Teacher teaching ability improving system based on large model

Abstract

The invention discloses a teacher teaching ability improving system based on a large model, which belongs to the technical field of teaching and comprises a teacher analysis module, a teaching analysis module and an ability improving module. The teacher analysis module is used for carrying out teaching ability analysis on a target teacher and generating a teaching ability portrait of the target teacher, and the teaching ability portrait comprises teaching scores and teaching advantage and disadvantage data of the target teacher on corresponding teaching evaluation items; the teaching analysis module is used for analyzing a teaching class of a target teacher to obtain a teaching ability demand of the teaching class, and the teaching ability demand is composed of corresponding single teaching demands; and the ability improving module is used for assisting in improving the teaching ability of the target teacher and displaying the teaching ability portrait of the target teacher and the teaching ability demand of the teaching class to the target teacher, and the target teacher improves the teaching ability according to the teaching ability portrait and the teaching ability demand of the teaching class.

Description

Technical Field

[0001] The present invention belongs to the technical field of teaching, and specifically is a system for improving teachers' teaching ability based on large models. Background Art

[0002] Traditional ways to improve teachers' teaching ability, such as centralized training, teaching competitions, etc., have many deficiencies. For example, centralized training often lacks pertinence and personalization, and it is difficult to meet the needs of teachers at different levels; teaching competitions focus more on teaching skills and forms, while ignoring the essence and connotation of teaching.

[0003] With the rapid development of artificial intelligence technology, the application of large model technology in the teaching field has gradually emerged. Large models have powerful data processing and analysis capabilities, can extract valuable information from massive data, and provide new possibilities for improving teachers' teaching ability. By using large model technology, the teaching behaviors of teachers can be deeply analyzed and accurately evaluated, so as to discover problems and deficiencies in the teaching process and provide personalized improvement suggestions for teachers.

[0004] However, although large model technology has broad application prospects in the teaching field, there are still some challenges and problems at present. For example, how to effectively apply large model technology to the improvement of teachers' teaching ability, how to ensure the accuracy and reliability of evaluation, and how to formulate targeted training and improvement plans according to the evaluation results, etc.

[0005] To solve the above problems, the present invention proposes a system for improving teachers' teaching ability based on large models. Summary of the Invention

[0006] To solve the problems existing in the above solutions, the present invention provides a system for improving teachers' teaching ability based on large models.

[0007] The object of the present invention can be achieved by the following technical solutions:

[0008] A system for improving teachers' teaching ability based on large models includes a teacher analysis module, a teaching analysis module, and an ability improvement module;

[0009] The teacher analysis module is used to analyze the teaching ability of the target teacher and generate a teaching ability portrait of the target teacher. The teaching ability portrait includes the teaching scores of the target teacher on corresponding teaching evaluation items and teaching advantages and disadvantages data;

[0010] Further, the method for analyzing the teaching ability of the target teacher includes:

[0011] Determine each teaching evaluation item for evaluating teachers' capabilities. The platform party establishes a large model for evaluating teachers' teaching capabilities based on the teaching evaluation items, and marks the large model as a teaching evaluation model;

[0012] Obtain the teacher teaching data of the target teacher in real time. The teacher teaching data includes classroom videos, students' homework, exam scores, teachers' self-evaluation and peer evaluation, and feedback from students and parents;

[0013] Analyze the teacher teaching data of the target teacher through the teaching evaluation model to obtain the teaching evaluation data of the target teacher on the teaching evaluation items;

[0014] Generate a teaching ability portrait of the target teacher according to the teaching evaluation data.

[0015] The teaching analysis module is used to analyze the teaching classes of the target teacher to obtain the teaching ability requirements of the teaching classes. The teaching ability requirements are composed of corresponding individual teaching requirements.

[0016] Further, the method for analyzing the teaching classes of the target teacher includes:

[0017] Obtain the student learning portraits of each student in the teaching class, and generate the class learning data of the teaching class according to the student learning portraits of the students in the teaching class;

[0018] The platform party establishes a class analysis model based on teaching historical data. The teaching historical data includes class learning data, teaching ability portraits, and comprehensive teaching scores;

[0019] Analyze the class learning data of the teaching class through the class analysis model to obtain the teaching representative curve of the teaching class;

[0020] Evaluate the comprehensive teaching score of the teaching class according to the class learning data, mark the comprehensive teaching score as the basic score, mark the basic score in the teaching representative curve, and identify the maximum comprehensive teaching score in the teaching representative curve, and mark the maximum comprehensive teaching score as the best score;

[0021] Determine the ability improvement path of the target teacher according to the basic score, the best score and the teaching representative curve, and generate teaching ability requirements according to the ability improvement path.

[0022] Further, the method for obtaining the student learning portrait includes:

[0023] Identify the student learning information of each student in the teaching class. The student learning information includes exam scores, personality, gender, age, homework records, and class attention records;

[0024] Generate the student learning portrait of the corresponding student according to the student learning information and the preset student portrait template.

[0025] Further, the method for determining the ability improvement path of the target teacher according to the basic score, the best score, and the teaching representative curve includes:

[0026] Step SA1: Mark the curve points corresponding to the basic score and the best score as the basic point and the best point respectively in the teaching representative curve;

[0027] Define the adjacent point, and the adjacent point is defined as the curve point with the smallest absolute value of the difference between the comprehensive teaching score of the corresponding curve point in the teaching representative curve and the basic score of the basic point;

[0028] Step SA2: Identify the adjacent point in the teaching representative curve according to the definition of the adjacent point and the basic point, mark the adjacent point as the new basic point in the teaching representative curve, and identify the basic score of the basic point;

[0029] Step SA3: When the new basic point coincides with the best point, generate the score improvement path according to the marking order of the basic points, and enter Step SA4;

[0030] When the new basic point does not coincide with the best point, return to Step SA2;

[0031] Step SA4: Identify the set of teaching ability portraits corresponding to each comprehensive teaching score within the score improvement path, and mark the set of teaching ability portraits as the score portrait set; mark the teaching ability portrait of the target teacher as the basic ability portrait;

[0032] Determine the ability improvement path planned for the target teacher according to the score improvement path, the score portrait set, and the basic ability portrait.

[0033] Further, the class learning data of the teaching class is updated in real time. When the teaching ability requirement is updated, determine the new teaching ability requirement.

[0034] Further, it also includes a teacher recommendation module, and the teacher recommendation module is used to recommend teaching teachers for each class in the school, and obtain the teaching representative curve and class learning data of each class;

[0035] Determine the score improvement path of the class according to the class learning data and the teaching representative curve;

[0036] Identify the teaching ability portraits of the corresponding teachers in the school, perform matching analysis according to the score improvement path and the teaching ability portraits, and determine the teaching teachers of the class.

[0037] Furthermore, the method for matching and analyzing according to the scoring improvement path and the teaching ability portrait includes:

[0038] The school administrators preset the weight coefficients for each class, mark the weight coefficients as δi, where i represents the corresponding class, i = 1, 2, ……, n, and n is the number of classes;

[0039] Determine a number of candidate matching schemes according to the corresponding class and teacher; conduct a simulation evaluation on the candidate matching schemes to obtain the estimated score change value of the class; mark the estimated score change value as YBPi;

[0040] Calculate the candidate matching value of the corresponding candidate matching scheme according to the allocation evaluation formula, and the allocation evaluation formula is:

[0041]

[0042] In the formula: PF is the candidate matching value;

[0043] Mark the candidate matching scheme with the largest candidate matching value as the target matching scheme, and determine the teacher in charge of the class according to the target matching scheme.

[0044] The ability improvement module is used to assist in improving the teaching ability of the target teacher, display the teaching ability portrait of the target teacher and the teaching ability requirements of the teaching class to the target teacher, and the target teacher improves the teaching ability according to the teaching ability portrait and the teaching ability requirements of the teaching class.

[0045] Compared with the prior art, the beneficial effects of the present invention are:

[0046] Through the teacher teaching ability improvement system based on the large model, the present invention can provide personalized teaching analysis and improvement suggestions according to the specific situation and teaching needs of each teacher. This helps teachers more accurately identify their deficiencies in the teaching process, so as to formulate targeted improvement plans and achieve significant improvement in teaching ability. Through the present invention, schools and educational institutions can reasonably allocate training resources according to the actual needs and evaluation results of teachers. For teachers with weak teaching ability, more training and support can be provided; while for teachers with strong teaching ability, more development opportunities and challenges can be provided. This helps to optimize the allocation of teacher training resources and enhance the training effect. At the same time, it realizes the priority improvement of the teaching ability of the teaching class, which is convenient for quickly improving the teaching effect of the teaching class. Description of the Drawings

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0048] Figure 1 This is the principle block diagram of the present invention. Specific embodiments

[0049] The following will clearly and completely describe the technical solutions of the present invention in combination with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0050] As Figure 1 shown, the teacher teaching ability improvement system based on the large model includes a teacher analysis module, a teaching analysis module, an ability improvement module, and a teacher recommendation module;

[0051] The teacher analysis module is used to analyze the abilities of the target teacher and generate a teaching ability portrait of the target teacher.

[0052] To generate the teaching ability portrait, it is necessary to obtain the evaluation data of the target teacher's teaching ability in multiple dimensions, such as teaching design ability, classroom management ability, knowledge teaching ability, student interaction ability, etc.; specific multi-dimensional teaching evaluation items are set according to relevant teaching requirements; when determining the teaching evaluation data corresponding to each teaching evaluation item, generate the teaching ability portrait of the target teacher according to the corresponding teaching evaluation data, and intuitively display the teaching ability of the target teacher in multiple dimensions through the teaching ability portrait. That is, the teaching ability portrait includes relevant data such as the teaching scores, teaching advantages and disadvantages of the target teacher corresponding to each teaching evaluation item.

[0053] In one embodiment, to obtain the teaching evaluation data, it can be evaluated based on the existing mature large model technology. Establish a teacher evaluation model based on the current large model technology, and evaluate the teacher teaching data of the target teacher through the teacher evaluation model to obtain the teaching evaluation data of the corresponding teaching evaluation items, where the teacher teaching data can include relevant data such as classroom videos, student assignments, exam scores, teacher self-evaluations and peer evaluations, and student and parent feedback.

[0054] Exemplarily, the establishment of the large model:

[0055] Data collection and preprocessing: Collect data related to teachers' teaching from multiple sources, such as classroom videos, students' assignments, exam scores, teachers' self-evaluations and peer evaluations, and feedback from students and parents. Preprocess the collected data, including data cleaning (removing invalid or redundant information), data annotation (assigning appropriate labels to the data for subsequent analysis), and data normalization (converting the data into a unified format or range).

[0056] Feature extraction: Extract features related to teachers' teaching ability from the preprocessed data, such as the diversity of teaching methods, the effectiveness of classroom management, students' participation, and the clarity of knowledge transmission. These features can be measured by quantitative indicators, such as the improvement rate of students' grades, the maintenance of classroom discipline, and the frequency of students' participation in discussions.

[0057] Model design and training:

[0058] Design the structure of the large model based on the extracted features, including the input layer, hidden layer, and output layer. Select appropriate algorithms and optimization methods to train the large model so that it can accurately identify and evaluate teachers' teaching ability. During the training process, pay attention to the convergence, performance, and generalization ability of the model to ensure that the model can work stably in different scenarios.

[0059] Model verification and optimization: Use the validation dataset to verify the trained model and evaluate its performance. Optimize the model according to the verification results, such as adjusting the model structure, increasing the number of features, or improving the algorithm. Repeat the verification and optimization process until the model reaches a satisfactory performance level.

[0060] Multi-dimensional evaluation of teachers' teaching ability:

[0061] Determine teaching evaluation items: According to the connotation and composition of teaching ability, determine multiple evaluation dimensions, such as teaching design ability, classroom management ability, knowledge imparting ability, and student interaction ability. Each dimension can be further refined into more specific evaluation indicators.

[0062] Use the large model for evaluation:

[0063] Input the data related to teachers' teaching collected into the large model. The large model conducts multi-dimensional evaluation of teachers' teaching ability according to the input data and the preset evaluation dimensions and indicators. Output the evaluation results, including the scores, rankings, and specific evaluations and suggestions for each teaching evaluation item.

[0064] Interpret and apply the evaluation results: Interpret and analyze the evaluation results, pointing out which aspects the teacher performs well in and which aspects need improvement.

[0065] In one embodiment, the acquisition of teaching evaluation data can also be evaluated and collected based on other methods.

[0066] The teaching analysis module is used to analyze the teaching classes of the target teacher, determine the teaching ability requirements of the corresponding teaching classes. The teaching ability requirements consist of the teaching requirement data of the corresponding teaching evaluation items. Marking the teaching requirement data as individual teaching requirements, it can be considered that the teaching ability requirements are composed of the corresponding individual teaching requirements.

[0067] In one embodiment, the teaching ability requirements of the corresponding teaching classes can be determined based on existing methods. For example, an intelligent model is established according to the above-mentioned large model technology or other intelligent technologies, and the intelligent model analyzes each student in the corresponding teaching class to determine the teaching ability requirements of the teaching class.

[0068] In one embodiment, the analysis of the teaching class can be carried out in the following ways, including:

[0069] Identify the student learning information of each student in the teaching class. The student learning information includes relevant data such as exam scores, personality, gender, age, homework records, and class attention records. For missing data, the target teacher can supplement it according to the class situation to facilitate obtaining complete and true student learning information; generate corresponding student learning portraits according to the student learning information according to a preset student portrait template; the student portrait template is set by the platform side to unify the portrait format for subsequent identification and analysis; or when there are other relevant teaching systems set up in the school, the student learning portraits of the students can be obtained through the corresponding teaching systems and converted according to the preset student portrait template.

[0070] Generate the class learning data of the teaching class according to the student learning portraits of each student in the teaching class.

[0071] The platform side makes full use of the teaching history data connected to each user. The teaching history data includes relevant data such as the class learning data, class score data, comprehensive class evaluation data, and teaching ability portraits of teachers in the corresponding classes. Determine the class teaching results of different teaching ability portraits under different class learning data by mining the teaching history data. The class teaching results can be represented by scores. For example, quantify according to the scores of the students in the class to form a comprehensive teaching score. Take the student score composition in a certain class as 100 and the student score composition in a certain class as 0, and determine the comprehensive teaching score by other methods such as interpolation. There are specifically various ways to quantify the class teaching results; that is, the teaching history data includes data such as class learning data, teaching ability portraits, and comprehensive teaching scores;

[0072] Generate a teaching material curve of corresponding class learning data based on teaching historical data. The horizontal axis of the teaching material curve is the teaching ability portrait, and the vertical axis is the comprehensive teaching score. That is, in the teaching material curve, the same comprehensive teaching may correspond to multiple teaching ability portraits, which can be represented by corresponding representative sets, numerical links, etc. The numerical link means using a certain numerical value to represent the set of multiple teaching ability portraits, and through this numerical value, the set of multiple teaching ability portraits can be quickly read later; for the teaching material curve, it can be generated in the order of increasing comprehensive teaching score from low to high, or generated according to the differences between teaching ability portraits, etc. Specifically, it can be generated based on the existing curve generation methods.

[0073] Establish a class analysis model based on numerous teaching material curves. The class analysis model is used to generate a corresponding teaching representative curve for a class according to the class learning data. The teaching representative curve is the corresponding teaching material curve; the class analysis model is established based on current intelligent technologies, such as established based on neural networks such as CNN networks or DNN networks, using the teaching material curve to form a training set. The training set includes input data and output data. The input data is the class learning data, and the output data is the teaching representative curve, and analysis is performed through the successfully trained class analysis model.

[0074] That is, the platform party uses the accumulated teaching historical data to establish a class analysis model.

[0075] Analyze the class learning data of the teaching class through the class analysis model to obtain the teaching representative curve of the teaching class;

[0076] Evaluate the comprehensive teaching score of the teaching class according to the class learning data, mark the obtained comprehensive teaching score as the basic score, mark the basic score in the teaching representative curve, and identify the maximum comprehensive teaching score in the teaching representative curve and mark it as the best score;

[0077] Determine the ability improvement path of the target teacher according to the basic score, the best score and the teaching representative curve, and generate teaching ability requirements according to the ability improvement path.

[0078] In one embodiment, the method for determining the ability improvement path of the target teacher according to the basic score, the best score and the teaching representative curve includes:

[0079] Step SA1: Mark the curve points corresponding to the basic score and the best score in the teaching representative curve as the basic point and the best point respectively;

[0080] Define the adjacent point. The adjacent point is defined as the curve point with the smallest absolute value of the difference between the comprehensive teaching score of the corresponding curve point in the teaching representative curve and the basic score of the basic point;

[0081] Step SA2: Identify adjacent points in the teaching representative curve according to the adjacent point definition and the base points, and mark the adjacent points in the teaching representative curve as new base points, that is, use the new base points to determine adjacent points subsequently;

[0082] Step SA3: When the new base point coincides with the optimal point, generate a scoring improvement path according to the marking order of the base points, and enter Step SA4, that is, starting from the first base point, connect the determined new base points one by one until reaching the optimal point to form a scoring improvement path;

[0083] When the new base point does not coincide with the optimal point, return to Step SA2;

[0084] Step SA4: Identify the set of teaching ability portraits corresponding to each comprehensive teaching score within the scoring improvement path, and mark the identified set of teaching ability portraits as the scoring portrait set; mark the teaching ability portrait of the target teacher as the basic ability portrait;

[0085] Plan an optimal improvement path for the target teacher according to the scoring improvement path, the scoring portrait set and the basic ability portrait, and mark it as the ability improvement path, which can be planned according to the path that is easiest to improve.

[0086] In one embodiment, to plan an optimal improvement path for the target teacher according to the scoring improvement path, the scoring portrait set and the basic ability portrait, it can be analyzed based on existing path planning techniques and determined according to the difficulty of improvement of each teaching evaluation item of the target teacher; or the platform side can set a corresponding intelligent model for intelligent analysis and planning of the ability improvement path; or calculate the improvement difficulty of different teaching ability portraits one by one, and then determine the improvement path in sequence.

[0087] In one embodiment, generate teaching ability requirements according to the ability improvement path. When the ability improvement path is clear, the stage improvement requirements of the corresponding teaching evaluation items can be determined to form the corresponding single-item teaching requirements, which are combined into teaching ability requirements.

[0088] In one embodiment, the class learning data of the teaching class is updated in real time, such as changes in student portraits, entry of new students, etc.;

[0089] When the class learning data is updated, determine the new teaching ability requirements.

[0090] The teacher recommendation module is used to serve the school to intelligently recommend suitable teachers for each class, reduce the subsequent improvement difficulty of the teachers in the corresponding classes, and obtain the teaching representative curves and class learning data of each class;

[0091] Determine the scoring improvement path of the class according to the class learning data and the teaching representative curve;

[0092] Identify the teaching ability portraits of each teacher, and perform matching analysis based on the scoring improvement paths of each class and the teaching ability portraits of each teacher to determine the target teachers for each class.

[0093] In one embodiment, after determining the scoring improvement paths of each class and the teaching ability portraits of each teacher and performing matching analysis, the distribution can be carried out according to the existing teacher assignment method.

[0094] In one embodiment, the method for performing matching analysis based on the scoring improvement paths of each class and the teaching ability portraits of each teacher includes:

[0095] The school administrators preset the weight coefficients of each class, and mark the obtained weight coefficients as δi, where i represents the corresponding class, i = 1, 2,..., n, and n is the number of classes;

[0096] Determine the teacher assignment method available, marked as the candidate matching plan, that is, determine the optional teacher assignment plans according to the number of classes taught by teachers, other school restriction conditions, etc.;

[0097] Conduct a simulation evaluation on the candidate matching plan to determine the estimated scoring change value of each class, that is, analyze according to the teaching ability portrait of the teacher matched with the corresponding class to determine the change value of the comprehensive teaching score brought to this class. If the teacher ability does not match, predict the corresponding comprehensive teaching score according to the scoring improvement path and the teaching representative curve, and then determine the estimated scoring change value;

[0098] Mark the obtained estimated scoring change value as YBPi;

[0099] Calculate the candidate matching value of the corresponding candidate matching plan according to the assignment evaluation formula. The assignment evaluation formula is:

[0100]

[0101] In the formula: PF is the candidate matching value;

[0102] Mark the candidate matching plan with the largest candidate matching value as the target matching plan, and determine the teachers in charge of each class according to the target matching plan.

[0103] In one embodiment, the above embodiment can also be used as the analysis basis for the subsequent teacher replacement in the school to estimate the change situation of the candidate matching value.

[0104] The ability improvement module is used to assist in improving the teaching ability of the target teacher, display the teaching ability portrait of the target teacher and the teaching ability requirements of the teaching class to the target teacher, and the target teacher improves the teaching ability according to the teaching ability portrait and the teaching ability requirements of the teaching class.

[0105] In one embodiment, the target teacher preferentially improves their capabilities according to the teaching ability requirements of the teaching class, and also takes into account the deficiencies in the teaching ability profile for improvement.

[0106] In one embodiment, the platform party can establish a corresponding teaching improvement analysis model, and through the teaching improvement analysis model, comprehensively analyze the teaching ability profile and the teaching ability requirements of the teaching class to determine an overall teaching ability improvement proposal.

[0107] In one embodiment, it is also possible to determine a teaching ability improvement plan for the target teacher based on existing methods such as manual means, according to the teaching ability profile and the teaching ability requirements of the teaching class.

[0108] The above formulas are all calculated by removing the dimension and taking their numerical values. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through a large amount of data simulation.

[0109] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A teacher teaching ability improvement system based on a large model, characterized by: It includes teacher analysis module, teaching analysis module and capacity improvement module; The teacher analysis module is used to analyze the teaching ability of the target teacher and generate a teaching ability portrait of the target teacher, wherein the teaching ability portrait includes the teaching score, teaching advantages and disadvantages data of the target teacher on the corresponding teaching evaluation items; The teaching analysis module is used to analyze the teaching class of the target teacher to obtain the teaching ability requirements of the teaching class, and the teaching ability requirements are composed of corresponding single teaching requirements; The ability improvement module is used to assist in improving the teaching ability of the target teacher. The teaching ability portrait of the target teacher and the teaching ability requirements of the teaching class are displayed to the target teacher. The target teacher improves his teaching ability based on the teaching ability portrait and the teaching ability requirements of the teaching class.

2. The teacher teaching ability improvement system based on a large model according to claim 1 is characterized in that: Methods for analyzing the teaching ability of target teachers include: Determine various teaching evaluation items for evaluating the teacher's ability, and the platform establishes a large model for evaluating the teacher's teaching ability based on the teaching evaluation items, and marks the large model as a teaching evaluation model; Obtain the target teacher's teaching data in real time, including classroom videos, student homework, test scores, teacher self-evaluation and mutual evaluation, and student and parent feedback; Analyze the teaching data of the target teacher through the teaching evaluation model to obtain the teaching evaluation data of the target teacher on the teaching evaluation item; A teaching ability portrait of the target teacher is generated based on the teaching evaluation data.

3. The teacher teaching ability improvement system based on a large model according to claim 1 is characterized in that: Methods for analyzing the target teacher's teaching class include: Obtaining a student learning portrait of each student in the teaching class, and generating class learning data of the teaching class according to the student learning portrait of the students in the teaching class; The platform establishes a class analysis model based on the teaching history data, which includes class learning data, teaching ability portrait, and comprehensive teaching score; Analyze the class learning data of the teaching class by using the class analysis model to obtain a teaching representative curve of the teaching class; Evaluate the comprehensive teaching score of the teaching class according to the class learning data, mark the comprehensive teaching score as a basic score, mark the basic score in the teaching representative curve, identify the maximum comprehensive teaching score in the teaching representative curve, and mark the maximum comprehensive teaching score as the best score; The target teacher's capacity improvement path is determined based on the basic score, the best score and the teaching representative curve, and the teaching capacity requirements are generated based on the capacity improvement path.

4. The system for improving teacher teaching ability based on a large model according to claim 3 is characterized in that: Methods for obtaining student learning portraits include: Identify the student learning information of each student in the teaching class, the student learning information includes test scores, personality, gender, age, homework records, and class attention records; A student learning portrait of the corresponding student is generated according to the student learning information and a preset student portrait template.

5. The system for improving teacher teaching ability based on a large model according to claim 3 is characterized in that: Methods for determining target teachers' capacity improvement paths based on basic scores, optimal scores, and teaching representative curves include: Step SA1: Mark the curve points corresponding to the basic score and the best score in the teaching representative curve as the basic point and the best point respectively; Define an adjacent point, where the adjacent point is defined as a curve point in the teaching representative curve where the absolute value of the difference between the comprehensive teaching score of the corresponding curve point and the basic score of the basic point is the smallest; Step SA2: identifying a neighboring point in the teaching representative curve according to the neighboring point definition and the basic point, marking the neighboring point as a new basic point in the teaching representative curve, and identifying a basic score of the basic point; Step SA3: When the new basic point coincides with the optimal point, a score improvement path is generated according to the marking order of the basic points, and the process proceeds to step SA4; When the new base point does not coincide with the optimal point, return to step SA2; Step SA4: Identify the teaching ability portrait set corresponding to each comprehensive teaching score in the score improvement path, mark the teaching ability portrait set as a score portrait set; mark the teaching ability portrait of the target teacher as a basic ability portrait; The ability improvement path of the target teacher is determined based on the score improvement path, score profile set and basic ability profile.

6. The system for improving teacher teaching ability based on a large model according to claim 3 is characterized in that: The class learning data of the teaching class is updated in real time, and when the teaching capacity requirements are updated, the new teaching capacity requirements are determined.

7. The system for improving teacher teaching ability based on a large model according to claim 5 is characterized in that: It also includes a teacher recommendation module, which is used to recommend teachers for each class in the school and obtain the teaching representative curve and class learning data of each class; Determine the score improvement path of the class based on the class learning data and the teaching representative curve; Identify the teaching ability portraits of the corresponding teachers in the school, conduct matching analysis based on the score improvement path and the teaching ability portraits, and determine the teacher for the class.

8. The system for improving teacher teaching ability based on a large model according to claim 7 is characterized in that: The methods for matching analysis based on the score improvement path and teaching ability profile include: The school administrators preset the weight coefficients of each class, and mark the weight coefficients as δi, where i represents the corresponding class, i=1, 2, ..., n, and n is the number of classes; Determine a number of candidate matching schemes according to the corresponding classes and teachers; perform simulation evaluation on the candidate matching schemes to obtain an estimated score change value of the class; mark the estimated score change value as YBPi; The candidate matching value of the corresponding candidate matching solution is calculated according to the allocation evaluation formula. The allocation evaluation formula is: Where: PF is the matching value to be selected; The candidate matching scheme with the largest candidate matching value is marked as the target matching scheme, and the teacher of the class is determined according to the target matching scheme.

Images