Intelligent teaching management system

Abstract

The invention discloses an intelligent teaching management system, and particularly relates to the technical field of teaching management, and the method comprises the steps: obtaining a teaching environment quality evaluation index through analyzing an audio signal, a display interface image and an environment parameter in a teaching time period; analyzing to obtain a correlation degree parameter of each class, matching a weight coefficient for each class, and performing weighted summation operation on the weight coefficient and the correlation degree parameter of each class to obtain a teaching quality evaluation index; based on the classroom interaction rate and the student activeness variance, carrying out conjoint analysis to obtain a teaching interaction quality evaluation index; jointly analyzing the teaching environment quality evaluation index, the teaching quality evaluation index and the teaching interaction quality evaluation index to obtain a teaching management quality coefficient; and the server is used for comparing the teaching management quality coefficient with a threshold value, indicating that the teaching management is abnormal when the teaching management quality coefficient is lower than the threshold value, giving an early warning to a manager, prompting to increase teaching management resources of a teaching place, and solving the problem that the existing teaching management is not intelligent and scientific enough.

Description

Technical Field

[0001] The present invention relates to the technical field of teaching management, and more specifically, to an intelligent teaching management system. Background Art

[0002] The teaching management system is an integrated software platform designed to help educational institutions, schools, teachers and administrators more effectively manage, monitor and evaluate all aspects of the teaching process. The system improves teaching efficiency, supports personalized learning, and promotes communication and collaboration between home and school by automating and optimizing management processes.

[0003] However, in actual use, it still has many shortcomings. For example, the existing teaching management system mainly relies on manual management of teaching venues, resulting in insufficient management coverage and lack of analysis of teaching venues and teaching audio, resulting in the problem that the existing teaching management is not intelligent and scientific enough. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides an intelligent teaching management system to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: an intelligent teaching management system, comprising:

[0006] The data acquisition module collects the audio signals of the teaching place, the display interface images of each position and the environmental parameters of the teaching place; and transmits the collected information to the teaching environment analysis module, the teaching quality analysis module and the teaching interaction quality analysis module;

[0007] The teaching environment analysis module screens the audio signal, display interface image and temperature and humidity parameters during the teaching period, and obtains the teaching environment quality evaluation index Hp through analysis;

[0008] The teaching quality analysis module extracts audio signals, obtains the teaching keywords of each class, extracts the target keywords from the teaching objectives, analyzes the correlation degree parameters of each class, matches the weight coefficient for each class, performs weighted summation operation on the weight coefficient and correlation degree parameter of each class, and obtains the teaching quality evaluation index Sp;

[0009] The teaching interaction quality analysis module analyzes the audio signal to obtain the average number of questions asked by teachers and students, and obtains the classroom interaction rate through joint analysis; obtains the classroom interaction frequency of each student and the variance of the classroom interaction frequency; based on the classroom interaction rate and the variance of student activity, jointly analyzes to obtain the teaching interaction quality evaluation index Xp;

[0010] The teaching management quality analysis module receives the analysis results of the teaching environment analysis module, the teaching quality analysis module and the teaching interaction quality analysis module, and jointly analyzes the teaching environment quality evaluation index, the teaching quality evaluation index and the teaching interaction quality evaluation index to obtain the teaching management quality coefficient;

[0011] The teaching management quality judgment module is used to compare the teaching management quality coefficient with the threshold and take measures according to the comparison result.

[0012] Preferably, in the data acquisition module, an audio and video monitoring device and an environmental monitoring sensor are installed in the teaching place, the audio signal of the teaching place is acquired by the audio acquisition device, the display interface image of each position in the teaching place is acquired by the video acquisition device, and the environmental parameters of the teaching place are acquired by the environmental monitoring sensor, and the environmental parameters include indoor temperature, average radiation temperature, air speed, air humidity, human metabolic rate and clothing thermal resistance.

[0013] Preferably, the teaching environment quality evaluation index Hp is obtained by:

[0014] Obtain the display interface image and standard display image at each location of the teaching venue, and compare the contrast deviation average z1, brightness deviation average z2 and distortion deviation average z3 of the display interface image at each location relative to the standard display image. q 1 *z2 q 2 *z3 q 3 The joint analysis obtains the display interface quality parameter scz of the teaching place; q1, q2, q3 represent the influence coefficients of each item respectively;

[0015] Analyze the audio signal, filter and denoise it to remove non-noise components, use the threshold method to detect the noise segment, calculate the ratio of the total duration of the detected noise segment to the entire audio duration, and obtain the noise ratio (scd);

[0016] The indoor temperature, average radiation temperature, air speed, air humidity, human metabolic rate and clothing thermal resistance of the teaching place are obtained, and the body discomfort scg is obtained using the PMV model.

[0017] The combined analysis shows the interface quality parameters, noise ratio and physical discomfort, and the formula The teaching environment quality evaluation index is calculated, where w1, w2, and w3 represent the weight coefficients of each item, respectively, based on the settings of management personnel.

[0018] Preferably, the contrast deviation average value is obtained by: reading the display interface image at each position, converting it into a grayscale image, calculating the standard deviation of the brightness of all pixels in the grayscale image as the contrast, obtaining the contrast deviation of the display image contrast at each position relative to the standard display image, and calculating the contrast deviation average value;

[0019] The method for obtaining the average brightness deviation is as follows: reading the display interface image at each position, performing grayscale processing, calculating the average brightness of all pixels in the grayscale image as the brightness, obtaining the brightness deviation of the image brightness at each position relative to the standard display image, and calculating the brightness deviation average;

[0020] The method for obtaining the average value of the distortion amount is as follows: taking the standard display image as the undistorted image, using a feature point detection algorithm to detect and match corresponding feature points in the display interface image and the standard display image at each position, using geometric transformation to fit the distortion model, and quantifying the distortion amount by comparing the position difference of the matched feature points in the standard image and the display interface image, and calculating the average value of the distortion amount.

[0021] Preferably, the intelligent teaching management system includes a teaching environment judgment module, which compares the acquired teaching environment quality evaluation index with a preset value. When the teaching environment quality evaluation index exceeds the preset value, it indicates that the environment of the teaching place is abnormal, and an early warning is issued to the management, indicating that the hardware of the teaching place is abnormal; when the teaching environment quality evaluation index does not exceed the preset value, it indicates that the environment of the teaching place is normal and no measures are taken.

[0022] Preferably, the process of obtaining the teaching quality evaluation index Sp includes the following steps:

[0023] Step S11, obtaining the audio signal of each class, converting the audio signal into text, processing the text using word segmentation technology, and extracting teaching keywords;

[0024] Step S12, extracting teaching target keywords: obtaining the teaching target text, processing the teaching target text using word segmentation technology, and extracting target keywords;

[0025] Step S13: Compare the teaching keywords with the teaching target keywords, use a text similarity algorithm to calculate the similarity between the teaching keywords and the teaching target keywords, and use the similarity to represent the correlation degree parameter of each lesson;

[0026] Step S14, weight coefficient allocation: taking the importance and difficulty of each class as influencing factors, a weight coefficient is allocated to each class;

[0027] Step S15: Assume that there are n courses, i represents the course number, the correlation parameter of the i-th course is recorded as xs_i, the weight coefficient of the i-th course is recorded as kq_i, and the formula is The teaching quality evaluation index Sp is calculated, where Qx represents the emotion correction coefficient.

[0028] Preferably, the emotion correction coefficient is obtained in the following manner:

[0029] Assume that each course is divided into t segments according to the time period, and KT represents the number of segments of the course. The teacher's emotional score in time period t is recorded as SPt, and the student's emotional score in time period t is recorded as YPt. The influence factor of teacher's emotion is set as f1, and the influence factor of student's emotion is set as f2. By formula The emotion correction coefficient is calculated.

[0030] Preferably, a speech emotion analysis model is built, the audio signal of each class is used as the input of the speech emotion analysis model, the emotion score of each audio segment is extracted, the emotion scores of all audio segments are summarized to obtain the emotion change curve, and the emotion change curve of each class is used as the output of the speech emotion analysis model; the classification of teacher and student voices is completed through voiceprint recognition, and the emotion change curve includes the teacher's emotion change curve and the student's emotion change curve.

[0031] Preferably, the process of building the speech emotion analysis model includes the following steps:

[0032] Step S21, constructing a speech emotion data set: classroom speech is collected through audio and video equipment, and after preprocessing the speech, several audio segments are obtained through speech slicing, and the audio segments are data-labeled based on the emotion scale, and the emotion scores are mapped on continuous coordinates to construct a speech emotion data set;

[0033] It needs to be explained that the preprocessing includes audio noise reduction, detection and removal of silence and irrelevant noise in speech; the emotional scale includes at least: the degree of positive or negative emotions, the degree of individual excitement and activity; ensuring that the collected speech data covers various emotional changes; the annotation process can be completed by an expert team, or machine learning-assisted annotation tools can be used to improve efficiency;

[0034] Step S22, dividing the acquired speech emotion data set into a training set and a test set; the training set is used for long short-term memory convolutional neural network training, and the test set is used to verify the performance of the long short-term memory convolutional neural network;

[0035] It needs to be explained that random partitioning or time-order-based partitioning methods are used to ensure that the data distribution between the training set and the test set is as consistent as possible;

[0036] Step S23, initialize the parameters of the long short-term memory convolutional neural network, including the network structure, learning rate, and number of iterations, and use the speech feature extraction tool to extract classroom speech features; input the classroom speech features corresponding to the training set into the long short-term memory convolutional neural network, verify the test set after training, and update the maximum number of iterations;

[0037] Step S24: During the training process, a loss function is used to measure the difference between the prediction result of the long short-term memory convolutional neural network and the actual emotion label, and the parameters of the long short-term memory convolutional neural network are updated through the back propagation algorithm to minimize the loss function; the long short-term memory convolutional neural network is trained until it satisfies the loss function or the maximum number of iterations, and the speech emotion analysis model is output.

[0038] Preferably, the process of obtaining the teaching interaction quality evaluation index Xp includes the following steps:

[0039] Step S31, analyzing the audio signal to obtain the average number of questions asked by teachers and the average number of questions asked by students: calculating the average number of questions asked by teachers and the average number of questions asked by students in all classes;

[0040] Step S32, obtaining the classroom interaction rate based on the total number of questions asked in the class, the class time and the number of students;

[0041] In the further design, the number of questions asked by the teacher, the number of questions asked by the students, the class time and the number of students are recorded as tc1, tc2, tc3 and tc4 respectively. Calculate the classroom interaction rate xh;

[0042] Step S33, obtaining the classroom interaction frequency of each student: record the number of times each student speaks in class, calculate the classroom interaction frequency of each student, assume that there are m students, j represents the student identity number, record the classroom interaction frequency of the jth student as hdj, and calculate the variance hs of the classroom interaction frequency;

[0043] Step S34: Calculate the teaching interaction quality evaluation index based on the classroom interaction rate and the variance of student activity.

[0044] Preferably, the teaching environment quality evaluation index, the teaching quality evaluation index and the teaching interaction quality evaluation index are jointly analyzed, and the formula The teaching management quality coefficient is calculated, where Form(·) represents a linear normalized function.

[0045] Preferably, in the teaching management quality judgment module, when the teaching management quality coefficient is lower than a threshold, it indicates that the teaching management is abnormal, and an early warning is given to the manager to prompt the increase of teaching management resources in the teaching venue; when the teaching management quality coefficient is not lower than the threshold, it indicates that the teaching management is normal and no measures are taken.

[0046] Technical effects and advantages of the present invention:

[0047] The intelligent teaching management system provided by the present invention collects audio signals of a teaching place, display interface images of each position and environmental parameters of the teaching place; obtains a teaching environment quality evaluation index Hp by analyzing the audio signals, display interface images and environmental parameters within the teaching time period; obtains the correlation degree parameter of each class by analysis, matches a weight coefficient for each class, performs a weighted sum operation on the weight coefficient and the correlation degree parameter of each class, and obtains a teaching quality evaluation index Sp; obtains a teaching interaction quality evaluation index Xp by joint analysis based on the classroom interaction rate and the variance of the student activity; obtains a teaching management quality coefficient by joint analysis of the teaching environment quality evaluation index, the teaching quality evaluation index and the teaching interaction quality evaluation index; and is used to compare the teaching management quality coefficient with a threshold value. When the teaching management quality coefficient is lower than the threshold value, it indicates that the teaching management is abnormal, and an early warning is given to the manager, prompting him to increase the teaching management resources of the teaching place, so as to solve the problem that the existing teaching management is not intelligent and scientific enough. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a structural block diagram of the intelligent teaching management system of the present invention. DETAILED DESCRIPTION

[0049] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0050] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0051] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0052] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0053] See also Figure 1 The intelligent teaching management system structure diagram of the present invention provides the following Figure 1 An intelligent teaching management system shown includes:

[0054] The data acquisition module collects the audio signals of the teaching place, the display interface images of each position and the environmental parameters of the teaching place; and transmits the collected information to the teaching environment analysis module, the teaching quality analysis module and the teaching interaction quality analysis module;

[0055] The teaching environment analysis module screens the audio signal, display interface image and temperature and humidity parameters during the teaching period, and obtains the teaching environment quality evaluation index Hp through analysis;

[0056] The teaching quality analysis module extracts audio signals, obtains the teaching keywords of each class, extracts the target keywords from the teaching objectives, analyzes the correlation degree parameters of each class, matches the weight coefficient for each class, performs weighted summation operation on the weight coefficient and correlation degree parameter of each class, and obtains the teaching quality evaluation index Sp;

[0057] The teaching interaction quality analysis module analyzes the audio signal to obtain the average number of questions asked by teachers and students, and obtains the classroom interaction rate through joint analysis; obtains the classroom interaction frequency of each student and the variance of the classroom interaction frequency; based on the classroom interaction rate and the variance of student activity, jointly analyzes to obtain the teaching interaction quality evaluation index Xp;

[0058] The teaching management quality analysis module receives the analysis results of the teaching environment analysis module, the teaching quality analysis module and the teaching interaction quality analysis module, and jointly analyzes the teaching environment quality evaluation index, the teaching quality evaluation index and the teaching interaction quality evaluation index to obtain the teaching management quality coefficient;

[0059] The teaching management quality judgment module is used to compare the teaching management quality coefficient with the threshold and take measures according to the comparison result.

[0060] What needs to be further explained in the embodiments of the present invention is that, in the data acquisition module, an audio and video monitoring device and an environmental monitoring sensor are installed in the teaching place, the audio signal of the teaching place is acquired by the audio acquisition device, the display interface image of each position in the teaching place is acquired by the video acquisition device, and the environmental parameters of the teaching place are acquired by the environmental monitoring sensor, and the environmental parameters include indoor temperature, average radiant temperature, air speed, air humidity, human metabolic rate and clothing thermal resistance.

[0061] It needs to be further explained in the embodiment of the present invention that the teaching environment quality evaluation index Hp is obtained in the following manner:

[0062] Obtain the display interface image and standard display image at each location of the teaching venue, and compare the contrast deviation average z1, brightness deviation average z2 and distortion deviation average z3 of the display interface image at each location relative to the standard display image.q 1 *z2 q 2 *z3 q 3 The joint analysis obtains the display interface quality parameter scz of the teaching place; q1, q2, q3 represent the influence coefficients of each item respectively;

[0063] Analyze the audio signal, filter and reduce noise on it to remove non-noise components, such as speech and music, use the threshold method to detect the noise segment, calculate the ratio of the total duration of the detected noise segment to the entire audio duration, and obtain the noise ratio (scd);

[0064] The indoor temperature, average radiation temperature, air speed, air humidity, human metabolic rate and clothing thermal resistance of the teaching place are obtained, and the PMV model is used to obtain the perceived discomfort scg; the PMV model is a thermal comfort prediction model that calculates the human body's perception of the thermal environment by evaluating a series of environmental factors and human factors.

[0065] The combined analysis shows the interface quality parameters, noise ratio and physical discomfort, and the formula The teaching environment quality evaluation index is calculated, where w1, w2, and w3 represent the weight coefficients of each item, respectively, based on the settings of management personnel.

[0066] It needs to be further explained in the embodiment of the present invention that the contrast deviation average value is obtained by: reading the display interface image at each position, converting it into a grayscale image, calculating the standard deviation of the brightness of all pixels in the grayscale image as the contrast, obtaining the contrast deviation of the display image contrast at each position relative to the standard display image, and calculating the contrast deviation average value;

[0067] The method for obtaining the average brightness deviation is as follows: reading the display interface image at each position, performing grayscale processing, calculating the average brightness of all pixels in the grayscale image as the brightness, obtaining the brightness deviation of the image brightness at each position relative to the standard display image, and calculating the brightness deviation average;

[0068] The method for obtaining the average value of the distortion amount is as follows: taking the standard display image as the undistorted image, using a feature point detection algorithm to detect and match corresponding feature points in the display interface image and the standard display image at each position, using geometric transformation to fit the distortion model, and quantifying the distortion amount by comparing the position difference of the matched feature points in the standard image and the display interface image, and calculating the average value of the distortion amount.

[0069] What needs to be further explained in the embodiments of the present invention is that the intelligent teaching management system includes a teaching environment judgment module, which compares the acquired teaching environment quality evaluation index with a preset value. When the teaching environment quality evaluation index exceeds the preset value, it indicates that the environment of the teaching place is abnormal, and an early warning is issued to the management, indicating that the hardware of the teaching place is abnormal; when the teaching environment quality evaluation index does not exceed the preset value, it indicates that the environment of the teaching place is normal and no measures are taken.

[0070] It needs to be further explained in the embodiment of the present invention that the process of obtaining the teaching quality evaluation index Sp includes the following steps:

[0071] Step S11, obtaining the audio signal of each class, converting the audio signal into text, processing the text using word segmentation technology, and extracting teaching keywords;

[0072] Step S12, extracting teaching target keywords: obtaining the teaching target text, processing the teaching target text using word segmentation technology, and extracting target keywords;

[0073] Step S13: Compare the teaching keywords with the teaching target keywords, use a text similarity algorithm to calculate the similarity between the teaching keywords and the teaching target keywords, and use the similarity to represent the correlation degree parameter of each lesson;

[0074] Step S14, weight coefficient allocation: taking the importance and difficulty of each class as influencing factors, a weight coefficient is allocated to each class;

[0075] Step S15: Assume that there are n courses, i represents the course number, the correlation parameter of the i-th course is recorded as xs_i, the weight coefficient of the i-th course is recorded as kq_i, and the formula is The teaching quality evaluation index Sp is calculated, where Qx represents the emotion correction coefficient.

[0076] In a further design, the emotion correction coefficient is obtained as follows:

[0077] Assume that each course is divided into t segments according to the time period, and KT represents the number of segments of the course. The teacher's emotional score in time period t is recorded as SPt, and the student's emotional score in time period t is recorded as YPt. The influence factor of teacher's emotion is set as f1, and the influence factor of student's emotion is set as f2. By formula The emotion correction coefficient is calculated.

[0078] Background technology: The positivity or negativity of classroom emotions is an important factor affecting students' learning status, so it is crucial to obtain a teaching quality evaluation index through an emotion correction coefficient.

[0079] Furthermore, a speech emotion analysis model is built, and the audio signal of each class is used as the input of the speech emotion analysis model to extract the emotion score of each audio segment. The emotion scores of all audio segments are summarized to obtain the emotion change curve, and the emotion change curve of each class is used as the output of the speech emotion analysis model; the classification of teacher and student voices is completed through voiceprint recognition, and the emotion change curve includes the teacher's emotion change curve and the student's emotion change curve.

[0080] Furthermore, the process of building the speech emotion analysis model includes the following steps:

[0081] Step S21, constructing a speech emotion data set: classroom speech is collected through audio and video equipment, and after preprocessing the speech, several audio segments are obtained through speech slicing, and the audio segments are data-labeled based on the emotion scale, and the emotion scores are mapped on continuous coordinates to construct a speech emotion data set;

[0082] It needs to be explained that the preprocessing includes audio noise reduction, detection and removal of silence and irrelevant noise in speech; the emotional scale includes at least: the degree of positive or negative emotions, the degree of individual excitement and activity; ensuring that the collected speech data covers various emotional changes; the annotation process can be completed by an expert team, or machine learning-assisted annotation tools can be used to improve efficiency;

[0083] Step S22, dividing the acquired speech emotion data set into a training set and a test set; the training set is used for long short-term memory convolutional neural network training, and the test set is used to verify the performance of the long short-term memory convolutional neural network;

[0084] It needs to be explained that random partitioning or time-order-based partitioning methods are used to ensure that the data distribution between the training set and the test set is as consistent as possible;

[0085] Step S23, initialize the parameters of the long short-term memory convolutional neural network, including the network structure, learning rate, and number of iterations, and use the speech feature extraction tool to extract classroom speech features; input the classroom speech features corresponding to the training set into the long short-term memory convolutional neural network, verify the test set after training, and update the maximum number of iterations;

[0086] Step S24: During the training process, a loss function is used to measure the difference between the prediction result of the long short-term memory convolutional neural network and the actual emotion label, and the parameters of the long short-term memory convolutional neural network are updated through the back propagation algorithm to minimize the loss function; the long short-term memory convolutional neural network is trained until it satisfies the loss function or the maximum number of iterations, and the speech emotion analysis model is output.

[0087] It needs to be further explained in the embodiment of the present invention that the process of obtaining the teaching interaction quality evaluation index Xp includes the following steps:

[0088] Step S31, analyzing the audio signal to obtain the average number of questions asked by teachers and the average number of questions asked by students: calculating the average number of questions asked by teachers and the average number of questions asked by students in all classes;

[0089] Step S32, obtaining the classroom interaction rate based on the total number of questions asked in the class, the class time and the number of students;

[0090] In the further design, the number of questions asked by the teacher, the number of questions asked by the students, the class time and the number of students are recorded as tc1, tc2, tc3 and tc4 respectively. Calculate the classroom interaction rate xh;

[0091] Step S33, obtaining the classroom interaction frequency of each student: record the number of times each student speaks in class, calculate the classroom interaction frequency of each student, assume that there are m students, j represents the student identity number, record the classroom interaction frequency of the jth student as hdj, and calculate the variance hs of the classroom interaction frequency;

[0092] Step S34: Calculate the teaching interaction quality evaluation index based on the classroom interaction rate and the variance of student activity.

[0093] In further design, the formula The teaching interaction quality evaluation index is calculated.

[0094] It is necessary to further explain in the embodiment of the present invention that the teaching environment quality evaluation index, the teaching quality evaluation index and the teaching interaction quality evaluation index are jointly analyzed, and the formula The teaching management quality coefficient is calculated, where Form(·) represents a linear normalized function.

[0095] What needs to be further explained in the embodiment of the present invention is that, when the teaching management quality coefficient is lower than the threshold value, the teaching management is abnormal, and the manager is warned to increase the teaching management resources of the teaching venue; when the teaching management quality coefficient is not lower than the threshold value, it indicates that the teaching management is normal and no measures are taken.

[0096] What needs to be further explained in the embodiments of the present invention is that the teaching management resources include human resources, material resources and training resources. By strengthening teaching management personnel or teaching assistants to assist in maintaining teaching order, answering students' questions, and supervising teaching quality; updating or adding teaching facilities, such as projectors, computers, experimental equipment, etc., to provide better teaching conditions; providing teachers with training in teaching skills and methods to help improve teaching quality and interactive ability.

[0097] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent teaching management system, characterized in that: include: The data acquisition module collects the audio signal of the teaching place, the display interface image of each position and the environmental parameters of the teaching place; The teaching environment analysis module screens the audio signal, display interface image and temperature and humidity parameters during the teaching period, and obtains the teaching environment quality evaluation index Hp through analysis; The teaching quality analysis module extracts audio signals, obtains the teaching keywords of each class, extracts the target keywords from the teaching objectives, analyzes the correlation degree parameters of each class, matches the weight coefficient for each class, performs weighted summation operation on the weight coefficient and correlation degree parameter of each class, and obtains the teaching quality evaluation index Sp; The teaching interaction quality analysis module analyzes the audio signal to obtain the average number of questions asked by teachers and students, and conducts joint analysis to obtain the classroom interaction rate; obtains the classroom interaction frequency of each student, and obtains the variance of the classroom interaction frequency; Based on the variance of classroom interaction rate and student activity, the teaching interaction quality evaluation index Xp is obtained through joint analysis; The teaching management quality analysis module jointly analyzes the teaching environment quality evaluation index, the teaching quality evaluation index and the teaching interaction quality evaluation index to obtain the teaching management quality coefficient; The teaching management quality judgment module is used to compare the teaching management quality coefficient with the threshold and take measures according to the comparison result.

2. An intelligent teaching management system according to claim 1, characterized in that: In the data acquisition module, an audio and video monitoring device and an environmental monitoring sensor are installed in the teaching place. The audio signal of the teaching place is acquired by the audio acquisition device, the display interface image of each position in the teaching place is acquired by the video acquisition device, and the environmental parameters of the teaching place are acquired by the environmental monitoring sensor. The environmental parameters include indoor temperature, average radiation temperature, air speed, air humidity, human metabolic rate and clothing thermal resistance.

3. An intelligent teaching management system according to claim 2, characterized in that: The teaching environment quality evaluation index Hp is obtained as follows: Obtain the display interface image and standard display image at each location of the teaching venue, and compare the contrast deviation average z1, brightness deviation average z2 and distortion deviation average z3 of the display interface image at each location relative to the standard display image. q 1 *z2 q 2 *z3 q 3 The joint analysis obtains the display interface quality parameter scz of the teaching place; q1, q2, q3 represent the influence coefficients of each item respectively; Analyze the audio signal, filter and denoise it to remove non-noise components, use the threshold method to detect the noise segment, calculate the ratio of the total duration of the detected noise segment to the entire audio duration, and obtain the noise ratio (scd); Obtain the indoor temperature, average radiation temperature, air speed, air humidity, human metabolic rate and clothing thermal resistance of the teaching place, and use the PMV model to obtain the somatic discomfort scg; The combined analysis shows the interface quality parameters, noise ratio and physical discomfort, and the formula The teaching environment quality evaluation index is calculated, where w1, w2, and w3 represent the weight coefficients of each item, which are set based on the management personnel.

4. An intelligent teaching management system according to claim 3, characterized in that: The contrast deviation average value is obtained by: reading the display interface image at each position, converting it into a grayscale image, calculating the standard deviation of the brightness of all pixels in the grayscale image as the contrast, obtaining the contrast deviation of the display image contrast at each position relative to the standard display image, and calculating the contrast deviation average value; The method for obtaining the average brightness deviation is as follows: reading the display interface image at each position, performing grayscale processing, calculating the average brightness of all pixels in the grayscale image as the brightness, obtaining the brightness deviation of the image brightness at each position relative to the standard display image, and calculating the brightness deviation average; The method for obtaining the average value of the distortion amount is as follows: taking the standard display image as the undistorted image, using a feature point detection algorithm to detect and match corresponding feature points in the display interface image and the standard display image at each position, using geometric transformation to fit the distortion model, and quantifying the distortion amount by comparing the position difference of the matched feature points in the standard image and the display interface image, and calculating the average value of the distortion amount.

5. An intelligent teaching management system according to claim 4, characterized in that: The intelligent teaching management system includes a teaching environment judgment module, which compares the acquired teaching environment quality evaluation index with a preset value. When the teaching environment quality evaluation index exceeds the preset value, it indicates that the environment of the teaching place is abnormal, and an early warning is issued to the management, indicating that the hardware of the teaching place is abnormal; when the teaching environment quality evaluation index does not exceed the preset value, it indicates that the environment of the teaching place is normal and no measures are taken.

6. The intelligent teaching management system according to claim 1, characterized in that: The process of obtaining the teaching quality evaluation index Sp includes the following steps: Step S11, obtaining the audio signal of each class, converting the audio signal into text, processing the text using word segmentation technology, and extracting teaching keywords; Step S12, extracting teaching target keywords: obtaining the teaching target text, processing the teaching target text using word segmentation technology, and extracting target keywords; Step S13: Compare the teaching keywords with the teaching target keywords, use a text similarity algorithm to calculate the similarity between the teaching keywords and the teaching target keywords, and use the similarity to represent the correlation degree parameter of each lesson; Step S14, weight coefficient allocation: taking the importance and difficulty of each class as influencing factors, a weight coefficient is allocated to each class; Step S15: Assume that there are n courses, i represents the course number, the correlation parameter of the i-th course is recorded as xs_i, the weight coefficient of the i-th course is recorded as kq_i, and the formula is The teaching quality evaluation index Sp is calculated, where Qx represents the emotion correction coefficient.

7. An intelligent teaching management system according to claim 6, characterized in that: The method for obtaining the emotion correction coefficient is as follows: Assume that each course is divided into t segments according to the time period, and KT represents the number of segments of the course. The teacher's emotional score in time period t is recorded as SPt, and the student's emotional score in time period t is recorded as YPt. The influence factor of teacher's emotion is set as f1, and the influence factor of student's emotion is set as f2. By formula The emotion correction coefficient is calculated.

8. The intelligent teaching management system according to claim 1, characterized in that: The process of obtaining the teaching interaction quality evaluation index Xp includes the following steps: Step S31, analyzing the audio signal to obtain the average number of questions asked by teachers and the average number of questions asked by students: calculating the average number of questions asked by teachers and the average number of questions asked by students in all classes; Step S32: Obtain the classroom interaction rate based on the total number of questions asked in the class, the class time and the number of students; record the number of questions asked by the teacher, the number of questions asked by the students, the class time and the number of students as tc1, tc2, tc3 and tc4 respectively, and use the formula Calculate the classroom interaction rate xh; Step S33, obtaining the classroom interaction frequency of each student: record the number of times each student speaks in class, calculate the classroom interaction frequency of each student, assume that there are m students, j represents the student identity number, record the classroom interaction frequency of the jth student as hdj, and calculate the variance hs of the classroom interaction frequency; Step S34: Calculate the teaching interaction quality evaluation index based on the classroom interaction rate and the variance of student activity.

9. The intelligent teaching management system according to claim 1, characterized in that: The teaching environment quality evaluation index, teaching quality evaluation index and teaching interaction quality evaluation index are jointly analyzed and the formula is used to The teaching management quality coefficient is calculated, where Form(·) represents a linear normalized function.

10. An intelligent teaching management system according to claim 9, characterized in that: The teaching management quality judgment module, when the teaching management quality coefficient is lower than the threshold, it indicates that the teaching management is abnormal, and the manager is warned to increase the teaching management resources in the teaching venue; when the teaching management quality coefficient is not lower than the threshold, it indicates that the teaching management is normal and no measures are taken.

Images