Teaching quality management and control method and device, computer equipment and storage medium

Abstract

The invention discloses a teaching quality management and control method and device, computer equipment and a storage medium. The method comprises the following steps: analyzing teaching behaviors of teachers and classroom performance behaviors of students in a real teaching video to obtain a first teaching quality evaluation result; generating a second teaching quality evaluation result according to the evaluation of the students on the teaching quality; generating a third teaching quality evaluation result according to the evaluation of the teacher on the teaching quality; generating a fourth teaching quality evaluation result according to the student score; and optimizing the weight of each teaching quality evaluation result by adopting an improved particle swarm optimization algorithm, calculating a comprehensive score through the optimized weight, and generating a final teaching quality evaluation report according to each teaching quality evaluation result and the comprehensive score. Therefore, a technical problem that it is difficult to understand the teaching condition of the teacher in a manner of evaluating the teaching quality only through one manner in the related art is solved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a teaching quality control method, apparatus, computer equipment and storage medium. Background Art

[0002] Teaching quality assessment refers to the evaluation and measurement of the effectiveness and quality of actual teaching and learning. In recent years, every university has recognized the importance of classroom teaching quality assessment and has developed corresponding methods. Student and peer review are mandatory, and some institutions also incorporate evaluation by administrators and supervisors. With the continuous development of information network technology in the field of intelligent education, teaching assessment has also entered the era of intelligentization.

[0003] Invention patent CN119398614 A discloses a teaching quality diagnosis and evaluation method based on behavior recognition, which relates to the field of behavior recognition technology. The teaching quality diagnosis and evaluation method based on behavior recognition includes: step one, collecting real classroom teaching videos and capturing key frames of the video content; step two, detecting teaching video targets and realizing behavior recognition based on target detection and human posture evaluation algorithms; step three, using the trained target detection model to detect the target teaching video image data set, and dividing different classroom types based on the detected teacher behavior; step four, according to the classroom type, determining the student behavior that affects the teaching quality and calculating the teaching quality scoring index; step five, evaluating the teaching quality according to the teaching quality scoring index, and diagnosing problems that affect the teaching quality; through the collection of classroom data from multiple sources, the classroom teaching quality is accurately analyzed and evaluated to assist teachers in precise teaching and students in personalized learning.

[0004] The above invention only uses classroom videos to evaluate teaching quality. It is difficult to understand the teacher's teaching situation by only using one method to evaluate teaching quality. In view of the above problems, no effective solution has been proposed yet. Summary of the Invention

[0005] The embodiments of the present invention provide a teaching quality control method, apparatus, computer equipment and storage medium to at least solve the technical problem in related technologies that it is difficult to understand the teaching situation of teachers by evaluating teaching quality in only one way.

[0006] According to one aspect of an embodiment of the present invention, a teaching quality control method is provided, comprising: obtaining a teaching video of a real classroom, analyzing the teacher's teaching behavior and the students' classroom performance in the real teaching video, and obtaining a first teaching quality evaluation result;

[0007] Collect students' evaluations of teaching quality, and generate a second teaching quality evaluation result based on the students' evaluations of teaching quality;

[0008] Collect teachers' evaluations of teaching quality, and generate the third teaching quality evaluation results based on teachers' evaluations of teaching quality;

[0009] Collect the student scores of teachers in real teaching videos, and generate the fourth teaching quality evaluation results based on the student scores;

[0010] An improved particle swarm optimization algorithm is used to optimize the weights of the first teaching quality evaluation result, the second teaching quality evaluation result, the third teaching quality evaluation result and the fourth teaching quality evaluation result. The comprehensive score is calculated based on the optimized weights, and the final teaching quality evaluation report is generated based on the teaching quality evaluation results and the comprehensive score.

[0011] Optionally, a YOLOv9+RNN deep learning model is used to analyze students' classroom performance behaviors.

[0012] Optionally, a multimodal data fusion method is used to analyze teachers' teaching behaviors.

[0013] Optionally, based on students' evaluation of teaching quality, a random forest algorithm is used to generate a second teaching quality evaluation result.

[0014] Optionally, based on the teacher's evaluation of the teaching quality, a random forest algorithm is used to generate a third teaching quality evaluation result.

[0015] Optionally, it also includes: when a teacher has objections to the final teaching quality evaluation report, he or she may lodge an appeal, and after review, the evaluation will be adjusted to obtain the teaching quality evaluation report after the appeal.

[0016] According to another aspect of an embodiment of the present invention, a teaching quality control device is provided, including:

[0017] The teaching video evaluation module is used to obtain real classroom teaching videos, analyze the teacher's teaching behavior and students' classroom performance in the real teaching videos, and obtain the first teaching quality evaluation results;

[0018] The student evaluation module is used to collect students' evaluation of teaching quality and generate a second teaching quality evaluation result based on the students' evaluation of teaching quality;

[0019] The teacher evaluation module is used to collect teachers' evaluation of teaching quality and generate the third teaching quality evaluation results based on the teachers' evaluation of teaching quality;

[0020] The performance evaluation module is used to collect the student performance of the teacher's corresponding teaching in the real teaching video and generate the fourth teaching quality evaluation result based on the student performance;

[0021] The teaching quality evaluation report generation module uses an improved particle swarm optimization algorithm to optimize the weights of the first teaching quality evaluation result, the second teaching quality evaluation result, the third teaching quality evaluation result and the fourth teaching quality evaluation result, calculates the comprehensive score through the optimized weights, and generates the final teaching quality evaluation report based on the teaching quality evaluation results and the comprehensive score.

[0022] According to another aspect of an embodiment of the present invention, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the methods in various embodiments of the present invention when executing the computer program.

[0023] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0024] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0025] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0026] According to another aspect of an embodiment of the present invention, a computer program is provided. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0027] In the embodiment of the present application, a teaching quality control method is provided, comprising: obtaining a teaching video of a real classroom, analyzing the teaching behavior of a teacher and the classroom performance behavior of students in the real teaching video to obtain a first teaching quality evaluation result; collecting student evaluations of teaching quality, generating a second teaching quality evaluation result according to the student evaluations of teaching quality; collecting teacher evaluations of teaching quality, generating a third teaching quality evaluation result according to the teacher evaluations of teaching quality; collecting student performance corresponding to the teaching of the teacher in the real teaching video, generating a fourth teaching quality evaluation result according to the student performance; using an improved particle swarm optimization algorithm to optimize the weights of the first teaching quality evaluation result, the second teaching quality evaluation result, the third teaching quality evaluation result and the fourth teaching quality evaluation result, calculating a comprehensive score through the optimized weights, and generating a final teaching quality evaluation report according to the teaching quality evaluation results and the comprehensive score. Through the embodiment of the present application, more intelligent and comprehensive teaching quality evaluation can be realized, and opportunities for teachers to appeal and improve are provided, thereby providing a reference for teachers to improve teaching, and thus solving the technical problem that the teaching situation of teachers cannot be understood in the related art by only evaluating teaching quality in one way. BRIEF DESCRIPTION OF DRAWINGS

[0028] The drawings described herein are used to provide further understanding of the present application, form a part of the present application, and the illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0029] Figure 1 is a flowchart of a teaching quality control method according to an embodiment of the present application;

[0030] Figure 2 is a schematic diagram of a teaching quality control device according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0032] It is to be understood that the terminology "first", "second" and the like used in the specification and the claims of the application as well as the foregoing drawings is merely used to distinguish one identifiable element from another, and does not imply a particular order or chronology. It is to be understood that the use of the term "or" in the description or the claims is used to denote non-exclusivity, for example, a process, method, system, product or device that includes a series of steps or elements is not necessarily limited to only those steps or elements that are expressly listed, but can include other steps or elements that are not expressly listed or inherent to such process, method, product or device.

[0033] According to an aspect of the embodiments of the present application, there is provided a teaching quality control method, it is to be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0034] Figure 1 is a flowchart of a teaching quality control method according to an embodiment of the present application, as shown in Figure 1 , the method comprises the following steps:

[0035] Step S10, obtaining a real classroom teaching video, analyzing the teaching behavior of the teacher and the classroom performance behavior of the students in the real teaching video to obtain a first teaching quality evaluation result;

[0036] Step S20, collecting the evaluation of the students on the teaching quality, generating a second teaching quality evaluation result according to the evaluation of the students on the teaching quality;

[0037] Step S30, collecting the evaluation of the teachers on the teaching quality, generating a third teaching quality evaluation result according to the evaluation of the teachers on the teaching quality;

[0038] Step S40, collecting the evaluation of the teachers on the teaching quality, generating a third teaching quality evaluation result according to the evaluation of the teachers on the teaching quality;

[0039] Step S50, using an improved particle swarm optimization algorithm to optimize the weights of the first teaching quality evaluation result, the second teaching quality evaluation result, the third teaching quality evaluation result and the fourth teaching quality evaluation result, calculating a comprehensive score through the optimized weights, and generating a final teaching quality evaluation report according to the teaching quality evaluation results and the comprehensive score.

[0040] In an alternative embodiment, a deep learning model using YOLOv9+RNN is used to analyze the classroom performance behavior of students, which specifically includes the following steps:

[0041] Step S1011, preprocessing the real classroom teaching video, including: labeling the teaching video data, labeling the class and timestamp of each behavior; dividing the teaching video data into frames for target detection and behavior recognition. The teaching video only evaluates the regular classroom in the classroom.

[0042] Step S1012, training the deep learning model of YOLOv9+RNN according to the data preprocessed in step S1011; specifically including the following steps:

[0043] Step S10121, training the YOLOv9 model:

[0044] Using the YOLOv9 model to detect the target of the frame segmented in step S1011, identifying the body parts and behavior categories of the students, and outputting the category and bounding box coordinates of the detected target from the YOLOv9 model, and converting the feature map output from the YOLOv9 model into a one-dimensional feature vector;

[0045] Extracting the feature vector of the target from the output of YOLOv9, including the bounding box coordinates and category information;

[0046] Concatenate the feature vectors of multiple time steps into a sequence to form a time series feature; use the time window method to divide the feature sequence into fixed-length time windows for input into the RNN model.

[0047] Step S10122, training the RNN model:

[0048] Input the sequenced features obtained in step S10121 into the RNN model, and the RNN model models the time series to capture the dynamic changes in student behavior.

[0049] Classify the student's behavior through the RNN model, i.e., the RNN model outputs the category of the student's behavior, such as: looking up, looking down, looking sideways, speaking, standing, etc.

[0050] In addition, the RNN model can also be optimized through a classification loss function (such as cross-entropy loss).

[0051] Step S1013, input the real classroom teaching video into the trained deep learning model of YOLOv9+RNN to obtain the student behavior type affecting the teaching quality;

[0052] Step S1014, calculating the teaching quality score according to the obtained student behavior type of the teaching quality:

[0053] For example: First, assign a weight to each behavior in one of the classroom types: the thresholds for raising the head, lowering the head, tilting the head, talking, and standing are x1, x2, x3, x4, and x5 respectively.

[0054] The number of positive and negative behaviors of each student in a class period is counted according to the behavior judgment rule. The behavior judgment rule is as follows: when the frequency of a behavior is greater than or equal to the corresponding threshold, it is judged as positive or negative behavior. When the frequency of a behavior is less than the corresponding threshold, it is judged as meaningless behavior.

[0055] The impact values ​​of positive and negative behaviors are calculated according to the impact value formula.

[0056] The impact value formula is: Among them, λ max represents the maximum value of the corresponding behavior in one class period, λ avg represents the average value of the corresponding behavior in one class, λ i Indicates the number of behaviors in the corresponding keyframe i.

[0057] The teaching quality score is calculated using the teaching quality score indicator formula based on the number of positive and negative behaviors of each student in a class and the impact value of the positive and negative behaviors.

[0058] The formula for teaching quality rating indicators is:

[0059]

[0060] Among them, a represents the number of students in the class; A represents the positive behavior adjustment value, which ensures that the S result is greater than 0; NPB represents the number of positive behaviors counted in a class; ZNB represents the impact value of negative behavior; k represents the weight, which ranges from 0 to 1.

[0061] Step S1015: Analyze the teaching quality scores obtained. The higher the score, the better the teaching quality; the lower the score, the worse the teaching quality. At the same time, randomly take a certain number of positive behaviors and negative behaviors as the content of the first teaching evaluation quality result.

[0062] In an optional embodiment, a multimodal data fusion method is used to analyze the teacher's teaching behavior, which specifically includes the following steps:

[0063] Step S1021: Preprocess the teaching video of the real classroom, including: image preprocessing, sound data preprocessing and text data preprocessing.

[0064] The picture preprocessing carding divides the teaching video, extracts the key frames, and detects the key frames through the YOLOv9 model to identify the actions and expressions of the teacher. The sound data preprocessing includes extracting the audio data from the teaching video and performing noise reduction processing on the audio data, and then converting the audio into text through speech recognition technology for sentiment analysis. The text data preprocessing includes: performing word segmentation and part-of-speech tagging on the teaching plan corresponding to the teaching video; and converting the text into a vector representation using word embedding technology.

[0065] Step S1022, feature extraction is performed on the preprocessed data, i.e., image feature extraction, sound feature extraction, and text feature extraction are performed respectively to obtain image, sound, and text feature vectors;

[0066] Specifically, a convolutional neural network (CNN) is used to extract the image feature vector. A pre-trained model such as ResNet is used for feature extraction to ensure the robustness and accuracy of the features.

[0067] Mel-frequency cepstral coefficients (MFCC) are used to extract audio features. An LSTM network is used to model the audio sequence to extract time series features.

[0068] Word embedding techniques such as Word2Vec or BERT are used to convert text into vectors. LSTM or Transformer models are used to model the text sequence to extract context information.

[0069] Step S1023, the image, sound, and text feature vectors are input into a multi-modal Transformer model, and the multi-modal Transformer model outputs a predicted evaluation result, which can be a numerical value including the teacher's emotional expression, the matching degree of the course content and the teaching outline, and the final teaching quality score, which can be calculated by weighting. The higher the score, the higher the teaching quality.

[0070] That is, the first teaching quality evaluation result is two teaching quality scores obtained by including the teacher's teaching behavior and the student's classroom performance,

[0071] In an optional embodiment, according to the student's evaluation of the teaching quality, a second teaching quality evaluation result is generated using a random forest algorithm, which includes the following steps:

[0072] Step S201, design a teaching evaluation questionnaire, including teaching objectives, teaching methods, teaching attitudes, classroom management, student participation, etc. A number of specific questions are designed for each aspect, and Likert scale (such as 1-5 points) is used for scoring, and the questionnaire is distributed to students for filling out.

[0073] Step S202, data cleaning and feature processing are performed on the filled-in teaching evaluation questionnaire data. Data cleaning includes checking the completeness of the questionnaire data and processing missing values. Remove duplicate or abnormal data. Feature processing is to take each question in the questionnaire as a feature and the score as a feature value. Encode the basic information of the teacher, such as converting the subject into one-hot encoding.

[0074] Step S203, the preprocessed data is divided into training set and test set. The training set is used to train the random forest model, so that the random forest model outputs the teaching quality score, the analysis result of the key indicators, and provides specific improvement suggestions, etc.

[0075] Step S204, input the test set into the trained random forest model to obtain the student teaching evaluation report, which includes the teaching quality score.

[0076] Step S30 can also use the random forest algorithm to generate a second teaching quality evaluation result according to the collected student evaluation of the teaching quality. The specific steps can refer to the steps of step S20, which will not be repeated here.

[0077] In an optional embodiment, generating a fourth teaching quality evaluation result according to student performance includes the following steps:

[0078] Step S401, collect student test scores, including midterm exam, final exam, homework, test scores, etc. Organize the scores into a structured table, including name, scores.

[0079] Step S402, process missing values and outliers to ensure data integrity and accuracy; and standardize different types of test scores (such as midterm, final, homework) to the same scoring standard (such as 0-100 points).

[0080] Step S403, select indicators, for example, the indicators include: average score, score distribution, progress, and target achievement, wherein the score can be reflected by the standard deviation of the score, the progress can be calculated by the difference between the final and the midterm, and the target achievement can be calculated according to the difference between the student score and the target score. Calculate the index value.

[0081] Step S404, this weighted scoring method, according to the index value obtained in step S403, to score the teaching quality;

[0082] Step S405, the data results calculated in steps S403 and S404 are taken as the fourth teaching quality evaluation result.

[0083] The weight calculation in the step S50 is the teaching quality score in each teaching quality evaluation result, i.e., the teaching quality score calculated in the step S1014, the final teaching quality score obtained in the step S1023, the teaching quality score in the step S204, and the teaching quality score obtained in the step S404.

[0084] In an optional embodiment, when the teacher has objection to the final teaching quality evaluation report, the teacher can file a complaint, and after the audit, the evaluation is adjusted to obtain the teaching quality evaluation report after the complaint.

[0085] According to another aspect of the embodiments of the present application, a teaching quality management and control device is also provided, which can execute the teaching quality management and control method of the above-mentioned embodiments, and the specific implementation method and preferred application scenarios are the same as those of the above-mentioned embodiments, which will not be repeated here.

[0086] Figure 2 is a schematic diagram of a teaching quality management and control device according to an embodiment of the present application, as shown in Figure 2 , the device comprises the following:

[0087] The teaching video evaluation module 10 is configured to obtain a teaching video of a real classroom, analyze the teaching behavior of the teacher and the classroom performance behavior of the students in the real teaching video, and obtain a first teaching quality evaluation result;

[0088] The student evaluation module 20 is configured to collect the evaluation of the students on the teaching quality, and generate a second teaching quality evaluation result according to the evaluation of the students on the teaching quality;

[0089] The teacher evaluation module 30 is configured to collect the evaluation of the teacher on the teaching quality, and generate a third teaching quality evaluation result according to the evaluation of the teacher on the teaching quality;

[0090] The score evaluation module 40 is configured to collect the scores of the students in the real teaching video corresponding to the teaching of the teacher, and generate a fourth teaching quality evaluation result according to the scores of the students;

[0091] The teaching quality evaluation report generation module 50 is configured to optimize the weights of the first teaching quality evaluation result, the second teaching quality evaluation result, the third teaching quality evaluation result, and the fourth teaching quality evaluation result by using the improved particle swarm optimization algorithm, calculate the comprehensive score by using the optimized weights, and generate a final teaching quality evaluation report according to each teaching quality evaluation result and the comprehensive score.

[0092] The embodiments of the present application also provide a computer device, characterized in that the computer device comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the method in the embodiments of the present application.

[0093] The embodiments of the present application further provide a computer readable storage medium comprising a stored executable program, wherein the computer readable storage medium controls the device where the computer readable storage medium is located to execute the method in each embodiment of the present application when the executable program is executed.

[0094] The computer storage medium described above can refer to a medium for storing certain discontinuous physical quantities in a computer memory, and the computer storage medium mainly includes semiconductor, magnetic core, drum, tape, laser disc, etc.

[0095] The embodiments of the present application further provide a computer program product comprising a computer program, which, when executed by a processor, implements the method in each embodiment of the present application.

[0096] The computer program product described above can refer to a software program that has been written, tested and released, and can run on a computer or other device. The computer program product can include application programs, operating systems, tool software, etc., and is used to implement specific functions or solve specific problems.

[0097] The embodiments of the present application further provide a computer program product comprising a non-volatile computer readable storage medium for storing a computer program, which, when executed by a processor, implements the method in each embodiment of the present application.

[0098] The non-volatile computer readable storage medium described above can refer to a medium for storing data, and the non-volatile computer readable storage medium can retain data without loss when power is off, and can be used to store long-term saved data such as operating systems, application programs and user files. The non-volatile storage medium can include hard drives, solid state drives, optical discs and flash memory devices, etc.

[0099] The embodiments of the present application further provide a computer program, which, when executed by a processor, implements the method in each embodiment of the present application described above.

[0100] The computer program described above can refer to a set of instructions for telling a computer to perform specific tasks or operations. The computer program can be written by a programmer using a specific programming language, and can include algorithms, data structures, logic and control flow, etc. The computer program can be used for various purposes, including application software, operating systems, etc.

[0101] In the above embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0102] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other ways. Among them, the above-described device embodiments are only illustrative, for example, the division of units can be a logical function division, and actual implementation can have another division way, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or modules shown or discussed can be indirect coupling or communication connection between the units or modules through some interfaces, and can be electrical or other forms.

[0103] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0104] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0105] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the technical solutions or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0106] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A teaching quality control method, characterized in that: include: Obtain real classroom teaching videos, analyze the teacher's teaching behavior and students' classroom performance in the real teaching videos, and obtain the first teaching quality evaluation results; Collect students' evaluations of teaching quality, and generate a second teaching quality evaluation result based on the students' evaluations of teaching quality; Collect teachers' evaluations of teaching quality, and generate the third teaching quality evaluation results based on teachers' evaluations of teaching quality; Collect the student scores of teachers in real teaching videos, and generate the fourth teaching quality evaluation results based on the student scores; An improved particle swarm optimization algorithm is used to optimize the weights of the first teaching quality evaluation result, the second teaching quality evaluation result, the third teaching quality evaluation result and the fourth teaching quality evaluation result. The comprehensive score is calculated based on the optimized weights, and the final teaching quality evaluation report is generated based on the teaching quality evaluation results and the comprehensive score.

2. The teaching quality control method according to claim 1, characterized in that: The YOLOv9+RNN deep learning model is used to analyze students' classroom performance.

3. The teaching quality control method according to claim 2, characterized in that: The analysis of students’ classroom behavior using the YOLOv9+RNN deep learning model includes the following steps: Step S1011: Preprocessing the teaching video of the real classroom, including: labeling the teaching video data, marking the category and timestamp of each behavior; dividing the teaching video data into frames; Step S1012: training the YOLOv9+RNN deep learning model based on the data preprocessed in step S1011; Step S1013: Input the real classroom teaching video into the trained YOLOv9+RNN deep learning model to obtain the student behavior types that affect the teaching quality; Step S1014: Calculate the teaching quality score based on the obtained student behavior type of the teaching quality; Step S1015: Analyze the teaching quality scores obtained. The higher the score, the better the teaching quality; the lower the score, the worse the teaching quality; randomly set a set number of positive behavior and negative behavior pictures as the content of the first teaching evaluation quality result.

4. The teaching quality control method according to claim 1, characterized in that: Multimodal data fusion method is used to analyze teachers' teaching behavior.

5. The teaching quality control method according to claim 1, characterized in that: Based on students' evaluation of teaching quality, the random forest algorithm is used to generate the second teaching quality evaluation results.

6. The teaching quality control method according to claim 1, characterized in that: Also includes: When teachers have objections to the final teaching quality evaluation report, they can file an appeal, and the evaluation will be adjusted after review, and the teacher will receive the teaching quality evaluation report after the appeal.

7. A teaching quality control device, characterized in that: include: The teaching video evaluation module is used to obtain real classroom teaching videos, analyze the teacher's teaching behavior and students' classroom performance in the real teaching videos, and obtain the first teaching quality evaluation results; The student evaluation module is used to collect students' evaluation of teaching quality and generate a second teaching quality evaluation result based on the students' evaluation of teaching quality; The teacher evaluation module is used to collect teachers' evaluation of teaching quality and generate the third teaching quality evaluation results based on the teachers' evaluation of teaching quality; The performance evaluation module is used to collect the student performance of the teacher's corresponding teaching in the real teaching video and generate the fourth teaching quality evaluation result based on the student performance; The teaching quality evaluation report generation module uses an improved particle swarm optimization algorithm to optimize the weights of the first teaching quality evaluation result, the second teaching quality evaluation result, the third teaching quality evaluation result and the fourth teaching quality evaluation result, calculates the comprehensive score through the optimized weights, and generates the final teaching quality evaluation report based on the teaching quality evaluation results and the comprehensive score.

8. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the teaching quality control method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored executable program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the teaching quality control method according to any one of claims 1 to 6.

10. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the teaching quality control method according to any one of claims 1 to 6.

Images