Method and system for comprehensive education evaluation based on smart education AI model

Abstract

The present invention provides a method and system for comprehensive education evaluation based on a smart education AI model. The system monitors the education evaluation data obtained by teachers on students in a dynamic teaching environment, and combines the teaching performance data. The smart education AI model identifies the data features in the education data, and intelligently matches and outputs the characteristic scores including academic performance, morality and physical education, and generates the education evaluation results of the students. Therefore, it is possible to conduct a comprehensive evaluation in combination with the students' moral, intellectual and physical qualities, avoid over-reliance on standardized tests to conduct a single teaching evaluation on students, avoid ignoring the comprehensive education assessment of students due to the lack of physical and moral evaluation, and achieve the comprehensiveness and comprehensiveness of education evaluation. Through dynamic evaluations that are not final or mid-term, the progress of students' learning, physical education and moral development in school can be tracked at any time, so that the evaluation results fully reflect the students' learning process; and the intelligent evaluation system can reduce the burden of teaching evaluation on teachers.

Description

Technical Field

[0001] The present invention relates to the field of intelligent education technology, and in particular to a method for comprehensive education evaluation based on a smart education AI model, a comprehensive education evaluation system, an electronic device and a computer-readable storage medium. Background Art

[0002] The role of educational evaluation is mainly reflected in the following aspects: First, it can provide a basis for educational decision-making, help educational managers understand the effectiveness and quality of educational activities, and make more reasonable decisions. Second, educational evaluation can promote the professional development of teachers. Through the evaluation results, teachers can understand their teaching effects and adjust teaching methods and content. Third, educational evaluation can serve as feedback on learning outcomes for students, helping them recognize their strengths and areas for improvement. Finally, educational evaluation can also enhance the transparency of education and the public's trust in the quality of education.

[0003] The traditional education evaluation methods mainly include examinations and tests, homework and projects, observation and record keeping, self-evaluation and peer evaluation, etc. The traditional education evaluation method mainly relies on teachers to evaluate students' learning and physical education performance. Although it can evaluate students at the end of the semester, this traditional education evaluation and assessment method still has the following shortcomings:

[0004] 1. Over-reliance on standardized tests: This may lead to educational evaluation relying almost entirely on final scores and rankings, while neglecting the comprehensive development of students and the cultivation of their innovative abilities in their daily learning process;

[0005] 2. Ignoring non-intellectual factors: Traditional evaluation methods often only focus on students’ knowledge mastery, but not enough on non-intellectual factors such as students’ creativity, critical thinking, and cooperative spirit;

[0006] 3. Inappropriate timing and frequency of evaluation: Evaluation is often concentrated at the end of the semester or at a specific time point, and it is not possible to continuously track students' academic, physical and moral development progress at school (anytime and anywhere), resulting in evaluation results that cannot fully reflect students' learning process;

[0007] 4. Low efficiency of teaching evaluation for students: Currently, the evaluation mainly relies on the participation of teachers, which requires teachers to perform manual ratings or the system to evaluate according to the grade evaluation rules configured at the end of the semester or at special nodes. Therefore, it is impossible to conduct intelligent evaluation of students' long-term learning progress, and it is impossible to overcome the inefficiency brought by teacher evaluation and the rigidity of the system's static evaluation. Summary of the invention

[0008] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions:

[0009] On the one hand, a method for comprehensive education evaluation based on a smart education AI model is provided, the method being implemented by an electronic device, and the method comprising:

[0010] S1. The backend server monitors and collects the educational evaluation data obtained by students in different dynamic teaching environments in real time;

[0011] S2. Record the education evaluation data under the identity ID of the corresponding student through the student management module and save it in the background database;

[0012] S3. When the node management module determines that the preset teaching evaluation node is reached, the education node data of the student at this time is read, including: education evaluation data and teaching performance data, and the education node data is imported into the preset smart education AI model;

[0013] S4, the smart education AI model identifies the data features in the education node data, and intelligently matches and outputs feature scores including academic performance, morality and sports;

[0014] S5. Write each of the characteristic scores into the evaluation module, and the evaluation module generates the student's education evaluation results based on each of the characteristic scores.

[0015] As a preferred embodiment of the present invention, preferably, the method further comprises:

[0016] After generating the educational evaluation results of the students, the educational evaluation results of the students are shared to the teaching management system;

[0017] The teaching management system records the educational evaluation results of the students and saves them in the background database;

[0018] When the teaching of this semester is completed, all the educational evaluation results obtained by the students at various teaching evaluation nodes of this semester are counted, and weighted average calculation is performed to obtain the educational evaluation score of the students in this semester;

[0019] Writing the education evaluation score into a preset education evaluation template, generating an education evaluation report for the student, and recording the education evaluation report under the identity ID of the corresponding student, and storing it in the background database;

[0020] At the same time, the education evaluation report is forwarded to the teacher end and the student end respectively.

[0021] As a preferred implementation scheme of the present invention, preferably, S1, the background server monitors and collects the education evaluation data obtained by students in different dynamic teaching environments in real time, including:

[0022] Establishing a communication connection between the teacher terminal and the backend server;

[0023] The teacher generates the educational evaluation data of the students in different dynamic teaching environments through the teacher terminal and reports it to the backend server in real time. The dynamic teaching environment includes classroom teaching, extracurricular activities and online teaching activities;

[0024] The backend server monitors the teaching activity data uploaded by the teacher in real time, and analyzes whether the teaching activity data contains the educational evaluation data for evaluating the students:

[0025] If yes, then identify the student's ID and forward it to the student management module together with the corresponding education evaluation data;

[0026] Otherwise, continue monitoring.

[0027] As a preferred embodiment of the present invention, preferably, the parsing and analyzing whether the teaching activity data contains the educational evaluation data for evaluating students includes:

[0028] Preprocessing the educational evaluation data, including cleaning, format conversion or voice-to-text conversion;

[0029] Calling a large language model to perform text analysis on the preprocessed education evaluation data, and identifying whether the education evaluation data contains student names and keyword text information related to the education evaluation:

[0030] If yes, then output the student's name and keyword text information related to the educational evaluation;

[0031] Otherwise give up.

[0032] As a preferred embodiment of the present invention, preferably, before calling the large language model, it also includes:

[0033] Collect students’ basic information and education evaluation data sets;

[0034] Importing the basic information of students and the educational evaluation data set into the large language model, and performing secondary training and learning of the model, so that the large language model learns the names of each student and each keyword text information related to the educational evaluation;

[0035] A cloud API is configured on the background server for calling the large language model.

[0036] As a preferred embodiment of the present invention, preferably, the method for generating the smart education AI model includes:

[0037] Preparing big data of educational information of several students, including: a first mapping data set of academic performances of different score ranges and corresponding evaluation scores, a second mapping data set of sports performances of different score ranges and corresponding evaluation scores, and a third mapping data set of moral comments of different degrees and corresponding evaluation scores;

[0038] Performing feature engineering on the education information big data, analyzing and extracting a first mapping relationship feature in the first mapping data set, a second mapping relationship feature in the second mapping data set, and a third mapping relationship feature in the third mapping data set;

[0039] Constructing a feature set including the first mapping relationship feature, the second mapping relationship feature and the third mapping relationship feature, and dividing the feature set into a training set Pa and a validation set Pb according to a preset ratio;

[0040] Importing the training set Pa into the initial RNN model, and performing feature training and learning on each mapping relationship feature in the training set Pa through the RNN model;

[0041] After the training and learning is completed, the initial smart education AI model for education evaluation is obtained, and the model performance of the initial smart education AI model for education evaluation is verified using the verification set Pb;

[0042] If the verification is successful, the smart education AI model is deployed on the background server.

[0043] As a preferred embodiment of the present invention, preferably, S4, the smart education AI model identifies the data features in the education node data, and intelligently matches and outputs the feature scores including academic performance, morality and sports, including:

[0044] The smart education AI model identifies the learning performance in the teaching performance data, and matches and outputs a first feature score corresponding to the learning performance according to the first mapping relationship;

[0045] The smart education AI model identifies the physical education scores in the teaching score data, and matches and outputs a second feature score corresponding to the physical education scores according to the second mapping relationship;

[0046] The smart education AI model identifies the evaluation degree of the moral comments in the teaching performance data, and matches and outputs a third feature score corresponding to the evaluation degree according to a third mapping relationship;

[0047] The first feature score, the second feature score and the third feature score are bound to the teaching evaluation node of this time, and the evaluation data packet of this time is obtained and sent to the evaluation module.

[0048] On the other hand, a comprehensive education evaluation system is provided, and the comprehensive education evaluation system is used to implement the method for comprehensive education evaluation based on the smart education AI model, and the system includes:

[0049] The teacher side is used to generate the educational evaluation data of students in different dynamic teaching environments and report it to the backend server in real time; and to view the educational evaluation report of students;

[0050] The backend server is used to monitor the teaching activity data uploaded by the teacher in real time, and parse and analyze whether the teaching activity data contains the educational evaluation data for evaluating students:

[0051] If yes, the student's ID is identified and forwarded to the student management module together with the corresponding education evaluation data;

[0052] Otherwise, continue to monitor;

[0053] The backend server comprises:

[0054] The student management module is used to record the education evaluation data under the identity ID of the corresponding student and save it in the background database;

[0055] Teaching management system, used to manage students' teaching performance data;

[0056] The node management module is used to monitor and determine whether the system has reached the preset teaching evaluation node. If it has, it reads the student's education node data at this time, including: education evaluation data and teaching performance data, and imports the education node data into the preset smart education AI model;

[0057] Smart education AI model, used to identify data features in the education node data, and intelligently match and output feature scores including academic performance, morality and sports;

[0058] An evaluation module, used to write each of the characteristic scores, and generate the student's education evaluation results according to each of the characteristic scores, and share the student's education evaluation results to the teaching management system;

[0059] Backend database, used for data storage;

[0060] The teaching management system is also used to record the education evaluation results of the students and save them in the background database; when the teaching of this semester is completed, all the education evaluation results obtained by the students at various teaching evaluation nodes in this semester are counted, and a weighted average calculation is performed to obtain the students' education evaluation scores in this semester; the education evaluation scores are written into a preset education evaluation template, an education evaluation report for the students is generated, and the education evaluation report is recorded under the corresponding student's identity ID and saved in the background database; at the same time, the education evaluation report is forwarded to the teacher end and the student end respectively.

[0061] Student side, used to view education evaluation reports;

[0062] The teacher terminal and the student terminal are respectively connected to the backend server for communication.

[0063] On the other hand, an electronic device is provided, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the methods for comprehensive education evaluation based on the smart education AI model is implemented.

[0064] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement any of the above-mentioned methods for comprehensive education evaluation based on the smart education AI model.

[0065] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0066] The present invention uses the system background server to monitor the education evaluation data obtained by teachers on students in a dynamic teaching environment in real time, combined with the student teaching and physical education scores recorded by the teaching management system. When the preset teaching evaluation node is reached, the system will read the education evaluation data and teaching performance data obtained by the student at the time of the teaching evaluation node, and input the smart education AI model to identify the data features in the education node data, and intelligently match and output the characteristic scores including academic performance, morality and physical education, and generate the student's education evaluation results according to each of the characteristic scores. Therefore, it is possible to monitor the student's full educational progress, and conduct a comprehensive assessment in combination with the student's moral, intellectual and physical qualities, and use the intelligent model to output the student's evaluation value to generate the student's evaluation result, which can avoid over-reliance on standardized tests and single teaching evaluation of students, avoid the lack of physical and moral evaluation and neglect of students' comprehensive education assessment, and achieve the comprehensiveness and comprehensiveness of education evaluation.

[0067] The present invention can track students' progress in learning, physical education and morality at school at any time through non-final or mid-term dynamic evaluation, so that the evaluation results fully reflect the students' learning process; and the intelligent evaluation system can reduce the teaching evaluation burden of teachers. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0069] Figure 1 It is a flow chart of a method for comprehensive education evaluation based on a smart education AI model provided by an embodiment of the present invention;

[0070] Figure 2 is a block diagram of an education comprehensive evaluation system provided by an embodiment of the present invention;

[0071] Figure 3 is a schematic diagram of node management of an exemplary education evaluation node provided in an embodiment of the present invention;

[0072] Figure 4 This is a schematic diagram of RNN model training provided by an embodiment of the present invention;

[0073] Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0074] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0075] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0076] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0077] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0078] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0079] Example 1

[0080] The embodiment of the present invention provides a method for comprehensive education evaluation based on a smart education AI model, which can be implemented by an electronic device, which can be a terminal or a server. Figure 1 The flowchart of the method for comprehensive education evaluation based on the smart education AI model is shown in the figure. The processing flow of the method may include the following steps:

[0081] S1. The backend server monitors and collects the educational evaluation data obtained by students in different dynamic teaching environments in real time;

[0082] S2. Record the education evaluation data under the identity ID of the corresponding student through the student management module and save it in the background database;

[0083] S3. When the node management module determines that the preset teaching evaluation node is reached, the education node data of the student at this time is read, including: education evaluation data and teaching performance data, and the education node data is imported into the preset smart education AI model;

[0084] S4, the smart education AI model identifies the data features in the education node data, and intelligently matches and outputs feature scores including academic performance, morality and sports;

[0085] S5. Write each of the characteristic scores into the evaluation module, and the evaluation module generates the student's education evaluation results based on each of the characteristic scores.

[0086] The present invention uses the system background server to monitor the education evaluation data obtained by teachers in a dynamic teaching environment in real time, combined with the student teaching and physical education scores recorded by the teaching management system. When the preset teaching evaluation node is reached, the system will read the education evaluation data and teaching performance data obtained by the student at the teaching evaluation node, and input the smart education AI model to identify the data features in the education node data, and intelligently match and output the feature scores including academic performance, morality and physical education, and generate the student's education evaluation results according to each of the feature scores. Finally, the teaching management system generates the final student education evaluation report based on the student's education evaluation results this semester.

[0087] like Figure 2 As shown, in combination with the application system of the present invention, in different dynamic teaching environments, such as when students are in classroom teaching, extracurricular activities or online teaching activities, teachers can conduct moral evaluation of students through the teacher terminal (PC terminal or teacher APP) and upload corresponding education evaluation data.

[0088] Educational evaluation data can be a teacher's written evaluation of a student (for example, Student A performs well in class XX and behaves properly. This evaluation corresponds to moral comments of varying degrees of goodness, and the model in the system can match it with an evaluation score of the corresponding degree, such as 6-8 points) (total score 10 points). Please refer to the subsequent training and application principles of the AI ​​model for details.

[0089] Educational evaluation data can also be the teacher's voice evaluation of students. For example, if the teacher finds that student A performs well outside of class (such as automatically cleaning the classroom), the teacher can conduct a moral evaluation on the student on the spot. The teacher can input the corresponding evaluation voice on the teacher side. For example, input a voice message saying that student A has done a general cleaning and has excellent moral behavior. The voice can then be uploaded to the backend server, which will parse the voice, identify the student's name and evaluation content, and thereby obtain the educational evaluation data for the student.

[0090] The communication connection between the teacher end and the background server can be TCP communication mode or IP communication mode; similarly, the student end can be PC end or APP, and students can log in to the background server through the student end to view corresponding reports, etc.

[0091] A student management module, a teaching management system, etc. are deployed on the background server. The student management module can manage the basic information of each student. After the system monitors the teacher's education evaluation data on the student, it will be recorded and bound to the student's identity ID, and the education evaluation data (mainly moral evaluation data) obtained by the student at different teaching evaluation nodes will be recorded. The teaching management system can manage the student's teaching work, including recording the student's academic performance, physical education performance, and other literacy records (which can be automatically converted into corresponding learning bonus points by the system rules and superimposed on the academic performance), etc. Therefore, when the node management module judges that the time point where the teaching evaluation node set by the administrator is reached, the teaching intelligent evaluation program of the present invention will be activated.

[0092] Intelligent teaching evaluation program: The node management module reads the academic performance, physical performance and education evaluation data bound to the student identity ID from the student management module and the teaching management system, and imports the education node data of morality, intelligence and physical fitness into the smart education AI model. The AI ​​model identifies the data features and matches the academic performance, morality and physical characteristics scores corresponding to the data features (see the subsequent model training and learning process for details).

[0093] The evaluation module will calculate the comprehensive education score (education evaluation result) of the students based on the characteristic scores of academic performance, morality and physical education, and bind it to the teaching evaluation node. For example, if the characteristic scores of academic performance, morality and physical education are 8, 9 and 8 respectively, the comprehensive score obtained by the students at this node will be calculated by weight: a8+b9+c8. abc can be constructed according to the school's attention to morality, intelligence and physical education, such as 0.3, 0.4 and 0.3 respectively. The weight of morality needs to account for at least 35% to improve quality education.

[0094] The teaching management system will record the comprehensive education scores of students at each teaching evaluation node this semester, and perform weighted average calculation again to obtain the final education evaluation score of the students in this semester, and generate an education evaluation report for the students based on this.

[0095] In this solution, AI models are used to comprehensively evaluate students’ moral, intellectual and physical qualities, output corresponding feature scores, and the evaluation module performs weighted calculations based on the feature scores. This allows for intelligent evaluation of students’ comprehensive teaching evaluation results of moral, intellectual and physical qualities at each teaching evaluation node, completes education evaluation of students at different evaluation stages and different evaluation time nodes, enables teachers to participate in dynamic evaluation of students, and increases teachers’ dynamic tracking of student development.

[0096] Therefore, it is possible to monitor the students' progress throughout the entire educational process, conduct a comprehensive assessment based on their moral, intellectual and physical qualities, and use intelligent models to output the students' evaluation values, thereby generating student evaluation results. This can avoid over-reliance on standardized tests and conducting a single teaching evaluation of students, avoid neglecting students' comprehensive educational assessment due to the lack of physical and moral evaluations, and achieve comprehensiveness and comprehensiveness of educational evaluation.

[0097] As a preferred embodiment of the present invention, preferably, the method further comprises:

[0098] After generating the educational evaluation results of the students, the educational evaluation results of the students are shared to the teaching management system;

[0099] The teaching management system records the educational evaluation results of the students and saves them in the background database;

[0100] When the teaching of this semester is completed, all the educational evaluation results (comprehensive educational scores) obtained by students at various teaching evaluation nodes of this semester are counted, and weighted average calculation is performed to obtain the educational evaluation scores of students in this semester;

[0101] Writing the education evaluation score into a preset education evaluation template, generating an education evaluation report for the student, and recording the education evaluation report under the identity ID of the corresponding student, and storing it in the background database;

[0102] At the same time, the education evaluation report is forwarded to the teacher end and the student end respectively.

[0103] like Figure 3 In the example node evaluation shown, the teaching evaluation node can be the teaching day or teaching week set by the corresponding administrator, or it can be a month. For example, collect the teaching data of students every day (August 5 and every day thereafter), or the teaching data of each week (such as the node every Friday), or the teaching data of each month (28th, 29th or 30th). The specific daily, weekly and monthly teaching evaluation nodes are set by the administrator, and it is preferred to set them to weekly, which can further refine the collection information of students' educational data at school.

[0104] The teaching management system can record the evaluation scores of students in each moral, intellectual and physical assessment. Therefore, students can get several education evaluation results in this semester. The teaching management system performs a weighted average calculation on the education evaluation results obtained by students at each assessment node to obtain the comprehensive education evaluation score of the students in this semester. When performing the weighted average calculation, the weights of the comprehensive education scores obtained at special teaching evaluation nodes can be specially set (for example, other daily nodes are set to a weight of 0.05, and monthly nodes are set to 0.15). For example, the weight coefficient of the comprehensive education score obtained in the monthly exam is specifically set to highlight its importance in this evaluation.

[0105] By taking a weighted average of the comprehensive education scores obtained by students at all nodes in this semester, the students' final comprehensive education evaluation scores for this semester are obtained and written into the education evaluation template (which is a blank template) pre-configured in the teaching management system. The students' final education evaluation scores for this semester are written into the education evaluation template to generate the students' final education evaluation report, which is shared by the teaching management system to the teacher and student ends.

[0106] The education evaluation template can be constructed and configured by the administrator, or the large language model (in order to save the background operation pressure, the third-party cloud model is called) can be used to generate teaching comments containing the student's education evaluation score, and the comments are written into the education evaluation template. In this way, according to the education level reflected by the different education evaluation scores of each student, the corresponding level (degree) of education comments can be output to achieve personalized evaluation.

[0107] As a preferred implementation scheme of the present invention, preferably, S1, the background server monitors and collects the education evaluation data obtained by students in different dynamic teaching environments in real time, including:

[0108] Establishing a communication connection between the teacher terminal and the backend server;

[0109] The teacher generates the educational evaluation data of the students in different dynamic teaching environments through the teacher terminal and reports it to the backend server in real time. The dynamic teaching environment includes classroom teaching, extracurricular activities and online teaching activities;

[0110] The backend server monitors the teaching activity data uploaded by the teacher in real time, and analyzes whether the teaching activity data contains the educational evaluation data for evaluating students:

[0111] If yes, then identify the student's ID and forward it to the student management module together with the corresponding education evaluation data;

[0112] Otherwise, continue monitoring.

[0113] Teachers can report students' teaching activity data to the backend at any time through the teacher terminal. The backend needs to parse and analyze the teaching activity data to identify the educational evaluation data containing the evaluation of students (that is, data monitoring and analysis). If the teaching activity data uploaded by the teacher contains educational evaluation data of the evaluation of students, it will be parsed and analyzed to identify the identity of the evaluated students and the evaluation content, which will be used for subsequent moral evaluation.

[0114] As a preferred embodiment of the present invention, preferably, the parsing and analyzing whether the teaching activity data contains the educational evaluation data for evaluating students includes:

[0115] Preprocessing the educational evaluation data, including cleaning, format conversion or voice-to-text conversion (because it may be text data or voice data, it is necessary to perform corresponding format conversion, voice-to-text conversion and other preprocessing);

[0116] Calling a large language model to perform text analysis on the preprocessed education evaluation data, and identifying whether the education evaluation data contains student names and keyword text information related to the education evaluation:

[0117] If so, output the student's name and keyword text information related to the educational evaluation;

[0118] Otherwise give up.

[0119] The present invention uses the cloud API configured on the backend server to call the third-party large language model to intelligently identify the education evaluation data, extract each keyword text, and determine whether there is a student's name and keywords related to education evaluation. Large language models, such as Baidu's Wenyan Yixin large model, can be trained twice to recognize student names and related evaluation keywords.

[0120] The recognition steps of the large language model can refer to the following steps:

[0121] 1. Determine the target text: First, clarify the content of the text to be analyzed and ensure that the text has enough information for the model to recognize.

[0122] 2. Text preprocessing: Clean the target text, including removing irrelevant characters, punctuation marks, unifying capitalization, etc., to improve the accuracy of keyword recognition.

[0123] 3. Select a keyword recognition model: Select a suitable large language model according to your needs, such as BERT and GPT based on deep learning. These models can understand the context and effectively identify keywords.

[0124] 4. Input text into the model: Input the preprocessed text into the selected language model to extract keywords.

[0125] 5. Model analysis: The model analyzes the text content and identifies key words or phrases in the text. These key words are usually related to the theme or core concepts of the text.

[0126] 6. Result output: The keywords identified by the model are output in the form of a list, and the relevance score or importance ranking of the keywords is usually provided.

[0127] 7. Application of results: Carry out subsequent information processing based on the identified keywords, such as text classification, information retrieval, content summarization, etc.

[0128] Through the large language model, it is possible to identify whether there is a student's name and key words related to education evaluation text information, and quickly identify and record the student's evaluation information, so that the background can monitor and collect student evaluation data in real time. After the background monitors the information uploaded by the classroom, it calls the large language model for intelligent analysis and data screening to improve the rapid identification of student evaluation data.

[0129] As a preferred embodiment of the present invention, preferably, before calling the large language model, it also includes:

[0130] Collect students’ basic information and education evaluation data sets;

[0131] Importing the basic information of students and the educational evaluation data set into the large language model, and performing secondary training and learning of the model, so that the large language model learns the names of each student and each keyword text information related to the educational evaluation;

[0132] A cloud API is configured on the background server for calling the large language model.

[0133] like Figure 4 The RNN model training process shown is a preferred embodiment of the present invention. Preferably, the method for generating the smart education AI model includes:

[0134] Preparing big data of educational information of several students, including: a first mapping data set of academic performances of different score ranges and corresponding evaluation scores, a second mapping data set of sports performances of different score ranges and corresponding evaluation scores, and a third mapping data set of moral comments of different degrees and corresponding evaluation scores;

[0135] Performing feature engineering on the education information big data, analyzing and extracting a first mapping relationship feature in the first mapping data set, a second mapping relationship feature in the second mapping data set, and a third mapping relationship feature in the third mapping data set;

[0136] Constructing a feature set including the first mapping relationship feature, the second mapping relationship feature and the third mapping relationship feature, and dividing the feature set into a training set Pa and a validation set Pb according to a preset ratio;

[0137] Importing the training set Pa into the initial RNN model, and performing feature training and learning on each mapping relationship feature in the training set Pa through the RNN model;

[0138] After the training and learning is completed, the initial smart education AI model for education evaluation is obtained, and the model performance of the initial smart education AI model for education evaluation is verified using the verification set Pb;

[0139] If the verification is successful, the smart education AI model is deployed on the background server.

[0140] Educational information big data can be extracted from the background database and screened to obtain the required training big data.

[0141] Among them, the first mapping data set of learning scores and corresponding evaluation scores in different score ranges, such as a student's comprehensive score of 300-400 points corresponds to an evaluation score of 6 points, and the corresponding mapping relationship between the learning scores and the evaluation scores can be configured by the administrator. Therefore, a mapping data set composed of several mapping data can be obtained.

[0142] The same is true for the second mapping data set of sports scores in different score ranges and corresponding evaluation scores.

[0143] For the third mapping data set of different levels of moral comments and corresponding evaluation scores, the corresponding evaluation scores can be configured according to the evaluation procedures of different moral comments. For example, for moral comments with a good evaluation level, the system matches the corresponding evaluation score, such as 8 points. Therefore, there can be a mapping relationship of poor, medium, good and excellent. The evaluation level can be manually labeled.

[0144] RNN (Recurrent Neural Network) is a neural network used to process sequence data. Its architecture includes:

[0145] 1. Input layer: Receives each element of the sequence data. For example, in natural language processing, the input at each time step can be a word or character.

[0146] 2. Hidden layer: The hidden layer is the core part of RNN, which contains recurrent units. At each time step, the hidden layer receives the current input and the hidden state of the previous time step as input, and generates the hidden state of the current time step through an activation function (such as tanh or ReLU). The hidden state can store previous information and affect subsequent outputs.

[0147] 3. Output layer: Depending on the task, the output layer can have different forms. For classification tasks, the output layer is usually a fully connected layer followed by a softmax activation function; for regression tasks, the output layer may directly output continuous values.

[0148] When using the RNN model for training and learning, you first need to prepare a dataset that contains features of different mapping relationships and their corresponding outputs. Next, divide the dataset into a training set and a validation set to evaluate the model performance during the training process.

[0149] 1. Data preprocessing: Normalize or standardize the input data to ensure that the model can learn the mapping relationship between features more effectively.

[0150] 2. Build the RNN model: Choose an appropriate RNN architecture, such as basic RNN, LSTM, or GRU units, and decide the number of layers and hidden units based on the complexity of the problem.

[0151] 3. Define the loss function and optimizer: Choose an appropriate loss function based on the nature of the task, such as mean squared error (MSE) for regression problems and cross entropy loss for classification problems. Also choose an optimizer, such as Adam or SGD, to update the network weights.

[0152] 4. Training model: Use the training set data to train the RNN model. During the training process, the loss is calculated through forward propagation, and then the network weights are updated through the back-propagation algorithm.

[0153] 5. Model evaluation: Use the test set to evaluate the performance of the trained model to ensure that the model has good generalization ability. The performance evaluation methods of the trained model usually include the following aspects: 5. 1. Accuracy: The proportion of correctly predicted samples to the total number of samples. 5. 2. Precision: The proportion of correctly predicted positive samples to all predicted positive samples. 5. 3. Recall: The proportion of correctly predicted positive samples to the actual positive samples. 5. 4. F1 Score: The harmonic mean of precision and recall, used to balance precision and recall. 5. 5. ROC Curve (Receiver Operating Characteristic Curve): A curve drawn by the True Positive Rate (TPR) and False Positive Rate (FPR) at different thresholds. 5. 6. AUC Value (Area Under Curve): The area under the ROC curve, used to measure the performance of the model at all possible classification thresholds.

[0154] According to the nature and requirements of the specific problem, choose appropriate evaluation metrics to measure model performance.

[0155] 6. Parameter tuning: Depending on the performance of the model on the test set, you may need to adjust the network structure or hyperparameters, such as learning rate, batch size, etc., to achieve better performance.

[0156] 7. Apply the model: Once the model is fully trained and tuned to the best state, it can be deployed in the background and used to map data to predict outputs.

[0157] The training process of the specific smart education AI model should be combined with the training and application principles of the RNN model. In this embodiment, the loop iteration conditions set in the model training are determined by the administrator, and the iterative training can be stopped when the required model performance is achieved. The division ratio of the training set Pa and the validation set Pb is preferably 7:3.

[0158] As a preferred embodiment of the present invention, preferably, S4, the smart education AI model identifies the data features in the education node data, and intelligently matches and outputs the feature scores including academic performance, morality and sports, including:

[0159] The smart education AI model identifies the learning performance in the teaching performance data, and matches and outputs a first feature score corresponding to the learning performance according to the first mapping relationship;

[0160] The smart education AI model identifies the physical education scores in the teaching score data, and matches and outputs a second feature score corresponding to the physical education scores according to the second mapping relationship;

[0161] The smart education AI model identifies the evaluation degree of the moral comments in the teaching performance data, and matches and outputs a third feature score corresponding to the evaluation degree according to a third mapping relationship;

[0162] The first feature score, the second feature score and the third feature score are bound to the teaching evaluation node of this time, and the evaluation data packet of this time is obtained and sent to the evaluation module.

[0163] Through model training, the AI ​​model can identify different types of feature mapping relationships. Therefore, after the education node data is subsequently input into the model, the model can intelligently match and output the corresponding feature scores based on the data feature types contained in the education node data. By matching features through the learned mapping relationships, the corresponding feature scores of morality, intelligence and physical fitness can be output, which can quickly evaluate the assessment scores of students in morality, intelligence and physical fitness.

[0164] Therefore, the present invention can realize comprehensive intelligent education evaluation and improve the efficiency of education evaluation. At the same time, through non-final or mid-term dynamic evaluation, the progress of students' learning, physical education and morality in school can be tracked at any time, so that the evaluation results fully reflect the students' learning process; and the intelligent evaluation system can reduce the teaching evaluation burden of teachers.

[0165] During the implementation of this application, the monitoring and collection of educational evaluation data requires the consent of both teachers and students. Only when students agree to teachers' monitoring can teachers collect their data and upload it to the backend server, so as to protect the safety and privacy of students' behavior in school.

[0166] Example 2

[0167] like Figure 2 As shown, based on Example 1, another aspect of the present invention provides an education comprehensive evaluation system, which is used to implement the method for performing education comprehensive evaluation based on the smart education AI model described in Example 1, and the system includes:

[0168] The teacher side is used to generate the educational evaluation data of students in different dynamic teaching environments and report it to the backend server in real time; and to view the educational evaluation report of students;

[0169] The backend server is used to monitor the teaching activity data uploaded by the teacher in real time, and parse and analyze whether the teaching activity data contains the educational evaluation data for evaluating students:

[0170] If yes, the student's ID is identified and forwarded to the student management module together with the corresponding education evaluation data;

[0171] Otherwise, continue to monitor;

[0172] The backend server comprises:

[0173] The student management module is used to record the education evaluation data under the identity ID of the corresponding student and save it in the background database;

[0174] Teaching management system, used to manage students' teaching performance data;

[0175] The node management module is used to monitor and determine whether the system has reached the preset teaching evaluation node. If it has, it reads the student's education node data at this time, including: education evaluation data and teaching performance data, and imports the education node data into the preset smart education AI model;

[0176] Smart education AI model, used to identify data features in the education node data, and intelligently match and output feature scores including academic performance, morality and sports;

[0177] An evaluation module, used to write each of the characteristic scores, and generate the student's education evaluation results according to each of the characteristic scores, and share the student's education evaluation results to the teaching management system;

[0178] Backend database, used for data storage;

[0179] The teaching management system is also used to record the education evaluation results of the students and save them in the background database; when the teaching of this semester is completed, all the education evaluation results obtained by the students at various teaching evaluation nodes in this semester are counted, and a weighted average calculation is performed to obtain the students' education evaluation scores in this semester; the education evaluation scores are written into a preset education evaluation template, an education evaluation report for the students is generated, and the education evaluation report is recorded under the corresponding student's identity ID and saved in the background database; at the same time, the education evaluation report is forwarded to the teacher end and the student end respectively.

[0180] Student side, used to view education evaluation reports;

[0181] The teacher terminal and the student terminal are respectively connected to the backend server for communication.

[0182] The functions and interactive relationships of each terminal or system and module of the above system should be understood and implemented in conjunction with the description of Example 1, and will not be described in detail in this example.

[0183] Example 3

[0184] Figure 5 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 5 As shown, the electronic device may include the above Figure 3 Optionally, the electronic device 410 may include a first processor 2001 .

[0185] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0186] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0187] Combine the following Figure 5 The components of the electronic device 410 are described in detail:

[0188] The first processor 2001 is the control center of the electronic device 410, and may be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be application specific integrated circuits (ASICs), or may be one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs).

[0189] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0190] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 5 CPU0 and CPU1 are shown in FIG.

[0191] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 5 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here can refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0192] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0193] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently and access the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0194] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0195] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 5 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0196] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0197] It should be noted that Figure 5 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than those shown in the figure, or combine certain components, or arrange the components differently.

[0198] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the method for comprehensive education evaluation based on the smart education AI model described in the above method embodiment, and will not be repeated here.

[0199] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0200] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0201] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0202] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0203] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0204] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0205] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0206] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0207] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of the system or unit, which can be electrical, mechanical or other forms.

[0208] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0209] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0210] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0211] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for comprehensive education evaluation based on a smart education AI model, characterized in that: The method comprises: S1. The backend server monitors and collects the education evaluation data obtained by students in different dynamic teaching environments in real time, wherein the dynamic teaching environment includes classroom teaching, extracurricular activities and online teaching activities; S2. Record the education evaluation data under the identity ID of the corresponding student through the student management module and save it in the background database; S3. When the node management module determines that the preset teaching evaluation node is reached, the education node data of the student at this time is read, including: education evaluation data and teaching performance data, and the education node data is imported into the preset smart education AI model; S4. The smart education AI model identifies the data features in the education node data, and intelligently matches and outputs feature scores including academic performance, morality and sports, including: The smart education AI model identifies the learning performance in the teaching performance data, and matches and outputs a first feature score corresponding to the learning performance according to the first mapping relationship; The smart education AI model identifies the physical education scores in the teaching score data, and matches and outputs a second feature score corresponding to the physical education scores according to the second mapping relationship; The smart education AI model identifies the evaluation degree of the moral comments in the education evaluation data, and matches and outputs a third feature score corresponding to the evaluation degree according to a third mapping relationship; Binding the first feature score, the second feature score and the third feature score to the teaching evaluation node of this time, obtaining the evaluation data packet of this time and sending it to the evaluation module; S5, writing each of the characteristic scores into the evaluation module, and the evaluation module generates the education evaluation result of the student according to each of the characteristic scores; The method for generating the smart education AI model includes: Preparing big data of educational information of several students, including: a first mapping data set of academic performances of different score ranges and corresponding evaluation scores, a second mapping data set of sports performances of different score ranges and corresponding evaluation scores, and a third mapping data set of moral comments of different degrees and corresponding evaluation scores; Performing feature engineering on the education information big data, analyzing and extracting a first mapping relationship feature in the first mapping data set, a second mapping relationship feature in the second mapping data set, and a third mapping relationship feature in the third mapping data set; Constructing a feature set including the first mapping relationship feature, the second mapping relationship feature and the third mapping relationship feature, and dividing the feature set into a training set Pa and a validation set Pb according to a preset ratio; Importing the training set Pa into the initial RNN model, and performing feature training and learning on each mapping relationship feature in the training set Pa through the RNN model; After the training and learning is completed, the initial smart education AI model for education evaluation is obtained, and the model performance of the initial smart education AI model for education evaluation is verified using the verification set Pb; If the verification is successful, the smart education AI model is deployed on the background server.

2. The method for comprehensive education evaluation based on the smart education AI model according to claim 1 is characterized in that: The method further comprises: After generating the educational evaluation results of the students, the educational evaluation results of the students are shared to the teaching management system; The teaching management system records the educational evaluation results of the students and saves them in the background database; When the teaching of this semester is completed, all the educational evaluation results obtained by the students at various teaching evaluation nodes of this semester are counted, and weighted average calculation is performed to obtain the educational evaluation score of the students in this semester; Writing the education evaluation score into a preset education evaluation template, generating an education evaluation report for the student, and recording the education evaluation report under the identity ID of the corresponding student, and storing it in the background database; At the same time, the education evaluation report is forwarded to the teacher end and the student end respectively.

3. The method for comprehensive education evaluation based on the smart education AI model according to claim 1 is characterized in that: S1. The backend server monitors and collects the educational evaluation data obtained by students in different dynamic teaching environments in real time, including: Establishing a communication connection between the teacher terminal and the backend server; The teacher generates the educational evaluation data of the students in different dynamic teaching environments through the teacher terminal and reports it to the backend server in real time; The backend server monitors the teaching activity data uploaded by the teacher in real time, and analyzes whether the teaching activity data contains the educational evaluation data for evaluating students: If yes, then identify the student's ID and forward it to the student management module together with the corresponding education evaluation data; Otherwise, continue monitoring.

4. The method for comprehensive education evaluation based on the smart education AI model according to claim 3 is characterized in that: The parsing and analyzing whether the teaching activity data contains the educational evaluation data for evaluating students includes: Preprocessing the educational evaluation data, including cleaning, format conversion or voice-to-text conversion; Calling a large language model to perform text analysis on the preprocessed education evaluation data to identify whether the education evaluation data contains student names and keyword text information related to education evaluation: If so, output the student's name and keyword text information related to the educational evaluation; Otherwise give up.

5. The method for comprehensive education evaluation based on the smart education AI model according to claim 4 is characterized in that: Before calling the large language model, also include: Collect students’ basic information and education evaluation data sets; Importing the basic information of students and the educational evaluation data set into the large language model, and performing secondary training and learning of the model, so that the large language model learns the names of each student and each keyword text information related to the educational evaluation; A cloud API is configured on the background server for calling the large language model.

6. A comprehensive education evaluation system, which is used to implement the method for comprehensive education evaluation based on the smart education AI model as described in any one of claims 1 to 5, characterized in that: The system comprises: The teacher side is used to generate the educational evaluation data of students in different dynamic teaching environments and report them to the backend server in real time. The dynamic teaching environment includes classroom teaching, extracurricular activities and online teaching activities; and to view the educational evaluation report of students; The backend server is used to monitor the teaching activity data uploaded by the teacher in real time, and parse and analyze whether the teaching activity data contains the educational evaluation data for evaluating students: If yes, the student's ID is identified and forwarded to the student management module together with the corresponding education evaluation data; Otherwise, continue to monitor; The backend server comprises: The student management module is used to record the education evaluation data under the identity ID of the corresponding student and save it in the background database; Teaching management system, used to manage students' teaching performance data; The node management module is used to monitor and determine whether the system has reached the preset teaching evaluation node. If reached, the education node data of the students at this time is read, including: education evaluation data and teaching performance data, and the education node data is imported into the preset smart education AI model; The smart education AI model is used to identify the data features in the education node data and intelligently match and output feature scores including academic performance, morality and sports, including: The smart education AI model identifies the learning performance in the teaching performance data, and matches and outputs a first feature score corresponding to the learning performance according to the first mapping relationship; The smart education AI model identifies the physical education scores in the teaching score data, and matches and outputs a second feature score corresponding to the physical education scores according to the second mapping relationship; The smart education AI model identifies the evaluation degree of the moral comments in the education evaluation data, and matches and outputs a third feature score corresponding to the evaluation degree according to a third mapping relationship; Binding the first feature score, the second feature score and the third feature score to the teaching evaluation node of this time, obtaining the evaluation data packet of this time and sending it to the evaluation module; An evaluation module, used to write each of the characteristic scores, and generate the student's education evaluation results according to each of the characteristic scores, and share the student's education evaluation results to the teaching management system; Backend database, used for data storage; The teaching management system is also used to record the education evaluation results of the students and save them in the background database; when the teaching of this semester is completed, all the education evaluation results obtained by the students at various teaching evaluation nodes in this semester are counted, and weighted average calculation is performed to obtain the education evaluation scores of the students in this semester; the education evaluation scores are written into a preset education evaluation template, and the education evaluation report of the students is generated, and the education evaluation report is recorded under the identity ID of the corresponding students and saved in the background database; at the same time, the education evaluation report is forwarded to the teacher end and the student end respectively; Student side, used to view education evaluation reports; The teacher terminal and the student terminal are respectively connected to the backend server for communication.

7. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 5.

Images