Teaching quality analysis method and system based on data processing

Abstract

The present invention relates to a teaching quality analysis method based on data processing, which belongs to the field of teaching quality supervision. The method includes: intelligently analyzing various teaching quality parameters corresponding to the current single teaching of the target classroom based on a set distance, the number of frames of each frame of the teaching monitoring screen, various teaching configuration information of the target classroom, and the time-sharing visual data of the target classroom in the current single teaching; mapping the teaching quality data corresponding to the current single teaching of the target classroom based on the various teaching quality parameters. The present invention also relates to a teaching quality analysis system based on data processing. Through the present invention, in order to solve the technical problem of the difficulty in evaluating the teaching quality of offline teaching, an artificial intelligence model can be introduced to realize the intelligent analysis of various teaching quality parameters corresponding to the current single teaching of the target classroom based on various customized filtered basic data, and then map out the teaching quality data of the current single teaching of the target classroom, thereby solving the above technical problems.

Description

Technical Field

[0001] The present invention relates to the field of teaching quality supervision, and in particular to a teaching quality analysis method and system based on data processing. Background Art

[0002] Teaching quality is crucial to students' all-round development and the overall completion of teaching tasks. Therefore, monitoring teaching quality is essential. This refers to the monitoring organization's continuous oversight of teaching quality, regularly collecting information on the quality of teaching work, teaching outcomes, and educational conditions. This analysis identifies potential issues and provides key data for developing appropriate solutions.

[0003] For example, Chinese invention patent publication CN110111011A proposes a teaching quality monitoring method, device, and electronic device. These methods collect teacher-student interaction data within a preset teaching assessment duration during online classes, and then calculate the value of a preset teaching indicator based on the data corresponding to the preset teaching indicator in the collected teacher-student interaction data. This allows the implementation process to provide accurate and reliable teaching indicator data, which can be used to evaluate and monitor the teaching quality of teachers, thereby ensuring teaching quality to a certain extent.

[0004] For example, Chinese invention patent publication CN106570802A proposes a course teaching quality evaluation and monitoring system, which includes: a server, which has an evaluation database for storing multiple evaluation subjects; a mobile client, which has multiple digital touch buttons and multiple evaluation subject touch buttons on its front; a control module for controlling a prompter to issue a prompt to remind the user to evaluate the course, and the evaluation process is: selecting evaluation subjects one by one through multiple evaluation subject touch buttons, and after selecting one of the evaluation subjects, inputting the evaluation score of the evaluation subject through multiple digital touch buttons; the control module uploads each evaluation subject and the evaluation score to the server. The present invention provides a mobile client, and students must submit their evaluation of the course upon completion of the course, which makes it convenient for students to provide timely feedback on various aspects of the course; moreover, the mobile client can be carried around, which is particularly suitable for practical subjects such as integrated wiring systems.

[0005] However, the technical solutions for teaching quality analysis involved in the above-mentioned existing technologies are either simple evaluation mechanisms for online teaching, or student evaluation mechanisms involving distributed architectures. The former solves the evaluation of online teaching, and the online teaching environment is relatively simple. The latter involves students' evaluation of teachers, and the evaluation results are subjective to the students, and the objectivity of the evaluated teaching quality data cannot be guaranteed. Therefore, the existing technology requires a technical solution that can objectively evaluate the teaching quality of complex offline teaching classroom environments to solve the technical problem of difficult offline teaching quality evaluation. Summary of the Invention

[0006] In order to solve technical problems in related fields, the present invention provides a teaching quality analysis method and system based on data processing. By introducing an artificial intelligence model with targeted structural design, based on various customized and screened basic data, an intelligent analysis of various teaching quality parameters corresponding to the current single class of teaching in the target classroom is realized, and the teaching quality data of the current single class of teaching in the target classroom is mapped out based on the various teaching quality parameters corresponding to the current single class of teaching in the target classroom, thereby completing a reliable evaluation of the teaching quality of offline teaching based on the artificial intelligence model.

[0007] According to a first aspect of the present invention, a teaching quality analysis method based on data processing is provided, the method comprising:

[0008] Acquire various teaching configuration information of the target classroom, wherein the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor space, and the number of desks in a single row of a desk array;

[0009] Obtaining each copy of visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, wherein the single copy of visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel point in the teaching monitoring screen frame, the depth of field value corresponding to each student target in the teaching monitoring screen frame, and the number of pixels occupied by each student target in the teaching monitoring screen frame;

[0010] performing a set total number of learning cycles on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, and outputting the convolutional neural network after the multiple learning cycles as a teaching quality parser, wherein the number of learning cycles is positively correlated with the number of students enrolled in the target classroom;

[0011] The teaching quality parser is used to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and output them as various teaching quality parameters corresponding to the current single teaching session in the target classroom;

[0012] Mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom;

[0013] Among them, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping relationship in which the number of sleepy students and the total duration of sleepiness corresponding to the current single teaching session in the target classroom are respectively inversely correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping, and a numerical mapping relationship in which the number of interactions and the total duration of interactions corresponding to the current single teaching session in the target classroom are respectively in positively correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping;

[0014] Among them, each frame of the teaching monitoring screen is captured by a teaching shooting device set above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within the single time interval corresponding to the current single teaching.

[0015] According to a second aspect of the present invention, a teaching quality analysis system based on data processing is provided, the system comprising a memory and one or more processors, the memory storing a computer program, the computer program being configured to be executed by the one or more processors to perform the following steps:

[0016] Acquire various teaching configuration information of the target classroom, wherein the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor space, and the number of desks in a single row of a desk array;

[0017] Obtaining each copy of visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, wherein the single copy of visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel point in the teaching monitoring screen frame, the depth of field value corresponding to each student target in the teaching monitoring screen frame, and the number of pixels occupied by each student target in the teaching monitoring screen frame;

[0018] performing a set total number of learning cycles on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, and outputting the convolutional neural network after the multiple learning cycles as a teaching quality parser, wherein the number of learning cycles is positively correlated with the number of students enrolled in the target classroom;

[0019] The teaching quality parser is used to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and output them as various teaching quality parameters corresponding to the current single teaching session in the target classroom;

[0020] Mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom;

[0021] Among them, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping relationship in which the number of sleepy students and the total duration of sleepiness corresponding to the current single teaching session in the target classroom are respectively inversely correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping, and a numerical mapping relationship in which the number of interactions and the total duration of interactions corresponding to the current single teaching session in the target classroom are respectively in positively correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping;

[0022] Among them, each frame of the teaching monitoring screen is captured by a teaching shooting device set above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within the single time interval corresponding to the current single teaching.

[0023] According to a third aspect of the present invention, a teaching quality analysis system based on data processing is provided, the system comprising:

[0024] The first input unit is used to obtain various teaching configuration information of the target classroom, wherein the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor space, and the number of desks in a single row of a desk array;

[0025] The second input mechanism is used to obtain the visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, where the visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel in the teaching monitoring screen, the depth of field value corresponding to each student target in the teaching monitoring screen, and the number of pixels occupied by each student target in the teaching monitoring screen;

[0026] a model reconstruction mechanism, configured to perform a set number of multiple learnings on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, and output the convolutional neural network after completing the multiple learnings as a teaching quality parser, wherein the number of learnings is positively correlated with the number of students enrolled in the target classroom;

[0027] a quality analysis mechanism, connected to the first input mechanism, the second input mechanism, and the model reconstruction mechanism, respectively, for using the teaching quality analysis body to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session of the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and output them as various teaching quality parameters corresponding to the current single teaching session of the target classroom;

[0028] a numerical mapping mechanism, connected to the quality analysis mechanism, for mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom;

[0029] Among them, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping relationship in which the number of sleepy students and the total duration of sleepiness corresponding to the current single teaching session in the target classroom are respectively inversely correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping, and a numerical mapping relationship in which the number of interactions and the total duration of interactions corresponding to the current single teaching session in the target classroom are respectively in positively correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping;

[0030] Among them, each frame of the teaching monitoring screen is captured by a teaching shooting device set above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within the single time interval corresponding to the current single teaching.

[0031] Compared with the prior art, the present invention has at least the following key inventive features:

[0032] First, an AI solution is provided to analyze the teaching quality data of a target classroom's current single-session lesson. This AI solution uses a custom-designed teaching quality parser, a convolutional neural network that has completed multiple learning cycles. The number of learning cycles is positively correlated with the number of students enrolled in the target classroom, allowing AI models with different structures to be customized for different classrooms.

[0033] Secondly: In order to ensure the effectiveness and stability of the intelligent analysis results of the teaching quality analyzer, a number of basic data were specifically screened for the teaching quality analyzer, namely the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor space, and the number of desks in a single row of the desk array. The visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session are the color component values of each pixel point in the teaching monitoring screen, the depth of field values corresponding to each student target in the teaching monitoring screen, and the number of occupied pixels corresponding to each student target in the teaching monitoring screen. The above-mentioned sufficient and comprehensive screening of multiple basic data further ensures the effectiveness and stability of the intelligent analysis results;

[0034] Again: based on the number of sleepy students, the total duration of sleepiness, the number of interactions and the total duration of interactions corresponding to the current single teaching in the target classroom obtained through intelligent analysis, the teaching quality data corresponding to the current single teaching in the target classroom is mapped. The number of sleepy students and the total duration of sleepiness corresponding to the current single teaching in the target classroom are respectively inversely correlated with the teaching quality data corresponding to the current single teaching in the target classroom obtained by mapping. The number of interactions and the total duration of interactions corresponding to the current single teaching in the target classroom are respectively in a positively correlated numerical mapping relationship with the teaching quality data corresponding to the current single teaching in the target classroom obtained by mapping, thereby completing a targeted evaluation of the teaching quality of the current single teaching in the target classroom;

[0035] Finally: In each learning execution of the convolutional neural network, the known number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to a single teaching session in the history of the target classroom are used as the output contents of the convolutional neural network, and the set distance, the number of frames of each frame of the teaching monitoring screen, the various teaching configuration information of the target classroom, and the various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in a single teaching session in the history are used as the input contents of the convolutional neural network to execute this learning, thereby ensuring the learning effect of each learning of the convolutional neural network. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The embodiments of the present invention will be described below with reference to the accompanying drawings, in which:

[0037] Figure 1 Schematic diagram of the working scenario of the teaching quality analysis method and system based on data processing according to the present invention.

[0038] Figure 2 The figure is a flowchart of the steps of the teaching quality analysis method based on data processing according to embodiment 1 of the present invention.

[0039] Figure 3 This is a flowchart of the steps of a teaching quality analysis method based on data processing according to embodiment 2 of the present invention.

[0040] Figure 4 This is a flowchart of the steps of a teaching quality analysis method based on data processing according to Example 3 of the present invention.

[0041] Figure 5 This is a flowchart of the steps of a teaching quality analysis method based on data processing according to embodiment 4 of the present invention.

[0042] Figure 6 Schematic diagram of the structure of a teaching quality analysis system based on data processing according to embodiment 5 of the present invention.

[0043] Figure 7 Schematic diagram of the structure of a teaching quality analysis system based on data processing according to embodiment 6 of the present invention. DETAILED DESCRIPTION

[0044] The embodiments of the present invention will be described below with reference to the accompanying drawings, in which:

[0045] Figure 1 Schematic diagram of the working scenario of the teaching quality analysis method and system based on data processing according to the present invention.

[0046] Figure 2The figure is a flowchart of the steps of the teaching quality analysis method based on data processing according to embodiment 1 of the present invention.

[0047] Figure 3 This is a flowchart of the steps of a teaching quality analysis method based on data processing according to embodiment 2 of the present invention.

[0048] Figure 4 This is a flowchart of the steps of a teaching quality analysis method based on data processing according to Example 3 of the present invention.

[0049] Figure 5 This is a flowchart of the steps of a teaching quality analysis method based on data processing according to embodiment 4 of the present invention.

[0050] Figure 6 Schematic diagram of the structure of a teaching quality analysis system based on data processing according to embodiment 5 of the present invention.

[0051] Figure 7 Schematic diagram of the structure of a teaching quality analysis system based on data processing according to embodiment 6 of the present invention.

[0052] Figure 1 A schematic diagram of the working scenario of the teaching quality analysis method and system based on data processing according to the present invention is given.

[0053] like Figure 1 As shown, the specific technical process of the present invention is as follows:

[0054] Technical process 1: Build a customized teaching quality analysis body for the analysis of the teaching quality information of the current single teaching session in the target classroom;

[0055] Specifically, the teaching quality parser is an artificial intelligence model, and its structure customization is reflected in the following three aspects:

[0056] Aspect A: The teaching quality parser is a convolutional neural network that has completed multiple learning cycles. The number of learning cycles of the convolutional neural network is positively correlated with the number of students enrolled in the target classroom, thereby customizing artificial intelligence models with different structures for different classrooms.

[0057] Aspect B: Targeted screening of multiple basic data for the teaching quality analysis body includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor space, and the number of desks in a single row of the desk array. The visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session are also included. The single visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel in the teaching monitoring screen, the depth of field value corresponding to each student target in the teaching monitoring screen, and the number of occupied pixels corresponding to each student target in the teaching monitoring screen. The above-mentioned comprehensive and comprehensive screening of multiple basic data further ensures the effectiveness and stability of the intelligent analysis results.

[0058] like Figure 1 As shown, each frame of the teaching monitoring picture is captured by a teaching shooting device suspended above the podium in the target classroom in a time-sharing manner;

[0059] For example, the duration of a single teaching session in the target classroom is a set duration value between 45 minutes and 60 minutes;

[0060] Aspect C: Targeted design of each model reconstruction process of the teaching quality parser, that is, each learning process of the convolutional neural network, to ensure the learning effect of each learning process of the convolutional neural network;

[0061] Specifically, in each learning process of the convolutional neural network, the number of dozing students, the total duration of dozing, the number of interactions, and the total duration of interactions corresponding to a single teaching session in the history of the target classroom are used as the output content of the convolutional neural network, and the set distance, the number of frames of each teaching monitoring screen, the teaching configuration information of the target classroom, and the visual data corresponding to each frame of the teaching monitoring screen of the target classroom in a single teaching session in the history are used as the input content of the convolutional neural network to perform this learning process;

[0062] Technical process 2: Use the teaching quality analyzer designed by the customized structure in technical process 1 to perform intelligent analysis of the teaching quality information of the current single lesson in the target classroom to obtain multiple teaching quality parameters output by the teaching quality analyzer;

[0063] Specifically, the teaching quality parser outputs multiple teaching quality parameters, including the number of dozing students, the total duration of dozing, the number of interactions, and the total duration of interactions corresponding to the current single teaching period in the target classroom;

[0064] Technical process three: mapping the teaching quality data corresponding to the current single class in the target classroom based on the multiple teaching quality parameters obtained through intelligent analysis in technical process two;

[0065] For example, the number of sleepy students and the total duration of sleepiness corresponding to the current single teaching period in the target classroom are respectively in a numerical mapping relationship with the teaching quality data corresponding to the current single teaching period in the target classroom obtained by mapping.

[0066] Furthermore, the number of interactions and the total duration of interactions corresponding to the current single teaching session in the target classroom are respectively in a numerical mapping relationship with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping;

[0067] It can be seen that through the coordinated operation of the above-mentioned technical processes, a targeted evaluation of the teaching quality of the current single class in the target classroom is completed.

[0068] The key points of the present invention are: the specific design of teaching quality analysis bodies with different structures for different target classrooms, the targeted design of each reconstruction process of the teaching quality analysis body, and the numerical mapping process of the number of sleepy students, the total duration of sleepiness, the number of interactions and the total duration of interactions corresponding to the current single teaching in the target classroom obtained based on intelligent analysis to the teaching quality data corresponding to the current single teaching in the target classroom.

[0069] The data processing-based teaching quality analysis method and system of the present invention will be specifically described below in the form of embodiments.

[0070] Example 1

[0071] Figure 2 The figure is a flowchart of the steps of the teaching quality analysis method based on data processing according to embodiment 1 of the present invention.

[0072] like Figure 2 As shown, the teaching quality analysis method based on data processing includes the following specific steps:

[0073] Step S1001: Acquire various teaching configuration information of a target classroom, wherein the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor space, and the number of desks in a single row of a desk array;

[0074] For example, a plurality of different configuration capture units may be selected to respectively obtain various teaching configuration information of the target classroom, including the number of registered students in the target classroom, the duration of a single teaching session, the floor area of the classroom, and the number of desks in a single row of a desk array;

[0075] Step S1002: Acquire each set of visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session. The single set of visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel in the teaching monitoring screen, the depth of field value corresponding to each student target in the teaching monitoring screen, and the number of pixels occupied by each student target in the teaching monitoring screen.

[0076] For example, obtaining each copy of visual data corresponding to each frame of teaching monitoring screen of the target classroom in the current single teaching session, wherein the single copy of visual data corresponding to each frame of teaching monitoring screen is a color component value of each pixel point in the frame of teaching monitoring screen, a depth of field value corresponding to each student target in the frame of teaching monitoring screen, and a number of occupied pixels corresponding to each student target in the frame of teaching monitoring screen, including: the resolution and clarity of each frame of teaching monitoring screen are the same;

[0077] Step S1003: performing a set number of learning cycles on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, and outputting the convolutional neural network after the multiple learning cycles as a teaching quality parser, wherein the number of learning cycles is positively correlated with the number of students enrolled in the target classroom;

[0078] For example, the positive correlation between the number of learning times and the number of registered students in the target classroom includes: the number of registered students in the target classroom is 30, the number of learning times is 50, the number of registered students in the target classroom is 40, the number of learning times is 100, the number of registered students in the target classroom is 50, the number of learning times is 150, the number of registered students in the target classroom is 60, the number of learning times is 200, and so on;

[0079] Step S1004: Using the teaching quality parser to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and outputting the result as various teaching quality parameters corresponding to the current single teaching session in the target classroom;

[0080] Specifically, a numerical simulation mode can be selected to realize the simulation and test of the data processing process of outputting various teaching quality parameters corresponding to the current single teaching session of the target classroom using the teaching quality analyzer to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session of the target classroom based on the set distance, the number of frames of each teaching monitoring screen, the various teaching configuration information of the target classroom, and the various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session;

[0081] Step S1005: mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of dozing students, the total duration of dozing, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom;

[0082] For example, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping function with N inputs and a single output can be selected to represent the numerical mapping relationship between the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom and the teaching quality data corresponding to the current single teaching session in the target classroom;

[0083] Among them, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping relationship in which the number of sleepy students and the total duration of sleepiness corresponding to the current single teaching session in the target classroom are respectively inversely correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping, and a numerical mapping relationship in which the number of interactions and the total duration of interactions corresponding to the current single teaching session in the target classroom are respectively in positively correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping;

[0084] Each frame of the teaching monitoring screen is captured by a teaching camera installed above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within the single-session time interval corresponding to the current single-session teaching.

[0085] For example, each frame of the teaching monitoring screen is captured by a teaching camera installed above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within a single-session time interval corresponding to the current single teaching session. This includes: when a teaching camera with a frame rate of 30 frames per second is used and the single-session time interval is 60 minutes, there are 30×60×60 frames, that is, 108,000 frames of teaching monitoring screens are evenly distributed within a single-session time interval lasting 60 minutes.

[0086] wherein, performing a set total number of multiple learnings on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, outputting the convolutional neural network after completing the multiple learnings as a teaching quality parser, and the number of learnings being positively correlated with the number of registered students in the target classroom, including: in each learning performed on the convolutional neural network, using the known number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to a single teaching session in the history of the target classroom as various output contents of the convolutional neural network, using the set distance, the number of frames of each frame of the teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in a single teaching session in the history as various input contents of the convolutional neural network, and performing this learning;

[0087] The single visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel point in the frame of the teaching monitoring screen, the depth of field value corresponding to each student target in the frame of the teaching monitoring screen, and the number of occupied pixels corresponding to each student target in the frame of the teaching monitoring screen. The single depth of field value corresponding to each student target in the frame of the teaching monitoring screen is the median value of the depth of field values corresponding to each pixel point in the imaging area of the student target in the frame of the teaching monitoring screen.

[0088] And wherein, the single visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel point in the frame of the teaching monitoring screen, the depth of field value corresponding to each student target in the frame of the teaching monitoring screen, and the number of occupied pixel points corresponding to each student target in the frame of the teaching monitoring screen, and also includes: the single number of occupied pixel points corresponding to each student target in the frame of the teaching monitoring screen is the total number of pixel points of the student target in the imaging area of the frame of the teaching monitoring screen.

[0089] Example 2

[0090] Figure 3 This is a flowchart of the steps of a teaching quality analysis method based on data processing according to embodiment 2 of the present invention.

[0091] like Figure 3 As shown, Figure 2 Different from the embodiment in, in the teaching quality analysis method based on data processing, after performing a set total number of multiple learnings on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, the convolutional neural network after completing the multiple learnings is output as a teaching quality parser, and the number of learnings is positively correlated with the number of registered students in the target classroom, that is, after step S1003, the method further includes:

[0092] Step S1006: completing the model storage of the teaching quality analysis body by storing various model parameters of the teaching quality analysis body;

[0093] Specifically, completing the model storage of the teaching quality analysis body by storing various model parameters of the teaching quality analysis body includes: selecting to use a TF storage chip, an MMC storage chip or an SD storage chip to realize the storage of various model parameters of the teaching quality analysis body.

[0094] Example 3

[0095] Figure 4 This is a flowchart of the steps of a teaching quality analysis method based on data processing according to Example 3 of the present invention.

[0096] like Figure 4 As shown, Figure 2 Unlike the embodiment in, in the teaching quality analysis method based on data processing, before obtaining various teaching configuration information of the target classroom, wherein the various teaching configuration information of the target classroom is the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor area, and the number of desks in a single row of a desk array, that is, before step S1001, the method further includes:

[0097] Step S1007: arranging the teaching camera for the target classroom so that the teaching camera is set above the podium in the target classroom and at a set distance from the ground;

[0098] The step of arranging the teaching camera device in the target classroom so as to place the teaching camera device above the podium in the target classroom and at a set distance from the ground comprises: setting a frame rate of the teaching camera device to a value equal to the number of frames of each teaching monitoring screen divided by the duration of a single teaching session;

[0099] For example, the teaching shooting device has a built-in CMOS sensor, a filter body, a shooting bracket, a shell, a flexible circuit board and an imaging lens. The filter body is arranged between the CMOS sensor and the imaging lens, the CMOS sensor is mounted on the flexible circuit board, the shooting bracket is used to support the shell, and the flexible circuit board is arranged inside the shell.

[0100] Example 4

[0101] Figure 5 This is a flowchart of the steps of a teaching quality analysis method based on data processing according to embodiment 4 of the present invention.

[0102] like Figure 5 As shown, Figure 2 Unlike the embodiment in , in the teaching quality analysis method based on data processing, after mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom, that is, after step S1005, the method further includes:

[0103] Step S1008: sending the teaching quality data corresponding to the current single teaching session in the target classroom to a remote teaching quality monitoring server via a wireless communication link;

[0104] Specifically, sending the teaching quality data corresponding to the current single-session teaching in the target classroom to the remote teaching quality supervision server via a wireless communication link includes: the wireless communication link is a time division duplex communication link or a frequency division duplex communication link.

[0105] Next, various method embodiments of the present invention will be described in detail.

[0106] In the teaching quality analysis method based on data processing according to various method embodiments of the present invention:

[0107] The teaching quality parser is used to intelligently analyze the number of dozing students, the total duration of dozing, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and output various teaching quality parameters corresponding to the current single teaching session in the target classroom, including: the total duration of dozing corresponding to the current single teaching session in the target classroom is the cumulative value of the duration of dozing of various students who have experienced a dozing process in the current single teaching session;

[0108] For example, the total dozing duration corresponding to the current single teaching session in the target classroom is the cumulative value of the dozing duration of each student who has dozed off in the current single teaching session. If, in the current single teaching session, student A and student B have dozed off twice, totaling 2 minutes, and student B has dozed off five times, totaling 10 minutes, then the cumulative value of the dozing duration of each student who has dozed off in the current single teaching session is 12 minutes.

[0109] The single visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel in the frame of the teaching monitoring screen, the depth of field value corresponding to each student target in the frame of the teaching monitoring screen, and the number of occupied pixels corresponding to each student target in the frame of the teaching monitoring screen. The color component value of each pixel in the frame of the teaching monitoring screen is the red and green component value, the black and white component value, and the yellow and blue component value of the pixel in the LAB color space;

[0110] Specifically, the color component value of each pixel in the teaching monitoring screen of this frame is the red and green component value, black and white component value and yellow and blue component value of the pixel in the LAB color space, including: the color component value of each pixel is the red and green component value, black and white component value and yellow and blue component value of the pixel in the LAB color space, and the value of any component is between 0-255.

[0111] And in the teaching quality analysis method based on data processing according to various method embodiments of the present invention:

[0112] The teaching configuration information of the target classroom includes the number of registered students, the duration of a single teaching session, the floor space of the classroom, and the number of desks in a single row of a desk array. The target classroom includes: the desk array of the target classroom is a matrix array, and the number of desks in a single row of the desk array of the target classroom is the number of desks in each row of the matrix array.

[0113] Among them, the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor area, and the number of desks in a single row of the desk array, and also includes: the duration of a single teaching session in the target classroom is a set duration value between 45 minutes and 60 minutes.

[0114] Example 5

[0115] Figure 6 Schematic diagram of the structure of a teaching quality analysis system based on data processing according to embodiment 5 of the present invention.

[0116] like Figure 6As shown, the data processing-based teaching quality analysis system includes a memory and one or more processors, the memory stores a computer program, and the computer program is configured to be executed by the one or more processors to complete the following steps:

[0117] Step S1001: Acquire various teaching configuration information of a target classroom, wherein the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor space, and the number of desks in a single row of a desk array;

[0118] For example, a plurality of different configuration capture units may be selected to respectively obtain various teaching configuration information of the target classroom, including the number of registered students in the target classroom, the duration of a single teaching session, the floor area of the classroom, and the number of desks in a single row of a desk array;

[0119] Step S1002: Acquire each set of visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session. The single set of visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel in the teaching monitoring screen, the depth of field value corresponding to each student target in the teaching monitoring screen, and the number of pixels occupied by each student target in the teaching monitoring screen.

[0120] For example, obtaining each copy of visual data corresponding to each frame of teaching monitoring screen of the target classroom in the current single teaching session, wherein the single copy of visual data corresponding to each frame of teaching monitoring screen is a color component value of each pixel point in the frame of teaching monitoring screen, a depth of field value corresponding to each student target in the frame of teaching monitoring screen, and a number of occupied pixels corresponding to each student target in the frame of teaching monitoring screen, including: the resolution and clarity of each frame of teaching monitoring screen are the same;

[0121] Step S1003: performing a set number of learning cycles on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, and outputting the convolutional neural network after the multiple learning cycles as a teaching quality parser, wherein the number of learning cycles is positively correlated with the number of students enrolled in the target classroom;

[0122] For example, the positive correlation between the number of learning times and the number of registered students in the target classroom includes: the number of registered students in the target classroom is 30, the number of learning times is 50, the number of registered students in the target classroom is 40, the number of learning times is 100, the number of registered students in the target classroom is 50, the number of learning times is 150, the number of registered students in the target classroom is 60, the number of learning times is 200, and so on;

[0123] Step S1004: Using the teaching quality parser to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and outputting the result as various teaching quality parameters corresponding to the current single teaching session in the target classroom;

[0124] Specifically, a numerical simulation mode can be selected to realize the simulation and test of the data processing process of outputting various teaching quality parameters corresponding to the current single teaching session of the target classroom using the teaching quality analyzer to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session of the target classroom based on the set distance, the number of frames of each teaching monitoring screen, the various teaching configuration information of the target classroom, and the various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session;

[0125] Step S1005: mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of dozing students, the total duration of dozing, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom;

[0126] For example, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping function with N inputs and a single output can be selected to represent the numerical mapping relationship between the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom and the teaching quality data corresponding to the current single teaching session in the target classroom;

[0127] Among them, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping relationship in which the number of sleepy students and the total duration of sleepiness corresponding to the current single teaching session in the target classroom are respectively inversely correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping, and a numerical mapping relationship in which the number of interactions and the total duration of interactions corresponding to the current single teaching session in the target classroom are respectively in positively correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping;

[0128] Each frame of the teaching monitoring screen is captured by a teaching camera installed above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within the single-session time interval corresponding to the current single-session teaching.

[0129] For example, each frame of the teaching monitoring screen is captured by a teaching camera installed above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within a single-session time interval corresponding to the current single teaching session. This includes: when a teaching camera with a frame rate of 30 frames per second is used and the single-session time interval is 60 minutes, there are 30×60×60 frames, that is, 108,000 frames of teaching monitoring screens are evenly distributed within a single-session time interval lasting 60 minutes.

[0130] wherein, performing a set total number of multiple learnings on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, outputting the convolutional neural network after completing the multiple learnings as a teaching quality parser, and the number of learnings being positively correlated with the number of registered students in the target classroom, including: in each learning performed on the convolutional neural network, using the known number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to a single teaching session in the history of the target classroom as various output contents of the convolutional neural network, using the set distance, the number of frames of each frame of the teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in a single teaching session in the history as various input contents of the convolutional neural network, and performing this learning;

[0131] The single visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel point in the frame of the teaching monitoring screen, the depth of field value corresponding to each student target in the frame of the teaching monitoring screen, and the number of occupied pixels corresponding to each student target in the frame of the teaching monitoring screen. The single depth of field value corresponding to each student target in the frame of the teaching monitoring screen is the median value of the depth of field values corresponding to each pixel point in the imaging area of the student target in the frame of the teaching monitoring screen.

[0132] And wherein, the single visual data corresponding to each frame of teaching monitoring screen is the color component value of each pixel in the frame of teaching monitoring screen, the depth of field value corresponding to each student target in the frame of teaching monitoring screen, and the number of occupied pixels corresponding to each student target in the frame of teaching monitoring screen, and further includes: the single number of occupied pixels corresponding to each student target in the frame of teaching monitoring screen is the total number of pixels of the student target in the imaging area of the frame of teaching monitoring screen;

[0133] like Figure 6 As shown, illustratively, M processors are provided, where M is a natural number greater than or equal to 1.

[0134] Example 6

[0135] Figure 7 Schematic diagram of the structure of a teaching quality analysis system based on data processing according to embodiment 6 of the present invention.

[0136] like Figure 7 As shown, the teaching quality analysis system based on data processing includes the following components:

[0137] The first input unit is used to obtain various teaching configuration information of the target classroom, wherein the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor space, and the number of desks in a single row of a desk array;

[0138] For example, the first input mechanism may be equipped with a plurality of different configuration capture units, which are used to respectively obtain various teaching configuration information of the target classroom, including the number of registered students in the target classroom, the duration of a single teaching session, the floor area of the classroom, and the number of desks in a single row of a desk array;

[0139] The second input mechanism is used to obtain the visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, where the visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel in the teaching monitoring screen, the depth of field value corresponding to each student target in the teaching monitoring screen, and the number of pixels occupied by each student target in the teaching monitoring screen;

[0140] For example, obtaining each copy of visual data corresponding to each frame of teaching monitoring screen of the target classroom in the current single teaching session, wherein the single copy of visual data corresponding to each frame of teaching monitoring screen is a color component value of each pixel point in the frame of teaching monitoring screen, a depth of field value corresponding to each student target in the frame of teaching monitoring screen, and a number of occupied pixels corresponding to each student target in the frame of teaching monitoring screen, including: the resolution and clarity of each frame of teaching monitoring screen are the same;

[0141] a model reconstruction mechanism, configured to perform a set number of multiple learnings on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, and output the convolutional neural network after completing the multiple learnings as a teaching quality parser, wherein the number of learnings is positively correlated with the number of students enrolled in the target classroom;

[0142] For example, the positive correlation between the number of learning times and the number of registered students in the target classroom includes: the number of registered students in the target classroom is 30, the number of learning times is 50, the number of registered students in the target classroom is 40, the number of learning times is 100, the number of registered students in the target classroom is 50, the number of learning times is 150, the number of registered students in the target classroom is 60, the number of learning times is 200, and so on;

[0143] a quality analysis mechanism, connected to the first input mechanism, the second input mechanism, and the model reconstruction mechanism, respectively, for using the teaching quality analysis body to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session of the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and output them as various teaching quality parameters corresponding to the current single teaching session of the target classroom;

[0144] Specifically, a numerical simulation mode can be selected to realize the simulation and test of the data processing process of outputting various teaching quality parameters corresponding to the current single teaching session of the target classroom using the teaching quality analyzer to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session of the target classroom based on the set distance, the number of frames of each teaching monitoring screen, the various teaching configuration information of the target classroom, and the various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session;

[0145] a numerical mapping mechanism, connected to the quality analysis mechanism, for mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom;

[0146] For example, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping function with N inputs and a single output can be selected to represent the numerical mapping relationship between the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom and the teaching quality data corresponding to the current single teaching session in the target classroom;

[0147] Among them, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping relationship in which the number of sleepy students and the total duration of sleepiness corresponding to the current single teaching session in the target classroom are respectively inversely correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping, and a numerical mapping relationship in which the number of interactions and the total duration of interactions corresponding to the current single teaching session in the target classroom are respectively in positively correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping;

[0148] Each frame of the teaching monitoring screen is captured by a teaching camera installed above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within the single-session time interval corresponding to the current single-session teaching.

[0149] For example, each frame of the teaching monitoring screen is captured by a teaching camera installed above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within a single-session time interval corresponding to the current single teaching session. This includes: when a teaching camera with a frame rate of 30 frames per second is used and the single-session time interval is 60 minutes, there are 30×60×60 frames, that is, 108,000 frames of teaching monitoring screens are evenly distributed within a single-session time interval lasting 60 minutes.

[0150] wherein, performing a set total number of multiple learnings on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, outputting the convolutional neural network after completing the multiple learnings as a teaching quality parser, and the number of learnings being positively correlated with the number of registered students in the target classroom, including: in each learning performed on the convolutional neural network, using the known number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to a single teaching session in the history of the target classroom as various output contents of the convolutional neural network, using the set distance, the number of frames of each frame of the teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in a single teaching session in the history as various input contents of the convolutional neural network, and performing this learning;

[0151] The single visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel point in the frame of the teaching monitoring screen, the depth of field value corresponding to each student target in the frame of the teaching monitoring screen, and the number of occupied pixels corresponding to each student target in the frame of the teaching monitoring screen. The single depth of field value corresponding to each student target in the frame of the teaching monitoring screen is the median value of the depth of field values corresponding to each pixel point in the imaging area of the student target in the frame of the teaching monitoring screen.

[0152] And wherein, the single visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel point in the frame of the teaching monitoring screen, the depth of field value corresponding to each student target in the frame of the teaching monitoring screen, and the number of occupied pixel points corresponding to each student target in the frame of the teaching monitoring screen, and also includes: the single number of occupied pixel points corresponding to each student target in the frame of the teaching monitoring screen is the total number of pixel points of the student target in the imaging area of the frame of the teaching monitoring screen.

[0153] In addition, the present invention may also cite the following technical contents to highlight the significant technological advancements of the present invention:

[0154] The teaching quality parser is used to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom based on the set distance, the number of frames of each teaching monitoring screen, the various teaching configuration information of the target classroom, and the various visual data corresponding to the various teaching monitoring screen frames of the target classroom in the current single teaching session, and output them as the various teaching quality parameters corresponding to the current single teaching session in the target classroom, further comprising: synchronously inputting the set distance, the number of frames of each teaching monitoring screen, the various teaching configuration information of the target classroom, and the various visual data corresponding to the various teaching monitoring screen frames of the target classroom in the current single teaching session into the teaching quality parser;

[0155] For example, before synchronously inputting the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session into the teaching quality analysis body, numerical normalization processing is performed on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session. Specifically, the numerical normalization processing is a binary numerical conversion processing;

[0156] wherein, using the teaching quality parser to intelligently analyze the number of sleepy students, the total duration of dozing, the number of interactions, and the total duration of interactions corresponding to the current single teaching session of the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and outputting the various teaching quality parameters corresponding to the current single teaching session of the target classroom as the teaching quality parameters further comprises: executing the teaching quality parser to obtain the number of sleepy students, the total duration of dozing, the number of interactions, and the total duration of interactions corresponding to the current single teaching session of the target classroom output by the teaching quality parser;

[0157] For example, executing the teaching quality analyzer to obtain the number of sleepy students, the total duration of dozing, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom output by the teaching quality analyzer includes: the number of sleepy students, the total duration of dozing, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom output by the teaching quality analyzer are all representations of numerical normalization processing, specifically, the representation of the numerical normalization processing is a binary numerical representation.

[0158] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the quantity of the technical features indicated. Thus, features defined as "first" or "second" may explicitly or implicitly include one or more of the aforementioned features.

[0159] In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. In the description of this specification, the description of the reference terms "one embodiment", "certain embodiments", "illustrative embodiments", "examples", "specific examples" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0160] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A teaching quality analysis method based on data processing, characterized in that: The method comprises: Acquire various teaching configuration information of the target classroom, wherein the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor space, and the number of desks in a single row of a desk array; Obtaining each copy of visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, wherein the single copy of visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel point in the teaching monitoring screen frame, the depth of field value corresponding to each student target in the teaching monitoring screen frame, and the number of pixels occupied by each student target in the teaching monitoring screen frame; performing a set total number of learning cycles on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, and outputting the convolutional neural network after the multiple learning cycles as a teaching quality parser, wherein the number of learning cycles is positively correlated with the number of students enrolled in the target classroom; The teaching quality parser is used to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and output them as various teaching quality parameters corresponding to the current single teaching session in the target classroom; Mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom; Among them, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping relationship in which the number of sleepy students and the total duration of sleepiness corresponding to the current single teaching session in the target classroom are respectively inversely correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping, and a numerical mapping relationship in which the number of interactions and the total duration of interactions corresponding to the current single teaching session in the target classroom are respectively in positively correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping; Among them, each frame of the teaching monitoring screen is captured by a teaching shooting device set above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within the single time interval corresponding to the current single teaching.

2. The teaching quality analysis method based on data processing according to claim 1, characterized in that: A set total number of learning cycles are performed on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, and the convolutional neural network after the multiple learning cycles is output as a teaching quality analysis body, and the number of learning cycles is positively correlated with the number of registered students in the target classroom, including: in each learning cycle performed on the convolutional neural network, the known number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to a single teaching session in the history of the target classroom are used as various output contents of the convolutional neural network, and the set distance, the number of frames of each frame of the teaching monitoring screen, the various teaching configuration information of the target classroom, and the various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in a single teaching session in the history are used as various input contents of the convolutional neural network to perform this learning.

3. The teaching quality analysis method based on data processing according to claim 2, characterized in that: The single visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel point in the frame of the teaching monitoring screen, the depth of field value corresponding to each student target in the frame of the teaching monitoring screen, and the number of occupied pixels corresponding to each student target in the frame of the teaching monitoring screen. The single depth of field value corresponding to each student target in the frame of the teaching monitoring screen is the median value of the depth of field values corresponding to each pixel point in the imaging area of the student target in the frame of the teaching monitoring screen. Among them, the single visual data corresponding to each frame of teaching monitoring screen is the color component value of each pixel point in the frame of teaching monitoring screen, the depth of field value corresponding to each student target in the frame of teaching monitoring screen, and the number of occupied pixel points corresponding to each student target in the frame of teaching monitoring screen. It also includes: the single number of occupied pixel points corresponding to each student target in the frame of teaching monitoring screen is the total number of pixel points of the student target in the imaging area of the frame of teaching monitoring screen.

4. The teaching quality analysis method based on data processing according to claim 3, characterized in that: After performing a set total number of multiple learnings on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, outputting the convolutional neural network after the multiple learnings as a teaching quality parser, and the number of learnings being positively correlated with the number of students enrolled in the target classroom, the method further includes: The model storage of the teaching quality analysis body is completed by storing various model parameters of the teaching quality analysis body.

5. The teaching quality analysis method based on data processing according to claim 3, characterized in that: Before obtaining various teaching configuration information of the target classroom, wherein the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor area, and the number of desks in a single row of a desk array, the method further includes: Arranging the teaching camera for the target classroom so that the teaching camera is set above the podium in the target classroom and at a set distance from the ground; Among them, arranging the teaching shooting device for the target classroom so that the teaching shooting device is set above the podium of the target classroom and at a set distance from the ground includes: setting the frame rate of the teaching shooting device to the number of frames of each frame of the teaching monitoring screen divided by the length of a single teaching class.

6. The teaching quality analysis method based on data processing according to claim 3, characterized in that: After mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of dozing students, the total duration of dozing, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom, the method further includes: The teaching quality data corresponding to the current single teaching session in the target classroom is sent to a remote teaching quality supervision server via a wireless communication link.

7. The teaching quality analysis method based on data processing according to any one of claims 3 to 6, characterized in that: The teaching quality parser is used to intelligently analyze the number of dozing students, the total duration of dozing, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and output various teaching quality parameters corresponding to the current single teaching session in the target classroom, including: the total duration of dozing corresponding to the current single teaching session in the target classroom is the cumulative value of the duration of dozing of various students who have experienced a dozing process in the current single teaching session; Among them, the single visual data corresponding to each frame of teaching monitoring screen is the color component value of each pixel point in the frame of teaching monitoring screen, the depth of field value corresponding to each student target in the frame of teaching monitoring screen, and the number of occupied pixels corresponding to each student target in the frame of teaching monitoring screen, including: the color component value of each pixel point in the frame of teaching monitoring screen is the red and green component value, black and white component value and yellow and blue component value of the pixel point in the LAB color space.

8. The teaching quality analysis method based on data processing according to any one of claims 3 to 6, characterized in that: The teaching configuration information of the target classroom includes the number of registered students, the duration of a single teaching session, the floor space of the classroom, and the number of desks in a single row of a desk array. The target classroom includes: the desk array of the target classroom is a matrix array, and the number of desks in a single row of the desk array of the target classroom is the number of desks in each row of the matrix array. Among them, the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor area, and the number of desks in a single row of the desk array, and also includes: the duration of a single teaching session in the target classroom is a set duration value between 45 minutes and 60 minutes.

9. A teaching quality analysis system based on data processing, characterized in that: The system includes a memory and one or more processors, wherein the memory stores a computer program configured to be executed by the one or more processors to perform the following steps: Acquire various teaching configuration information of the target classroom, wherein the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor space, and the number of desks in a single row of a desk array; Obtaining each copy of visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, wherein the single copy of visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel point in the teaching monitoring screen frame, the depth of field value corresponding to each student target in the teaching monitoring screen frame, and the number of pixels occupied by each student target in the teaching monitoring screen frame; performing a set total number of learning cycles on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, and outputting the convolutional neural network after the multiple learning cycles as a teaching quality parser, wherein the number of learning cycles is positively correlated with the number of students enrolled in the target classroom; The teaching quality parser is used to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and output them as various teaching quality parameters corresponding to the current single teaching session in the target classroom; Mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom; Among them, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping relationship in which the number of sleepy students and the total duration of sleepiness corresponding to the current single teaching session in the target classroom are respectively inversely correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping, and a numerical mapping relationship in which the number of interactions and the total duration of interactions corresponding to the current single teaching session in the target classroom are respectively in positively correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping; Among them, each frame of the teaching monitoring screen is captured by a teaching shooting device set above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within the single time interval corresponding to the current single teaching.

10. A teaching quality analysis system based on data processing, characterized in that: The system comprises: The first input unit is used to obtain various teaching configuration information of the target classroom, wherein the various teaching configuration information of the target classroom includes the number of registered students in the target classroom, the duration of a single teaching session, the classroom floor space, and the number of desks in a single row of a desk array; The second input mechanism is used to obtain the visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, where the visual data corresponding to each frame of the teaching monitoring screen is the color component value of each pixel in the teaching monitoring screen, the depth of field value corresponding to each student target in the teaching monitoring screen, and the number of pixels occupied by each student target in the teaching monitoring screen; a model reconstruction mechanism, configured to perform a set number of multiple learnings on the convolutional neural network to complete multiple reconstructions of the convolutional neural network, and output the convolutional neural network after completing the multiple learnings as a teaching quality parser, wherein the number of learnings is positively correlated with the number of students enrolled in the target classroom; a quality analysis mechanism, connected to the first input mechanism, the second input mechanism, and the model reconstruction mechanism, respectively, for using the teaching quality analysis body to intelligently analyze the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session of the target classroom based on the set distance, the number of frames of each teaching monitoring screen, various teaching configuration information of the target classroom, and various visual data corresponding to each frame of the teaching monitoring screen of the target classroom in the current single teaching session, and output them as various teaching quality parameters corresponding to the current single teaching session of the target classroom; a numerical mapping mechanism, connected to the quality analysis mechanism, for mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom; Among them, mapping the teaching quality data corresponding to the current single teaching session in the target classroom based on the number of sleepy students, the total duration of sleepiness, the number of interactions, and the total duration of interactions corresponding to the current single teaching session in the target classroom includes: a numerical mapping relationship in which the number of sleepy students and the total duration of sleepiness corresponding to the current single teaching session in the target classroom are respectively inversely correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping, and a numerical mapping relationship in which the number of interactions and the total duration of interactions corresponding to the current single teaching session in the target classroom are respectively in positively correlated with the teaching quality data corresponding to the current single teaching session in the target classroom obtained by mapping; Among them, each frame of the teaching monitoring screen is captured by a teaching shooting device set above the podium of the target classroom and at a set distance from the ground. The shooting moments corresponding to each frame of the teaching monitoring screen are evenly spaced within the single time interval corresponding to the current single teaching.

Images