. Use natural language processing technology to perform semantic analysis on the pre-processed text data and extract a set of keywords:

[0173] K={k1,k2,…,k m};

[0174] Among them, k j represents the jth keyword;

[0175] Keyword extraction is performed by calculating term frequency-inverse document frequency TF-IDF:

[0176]

[0177] Among them, DF(k j ) indicates keyword k j In the text t' i The word frequency in, N represents the total number of text data, DF(k j ) means it contains the keyword k j The number of texts;

[0178] S23. Perform sentiment analysis to classify text data into positive, negative, and neutral sentiments:

[0179] S(t' i ) = argmax c∈{pos,neg,neu} P(c|t' i );

[0180] Among them, S(t' i ) represents the text t' i The sentiment classification result of , c represents the sentiment category, including positive pos, negative neg and neutral neu, P(c|t′ i ) represents the text t′ i The probability of belonging to sentiment category c;

[0181] S24. Calculate the overall sentiment tendency score of each student:

[0182]

[0183] Among them, E i represents the overall sentiment score of the i-th student, n i represents the number of texts of the student, S(t j ′) represents the sentiment score of the jth text, and the sentiment score is assigned 1, -1 and 0 according to positive, negative and neutral respectively;

[0184] S25. Generate a student sentiment analysis report based on the sentiment analysis results. The report content includes keyword extraction results, sentiment classification results and sentiment tendency scores, and is stored in the database:

[0185] ″′

[0186] R i =(K,{S(t1),S(t2),…,S(t n )},E i );

[0187] Among them, R i represents the sentiment analysis report of the i-th student, K represents the keyword set, {S(t′1), S(t′2),…, S(t′ n )} represents the sentiment classification result of each text of the student, E i Represents the overall sentiment tendency score.

[0188] S3, conduct data mining on student behavior data, identify and extract behavior patterns, and conduct classification and cluster analysis;

[0189] In this implementation, S3 specifically includes:

[0190] S31, for the student behavior data set B = {b1, b2, ..., b m} is preprocessed, and the processed behavior data is expressed as B′={b′1,b′2,…,b′ m};

[0191] Among them, b j ′ represents the jth preprocessed behavior data;

[0192] S32, extracting features from the preprocessed behavior data to extract feature vectors:

[0193] F j ={f j1 ,f j2 ,…,f jn};

[0194] Among them, F j represents the feature vector of the jth behavior data, f jk represents the kth eigenvalue;

[0195] S33. Use cluster analysis to perform cluster analysis on feature vectors and identify behavior patterns:

[0196]

[0197] Among them, m represents the total number of behavioral data, c j represents the cluster label of the jth eigenvector, Indicates the c j The center of the cluster, Denotes the eigenvector F j The cluster center to which it belongs The Euclidean distance between

[0198] S34. Based on the clustering results, identify the typical behavior patterns of students:

[0199] P={p1,p2,…,p q};

[0200] Among them, p q represents the qth identified behavior pattern;

[0201] S35. Calculate the behavior pattern score for each student:

[0202]

[0203] Among them, M i represents the behavior pattern score of the i-th student, Q represents the total number of identified behavior patterns, and w q represents the weight of the qth behavior pattern, I(p q |F i ) represents the i-th student and behavior pattern p q The matching function of

[0204] S36. Generate a student behavior pattern report based on the behavior pattern analysis results. The report content includes feature extraction results, behavior pattern classification results and behavior pattern scores, and is stored in the database:

[0205] R i =(F,{P},M i );

[0206] Among them, R i represents the behavior pattern report of the i-th student, F represents the feature vector set, {P} represents the behavior pattern set, M i Indicates the behavioral pattern score.

[0207] S4. Establish a moral education evaluation model, conduct quantitative evaluation based on moral cognition, moral emotion and moral behavior, and generate comprehensive moral education evaluation results;

[0208] In this implementation, S4 specifically includes:

[0209] S41. Based on the multi-dimensional data of students, a moral education evaluation model is established and a moral education evaluation index system is defined, including three dimensions: moral cognition, moral emotion and moral behavior:

[0210]

[0211] Among them, I i represents the i-th evaluation index;

[0212] S42. Convert text data, behavior data and academic performance data into evaluation index vectors:

[0213]

[0214] in, represents the text data evaluation index vector of the i-th student, represents the evaluation index vector of the behavior data of the i-th student, represents the evaluation index vector of the academic performance data of the i-th student, x i is the eigenvalue, min(x) and max(x) are the minimum and maximum values ​​of the eigenvalue respectively;

[0215] S43. Use the support vector machine algorithm to quantitatively evaluate students' moral education performance and build an evaluation model:

[0216]

[0217] in, represents the weight vector, b represents the bias, C represents the penalty parameter, N represents the number of samples, and y irepresents the true label of the sample, Represents the feature vector of the i-th sample. By optimizing the objective function, the optimal weight vector is obtained. and bias b;

[0218] S44. Substitute each student's multi-dimensional data into the evaluation model to calculate the moral education performance score:

[0219]

[0220] Among them, S i represents the moral education performance score of the i-th student, represents the evaluation index vector of the i-th student, and the moral education performance score S i The value of represents the comprehensive performance of the student in all aspects of moral education;

[0221] S45. According to the scoring results, students are divided into different moral education performance levels:

[0222] G = {g1, g2, ..., gm};

[0223] Among them, g m represents the mth level of moral education performance;

[0224] S46. Generate a moral education evaluation report, the content of which includes an evaluation index vector, a moral education performance score and a moral education performance grade, and store it in a database:

[0225]

[0226] Among them, R i represents the moral education evaluation report of the i-th student, represents the evaluation index vector, S i represents the moral education performance score, g i Indicates the level of moral education performance.

[0227] S5. Through the intelligent evaluation system, personalized moral education feedback and suggestions are automatically generated to provide students with self-reflection and improvement, and provide guidance for teachers;

[0228] In this implementation, S5 specifically includes:

[0229] S51. Score based on moral education performance i Generate personalized moral education feedback and suggestions, conduct detailed analysis of students' moral education performance, and calculate the impact of each evaluation indicator's weight on the student's overall score:

[0230]

[0231] Among them, W i,jrepresents the weight influence of the jth evaluation index of the i-th student, V i,j represents the jth evaluation index value of the i-th student, w j represents the weight of the jth evaluation index, and n represents the total number of evaluation indicators;

[0232] S52. Generate a personalized feedback report based on the impact analysis results. The report includes the student's strengths, areas for improvement, and specific suggestions. The suggestions are generated based on the student's performance on various evaluation indicators:

[0233] R suggestion (i) = f(W i,1 ,W i,2 ,…,W i,n );

[0234] Among them, R suggestion (i) represents the feedback suggestions of the i-th student, and the function f affects the value W according to the student’s weight i,j Generate specific recommendations;

[0235] S53. Provide personalized moral education guidance and improvement plans, which are presented to students and teachers through intelligent systems. Personalized guidance includes behavioral suggestions and emotional development suggestions, which are stored in the database for easy access by students and teachers:

[0236] G i =(S i ,R suggestion (i));

[0237] Among them, G i Represents the personalized moral education guidance content of the i-th student, including the moral education performance score S i and personalized feedback suggestions R suggestion (i);

[0238] S54. Regularly update feedback and suggestions, and dynamically adjust according to students’ latest performance:

[0239]

[0240] Among them, ΔS i represents the change rate of the moral education performance score of the i-th student, Indicates the latest rating. represents the previous score, and T represents the time interval.

[0241] S6. During data processing and storage, data encryption and access control technologies are used to ensure the privacy and security of student data.

[0242] In this implementation, S6 specifically includes:

[0243] S61. In the process of data processing and storage, data encryption technology is used to protect the privacy and security of students' personal data. The data is encrypted using a symmetric encryption algorithm:

[0244] C i =E K (D i );

[0245] Among them, C i Indicates the encrypted data, E K Denotes the symmetric encryption algorithm, D i represents the original data, K represents the symmetric encryption key;

[0246] S62. During data transmission, an asymmetric encryption algorithm is used to encrypt and decrypt data:

[0247] C i =E pub (D i );

[0248] D i =D priv (C i );

[0249] Among them, E pub represents the public key encryption algorithm, D priv Denotes the private key decryption algorithm, D i represents the original data, C i Indicates encrypted data, pub indicates public key, and priv indicates private key;

[0250] S63. Perform access control on stored data, define access control policies, and implement them through the role-based access control model:

[0251] P = (U, R, PA, UA);

[0252] Among them, P represents the access control policy, U represents the user set, R represents the role set, PA represents the permission allocation set, and UA represents the user allocation set;

[0253] S64. Authenticate and authorize data access requests. The authentication process uses a hash function:

[0254] H i =H(U i +T);

[0255] Among them, H i represents the hash value, H represents the hash function, and U i represents user information, T represents timestamp;

[0256] S65. Audit and monitor data access records to promptly detect and handle abnormal access behaviors. The audit and monitoring process includes recording the user ID, access time, and access operations for each access:

[0257] A={(U i ,T i ,O i )|i=1,2,…,n};

[0258] Among them, A represents the audit log, U i Indicates user ID, T i Indicates the access time, O i Represents an access operation.

[0259] A college student moral education wisdom evaluation system based on an artificial intelligence college student moral education wisdom evaluation method, characterized by comprising:

[0260] The data collection module is used to collect students' text data, behavior data and academic performance data, including a web crawler interface, a student management system interface and a behavior data collection device;

[0261] The data processing module is used to preprocess and extract features from the collected data, including data cleaning, deduplication, missing value processing and formatting, as well as text segmentation, sentiment analysis and behavioral feature extraction;

[0262] The moral education evaluation module uses machine learning algorithms to conduct quantitative evaluation of processed data, establish a moral education evaluation model, and evaluate students' moral education performance, including the establishment of an evaluation index system, the calculation of moral education performance scores, and the classification of moral education performance levels;

[0263] The feedback generation module is used to generate personalized feedback and suggestions based on the moral education performance score, and generate a detailed moral education feedback report based on the student's specific performance, including strengths, areas for improvement and specific suggestions;

[0264] A data storage module is used to store processed data, evaluation results and feedback reports, including text data, behavior data, academic performance data, evaluation index vectors, moral education performance scores, moral education performance levels and feedback suggestions;

[0265] Data encryption and security module, responsible for encrypting and protecting data in the system and controlling access, including symmetric encryption algorithms, asymmetric encryption algorithms and role-based access control models;

[0266] The user interaction module provides an interactive interface for students and teachers to display moral education evaluation results and personalized feedback, supports querying and downloading feedback reports, and includes user authentication, permission control, and log auditing functions;

[0267] The system management module is responsible for the overall management and maintenance of the system, including user management, permission configuration, data backup and recovery, as well as system monitoring and troubleshooting.

[0268] Embodiment 1:

[0269] In order to verify the feasibility and effectiveness of the present invention, the college student moral education wisdom evaluation system of the present invention has been put into practical application in a certain university. The university is located in Beijing and has about 15,000 undergraduate students. Moral education is one of the focuses of the school's educational work. However, the traditional moral education evaluation method mainly relies on the subjective judgment of teachers and static evaluation standards, which has many shortcomings. In order to solve these problems, the school decided to adopt the intelligent moral education evaluation system of the present invention to improve the objectivity and comprehensiveness of moral education evaluation.

[0270] In the application scenario, the system first collected multi-dimensional data of students through the data collection module, including classroom performance, participation in volunteer activities, academic performance, social media postings, etc. These data were obtained through web crawler technology, school management system interface and behavior data collection device. During the data collection process, the system collected about 30,000 text data, 5,000 behavior records and 15,000 academic performance records.

[0271] The system uses the data processing module to clean and preprocess these data, remove noise and duplicate data, and analyze the text data in detail through natural language processing and sentiment analysis technology. The system extracts the characteristic vector of students' moral education performance and conducts quantitative evaluation through machine learning models. In order to evaluate the effectiveness of the system, the system selects 50 students as test samples and divides them into experimental and control groups. The data of the experimental group students are analyzed and fed back by the system of the present invention, while the control group still uses traditional subjective evaluation by teachers.

[0272] In specific applications, the system uses the support vector machine algorithm to score students' moral education performance and calculates the moral education performance score of each student. The experimental results show that the moral education performance scores of the experimental group of students are more accurate and objective, and the system's scores are highly correlated with the students' actual performance, while the scores of the control group are more subjective and biased. The personalized feedback reports generated by the system detail the students' strengths, weaknesses, and improvement suggestions. These reports not only provide specific behavioral suggestions, but also include emotional development suggestions to help students reflect on themselves and improve.

[0273] During the one-semester application, students in the experimental group generally reported that the feedback and suggestions provided by the system were of high reference value. The specific data are shown in Table 1 below:

[0274] Table 1 Comparison of moral education performance of students in the experimental group and the control group

[0275]

[0276]

[0277] As can be seen from Table 1 above, after applying the system of the present invention, the moral education performance scores of the students in the experimental group were significantly higher than those of the control group, and the feedback accuracy rate provided by the system was as high as 96.7%, with a false alarm rate of only 2.3%. In addition, the participation in volunteer activities and the enthusiasm for classroom performance of the students in the experimental group also increased significantly, by 15% and 10% respectively, which was much higher than the increase in the control group.

[0278] The data encryption and security module adopted by the system ensures the privacy and security of students' personal data. During the entire implementation process, the system strictly encrypted and protected the data, and no data leakage incidents occurred. The system uses symmetric encryption algorithms to store and encrypt data, and uses asymmetric encryption algorithms to protect data during transmission, and combines the role access control model to ensure that only authorized users can access and operate data.

[0279] The college students' moral education wisdom evaluation system of the present invention significantly improves the objectivity, comprehensiveness and efficiency of moral education evaluation in practical applications, and effectively solves the subjective and static problems in traditional evaluation methods. The system can not only provide accurate moral education performance scores, but also provide personalized feedback and guidance according to the actual situation of students, helping students to better develop their own moral education literacy. At the same time, the high-security design of the system ensures the privacy and integrity of the data, and ensures the security of data processing and transmission. Through these beneficial effects, the system provides strong technical support and guarantee for the moral education work of colleges and universities.

[0280] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for evaluating college students' moral education wisdom based on artificial intelligence, characterized in that: The steps include: S1. Through the data collection module, comprehensively collect students' text data, behavioral data and academic performance information to establish a multi-dimensional data set; S2. Use natural language processing and sentiment analysis techniques to conduct semantic analysis on student text data, extract keywords, classify sentiment tendencies, and identify positive, negative, and neutral sentiments; S3, conduct data mining on student behavior data, identify and extract behavior patterns, and conduct classification and cluster analysis; S4. Establish a moral education evaluation model, conduct quantitative evaluation based on moral cognition, moral emotion and moral behavior, and generate comprehensive moral education evaluation results; S5. Through the intelligent evaluation system, personalized moral education feedback and suggestions are automatically generated to provide students with self-reflection and improvement, and provide guidance for teachers; S6. During data processing and storage, data encryption and access control technologies are used to ensure the privacy and security of student data.

2. According to the method for evaluating college students' moral education wisdom based on artificial intelligence in claim 1, it is characterized by: The S1 specifically includes: S11. Collect student text data, including students’ essays, papers, social media posts, and other written expressions, through web crawler technology and student management system interfaces: T={t1,t2,…,t n }; Among them, t i Represents the i-th text data; S12. Obtain student behavior data through a behavior data collection device, including library borrowing records, class attendance records, extracurricular activity participation records, and volunteer service records: B={b1,b2,…,b m }; Among them, b j represents the jth behavior data; S13. Obtain students’ academic performance information through the academic information collection module, including subject performance, course selection, academic competition results and scientific research achievements: <h2 style=";text-align:left;direction:ltr">A = {a1,a2,…,a<h2 style=";text-align:left;direction:ltr"> k <h2 style=";text-align:left;direction:ltr">}; Among them, a l represents the lth academic achievement data; S14. During the data collection process, pre-process the data: Among them, d i,j Represents the original data, represents the normalized data, min(d i ) and max(d i ) represent the minimum and maximum values ​​of the i-th category data respectively; S15. Store the processed text data, behavior data and academic performance information in the database and use big data technology to perform structured storage and management of the data: D={(T i ,B i ,A i )∣i=1,2,…,N}; Where D represents the database, N represents the number of students, and T i ,B i ,A i Respectively represent the text data, behavior data and academic performance data of the i-th student; S16. Label the data and build a multi-dimensional data set. The data of each student is represented as a vector And define the tag collection: L＝{l1,l2,…,l p}； Among them, l p represents the pth label; S17. In the process of data storage and transmission, data encryption technology is adopted, using symmetric encryption algorithms and asymmetric encryption algorithms: C=E K (M); Among them, M represents plaintext data, K represents the key, and E K represents the encryption function, and C represents the ciphertext data.

3. According to the method for evaluating college students' moral education wisdom based on artificial intelligence in claim 1, it is characterized in that: The S2 specifically includes: S21, for the student text data set T = {t1, t2, ..., t n }, the processed text data is represented by T′={t′1,t′2,…,t′ n }; Among them, t′ i Represents the i-th processed text data; S22. Use natural language processing technology to perform semantic analysis on the pre-processed text data and extract a set of keywords: K={k1,k2,…,k m }; Among them, k j represents the jth keyword; Keyword extraction is performed by calculating term frequency-inverse document frequency TF-IDF: Among them, DF(k j ) indicates keyword k j In the text t' i The word frequency in, N represents the total number of text data, DF(k j Indicates that it contains the keyword k j The number of texts; S23. Perform sentiment analysis to classify text data into positive, negative, and neutral sentiments: S(t' i )=argmax c∈{pos,neg,neu} P(c|t' i ); Among them, S(t' i ) represents the text t' i The sentiment classification result of , c represents the sentiment category, including positive pos, negative neg and neutral neu, P(c|t′ i ) represents the text t′ i The probability of belonging to sentiment category c; S24. Calculate the overall sentiment tendency score of each student: Among them, E i represents the overall sentiment score of the i-th student, n i represents the number of texts of the student, S(t j ′) represents the sentiment score of the jth text, and the sentiment score is assigned 1, -1 and 0 according to positive, negative and neutral respectively; S25. Generate a student sentiment analysis report based on the sentiment analysis results. The report content includes keyword extraction results, sentiment classification results and sentiment tendency scores, and is stored in the database: ″′ R i =(K,{S(t1),S(t2),…,S(t n )},E i ); Among them, R i represents the sentiment analysis report of the i-th student, K represents the keyword set, {S(t′1), S(t′2),…, S(t′ n )} represents the sentiment classification result of each text of the student, E i Represents the overall sentiment tendency score.

4. According to the method for evaluating college students' moral education wisdom based on artificial intelligence in claim 1, it is characterized in that: The S3 specifically includes: S31, for the student behavior data set B = {b1, b2, ..., b m } is preprocessed, and the processed behavior data is expressed as B′={b′1,b′2,…,b′ m }; Among them, b j ′ represents the jth preprocessed behavior data; S32, extracting features from the preprocessed behavior data to extract feature vectors: F j ={f j1 ,f j2 ,…,f jn }; Among them, F j represents the feature vector of the jth behavior data, f jk represents the kth eigenvalue; S33. Use cluster analysis to perform cluster analysis on feature vectors and identify behavior patterns: Among them, m represents the total number of behavioral data, c j represents the cluster label of the jth eigenvector, Indicates the c j The centers of the clusters, Denotes the eigenvector F j The cluster center The Euclidean distance between S34. Based on the clustering results, identify the typical behavior patterns of students: P={p1,p2,…,p q }; Among them, p q represents the qth identified behavior pattern; S35. Calculate the behavior pattern score for each student: Among them, M i represents the behavior pattern score of the i-th student, Q represents the total number of identified behavior patterns, and w q represents the weight of the qth behavior pattern, I(p q |F i ) represents the i-th student and behavior pattern p q The matching function of S36. Generate a student behavior pattern report based on the behavior pattern analysis results. The report content includes feature extraction results, behavior pattern classification results and behavior pattern scores, and is stored in the database: R i =(F,{P},M i ); Among them, R i represents the behavior pattern report of the i-th student, F represents the feature vector set, {P} represents the behavior pattern set, M i Indicates the behavioral pattern score.

5. According to the method for evaluating college students' moral education wisdom based on artificial intelligence in claim 1, it is characterized in that: The S4 specifically includes: S41. Based on the multi-dimensional data of students, a moral education evaluation model is established and a moral education evaluation index system is defined, including three dimensions: moral cognition, moral emotion and moral behavior: Among them, I i represents the i-th evaluation index; S42. Convert text data, behavior data and academic performance data into evaluation index vectors: in, represents the text data evaluation index vector of the i-th student, represents the evaluation index vector of the behavior data of the i-th student, represents the evaluation index vector of the academic performance data of the i-th student, x i is the eigenvalue, min(x) and max(x) are the minimum and maximum values ​​of the eigenvalue respectively; S43. Use the support vector machine algorithm to quantitatively evaluate students' moral education performance and build an evaluation model: in, represents the weight vector, b represents the bias, C represents the penalty parameter, N represents the number of samples, and y i represents the true label of the sample, Represents the feature vector of the i-th sample. By optimizing the objective function, the optimal weight vector is obtained. and bias b; S44. Substitute each student's multi-dimensional data into the evaluation model to calculate the moral education performance score: Among them, S i represents the moral education performance score of the i-th student, represents the evaluation index vector of the i-th student, and the moral education performance score S i The value of represents the comprehensive performance of the student in all aspects of moral education; S45. According to the scoring results, students are divided into different moral education performance levels: G={g1,g2,…,g m }; Among them, g m represents the mth level of moral education performance; S46. Generate a moral education evaluation report, the content of which includes an evaluation index vector, a moral education performance score and a moral education performance grade, and store it in a database: Among them, R i represents the moral education evaluation report of the i-th student, represents the evaluation index vector, S i represents the moral education performance score, g i Indicates the level of moral education performance.

6. According to the method of evaluating college students' moral education wisdom based on artificial intelligence in claim 1, it is characterized by: The S5 specifically includes: S51. Score based on moral education performance i Generate personalized moral education feedback and suggestions, conduct detailed analysis of students' moral education performance, and calculate the impact of each evaluation indicator's weight on the student's overall score: Among them, W i,j represents the weight influence of the jth evaluation index of the i-th student, V i,j represents the jth evaluation index value of the i-th student, w j represents the weight of the jth evaluation index, and n represents the total number of evaluation indicators; S52. Generate a personalized feedback report based on the impact analysis results. The report includes the student's strengths, areas for improvement, and specific suggestions. The suggestions are generated based on the student's performance on various evaluation indicators: R suggestion (i)=f(W i,1 ,W i,2 ,…,W i,n ); Among them, R suggestion (i) represents the feedback suggestions of the i-th student, and the function f affects the value W according to the student’s weight i,j Generate specific recommendations; S53. Provide personalized moral education guidance and improvement plans, which are presented to students and teachers through intelligent systems. Personalized guidance includes behavioral suggestions and emotional development suggestions, which are stored in the database for easy access by students and teachers: G i =(S i ,R suggestion (i)); Among them, G i Represents the personalized moral education guidance content of the i-th student, including the moral education performance score S i and personalized feedback suggestions R suggestion (i); S54. Regularly update feedback and suggestions, and dynamically adjust according to students’ latest performance: Among them, ΔS i represents the change rate of the moral education performance score of the i-th student, Indicates the latest rating. represents the previous score, and T represents the time interval.

7. According to the artificial intelligence-based method for evaluating college students' moral education wisdom, the method is characterized by: The S6 specifically includes: S61. In the process of data processing and storage, data encryption technology is used to protect the privacy and security of students' personal data. The data is encrypted using a symmetric encryption algorithm: C i =E K (Tue); Among them, C i Indicates the encrypted data, E K Denotes the symmetric encryption algorithm, D i represents the original data, K represents the symmetric encryption key; S62. During data transmission, an asymmetric encryption algorithm is used to encrypt and decrypt data: C i =E pub (D i ); D i =D priv (C i ); Among them, E pub represents the public key encryption algorithm, D priv Denotes the private key decryption algorithm, D i represents the original data, C i Indicates encrypted data, pub indicates public key, and priv indicates private key; S63. Perform access control on stored data, define access control policies, and implement them through the role-based access control model: P = (U, R, PA, UA); Among them, P represents the access control policy, U represents the user set, R represents the role set, PA represents the permission allocation set, and UA represents the user allocation set; S64. Authenticate and authorize data access requests. The authentication process uses a hash function: H i =H(U i +T); Among them, H i represents the hash value, H represents the hash function, and U i represents user information, T represents timestamp; S65. Audit and monitor data access records to promptly detect and handle abnormal access behaviors. The audit and monitoring process includes recording the user ID, access time, and access operations for each access: A={(U i ,T i ,O i )∣i=1,2,…,n}; Among them, A represents the audit log, U i Indicates user ID, T i Indicates the access time, O i Represents an access operation.

8. A college student moral education wisdom evaluation system based on an artificial intelligence-based college student moral education wisdom evaluation method as claimed in any one of claims 1 to 7, characterized in that: include: The data collection module is used to collect students' text data, behavior data and academic performance data, including a web crawler interface, a student management system interface and a behavior data collection device; The data processing module is used to preprocess and extract features from the collected data, including data cleaning, deduplication, missing value processing and formatting, as well as text segmentation, sentiment analysis and behavioral feature extraction; The moral education evaluation module uses machine learning algorithms to conduct quantitative evaluation of processed data, establish a moral education evaluation model, and evaluate students' moral education performance, including the establishment of an evaluation index system, the calculation of moral education performance scores, and the classification of moral education performance levels; The feedback generation module is used to generate personalized feedback and suggestions based on the moral education performance score, and generate a detailed moral education feedback report based on the student's specific performance, including strengths, areas for improvement and specific suggestions; A data storage module is used to store processed data, evaluation results and feedback reports, including text data, behavior data, academic performance data, evaluation index vectors, moral education performance scores, moral education performance levels and feedback suggestions; Data encryption and security module, responsible for encrypting and protecting data in the system and controlling access, including symmetric encryption algorithms, asymmetric encryption algorithms and role-based access control models; The user interaction module provides an interactive interface for students and teachers to display moral education evaluation results and personalized feedback, supports querying and downloading feedback reports, and includes user authentication, permission control, and log auditing functions; The system management module is responsible for the overall management and maintenance of the system, including user management, permission configuration, data backup and recovery, as well as system monitoring and troubleshooting.

Images