Classroom evaluation and model training method, device and equipment

Abstract

The invention discloses a classroom evaluation and model training method, device and equipment. The method comprises the following steps: acquiring first classroom teaching data of a plurality of known evaluation results; the first classroom teaching data comprises various types of teaching data corresponding to the same classroom; inputting the first classroom teaching data into a classroom evaluation model, and outputting a prediction result of the first classroom teaching data; and updating the classroom evaluation model based on the evaluation results and the prediction results corresponding to the plurality of first classroom teaching materials. According to the method, the machine learning model can be used for replacing manual work to carry out classroom observation evaluation, the labor cost is reduced, the feedback speed is increased, and the classroom evaluation model is trained by using various types of data information in the education and teaching field, so that the output evaluation result has relatively high evaluation effectiveness.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a classroom evaluation and model training method, device and equipment. Background Art

[0002] Classroom observation is a widely used educational research method, usually conducted by researchers or professional teachers to systematically observe, record, and analyze teaching and learning behaviors in the classroom to gain insights into educational practice. The goal of classroom observation is to provide an in-depth understanding of classroom dynamics and obtain effective classroom evaluations, thereby providing educators with feedback on teaching effectiveness, student engagement, teaching strategies, and classroom environment. Traditional classroom observation and evaluation methods mainly involve observers entering the classroom or observing classroom videos, and using pre-designed observation tools such as scales or checklists to systematically record specific teaching and learning behaviors. Since traditional classroom observation and evaluation methods require in-depth analysis by professionals, and different schools or subjects may use different evaluation criteria, there are problems such as inconsistent evaluation criteria, high costs, and long feedback times. Summary of the invention

[0003] The embodiments of the present application provide a classroom evaluation and model training method, device and equipment, which can use a machine learning model to replace manual classroom observation and evaluation, reduce labor costs, speed up feedback, and use various types of data information in the field of education and teaching to train the classroom evaluation model, so that the evaluation results it outputs have higher evaluation effectiveness.

[0004] In a first aspect, an embodiment of the present application provides a classroom evaluation model training method, the method comprising:

[0005] Acquire a plurality of first classroom teaching materials with known evaluation results; the first classroom teaching materials include a plurality of types of teaching data corresponding to the same classroom;

[0006] Inputting the first classroom teaching material into the classroom evaluation model, and outputting the prediction result of the first classroom teaching material;

[0007] The classroom evaluation model is updated based on the evaluation results and the prediction results corresponding to each of the plurality of first classroom teaching materials.

[0008] In a possible implementation, the classroom evaluation model includes a first language model; the step of inputting the first classroom teaching material into the classroom evaluation model and outputting a prediction result of the first classroom teaching material includes:

[0009] All the teaching data in the first classroom teaching materials are spliced ​​together to obtain spliced ​​text data;

[0010] The concatenated text data is input into the first language model, and the prediction result of the first classroom teaching material is output.

[0011] In a possible implementation, the classroom evaluation model includes a second language model and a third language model, the multiple types of teaching data include main type teaching data and multiple auxiliary types of teaching data, and the main type of teaching data includes text data obtained by speech recognition of classroom audio data;

[0012] The above-mentioned inputting the first classroom teaching material into the classroom evaluation model and outputting the prediction result of the first classroom teaching material includes:

[0013] Combining the main type of teaching data and the auxiliary type of teaching data in the first classroom teaching material to obtain a plurality of combined text data;

[0014] Input the main type of teaching data and the multiple combined text data into the second language model, and output a first initial result of the main type of teaching data and a second initial result corresponding to each of the multiple combined text data;

[0015] The first initial result and the second initial result are input into the third language model, and the prediction result of the first classroom teaching material is output.

[0016] In a possible implementation, before inputting the first classroom teaching material into the classroom evaluation model, the method further includes:

[0017] Acquire multiple second-classroom teaching materials; the second-classroom teaching materials include multiple types of teaching data;

[0018] The initial model is pre-trained based on the above-mentioned multiple second classroom teaching materials to obtain the above-mentioned classroom evaluation model.

[0019] In a second aspect, an embodiment of the present application provides a classroom evaluation method, the method comprising:

[0020] Obtaining target teaching materials of the class to be evaluated; the target teaching materials include various types of target teaching data;

[0021] Input the above target teaching materials into the classroom evaluation model to obtain the target evaluation results of the above classroom to be evaluated;

[0022] Among them, the above-mentioned classroom evaluation model is trained based on any of the above-mentioned classroom evaluation model training methods.

[0023] In a possible implementation, the classroom evaluation model includes a first language model, and the target teaching materials are input into the classroom evaluation model to obtain the target evaluation result of the classroom to be evaluated, including:

[0024] All target teaching data in the target teaching materials are spliced ​​together to obtain target spliced ​​text data;

[0025] Determine whether the target concatenated text data exceeds a preset length threshold;

[0026] In the case that the target concatenated text data does not exceed the preset length threshold, the target concatenated text data is input into the first language model, and the target evaluation result of the class to be evaluated is output.

[0027] In a possible implementation, the classroom evaluation model includes a second language model and a third language model, the multiple types of target teaching data include a main type of target teaching data and multiple auxiliary types of target teaching data, the main type of target teaching data includes target text data obtained by speech recognition from the audio data of the classroom to be evaluated;

[0028] After determining whether the target concatenated text data exceeds a preset length threshold, the method further includes:

[0029] In the case where the target spliced ​​text data exceeds the preset length threshold, combining the target teaching data of the main type in the target teaching material with the target teaching data of the plurality of auxiliary types to obtain a plurality of target combined text data;

[0030] Input the target teaching data of the main type and the multiple target combination text data into the second language model, and output the first target initial result of the target teaching data of the main type and the second target initial results corresponding to the multiple target combination text data respectively;

[0031] The first target initial result and the second target initial result are input into the third language model, and the target evaluation result of the class to be evaluated is output.

[0032] In a third aspect, an embodiment of the present application provides a classroom evaluation model training device, the device comprising:

[0033] A first acquisition module is used to acquire a plurality of first classroom teaching materials with known evaluation results; the first classroom teaching materials include a plurality of types of teaching data corresponding to the same classroom;

[0034] A first training module, used for inputting the first classroom teaching material into the classroom evaluation model, and outputting the prediction result of the first classroom teaching material;

[0035] The second training module is used to update the classroom evaluation model based on the evaluation results and the prediction results corresponding to each of the plurality of first classroom teaching materials.

[0036] In a possible implementation, the classroom evaluation model includes a first language model; the first training module is specifically used for:

[0037] All the teaching data in the first classroom teaching materials are spliced ​​together to obtain spliced ​​text data;

[0038] The concatenated text data is input into the first language model, and the prediction result of the first classroom teaching material is output.

[0039] In a possible implementation, the classroom evaluation model includes a second language model and a third language model, the multiple types of teaching data include main type teaching data and multiple auxiliary types of teaching data, and the main type of teaching data includes text data obtained by speech recognition of classroom audio data;

[0040] The first training module is specifically used for:

[0041] Combining the main type of teaching data and the auxiliary type of teaching data in the first classroom teaching material to obtain a plurality of combined text data;

[0042] Input the main type of teaching data and the multiple combined text data into the second language model, and output a first initial result of the main type of teaching data and a second initial result corresponding to each of the multiple combined text data;

[0043] The first initial result and the second initial result are input into the third language model, and the prediction result of the first classroom teaching material is output.

[0044] In a possible implementation, the device further includes:

[0045] A third acquisition module is used to acquire a plurality of second classroom teaching materials; the second classroom teaching materials include a plurality of types of teaching data;

[0046] The third training module is used to pre-train the initial model based on the above-mentioned multiple second classroom teaching materials to obtain the above-mentioned classroom evaluation model.

[0047] In a fourth aspect, an embodiment of the present application provides a classroom evaluation device, the device comprising:

[0048] The second acquisition module is used to acquire target teaching materials of the class to be evaluated; the target teaching materials include multiple types of target teaching data;

[0049] An evaluation module, used to input the target teaching materials into the classroom evaluation model to obtain the target evaluation results of the classroom to be evaluated;

[0050] The classroom evaluation model is trained based on any of the classroom evaluation model training methods. In a possible implementation, the classroom evaluation model includes a first language model, and the evaluation module is specifically used for:

[0051] All target teaching data in the target teaching materials are spliced ​​together to obtain target spliced ​​text data;

[0052] Determine whether the target concatenated text data exceeds a preset length threshold;

[0053] In the case that the target concatenated text data does not exceed the preset length threshold, the target concatenated text data is input into the first language model, and the target evaluation result of the class to be evaluated is output.

[0054] In a possible implementation, the classroom evaluation model includes a second language model and a third language model, the multiple types of target teaching data include a main type of target teaching data and multiple auxiliary types of target teaching data, the main type of target teaching data includes target text data obtained by speech recognition from the audio data of the classroom to be evaluated;

[0055] After determining whether the target concatenated text data exceeds a preset length threshold, the evaluation module is further specifically used to:

[0056] In the case where the target spliced ​​text data exceeds the preset length threshold, combining the target teaching data of the main type in the target teaching material with the target teaching data of the plurality of auxiliary types to obtain a plurality of target combined text data;

[0057] Input the target teaching data of the main type and the multiple target combination text data into the second language model, and output the first target initial result of the target teaching data of the main type and the second target initial results corresponding to the multiple target combination text data respectively;

[0058] The first target initial result and the second target initial result are input into the third language model, and the target evaluation result of the class to be evaluated is output.

[0059] In a fifth aspect, an embodiment of the present application provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above method steps.

[0060] In a sixth aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above method steps.

[0061] In one or more embodiments of the present application, a first classroom teaching material with multiple known evaluation results is obtained; the first classroom teaching material includes multiple types of teaching data corresponding to the same classroom; the first classroom teaching material is input into the classroom evaluation model, and the prediction result of the first classroom teaching material is output; the classroom evaluation model is updated based on the evaluation results and the prediction results corresponding to each of the multiple first classroom teaching materials. This method can use a machine learning model to replace manual classroom observation and evaluation, which reduces labor costs and speeds up feedback. It also uses multiple types of data information in the field of education and teaching to train the classroom evaluation model, so that the evaluation results it outputs have higher evaluation validity. At the same time, this method has strong scalability, and the trained classroom evaluation model can be easily applied to other types of classroom teaching materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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.

[0063] Figure 1 A system architecture diagram of a classroom evaluation system provided in an embodiment of the present application;

[0064] Figure 2 A flow chart of a classroom evaluation model training method provided in an embodiment of the present application;

[0065] Figure 3 A training architecture diagram of a classroom evaluation model provided in an embodiment of the present application;

[0066] Figure 4 A training architecture diagram of another classroom evaluation model provided in an embodiment of the present application;

[0067] Figure 5 A training architecture diagram of another classroom evaluation model provided in an embodiment of the present application;

[0068] Figure 6A flow chart of a classroom evaluation method provided in an embodiment of the present application;

[0069] Figure 7 A schematic diagram of the structure of a classroom evaluation model training device provided in an embodiment of the present application;

[0070] Figure 8 A schematic diagram of the structure of a classroom evaluation device provided in an embodiment of the present application;

[0071] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0072] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0073] In the description of the present application, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0074] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in the embodiments of this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions. For example, the teaching materials of the classroom to be evaluated involved in this specification are all obtained with full authorization.

[0075] The present application is described in detail below with reference to specific embodiments.

[0076] Please refer to Figure 1 , Figure 1 The following is a schematic diagram of the architecture of a classroom evaluation system provided by an exemplary embodiment of the present application. Figure 1 As shown, the classroom evaluation system may include a terminal 110 and a server 120 .

[0077] The terminal 110 is connected to the server 120 via the network 130. Optionally, the terminal 110 is a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart watch, etc., but is not limited thereto. The terminal 110 installs and runs an application that supports classroom evaluation. The network 130 can be a wireless network or a wired network.

[0078] The server 120 is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, distribution networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. The server 120 provides background services for applications running on the terminal 110. For example, the server 120 provides corresponding services for applications running on the terminal 110. In the embodiment of the present application, the server 120 provides background services for applications running on the terminal that support classroom evaluation, such as running or training classroom evaluation models.

[0079] Those skilled in the art will appreciate that the number of the above-mentioned terminals 110 and servers 120 may be more or less. For example, there may be only one terminal 110 and server 120, or there may be dozens or hundreds of terminals 110 and servers 120, or a greater number. In this case, the above-mentioned system architecture may also include other terminals and servers. The embodiment of the present application does not limit the number of terminals and device types.

[0080] The classroom evaluation method or classroom evaluation model training method involved in one or more embodiments of the present application can be implemented by relying on a computer program and can be run on a classroom evaluation device or a classroom evaluation model training device based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application. The execution subject corresponding to the classroom evaluation method can be the above-mentioned terminal 110, and the server 120 can be responsible for running or training the classroom evaluation model, and sending the model or model call interface to the terminal 110; the execution subject corresponding to the classroom evaluation method can also be the server 120, and the terminal 110 can be responsible for uploading the teaching data of the classroom to be evaluated to the server 120. It is determined specifically based on the actual application environment, and the embodiments of the present application are not limited to this.

[0081] Next, combine Figure 1 , introduces the classroom evaluation model training method provided by the embodiment of this specification. For details, please refer to Figure 2 , which is a flow chart of a classroom evaluation model training method provided by an exemplary embodiment of the present application. Figure 2As shown, with the execution subject being the server, the classroom evaluation method includes the following steps:

[0082] S201, obtaining first classroom teaching materials with multiple known evaluation results.

[0083] Specifically, in the embodiment of the present application, the first classroom teaching materials can be obtained from existing data sets, which have been annotated or evaluated and are associated with past classroom observation and evaluation content. By training the classroom evaluation model with these first classroom teaching materials with known classroom observation and evaluation, the model can learn and analyze the features in the first classroom teaching materials to effectively evaluate and predict new data and generate accurate and effective evaluation results.

[0084] The above-mentioned first classroom teaching materials include multiple types of teaching data corresponding to the same classroom. In other words, the multiple different types of teaching data in the first classroom teaching materials are associated with the same classroom, and there is a corresponding relationship between the various teaching data; when conducting classroom observation and evaluation of the classroom, these teaching data need to be processed synchronously. For example, when processing a teacher-student dialogue in a classroom, it is necessary to match the courseware corresponding to the class, the knowledge point system corresponding to the class, the teaching objectives, the new curriculum standards and other factors, and process these teaching data synchronously to obtain a classroom evaluation result for the class.

[0085] For example, Figure 3 A training architecture diagram of a classroom evaluation model provided in an embodiment of the present application. Figure 3 As shown, in this embodiment, the first classroom teaching materials may include various types of teaching data such as classroom dialogue text, courseware text, knowledge point system, teaching objectives and new curriculum standards.

[0086] Classroom dialogue text is text data obtained through speech recognition based on classroom audio data, which can reveal the communication and interaction in the classroom, the content of the teacher and students' speeches, etc. Among them, speech recognition can be achieved using ASR technology (Automatic Speech Recognition).

[0087] The courseware text is the courseware elements and coordinates extracted from the XML format courseware information of the current class, which can be used to parse the main content and layout of the courseware.

[0088] The knowledge point system is based on the established relationship between class, chapter and knowledge point, and is a list of knowledge points corresponding to the current class obtained through chapter information.

[0089] The teaching objectives are the teaching objectives corresponding to the current class obtained through chapter information based on the established class-chapter-teaching objective relationship. This can reflect the original intention of the course design, as well as the key points and difficulties of teaching.

[0090] The new curriculum standard is the basic programmatic document of the national curriculum corresponding to the current classroom subjects, which reflects the basic norms and quality requirements of the country for basic education courses. Among them, the content of the new curriculum standard is relatively long. We can first use the summarization ability of the Large Language Model (LLM) to compress the content of the new curriculum standard to a smaller number of words before inputting it in the subsequent steps. This can reduce the pressure on the model and also facilitate subsequent data analysis and model training.

[0091] S202, input the first classroom teaching materials into the classroom evaluation model, and output the prediction results of the first classroom teaching materials.

[0092] Specifically, the first classroom teaching data is input into the classroom evaluation model, and the features in the first classroom teaching data are analyzed by applying the machine learning model, thereby generating a prediction result about the first classroom teaching data. This prediction result is the classroom observation evaluation result of the classroom corresponding to the first classroom teaching data predicted by the classroom evaluation model.

[0093] In some embodiments, the classroom evaluation model includes a first language model; the step of inputting the first classroom teaching material into the classroom evaluation model and outputting the prediction result of the first classroom teaching material includes:

[0094] All teaching data in the first classroom teaching materials are spliced ​​together to obtain spliced ​​text data;

[0095] The concatenated text data is input into the first language model, and the prediction result of the first classroom teaching material is output.

[0096] Specifically, the various types of teaching data in the first classroom teaching materials are spliced ​​into a long text, namely, spliced ​​text data, by splicing. Then the spliced ​​text data is input into the first large language model, and the large language model is used to process the spliced ​​text data to generate the predicted evaluation results of the first classroom teaching materials. In this way, the first large language model can directly use other multiple educational data at the same time when analyzing the classroom dialogue text, and the connection between each teaching data is closer. At the same time, the input of multiple teaching data into the first large language model may have a complementary effect, so that the first large language model can learn more in-depth features and improve the training effect and model performance.

[0097] For example, Figure 4As shown, the first classroom teaching material includes various teaching data such as classroom ASR text, courseware text, knowledge point system, teaching objectives and new curriculum standards; the above teaching data are spliced ​​into a long text, which contains all the data in the classroom ASR text, courseware text, knowledge point system, teaching objectives and new curriculum standards; then the long text is input into a large language model (NLP large model), and after being processed by the large language model, the classroom evaluation is output, which is the prediction result output by the classroom evaluation model.

[0098] It should be noted that since all the first classroom teaching materials are input into the classroom evaluation model in a concatenated manner, there may be a problem of too long input. For large language models based on the Transformer architecture, such as GPT-3.5, GPT-4, LLaMa, etc., the input length is a quadratic algorithm complexity. Therefore, large language models will have output length restrictions, such as the maximum length of GPT-4 is 32K. When the concatenated text data is too long, the first large language model can use a base model based on LSTM and Transformer structure, such as RWKV.

[0099] In some embodiments, the classroom evaluation model includes a second language model and a third language model, the multiple types of teaching data include main type teaching data and multiple auxiliary types of teaching data, and the main type of teaching data includes text data obtained by speech recognition of classroom audio data;

[0100] The above-mentioned inputting the first classroom teaching material into the classroom evaluation model and outputting the prediction result of the above-mentioned first classroom teaching material includes:

[0101] Combining the main type of teaching data with the auxiliary type of teaching data in the first classroom teaching material to obtain a plurality of combined text data;

[0102] Inputting the teaching data of the main type and the multiple combined text data into the second largest language model, and outputting the first initial result of the teaching data of the main type and the second initial results corresponding to the multiple combined text data respectively;

[0103] The first initial result and the second initial result are input into the third language model, and the prediction result of the first classroom teaching material is output.

[0104] Specifically, in order to avoid the spliced ​​text data in the classroom evaluation model being too long, the teaching data parts can be combined into one input, so that the combined text data of multiple different teaching data combinations can be obtained. After being processed by the large language model, multiple initial prediction results can be obtained. Finally, these initial prediction results are aggregated through the text summarization ability of the large language model to obtain the final prediction result. The input length of the combined text data is much shorter than the spliced ​​text data, so it can significantly reduce the pressure on the classroom evaluation model, and can maintain a high prediction accuracy. At the same time, it is more scalable. If other teaching data is added later, it can be quickly updated without affecting other teaching data.

[0105] Among them, the classroom dialogue is the most reflective of the classroom status in the first classroom teaching material, and is the object that needs to be analyzed in detail. Therefore, the text data obtained by voice recognition of the classroom audio data can be used as the main type of teaching data in the first classroom teaching material, and other teaching data can be used as auxiliary type teaching data. The main type of teaching data can be used as the input of the large language model alone, or the main type of teaching data can be matched and combined with the auxiliary type of teaching data, and the combined text data can be used as the input of the large language model. The main type of teaching data can be matched and combined with one auxiliary type of teaching data, or the main type of teaching data can be matched and combined with multiple auxiliary types of teaching data, but the length of the combined text data to be obtained does not exceed the input limit of the third largest language model. In this embodiment, the second largest language model and the third largest language model can be the same large language model, or they can be large language models set separately.

[0106] For example, Figure 5 As shown in the figure, the first classroom teaching materials include classroom ASR text, courseware text, knowledge point system, teaching objectives and new curriculum standards and other teaching data; classroom ASR text is used as the main type of teaching data, and courseware text, knowledge point system, teaching objectives and new curriculum standards are used as auxiliary types of teaching data; the classroom ASR text is input into the large language model to obtain an initial classroom evaluation, and after combining the classroom ASR text and other auxiliary types of teaching data, multiple combined initial classroom evaluations are output. Finally, these initial classroom evaluations are spliced ​​and input into the large language model for summary to obtain a final classroom evaluation, which is the prediction result output by the classroom evaluation model.

[0107] S203: Update the classroom evaluation model based on the evaluation results and prediction results corresponding to each of the plurality of first classroom teaching materials.

[0108] Specifically, optimization algorithms such as back propagation and gradient descent can be used to continuously adjust the parameters of the model so that the model can more and more accurately predict the evaluation results of the unknown first classroom teaching materials. Among them, the back propagation algorithm can calculate the contribution of each parameter to the prediction result and adjust the value of the parameter accordingly. The gradient descent algorithm can update the parameters according to the difference between the predicted result and the actual result, and gradually reduce the difference.

[0109] Repeat the above steps until the difference between the model's predicted results and the actual results is small enough, or the preset number of training times is reached. This process can be completed through iterative training. Each iteration will update the model's parameters so that the model gradually approaches the optimal solution. By continuously updating and optimizing the model, the classroom evaluation model can be made more accurate and reliable, and better serve classroom observation and evaluation.

[0110] In some embodiments, before inputting the above-mentioned first classroom teaching materials into the classroom evaluation model, it also includes: obtaining multiple second classroom teaching materials; the above-mentioned second classroom teaching materials include multiple types of teaching data; pre-training the initial model based on the above-mentioned multiple second classroom teaching materials to obtain the above-mentioned classroom evaluation model.

[0111] Specifically, the above-mentioned classroom evaluation model is a pretrained model. The above-mentioned training process belongs to the supervised fine-tuning (SFT) stage. The pre-trained classroom evaluation model can learn the common features in the data from large-scale data. Therefore, in the supervised fine-tuning stage, it can achieve better generalization effect and improve the output accuracy and effectiveness of the model.

[0112] In this embodiment, the initial model pre-training step, the second classroom teaching materials can be obtained from an existing data set, the second classroom teaching materials have a large number of scales, and do not need data annotation. The second classroom teaching materials can be text data in the field of education. By pre-training the general large language model (initial model), the large language model can understand the content in the field of education and obtain a pre-trained model in the field of education.

[0113] The second classroom teaching materials may include multiple types of teaching data, and these teaching data do not need to have a corresponding relationship. The teaching data may include:

[0114] Textbook information: This section includes various versions of educational textbooks, which can cover multiple subjects such as Chinese, mathematics, English, science, etc. These textbook contents can provide basic knowledge points and teaching materials, and are important references for teaching activities.

[0115] Courseware information: This part includes the text content on the courseware, as well as the standards or explanations corresponding to these text contents, which are usually used to assist teaching or learning understanding.

[0116] Classroom video: This part uses speech-to-text technology (ASR) to convert the voice of teachers and students during class into text, which can provide the interaction and communication content between teachers and students during class.

[0117] Lesson plan: This part includes the teacher's pre-design and planning of classroom content, including teaching objectives, content, methods, steps, etc. It can provide teachers with detailed information on how to arrange teaching content and organize teaching activities. It is the core guiding document for teaching activities.

[0118] Knowledge point system information: This part includes the hierarchical relationship of knowledge points in each subject, that is, the mutual relationship and logical structure between each knowledge point.

[0119] Exercise Bank: This part includes after-class exercises and exam exercises in various subjects.

[0120] Classroom evaluation information: This information comes from the evaluation indicators and evaluation reports of previous classroom observations.

[0121] Other information related to teaching: such as teaching software, teaching strategies and other types of teaching resources or information.

[0122] In one or more embodiments of the present application, a first classroom teaching material with multiple known evaluation results is obtained; the first classroom teaching material includes multiple types of teaching data corresponding to the same classroom; the first classroom teaching material is input into the classroom evaluation model, and the prediction result of the first classroom teaching material is output; the classroom evaluation model is updated based on the evaluation results and the prediction results corresponding to each of the multiple first classroom teaching materials. This method can use a machine learning model to replace manual classroom observation and evaluation, which reduces labor costs and speeds up feedback. It also uses multiple types of data information in the field of education and teaching to train the classroom evaluation model, so that the evaluation results it outputs have higher evaluation validity. At the same time, this method has strong scalability, and the trained classroom evaluation model can be easily applied to other types of classroom teaching materials.

[0123] Next, combine Figure 1 , taking the server as the execution subject, introduces the classroom evaluation method provided by the embodiment of the present application. Figure 6 As shown in the figure, the classroom evaluation method includes the following steps:

[0124] S601, obtaining target teaching materials of the class to be evaluated.

[0125] Specifically, the classroom to be evaluated in the embodiment of the present application is a classroom that needs to be observed and evaluated in the classroom, and the place where the educational or teaching activities are carried out includes but is not limited to classrooms, conference rooms in schools, and online education platforms. The classroom to be evaluated can be an education or teaching unit (such as an online course), which usually includes teacher lectures, student participation, questions and answers, discussions, etc., reflecting the students' learning status and the teacher's teaching methods. By evaluating and analyzing the classroom to be evaluated, educators can understand students' learning situation and feedback, improve teaching methods and strategies, and thus improve teaching quality and effectiveness.

[0126] The target teaching materials in the embodiment of the present application include various types of target teaching data, such as classroom dialogue texts, courseware texts, knowledge point systems, teaching objectives, new curriculum standards and other types of target teaching data, and various types of target teaching data are matched with the classroom to be evaluated.

[0127] S602, input the target teaching materials into the classroom evaluation model to obtain the target evaluation results of the classroom to be evaluated.

[0128] The classroom evaluation model is trained based on any of the classroom evaluation model training methods. The trained classroom evaluation model can realize automation and intelligence of classroom evaluation.

[0129] In some embodiments, the classroom evaluation model includes a first language model, and the target teaching materials are input into the classroom evaluation model to obtain the target evaluation result of the classroom to be evaluated, including:

[0130] Splicing all target teaching data in the target teaching materials to obtain target spliced ​​text data;

[0131] Determine whether the target concatenated text data exceeds a preset length threshold;

[0132] When the target concatenated text data does not exceed a preset length threshold, the target concatenated text data is input into the first language model, and a target evaluation result of the class to be evaluated is output.

[0133] In some embodiments, the classroom evaluation model includes a second language model and a third language model, the multiple types of target teaching data include a main type of target teaching data and multiple auxiliary types of target teaching data, and the main type of target teaching data includes target text data obtained by speech recognition from audio data of the classroom to be evaluated;

[0134] After determining whether the target concatenated text data exceeds a preset length threshold, the method further includes:

[0135] When the target concatenated text data exceeds a preset length threshold, combining the target teaching data of the main type in the target teaching material with the target teaching data of the plurality of auxiliary types to obtain a plurality of target combined text data;

[0136] Inputting the target teaching data of the main type and the multiple target combination text data into the second language model, and outputting the first target initial result of the target teaching data of the main type and the second target initial result corresponding to each of the multiple target combination text data;

[0137] The first target initial result and the second target initial result are input into the third language model to output the target evaluation result of the class to be evaluated.

[0138] Specifically, after the target teaching data of various types in the target teaching material are spliced ​​into the target spliced ​​text data, the target spliced ​​text data may be too long. Therefore, it can be determined whether the length of the target spliced ​​text data exceeds a preset length threshold, which can be determined according to the maximum input length of the first language model.

[0139] When the length of the target concatenated text data does not exceed the preset length threshold, the target concatenated text data is input into the first language model of the classroom evaluation model for classroom observation and evaluation to output the target evaluation result of the classroom to be evaluated. Directly inputting the target concatenated text data into the model can make full use of various types of target teaching data, so that the output classroom evaluation has higher accuracy and effectiveness.

[0140] When the length of the target concatenated text data exceeds the preset length threshold, it means that the target concatenated text data cannot be directly input into the first language model of the classroom evaluation model. In order to be able to conduct classroom observation and evaluation, the main type of target teaching data and the auxiliary type of target teaching data in the target teaching data can be combined into target combined text data. Then, after the main type of target teaching data and the target combined text data are respectively input into the second largest language model, multiple initial prediction results can be obtained. Finally, these initial prediction results are spliced ​​together and aggregated through the text summarization ability of the third largest language model to obtain the final prediction result. This method can conduct classroom observation and evaluation of target teaching materials with more content, and it is more extensible. If auxiliary type of target teaching data is added later, it can be quickly updated without affecting other target teaching data.

[0141] It should be noted that, in this embodiment, the length of the target teaching data and target combined text data of the main type should be less than the maximum input length of the second largest language model. The second largest language model and the third largest language model can be the same large language model or a separately set large language model.

[0142] Please refer to the following Figure 7 , Figure 7 The following is a schematic diagram of a classroom evaluation model training device provided by an exemplary embodiment of the present application. Figure 7 As shown, the classroom evaluation model training device 700 includes:

[0143] A first acquisition module 710 is used to acquire a plurality of first classroom teaching materials with known evaluation results; the first classroom teaching materials include a plurality of types of teaching data corresponding to the same classroom;

[0144] A first training module 720, used to input the first classroom teaching data into the classroom evaluation model and output the prediction result of the first classroom teaching data;

[0145] The second training module 730 is used to update the classroom evaluation model based on the evaluation results and the prediction results corresponding to each of the plurality of first classroom teaching materials.

[0146] In some possible embodiments, the classroom evaluation model includes a first language model; the first training module 720 is specifically used for:

[0147] All the teaching data in the first classroom teaching materials are spliced ​​together to obtain spliced ​​text data;

[0148] The concatenated text data is input into the first language model, and the prediction result of the first classroom teaching material is output.

[0149] In some possible embodiments, the classroom evaluation model includes a second language model and a third language model, the multiple types of teaching data include main type teaching data and multiple auxiliary types of teaching data, and the main type of teaching data includes text data obtained by speech recognition of classroom audio data;

[0150] The first training module 720 is specifically used for:

[0151] Combining the main type of teaching data and the auxiliary type of teaching data in the first classroom teaching material to obtain a plurality of combined text data;

[0152] Input the main type of teaching data and the multiple combined text data into the second language model, and output a first initial result of the main type of teaching data and a second initial result corresponding to each of the multiple combined text data;

[0153] The first initial result and the second initial result are input into the third language model, and the prediction result of the first classroom teaching material is output.

[0154] In some possible embodiments, the device 700 further includes:

[0155] A third acquisition module is used to acquire a plurality of second classroom teaching materials; the second classroom teaching materials include a plurality of types of teaching data;

[0156] The third training module is used to pre-train the initial model based on the above-mentioned multiple second classroom teaching materials to obtain the above-mentioned classroom evaluation model.

[0157] The division of each module in the above-mentioned classroom evaluation model training device is only for illustration. In other embodiments, the classroom evaluation model training device can be divided into different modules as needed to complete all or part of the functions of the above-mentioned classroom evaluation model training device. The implementation of each module in the classroom evaluation model training device provided in the embodiments of this specification can be in the form of a computer program. The computer program can be run on a terminal or a server. The program modules constituted by the computer program can be stored in the memory of a terminal or a server. When the computer program is executed by the processor, all or part of the steps of the classroom evaluation model training method described in the embodiments of this specification are implemented.

[0158] Please refer to the following Figure 8 , Figure 8 The following is a schematic diagram of a classroom evaluation device provided by an exemplary embodiment of the present application. Figure 8 As shown, the classroom evaluation device 800 includes:

[0159] The second acquisition module 810 is used to acquire target teaching materials of the class to be evaluated; the target teaching materials include multiple types of target teaching data;

[0160] Evaluation module 820, used to input the target teaching materials into the classroom evaluation model to obtain the target evaluation result of the classroom to be evaluated;

[0161] Among them, the above-mentioned classroom evaluation model is trained based on any of the above-mentioned classroom evaluation model training methods.

[0162] In some possible embodiments, the classroom evaluation model includes a first language model, and the evaluation module 820 is specifically used to:

[0163] All target teaching data in the target teaching materials are spliced ​​together to obtain target spliced ​​text data;

[0164] Determine whether the target concatenated text data exceeds a preset length threshold;

[0165] In the case that the target concatenated text data does not exceed the preset length threshold, the target concatenated text data is input into the first language model, and the target evaluation result of the class to be evaluated is output.

[0166] In some possible embodiments, the classroom evaluation model includes a second language model and a third language model, the multiple types of target teaching data include a main type of target teaching data and multiple auxiliary types of target teaching data, the main type of target teaching data includes target text data obtained by speech recognition of the audio data of the classroom to be evaluated;

[0167] After determining whether the target concatenated text data exceeds a preset length threshold, the evaluation module 820 is further specifically configured to:

[0168] In the case where the target spliced ​​text data exceeds the preset length threshold, combining the target teaching data of the main type in the target teaching material with the target teaching data of the plurality of auxiliary types to obtain a plurality of target combined text data;

[0169] Input the target teaching data of the main type and the multiple target combination text data into the second language model, and output the first target initial result of the target teaching data of the main type and the second target initial results corresponding to the multiple target combination text data respectively;

[0170] The first target initial result and the second target initial result are input into the third language model, and the target evaluation result of the class to be evaluated is output.

[0171] The division of each module in the above-mentioned classroom evaluation device is only for illustration. In other embodiments, the classroom evaluation device can be divided into different modules as needed to complete all or part of the functions of the above-mentioned classroom evaluation device. The implementation of each module in the classroom evaluation device provided in the embodiment of this specification can be in the form of a computer program. The computer program can be run on a terminal or a server. The program module composed of the computer program can be stored in the memory of the terminal or the server. When the computer program is executed by the processor, all or part of the steps of the classroom evaluation method described in the embodiment of this specification are implemented.

[0172] See also Fig. 9 , Fig. 9 This is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of this specification. Fig. 9 As shown, the electronic device 900 may include: at least one processor 910, at least one communication bus 920, a user interface 930, at least one network interface 940, and a memory 950. The communication bus 920 may be used to realize the connection and communication of the above components.

[0173] The user interface 930 may include a display screen (Display) and a camera (Camera), and the optional user interface may also include a standard wired interface and a wireless interface.

[0174] The network interface 940 may optionally include a Bluetooth module, a Near Field Communication (NFC) module, a Wireless Fidelity (Wi-Fi) module, and the like.

[0175] Among them, the processor 910 may include one or more processing cores. The processor 910 uses various interfaces and lines to connect various parts within the entire electronic device 900, and executes various functions and processes data of the routing electronic device 900 by running or executing instructions, programs, code sets or instruction sets stored in the memory 950, and calling data stored in the memory 950. Optionally, the processor 910 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 910 can integrate one or more combinations of a processor (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 910, but may be implemented separately through a chip.

[0176] The memory 950 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 950 includes a non-transitory computer-readable medium. The memory 950 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 950 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as an acquisition function, an evaluation function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 950 may optionally be at least one storage device located away from the aforementioned processor 910. As Fig. 9 As shown, the memory 950 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0177] Specifically, the processor 910 may be used to call the program instructions stored in the memory 950, and specifically perform the following operations:

[0178] Acquire a plurality of first classroom teaching materials with known evaluation results; the first classroom teaching materials include a plurality of types of teaching data corresponding to the same classroom;

[0179] Inputting the first classroom teaching material into the classroom evaluation model, and outputting the prediction result of the first classroom teaching material;

[0180] The classroom evaluation model is updated based on the evaluation results and the prediction results corresponding to each of the plurality of first classroom teaching materials.

[0181] In some possible embodiments, the classroom evaluation model includes a first large language model; when the processor 910 inputs the first classroom teaching material into the classroom evaluation model and outputs the prediction result of the first classroom teaching material, it is specifically used to execute:

[0182] All the teaching data in the first classroom teaching materials are spliced ​​together to obtain spliced ​​text data;

[0183] The concatenated text data is input into the first language model, and the prediction result of the first classroom teaching material is output.

[0184] In some possible embodiments, the classroom evaluation model includes a second language model and a third language model, the multiple types of teaching data include main type teaching data and multiple auxiliary types of teaching data, and the main type of teaching data includes text data obtained by speech recognition of classroom audio data;

[0185] When the processor 910 inputs the first classroom teaching material into the classroom evaluation model and outputs the prediction result of the first classroom teaching material, it is specifically used to execute:

[0186] Combining the main type of teaching data and the auxiliary type of teaching data in the first classroom teaching material to obtain a plurality of combined text data;

[0187] Input the main type of teaching data and the multiple combined text data into the second language model, and output a first initial result of the main type of teaching data and a second initial result corresponding to each of the multiple combined text data;

[0188] The first initial result and the second initial result are input into the third language model, and the prediction result of the first classroom teaching material is output.

[0189] In some possible embodiments, before inputting the first classroom teaching material into the classroom evaluation model, the processor 910 further specifically executes:

[0190] Acquire multiple second-classroom teaching materials; the second-classroom teaching materials include multiple types of teaching data;

[0191] The initial model is pre-trained based on the above-mentioned multiple second classroom teaching materials to obtain the above-mentioned classroom evaluation model.

[0192] In some possible embodiments, the electronic device 900 may be the aforementioned classroom evaluation device, and the processor 910 may further specifically execute:

[0193] Obtaining target teaching materials of the class to be evaluated; the target teaching materials include various types of target teaching data;

[0194] Input the above target teaching materials into the classroom evaluation model to obtain the target evaluation results of the above classroom to be evaluated;

[0195] Among them, the above-mentioned classroom evaluation model is trained based on any of the above-mentioned classroom evaluation model training methods.

[0196] In some possible embodiments, the classroom evaluation model includes a first language model. When the processor 910 inputs the target teaching material into the classroom evaluation model to obtain the target evaluation result of the classroom to be evaluated, the processor 910 is specifically configured to execute:

[0197] All target teaching data in the target teaching materials are spliced ​​together to obtain target spliced ​​text data;

[0198] Determine whether the target concatenated text data exceeds a preset length threshold;

[0199] In the case that the target concatenated text data does not exceed the preset length threshold, the target concatenated text data is input into the first language model, and the target evaluation result of the class to be evaluated is output.

[0200] In some possible embodiments, the classroom evaluation model includes a second language model and a third language model, the multiple types of target teaching data include a main type of target teaching data and multiple auxiliary types of target teaching data, the main type of target teaching data includes target text data obtained by speech recognition of the audio data of the classroom to be evaluated;

[0201] After determining whether the target concatenated text data exceeds a preset length threshold, the processor 910 further specifically executes:

[0202] In the case where the target spliced ​​text data exceeds the preset length threshold, combining the target teaching data of the main type in the target teaching material with the target teaching data of the plurality of auxiliary types to obtain a plurality of target combined text data;

[0203] Input the target teaching data of the main type and the multiple target combination text data into the second language model, and output the first target initial result of the target teaching data of the main type and the second target initial results corresponding to the multiple target combination text data respectively;

[0204] The first target initial result and the second target initial result are input into the third language model, and the target evaluation result of the class to be evaluated is output.

[0205] The embodiment of the present application also provides a computer-readable storage medium, which stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes one or more steps in the above embodiment. If the components of the above classroom evaluation device or classroom evaluation model training device are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium.

[0206] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The above-mentioned computer program product includes one or more computer instructions. When the above-mentioned computer program instructions are loaded and executed on a computer, the above-mentioned process or function according to the embodiment of the present application is generated in whole or in part. The above-mentioned computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The above-mentioned computer instructions can be stored in a computer-readable storage medium or transmitted by the above-mentioned computer-readable storage medium. The above-mentioned computer instructions can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (such as coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The above-mentioned computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, a data center, etc. that contains one or more available media integrated. The above-mentioned available media can be magnetic media (for example, floppy disks, hard disks, tapes), optical media (for example, digital versatile discs (DVD)), or semiconductor media (for example, solid state disks (SSD)), etc.

[0207] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes. In the absence of conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0208] The embodiments described above are merely preferred embodiments of the present application and are not intended to limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements made to the technical solutions of the present application by ordinary technicians in this field should fall within the protection scope determined by the claims.

[0209] The above describes a specific embodiment of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims and the specification can be performed in an order different from the order in the embodiments recorded in the specification and still achieve the desired results. In addition, the process depicted in the drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A classroom evaluation model training method, characterized in that: The method comprises: Acquire a plurality of first classroom teaching materials with known evaluation results; the first classroom teaching materials include a plurality of types of teaching data corresponding to the same classroom; Inputting the first classroom teaching material into a classroom evaluation model, and outputting a prediction result of the first classroom teaching material; The classroom evaluation model is updated based on the evaluation results and the prediction results corresponding to each of the plurality of first classroom teaching materials.

2. The method according to claim 1, characterized in that The classroom evaluation model includes a first language model; the step of inputting the first classroom teaching material into the classroom evaluation model and outputting a prediction result of the first classroom teaching material includes: splicing all the teaching data in the first classroom teaching material to obtain spliced ​​text data; The concatenated text data is input into the first large language model, and a prediction result of the first classroom teaching material is output.

3. The method according to claim 1, characterized in that The classroom evaluation model includes a second language model and a third language model, the multiple types of teaching data include main type teaching data and multiple auxiliary types of teaching data, the main type of teaching data includes text data obtained by speech recognition of classroom audio data; The step of inputting the first classroom teaching material into a classroom evaluation model and outputting a prediction result of the first classroom teaching material comprises: Combining the teaching data of the main type with the teaching data of the auxiliary type in the first classroom teaching material to obtain a plurality of combined text data; Inputting the teaching data of the main type and the multiple combined text data into the second language model, and outputting a first initial result of the teaching data of the main type and second initial results corresponding to each of the multiple combined text data; The first initial result and the second initial result are input into the third language model, and the prediction result of the first classroom teaching material is output.

4. The method according to claim 1, characterized in that: Before inputting the first classroom teaching material into the classroom evaluation model, the method further includes: Acquire a plurality of second classroom teaching materials; the second classroom teaching materials include a plurality of types of teaching data; The initial model is pre-trained based on the multiple second classroom teaching materials to obtain the classroom evaluation model.

5. A classroom evaluation method, characterized in that: The method comprises: Obtaining target teaching materials of the class to be evaluated; the target teaching materials include multiple types of target teaching data; Inputting the target teaching materials into the classroom evaluation model to obtain the target evaluation result of the classroom to be evaluated; Wherein, the classroom evaluation model is trained based on any one of the methods described in claims 1-4.

6. The method according to claim 5, characterized in that The classroom evaluation model includes a first language model, and the target teaching material is input into the classroom evaluation model to obtain the target evaluation result of the classroom to be evaluated, including: Splicing all target teaching data in the target teaching material to obtain target spliced ​​text data; Determining whether the target spliced ​​text data exceeds a preset length threshold; In a case where the target concatenated text data does not exceed the preset length threshold, the target concatenated text data is input into the first large language model, and a target evaluation result of the class to be evaluated is output.

7. The method according to claim 6, characterized in that The classroom evaluation model includes a second language model and a third language model, the multiple types of target teaching data include a main type of target teaching data and multiple types of auxiliary types of target teaching data, the main type of target teaching data includes target text data obtained by speech recognition of audio data of the classroom to be evaluated; After determining whether the target spliced ​​text data exceeds a preset length threshold, the method further includes: In the case where the target concatenated text data exceeds the preset length threshold, combining the target teaching data of the main type in the target teaching material with the target teaching data of the plurality of auxiliary types to obtain a plurality of target combined text data; Input the target teaching data of the main type and the multiple target combination text data into the second language model, and output the first target initial result of the target teaching data of the main type and the second target initial results corresponding to the multiple target combination text data respectively; The first target initial result and the second target initial result are input into the third language model, and the target evaluation result of the class to be evaluated is output.

8. A classroom evaluation model training device, characterized in that: The device comprises: A first acquisition module is used to acquire a plurality of first classroom teaching materials with known evaluation results; the first classroom teaching materials include multiple types of teaching data corresponding to the same classroom; a first training module, used for inputting the first classroom teaching material into a classroom evaluation model and outputting a prediction result of the first classroom teaching material; The second training module is used to update the classroom evaluation model based on the evaluation results and the prediction results corresponding to each of the plurality of first classroom teaching materials.

9. A classroom evaluation device, characterized in that: The device comprises: The second acquisition module is used to acquire target teaching materials of the class to be evaluated; the target teaching materials include multiple types of target teaching data; An evaluation module, used for inputting the target teaching materials into a classroom evaluation model to obtain a target evaluation result of the classroom to be evaluated; Wherein, the classroom evaluation model is trained based on any one of the methods described in claims 1-4.

10. An electronic device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps as claimed in any one of claims 1 to 7.

Images