Personalized teaching skill training system, device, medium and product based on large language model

Abstract

The invention discloses a personalized teaching skill training system based on a large language model, equipment, a medium and a product, and relates to the technical field of teaching skill training.In the system, firstly, a teaching skill learning module provides answers meeting teaching requirements for teaching questions proposed by teachers so as to help the teachers to learn teaching skills; secondly, a plurality of virtual student roles and live-action teaching scenes are generated through a live-action teaching simulation module, and the virtual student roles and the live-action teaching scenes are simulated by teachers in an online video mode, so that the actual teaching ability is trained and improved; the teaching feedback analysis module analyzes the teaching behavior performance data and the teacher-student interaction data, generates a report and provides suggestions for defects; and finally, proper teaching skill training resources are recommended through a teaching resource recommendation module, so that the teacher is helped to deeply learn and improve the teaching method. According to the scheme of the invention, the teaching ability of teachers can be effectively improved, and especially the coping ability of the teachers facing diversified student behaviors and demands can be effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of teaching skill training, and in particular to a personalized teaching skill training system, equipment, medium and product based on a large language model. Background Art

[0002] With the increasing diversification of the educational environment, the challenges faced by teachers are also increasing. In particular, novice teachers often find it difficult to quickly adapt to the variability of student behavior and teaching needs in the actual teaching process. The current teacher training methods are mainly divided into offline and online. Most online training modes are non-interactive, such as watching videos and theoretical explanations, but these methods cannot fully simulate real teaching scenarios, resulting in teachers' lack of experience in actual teaching. Compared with online training modes, offline training modes can provide teachers with real classroom scenarios, but on the one hand, the cost of offline training is high and it is difficult to apply and promote it at any time; on the other hand, although offline training facilitates the sharing of teaching experience between novice teachers and experienced old teachers, it is often difficult to combine it with actual teaching scenarios to exercise teachers' teaching abilities, and it is also difficult to provide personalized feedback and support, making it difficult for teachers to adjust according to the diverse needs of students.

[0003] Therefore, in the current situation where the teacher training system generally lacks real-time feedback and simulation of real teaching scenarios, it is particularly necessary to effectively improve the ability of teachers, especially novice teachers, to cope with diverse student behaviors and needs. Summary of the invention

[0004] The purpose of this application is to provide a personalized teaching skills training system, equipment, media and products based on a large language model, which can effectively improve teachers' teaching ability, especially their ability to cope with diverse student behaviors and needs.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a personalized teaching skills training system based on a large language model, including: a teaching skills learning module, a real-life teaching simulation module, a teaching feedback analysis module, and a teaching resource recommendation module.

[0007] The teaching skills learning module is used to answer teaching questions raised by teachers based on the large language model, and provide teaching theories, teaching strategies and / or teaching cases that meet the teaching needs of teachers to help teachers learn teaching skills.

[0008] The real-life teaching simulation module is used to generate several virtual student roles and real-life teaching scenes based on a large language model, and provide teachers with teaching simulations in the form of online videos. During the teaching simulation, the virtual student roles will simulate the behavior patterns of real students to provide feedback to teachers, thereby training and improving teachers' actual teaching abilities.

[0009] The teaching feedback analysis module is used to obtain the teacher's teaching behavior performance data and teacher-student interaction data during the teaching simulation. Based on the large language model, the teaching behavior performance data and teacher-student interaction data are analyzed to generate a teaching analysis report and generate improvement suggestions for the deficiencies in the teaching simulation process.

[0010] The teaching resource recommendation module is used to recommend teaching skill training resources to teachers based on the large language model and teaching analysis report to help teachers learn in depth and improve teaching methods.

[0011] Optionally, a teaching problem solving big model is used in the teaching skills learning module to answer teaching problems raised by teachers, and provide teaching theories, teaching strategies and / or teaching cases that meet the teaching needs of teachers; the teaching problem solving big model is constructed based on the big language model, and the teaching problem solving big model is trained using the teaching skills knowledge data set. The trained teaching problem solving big model can fully understand the teaching needs of teachers and generate teaching theories, teaching strategies and / or teaching cases that meet the teaching needs of teachers, so as to help teachers learn teaching skills.

[0012] The large model for answering teaching questions includes an input layer, a position encoding layer, an encoding layer, a multi-head self-attention mechanism, a feedforward neural network layer, a decoding layer and an output layer; the input layer is used to accept the teaching questions input by the teacher and convert them into word embedding forms that the model can handle; the position encoding layer is used to provide position information for each word in the teaching question to ensure that the model can understand the order and context of words when processing the text; the encoding layer is used to analyze and process the context of the teaching question through the self-attention mechanism to understand the teacher's teaching needs; the multi-head self-attention mechanism is used to pay attention to multiple parts of the teaching question at the same time, capture the dependencies between different teaching concepts, and ensure that the generated answers cover multiple knowledge points; the feedforward neural network layer is used to further process the context representation generated by the multi-head self-attention mechanism to enhance the model's ability to handle complex teaching problems; the decoding layer is used to generate teaching theories, teaching strategies and / or teaching cases that meet the teacher's teaching needs based on the encoding results of the model; the output layer is used to output probability distribution through the softmax activation function to output the model's answers to teaching questions.

[0013] Optionally, the teaching problem solving big model is trained using the teaching skill knowledge dataset, specifically including: using the teaching skill knowledge dataset as the input of the teaching problem solving big model, training the model by giving input data and expected output, adjusting the parameters of the teaching problem solving big model, so that the teaching problem solving big model is more suitable for content generation in the field of education; the teaching skill knowledge dataset includes teaching theories, teaching strategies and teaching cases.

[0014] Optionally, a teaching scene generation big model is used in the real-life teaching simulation module to generate several virtual student roles and real-life teaching scenes, which are provided to teachers for teaching simulation in the form of online videos; the teaching scene generation big model is constructed based on a big language model, and the teaching scene generation big model is trained using a student behavior pattern data set. The trained teaching scene generation big model can generate several virtual student roles and real-life teaching scenes with different behavior patterns for teachers to perform teaching simulations. During the teaching simulation, the virtual student roles will simulate the behavior patterns of real students to provide feedback to teachers, thereby training and improving teachers' actual teaching abilities.

[0015] Optionally, in the teaching feedback analysis module, a teaching feedback analysis big model is used to analyze the teaching behavior performance data and the teacher-student interaction data, generate a teaching analysis report, and generate improvement suggestions for the deficiencies in the teaching simulation process; the teaching feedback analysis big model is constructed based on the big language model, and is obtained after the teaching feedback analysis big model is trained using the teaching process evaluation data set. The trained teaching feedback analysis big model can use the teaching behavior analysis unit, the interaction data analysis unit, the teaching language sentiment analysis unit, and the teaching feedback strategy analysis unit to perform multi-dimensional analysis of the teaching behavior performance data and the teacher-student interaction data, accurately generate a teaching analysis report, and generate improvement suggestions for the deficiencies in the teaching simulation process.

[0016] Optionally, the teaching behavior analysis unit is used to automatically detect and classify the teacher's classroom language through natural language processing technology, and analyze the type of teaching behavior and its applicability; the interaction data analysis unit is used to adopt social network analysis and multidimensional interaction analysis methods to evaluate the frequency, depth and quality of interaction between teachers and students reflected in the teacher-student interaction data; the teaching language sentiment analysis unit is used to evaluate the teacher's language emotion expression in the classroom based on the sentiment analysis algorithm; the teaching feedback strategy analysis unit is used to evaluate the effectiveness of the feedback strategy by analyzing the teacher's feedback strategy to students.

[0017] Optionally, a teaching resource recommendation big model is used in the teaching resource recommendation module to recommend teaching skills training resources to teachers based on the teaching analysis report; the teaching resource recommendation big model is constructed based on the big language model, and the teaching resource recommendation big model is trained using the teaching analysis report data set, so that the teaching resource recommendation big model can fully understand and parse the language content in the teaching analysis report, analyze the specific aspects that teachers need to improve, and accurately recommend teaching skills training resources to teachers, so as to help teachers learn in depth and improve teaching methods.

[0018] In a second aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the functions of the personalized teaching skills training system based on a large language model as described above.

[0019] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the functions of the personalized teaching skills training system based on a large language model as described above.

[0020] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the functions of the personalized teaching skills training system based on a large language model as described above.

[0021] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0022] The present application provides a personalized teaching skills training system, equipment, medium and product based on a large language model. In the system, firstly, a teaching skills learning module is used to answer teaching questions raised by teachers, and teaching theories, teaching strategies and / or teaching cases that meet the teaching needs of teachers are provided to help teachers learn teaching skills; secondly, a real-life teaching simulation module is used to generate a number of virtual student roles and real-life teaching scenes, which are provided to teachers for teaching simulation in the form of online videos. During the teaching simulation, the virtual student roles will simulate the behavior patterns of real students to provide feedback to teachers, thereby training and improving the actual teaching ability of teachers; furthermore, a teaching feedback analysis module is used to analyze teaching behavior performance data and teacher-student interaction data, generate a teaching analysis report and generate improvement suggestions for the deficiencies in the teaching simulation process; finally, a teaching resource recommendation module is used to recommend teaching skills training resources to teachers based on the teaching analysis report, thereby helping teachers to deeply learn and improve teaching methods. The above-mentioned scheme provided in this application, on the one hand, answers the teaching questions raised by teachers and improves the basic teaching ability of teachers. On the other hand, it exercises the actual teaching ability of teachers by simulating real-life teaching scenarios. In addition, it also analyzes and quantifies the data in the teaching simulation process, obtains an analysis report and makes targeted improvement suggestions for the deficiencies, helps teachers to deeply study and improve the deficiencies of teaching methods, and improves the ability of teachers, especially novice teachers, to cope with diverse student behaviors and needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 A schematic diagram of functional modules of a personalized teaching skill training system based on a large language model provided in one embodiment of the present application.

[0025] Figure 2 A schematic diagram of the model structure of a large model for answering teaching questions in a personalized teaching skill training system based on a large language model provided in one embodiment of the present application.

[0026] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0029] In an exemplary embodiment, Figure 1 As shown, a personalized teaching skill training system based on a large language model is provided, including: a teaching skill learning module M1, a real-life teaching simulation module M2, a teaching feedback analysis module M3 and a teaching resource recommendation module M4. The functions implemented by each functional module are described below.

[0030] The teaching skill learning module M1 is used to answer the teaching questions raised by the teacher based on the large language model, and provide teaching theories, teaching strategies and / or teaching cases that meet the teaching needs of the teacher to help the teacher learn teaching skills. The teaching skill learning module M1 is used to provide teachers with professional knowledge about teaching theories, strategies and cases. Specifically in this embodiment, the teaching problem answering large model is used in the teaching skill learning module M1 to answer the teaching questions raised by the teacher, and provide teaching theories, teaching strategies and / or teaching cases that meet the teaching needs of the teacher; the teaching problem answering large model is constructed based on the large language model, and the teaching problem answering large model is trained using the teaching skill knowledge data set. The trained teaching problem answering large model can fully understand the teaching needs of the teacher and generate teaching theories, teaching strategies and / or teaching cases that meet the teaching needs of the teacher. For example, the teaching problem answering large model can be adjusted on the basis of an open source large language model (such as Llama).

[0031] Specifically in this embodiment, Figure 2As shown in the figure, the large teaching problem answering model used in the teaching skill learning module M1 structurally includes an input layer, a position encoding layer, an encoding layer, a multi-head self-attention mechanism, a feedforward neural network layer, a decoding layer and an output layer; the input layer is used to accept the teaching problems input by the teacher and convert them into word embedding forms that the model can handle; the position encoding layer is used to provide position information for each word in the teaching problem, ensuring that the model can understand the order and context of words when processing the text; the encoding layer is used to analyze and process the context of the teaching problem through the self-attention mechanism, and understand the teaching needs of the teacher; the multi-head self-attention mechanism is used to pay attention to multiple parts of the teaching problem at the same time, capture the dependencies between different teaching concepts, and ensure that the generated answers cover multiple knowledge points; the feedforward neural network layer is used to further process the context representation generated by the multi-head self-attention mechanism, and enhance the model's ability to handle complex teaching problems; the decoding layer is used to generate teaching theories, teaching strategies and / or teaching cases that meet the teacher's teaching needs based on the encoding results of the model; the output layer is used to output probability distribution through the softmax activation function, and output the model's answers to the teaching problems.

[0032] The teaching skill knowledge dataset is used to train the teaching problem-solving model. Specifically, the teaching skill knowledge dataset is used as the input of the teaching problem-solving model, the model is trained by given input data and expected output, and the parameters of the teaching problem-solving model are adjusted to make the teaching problem-solving model more suitable for content generation in the field of education. For example, input "How to conduct differentiated teaching?", and gradually fine-tune the model parameters according to the output and expected output of the model to generate accurate suggestions on teaching strategies; in addition, the trained model needs to be verified and tested: the model is tested on the verification set to ensure that it can correctly understand and generate education-related content, and the model is adjusted as necessary. The teaching skill knowledge dataset includes teaching theories, teaching strategies, and teaching cases.

[0033] Specifically in this embodiment, teaching skills only include multiple types of text data in the data set to ensure that the model can fully understand and generate suggestions on teaching. Specifically, (1) teaching theory, including classical education theory and learning theory, covering constructivism, behaviorism, cognitivism and other contents, the data form is theoretical literature, research review and teaching theory book abstract. (2) teaching strategy, covering a variety of teaching methods (such as lecture method, discussion method, experimental method, etc.) and differentiated teaching strategies, the data form is teaching method guide, strategy description and comparative analysis document. (3) teaching case, success and failure cases in actual classroom, including strategy application and result analysis, the data form is case analysis report, research paper and classroom video text description. (4) course design and teaching plan, summarizing course goal setting, course structure design and teaching link planning, the data form includes course outline, teaching plan template and case study. (5) teaching evaluation and feedback, collecting formative and summative evaluation strategies, combining student feedback to make teaching adjustments, the data form is teacher evaluation report and feedback data. (6) Subject knowledge, including specific knowledge points and teaching methods of each subject, especially for core courses (Chinese, mathematics, English, etc.). The data is in the form of subject knowledge point descriptions and teaching materials.

[0034] As an exemplary embodiment, when a teacher acquires teaching knowledge in the form of questions and answers through the teaching skill learning module M1, the execution process of the teaching skill learning module M1 is as follows:

[0035] Teaching question input: The teacher inputs a teaching-related question, such as "What are classroom management techniques for cooperative learning?".

[0036] Semantic parsing: The input layer of the model first receives the question, and then performs semantic parsing on the question through a multi-head self-attention mechanism in the encoding layer to understand the core requirements of the question.

[0037] Knowledge retrieval: Retrieve teaching theories, strategies, or cases related to the problem from the knowledge base where the model has been fine-tuned.

[0038] Answer generation: The decoding layer generates specific answers based on the encoded information and provides teachers with teaching suggestions that meet their needs.

[0039] Result output: The output layer converts the generated answers into natural language output, such as "In collaborative learning, the effectiveness of classroom order management can be improved by assigning clear roles and tasks."

[0040] In the above-mentioned teaching skill learning module M1, the teaching question answering model generates answers through the encoding and decoding layers, and finally provides detailed suggestions on teaching theories, teaching strategies or cases. This not only helps teachers quickly acquire the required professional knowledge, but also provides personalized and precise teaching support.

[0041] The real-life teaching simulation module M2 is used to generate several virtual student roles and real-life teaching scenes based on the large language model, and provide teachers with teaching simulations in the form of online videos. During the teaching simulation, the virtual student roles will simulate the behavior patterns of real students to provide feedback to teachers, thereby training and improving teachers' actual teaching abilities. Specifically, the real-life teaching simulation module M2 allows teachers to access a highly simulated simulated classroom environment through online videos. In this simulated classroom environment, the large language model not only plays different types of student roles, but also simulates various situations in a real classroom through dynamic interactions.

[0042] In this embodiment, a teaching scene generation big model is used in the real-life teaching simulation module M2 to generate several virtual student roles and real-life teaching scenes in an online video format for teachers to conduct teaching simulations; the teaching scene generation big model is constructed based on a big language model, and the teaching scene generation big model is trained using a student behavior pattern data set. The trained teaching scene generation big model can generate several virtual student roles and real-life teaching scenes with different behavior patterns for teachers to conduct teaching simulations. During the teaching simulation, the virtual student roles will simulate the behavior patterns of real students to provide feedback to teachers, thereby training and improving teachers' actual teaching abilities.

[0043] Specifically, the large model for generating teaching scenarios can generate virtual student characters with different learning levels, learning styles, and personality characteristics through a pre-adjusted data set. For example, the model will create characters such as students with weak basic knowledge, proactive students, and introverted and quiet students. Each virtual student has different behavior patterns in the classroom, which can present a diverse student group.

[0044] For this function, during the training process of the large model for generating teaching scenarios, the input content mainly includes multi-dimensional data related to student characteristics and teaching interactions, so that the model can generate diverse virtual student roles; the expected output is that the model can learn to generate text descriptions that conform to the input characteristics, that is, for each different type of virtual student, the model can give its behavior pattern and corresponding classroom interaction response.

[0045] Specifically, the input for model training may include: student characteristic description data, classroom interaction behavior data, and scenario simulation and teaching cases.

[0046] Among them, student feature description data includes learning levels, learning styles, personality traits, etc. of different students. The input data will describe the specific manifestations of these features in detail, such as: learning level (beginner, intermediate, advanced), learning style (visual learning, auditory learning, hands-on operation), personality (introvert, extrovert, proactive, shy, etc.). Classroom interaction behavior data contains a large number of descriptions of teacher-student interactions in actual classrooms, involving how students respond to teachers' questions in class, how they cooperate with classmates, and the specific problems encountered by different types of students in the learning process. These interactive behavior descriptions can help the model learn the behavior patterns of different students in the classroom. Scenario simulations and teaching cases contain descriptions of scenes in the classroom and students' reactions in different teaching situations, such as performance in a certain classroom task, reaction to different teaching methods, etc. These data can enable the model to understand the diverse ways students react.

[0047] The expected outputs of the model training include: virtual student images that meet the feature description, virtual student classroom interaction behaviors, and student responses in scenario simulations.

[0048] Among them, the specific requirements for the virtual student image that meets the feature description are: the model should be able to generate detailed virtual student images that meet these features based on the input student features. For example, for a student who is "weak in basic knowledge, introverted and quiet", the model should be able to generate the typical reactions of this student in the classroom, such as "hesitating to answer when the teacher asks questions, and tending to complete tasks independently". The specific requirements for the classroom interactive behavior of virtual students are: descriptions of students' behavioral reactions in different classroom situations. For example, when faced with a certain question or task, proactive students may rush to answer questions or actively seek help, while introverted students may think for a long time before answering. The descriptions of these behavioral patterns are the expected outputs of training and are used to simulate different student reactions. The specific requirements for student reactions in scenario simulation are: in scenario simulation tasks, the model should be able to generate specific reactions of virtual students based on the input classroom scenes. For example, in teamwork tasks, the model can generate student behavioral dialogues that reflect individual differences in cooperation, such as a student who is good at leading a team, while other students may follow the team.

[0049] In specific applications, the large language model in the system has a built-in general template framework and some basic and common virtual student role designs, such as naughty boys in the first grade and quiet girls in the third grade. Teachers only need the number of students and the corresponding template roles to quickly generate virtual students in the classroom. In addition to basic student roles, teachers can also customize student roles. Teachers can enter a simple description, such as "a fourth-grade student who has excellent math grades, likes to participate in group discussions, but is occasionally distracted." The system will automatically expand the details based on this description and fill it into the general template framework. Generate a more detailed virtual student image. In addition, the template framework has a parameterized structure that allows students to adjust their interaction methods, question types, participation frequency, etc. according to the description, so that the generated roles are more in line with the specific needs of teachers and situations that may occur in actual classrooms. The general template framework also supports the combination of different types of student groups. For example, teachers can set a classroom to contain different types of student roles, such as students who actively ask questions, shy but smart students, and students with weaker comprehension abilities. The model will generate classroom scenes with rich interaction patterns based on different template combinations in the framework to simulate diverse classroom situations.

[0050] In addition, the large model of teaching scene generation adopted by the real-life teaching simulation module M2 also has a questioning mechanism and a feedback mechanism.

[0051] Questioning mechanism: Virtual students can actively ask questions based on the course content, and the types of questions will be adjusted according to the characteristics of the student role. For example, students with weak foundations may ask simple clarification questions, while advanced students may ask challenging questions. This questioning mechanism can train teachers' ability to handle problems at different levels.

[0052] Feedback mechanism: During the teacher's teaching process, virtual students can give real-time feedback in the form of nodding, doubts, questions or raising hands. Through this interaction, teachers can feel the students' participation and adjust their teaching strategies based on the feedback.

[0053] As an exemplary embodiment, the large model for generating teaching scenarios should also simulate classroom situations: the large language model can generate complex classroom situations according to different teaching situations. For example, some students in the simulated classroom may be distracted, interrupt, or not understand. Teachers need to adjust their explanation methods and management strategies according to these situations to maintain classroom order and improve teaching efficiency.

[0054] The large model generated by the teaching scene should also simulate the complexity of role interaction: as the teacher's performance in the simulated classroom continues to improve, the student role generated by the large language model will be dynamically adjusted, and the complexity and difficulty of the interaction will gradually increase. For example, students' questions may be relatively simple in the early stage, but as the teacher's teaching skills improve, students' questions will become more challenging, and even cross-disciplinary questions or complex thinking challenges will appear, in order to train the teacher's ability to respond.

[0055] The large model for generating teaching scenarios should also simulate customized scenarios: According to different teaching objectives, the actual combat simulation module also supports teachers to select specific scenarios for training, such as large-class teaching, group discussion or 1-on-1 tutoring. The virtual student interaction mode and question feedback method in each scenario will be different to meet the practical needs of teachers in a variety of teaching environments.

[0056] The teaching feedback analysis module M3 is used to obtain the teacher's teaching behavior performance data and teacher-student interaction data during the teaching simulation process. Based on the large language model, the teaching behavior performance data and teacher-student interaction data are analyzed to generate a teaching analysis report and generate improvement suggestions for the deficiencies in the teaching simulation process.

[0057] In this embodiment, a teaching feedback analysis big model is used in the teaching feedback analysis module M3 to analyze the teaching behavior performance data and the teacher-student interaction data, generate a teaching analysis report, and generate improvement suggestions for the deficiencies in the teaching simulation process; the teaching feedback analysis big model is constructed based on the big language model, and is obtained after the teaching feedback analysis big model is trained using the teaching process evaluation data set. The trained teaching feedback analysis big model can use the teaching behavior analysis unit, the interaction data analysis unit, the teaching language emotion analysis unit, and the teaching feedback strategy analysis unit to perform multi-dimensional analysis on the teaching behavior performance data and the teacher-student interaction data, accurately generate a teaching analysis report, and generate improvement suggestions for the deficiencies in the teaching simulation process.

[0058] Specifically, the teaching behavior analysis unit is used to automatically detect and classify teachers' classroom language through natural language processing technology, and analyze the types of teaching behaviors and their applicability. In this teaching behavior analysis unit, a data set containing actual classroom teaching interaction data can be used to fine-tune the large language model so that it can recognize and classify teaching behaviors (such as explanations, questions, feedback, management, etc.). For example, the data of the Flanders interaction analysis method is used for annotation and training. During the training process, the model needs to learn the characteristics and classification standards of different teaching behaviors.

[0059] Explanations for several common teaching behaviors:

[0060] Explanation refers to the act of imparting knowledge to students in class, usually in the form of a one-way explanation of concepts, theories or knowledge points by the teacher. This is a major part of teaching, and its purpose is to help students understand the teaching content. Example: The teacher writes a formula on the blackboard and then explains in detail the derivation of the formula. Tell the background, development process and impact of historical events, such as explaining "the cause of World War II and its impact on the world situation." Help students understand phenomena in physical experiments, such as the principles of refraction and reflection of light, through demonstration and explanation.

[0061] Questioning is the act of asking students questions in class to stimulate students' thinking, understand their level of understanding, or guide them to gain a deeper understanding of knowledge. Questions can be divided into open questions and closed questions. Example: Open question: The teacher asks: "What do you think are the advantages of constructivist teaching methods in actual classes?" This type of question does not have a single correct answer and is intended to encourage students to express their own ideas. Closed question: The teacher asks: "What is 2 plus 2?" This type of question usually has only one correct answer and is intended to test students' mastery of basic knowledge. During a class discussion, the teacher asked: "Who can give an example of the application of the law of conservation of energy in life?"

[0062] Feedback is a teacher's response to a student's performance, answer, or behavior, with the goal of encouraging the student to keep working on it or correcting their mistakes. Feedback can be positive (praise, encouragement) or negative (correction, criticism). Examples: When a student correctly answers a question, the teacher says, "Great! Your answers are very comprehensive. Keep it up." A student makes a mistake while solving a math problem, and the teacher says, "You had a problem with your calculations here. Let's look at what went wrong, shall we?" A student uses a very vivid metaphor in his or her writing, and the teacher comments, "You used the metaphor very well, and it makes the whole description vivid and concrete."

[0063] Classroom management refers to the behavior of teachers in maintaining order and organizing teaching activities in the classroom. It includes maintaining classroom discipline, managing students' activities and time arrangements, etc. Effective classroom management is a key factor in ensuring the smooth progress of teaching. Examples: The teacher reminds students to pay attention to the class time: "There are 10 minutes left, we have to finish this part as soon as possible"; distributes group tasks among students, ensuring that each group member has clear responsibilities: "Your group is responsible for collecting experimental data, and the other group is responsible for analyzing the results"; when students begin to distract, the teacher says: "Students, please focus here, we are discussing a very important concept."

[0064] The interactive data analysis unit is used to evaluate the frequency, depth and quality of interaction between teachers and students as reflected in the teacher-student interaction data by using social network analysis and multidimensional interaction analysis methods; the interactive data analysis unit involves modeling the interaction between teachers and students, which can be trained through graph data (such as teacher-student interaction network graph). Using social network analysis (SNA) tools, combined with classroom interaction data, the graph model is trained so that the model can learn to identify the frequency and depth of interaction between different students and teachers, and then determine whether any students are ignored.

[0065] The teaching language sentiment analysis unit is used to evaluate the teacher's language emotional expression in the classroom based on the sentiment analysis algorithm; the teaching language sentiment analysis unit can use a pre-trained sentiment classification model, such as a sentiment classifier based on the Transformer architecture, combined with a sentiment annotation dataset in a specific teaching scenario for fine-tuning training. For example, through a large amount of labeled classroom teaching language data (including positive, negative, encouraging, corrective, etc. labels), the model can accurately judge the emotions conveyed by the teacher during the teaching process.

[0066] The teaching feedback strategy analysis unit is used to evaluate the effectiveness of the feedback strategy by analyzing the teacher's feedback strategy to students. In the teaching feedback strategy analysis unit, for the content of the teacher's feedback, a data set marked with "feedback type" (such as praise, correction, suggestion, etc.) can be used to train the large language model so that it can understand and generate different types of feedback content and evaluate its effectiveness.

[0067] The teaching feedback analysis model is also used to summarize the above analysis results. The system integrates the analysis results of each dimension to generate a comprehensive teaching analysis report, which includes:

[0068] Behavioral performance evaluation: List in detail the teacher's performance in different teaching links, such as the quality of explanation, questioning and feedback, and point out the areas that need improvement.

[0069] Interaction Charts: Generate network diagrams or heat maps of the interaction between teachers and virtual students to show the coverage and quality of the interaction.

[0070] Emotional analysis feedback: Feedback on teachers’ emotional expression in simulated teaching to help teachers improve classroom atmosphere management.

[0071] Improvement suggestions: Based on the analysis results, the system makes suggestions for improving teaching, such as enhancing interactive strategies or adjusting question types.

[0072] After the analysis is completed, the system generates a visual report and provides data feedback to teachers to help them improve their teaching performance.

[0073] The teaching resource recommendation module M4 is used to recommend teaching skill training resources to teachers based on the large language model and the teaching analysis report to help teachers learn in depth and improve their teaching methods.

[0074] In this embodiment, a teaching resource recommendation big model is used in the teaching resource recommendation module M4 to recommend teaching skill training resources to teachers based on the teaching analysis report; the teaching resource recommendation big model is constructed based on the big language model, and the teaching resource recommendation big model is trained using the teaching analysis report data set, so that the teaching resource recommendation big model can fully understand and parse the language content in the teaching analysis report, analyze the specific aspects that teachers need to improve, and accurately recommend teaching skill training resources to teachers, such as teaching videos, articles, online courses, etc., to help teachers deeply learn and improve teaching methods.

[0075] In the teaching resource recommendation module M4, the main function of the teaching resource recommendation model is to understand and analyze the language content in the analysis report and make reasonable recommendations based on these analysis results.

[0076] During the training process of the large model for teaching resource recommendation, the model input may include the following types of information: teacher feedback analysis report, teacher background and needs, and teaching resource library labels.

[0077] The text content of the teacher feedback analysis report is a detailed report generated by the teaching feedback analysis module M3, which describes the teacher's performance in the simulated teaching, including teaching behavior, interaction data, emotional expression, and feedback strategies. The teacher's weaknesses or specific areas that need improvement are marked in the feedback report. For example: "Insufficient classroom management", "Low frequency of interaction with students", "Lack of diverse questioning strategies", etc.

[0078] Teacher Background and Needs records teachers’ historical performance, course subjects, teaching style preferences, etc., which help to achieve personalized recommendations.

[0079] The teaching resource library tags include: Resource library description: description information and related tags of each resource in the resource library, such as "interactive teaching strategy", "classroom management video", "teaching theory article", etc. Keywords and classification tags: tags related to teaching resources and their classification, including teaching stage (such as junior high school, high school), teaching topic (such as classroom management, teaching method), teaching type (video, article, course, etc.) and other information.

[0080] During the training process of the large model for teaching resource recommendation, the output of the model mainly includes the following contents: generated recommendation content, resource summary and applicable scenarios, and personalized recommendation content.

[0081] The generated recommendations are output in the form of a list of recommended resources. The model outputs a list of recommended resources for the problems or weaknesses identified in the feedback analysis report. Each resource recommendation includes relevant descriptive information to help teachers understand the purpose and applicable scenarios of the recommended resource. The model also generates a brief explanation of why a resource is recommended. For example, "Due to the shortcomings of teachers in classroom management, classroom management teaching videos are recommended to learn effective classroom control strategies."

[0082] Resource Summary and Applicable Scenarios Generate a concise summary for each recommended resource to help teachers quickly understand the main content and value of the resource. For example, if a video about interactive teaching is recommended, the model will generate a brief introduction to the video, such as "This video introduces three different interactive teaching methods, which are suitable for classroom discussions and teamwork activities." It also generates applicable scenarios for recommended resources to ensure that teachers know in what circumstances to use the recommended resources. For example, "This course design template is suitable for experimental teaching scenarios in junior high school science courses."

[0083] Personalized recommendations mean that the model generates resources tailored to individual needs based on the teacher's background, teaching preferences, and historical usage records. For example, if a teacher is interested in a certain teaching method, the model will prioritize more in-depth learning materials related to that teaching method. For multiple consecutive training simulations and feedback from teachers, the model will dynamically adjust the recommended content based on the latest feedback results and the teacher's improved performance. For example, if a teacher's performance improves in a certain area, the model can recommend advanced resources to further improve their skills.

[0084] In addition, it also includes multi-level resource recommendations. First, for basic problems in teacher performance, the system first recommends some basic teaching resources, such as teaching skills videos, case studies, and teaching articles. These resources focus on helping teachers master core teaching skills. For teachers who have certain teaching experience but need further improvement in certain areas, the system will recommend more in-depth resources, such as online courses, teaching strategy seminars, and teaching research articles. These resources can help teachers gain deeper theoretical knowledge and practical experience. If the analysis results show that the teacher has outstanding performance in a specific field, but there is room for improvement, the system will also recommend some personalized tutoring resources, such as academic articles or professional research on specific issues, to help teachers explore in depth in a certain field.

[0085] It is understandable that, whether it is when using the teaching skills learning module to answer the teaching questions raised by teachers, or when using the teaching resource recommendation module to recommend teaching skills training resources to teachers, or when adjusting the parameters of the large language model through training so that it can achieve the predetermined functions, the knowledge resources used can all come from Internet retrieval or self-built knowledge base. Of course, under legal and compliant conditions, the source of the resources used is not limited to this, and this application does not impose additional restrictions.

[0086] The solution provided in the above-mentioned embodiment of the present application, on the one hand, answers the teaching questions raised by teachers through the teaching skills learning module M1, and on the other hand, simulates the real-life teaching scene through the real-life teaching simulation module M2 to exercise the actual teaching ability of teachers. In addition, the data in the teaching simulation process is analyzed and quantified through the teaching feedback analysis module M3 to obtain an analysis report and use the teaching resource recommendation module M4 to make targeted improvement suggestions for the deficiencies, thereby helping teachers to deeply learn and improve the deficiencies of teaching methods, and improving the ability of teachers, especially novice teachers, to cope with diverse student behaviors and needs.

[0087] certainly, Figure 1 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different functions. Figure 1 One or at least two components of the system shown.

[0088] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the function of a personalized teaching skill training system based on a large language model provided in the above embodiment is realized.

[0089] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0090] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0091] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0092] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0093] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0094] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0095] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0096] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0097] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A personalized teaching skills training system based on a large language model, characterized in that: include: Teaching skills learning module, real-life teaching simulation module, teaching feedback analysis module and teaching resource recommendation module; The teaching skill learning module is used to answer the teaching questions raised by the teacher based on the large language model, and provide teaching theories, teaching strategies and / or teaching cases that meet the teaching needs of the teacher to help the teacher learn teaching skills; The real-life teaching simulation module is used to generate a number of virtual student roles and real-life teaching scenes based on the large language model, and provide teachers with teaching simulations in the form of online videos. During the teaching simulation, the virtual student roles will simulate the behavior patterns of real students to provide feedback to teachers, thereby improving the actual teaching ability of teachers. The teaching feedback analysis module is used to obtain the teacher's teaching behavior performance data and teacher-student interaction data during the teaching simulation, analyze the teaching behavior performance data and the teacher-student interaction data based on the large language model, generate a teaching analysis report and generate improvement suggestions for the deficiencies in the teaching simulation process; The teaching resource recommendation module is used to recommend teaching skill training resources to teachers based on the large language model and the teaching analysis report, so as to help teachers to deeply learn and improve teaching methods.

2. The personalized teaching skill training system based on a large language model according to claim 1 is characterized in that: In the teaching skill learning module, a teaching problem answering big model is used to answer the teaching problems raised by the teacher, and provide teaching theories, teaching strategies and / or teaching cases that meet the teaching needs of the teacher; the teaching problem answering big model is constructed based on a big language model, and is obtained after the teaching problem answering big model is trained using a teaching skill knowledge data set. The trained teaching problem answering big model can fully understand the teaching needs of the teacher and generate teaching theories, teaching strategies and / or teaching cases that meet the teaching needs of the teacher, so as to help the teacher learn teaching skills; The large model for answering teaching questions includes an input layer, a position encoding layer, an encoding layer, a multi-head self-attention mechanism, a feedforward neural network layer, a decoding layer and an output layer; the input layer is used to accept the teaching questions input by the teacher and convert them into a word embedding form that the model can process; the position encoding layer is used to provide position information for each word in the teaching question to ensure that the model can understand the order and context of words when processing the text; the encoding layer is used to analyze and process the context of the teaching question through the self-attention mechanism to understand the teaching needs of the teacher; the multi-head self-attention mechanism is used to pay attention to multiple parts of the teaching question at the same time, capture the dependencies between different teaching concepts, and ensure that the generated answers cover multiple knowledge points; the feedforward neural network layer is used to further process the context representation generated by the multi-head self-attention mechanism to enhance the model's ability to handle complex teaching problems; the decoding layer is used to generate teaching theories, teaching strategies and / or teaching cases that meet the teaching needs of the teacher based on the encoding results of the model; the output layer is used to output probability distribution through the softmax activation function to output the model's answer to the teaching question.

3. The personalized teaching skill training system based on a large language model according to claim 2 is characterized in that: The teaching problem solving big model is trained using the teaching skill knowledge data set, specifically including: taking the teaching skill knowledge data set as the input of the teaching problem solving big model, training the model by giving input data and expected output, adjusting the parameters of the teaching problem solving big model, so that the teaching problem solving big model is more suitable for content generation in the field of education; the teaching skill knowledge data set includes teaching theories, teaching strategies and teaching cases.

4. The personalized teaching skill training system based on a large language model according to claim 1 is characterized in that: In the real-life teaching simulation module, a teaching scene generation big model is used to generate several virtual student roles and real-life teaching scenes, which are provided for teachers to conduct teaching simulations in the form of online videos; the teaching scene generation big model is constructed based on a big language model, and is obtained after the teaching scene generation big model is trained using a student behavior pattern data set. The trained teaching scene generation big model can generate several virtual student roles and real-life teaching scenes with different behavior patterns for teachers to conduct teaching simulations. During the teaching simulation, the virtual student roles will simulate the behavior patterns of real students to provide feedback to teachers, thereby training and improving teachers' actual teaching abilities.

5. The personalized teaching skill training system based on a large language model according to claim 1 is characterized in that: In the teaching feedback analysis module, a teaching feedback analysis big model is used to analyze the teaching behavior performance data and the teacher-student interaction data, generate a teaching analysis report and generate improvement suggestions for the deficiencies in the teaching simulation process; The teaching feedback analysis big model is constructed based on the big language model and is obtained after training the teaching feedback analysis big model using the teaching process evaluation data set. The trained teaching feedback analysis big model can use the teaching behavior analysis unit, the interactive data analysis unit, the teaching language sentiment analysis unit and the teaching feedback strategy analysis unit to perform multi-dimensional analysis on the teaching behavior performance data and the teacher-student interaction data, accurately generate a teaching analysis report and generate improvement suggestions for the deficiencies in the teaching simulation process.

6. The personalized teaching skill training system based on a large language model according to claim 5 is characterized in that: The teaching behavior analysis unit is used to automatically detect and classify the teacher's classroom language through natural language processing technology, and analyze the type of teaching behavior and its applicability; the interaction data analysis unit is used to use social network analysis and multi-dimensional interaction analysis methods to evaluate the interaction frequency, depth and quality between teachers and students reflected in the teacher-student interaction data; The teaching language sentiment analysis unit is used to evaluate the teacher's language sentiment expression in the classroom based on the sentiment analysis algorithm; the teaching feedback strategy analysis unit is used to evaluate the effectiveness of the feedback strategy by analyzing the teacher's feedback strategy to the students.

7. The personalized teaching skill training system based on a large language model according to claim 1 is characterized in that: In the teaching resource recommendation module, a teaching resource recommendation big model is used to recommend teaching skill training resources to teachers based on the teaching analysis report; the teaching resource recommendation big model is constructed based on a big language model, and is obtained after training the teaching resource recommendation big model using the teaching analysis report data set, so that the teaching resource recommendation big model can fully understand and parse the language content in the teaching analysis report, analyze the specific aspects that teachers need to improve, and accurately recommend teaching skill training resources to teachers, so as to help teachers learn in depth and improve teaching methods.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the functions of the personalized teaching skill training system based on a large language model as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the functions of the personalized teaching skill training system based on a large language model described in any one of claims 1 to 7 are realized.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the functions of the personalized teaching skill training system based on a large language model described in any one of claims 1 to 7 are realized.

Images