Remote intelligent teaching management system and method

Abstract

The invention discloses a remote intelligent teaching management system and method, and relates to the technical field of education, and the method comprises the steps: a student carries out the online learning of each course according to teaching information, records the learning process data, captures the facial expression image of the student during the learning of each course through a camera, and carries out the preprocessing; based on the preprocessed facial expression image, key features are extracted, dimension reduction operation is carried out, an expression intensity comprehensive value is calculated, and the emotional state of the student is evaluated according to the expression intensity comprehensive value; the teacher creates an examination according to the emotional state of the student in combination with the learning process data to obtain a test report of each course of the student; and the students and the teachers carry out remote guidance learning according to the test reports of the courses. By combining the emotion of the student and the mastering condition of the knowledge points, the teaching content is dynamically adjusted, the learning efficiency is improved, the teacher is helped to discover weak links of the student on some knowledge points, and personalized guidance is realized.

Description

Technical Field

[0001] The present invention relates to the field of educational technology, and in particular to a remote intelligent teaching management system and method. Background Art

[0002] Currently, remote intelligent teaching management technology has been widely used around the world, enabling the sharing of teaching resources, tracking of student progress, and personalized learning guidance through online platforms. However, although existing systems can provide basic course management and online testing functions, most platforms lack the interactivity of emotion recognition and teaching feedback.

[0003] Specifically, existing systems have difficulty analyzing students' emotional states in real time during the learning process, and cannot dynamically adjust teaching content or methods according to students' emotional changes. This leads to limited effectiveness of personalized teaching and inability to fully meet the needs of different students, especially in remote learning environments, where it is difficult for teachers to provide timely and effective intervention and guidance. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a remote intelligent teaching management system and method to solve the problem of insufficient interactivity of emotion recognition and teaching feedback.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a remote intelligent teaching management method, which includes: students learning each course online according to teaching information, recording learning process data and capturing facial expression images of students learning each course through a camera, and performing preprocessing;

[0008] Based on the preprocessed facial expression images, key features are extracted and dimension reduction is performed, the comprehensive value of expression intensity is calculated, and the emotional state of students is evaluated according to the comprehensive value of expression intensity;

[0009] Teachers create exams based on students’ emotional states and learning process data, and get students’ test reports for each course;

[0010] Students and teachers conduct remote guided learning based on the test reports of each course.

[0011] As a preferred solution of the remote intelligent teaching management method of the present invention, wherein:

[0012] The teaching information includes the course learning plan, electronic textbooks, handouts and online homework uploaded by the teacher; the learning process data is the completion rate and accuracy rate of the online homework; the facial expression images include facial expression images of students when viewing the learning plan, facial expression images when reading handouts, facial expression images when studying electronic textbooks and facial expression images when completing online homework; the preprocessing includes adding knowledge point IDs and timestamps to the teaching information, learning process data and facial expression images, image grayscale, histogram equalization, face detection, face alignment, image size standardization, image normalization and noise removal.

[0013] As a preferred solution of the remote intelligent teaching management method of the present invention, the preprocessing includes adding knowledge point IDs and timestamps to teaching information, learning process data and facial expression images, image grayscale, histogram equalization, face detection, face alignment, image normalization, image size standardization and noise removal. The specific steps are as follows:

[0014] Add corresponding knowledge point ID and timestamp to each teaching information and learning process data;

[0015] Detect the facial area in the image based on the Haar algorithm and extract the facial expression area image;

[0016] The extracted facial expression area images are used in conjunction with the Dlib library for face alignment operations;

[0017] The facial expression area image after face alignment is grayed out with cv2.cvtColor function to reduce the dimension of the facial expression image.

[0018] Apply cv2.equalizeHist function to the grayscale facial expression area image for histogram equalization to enhance the contrast;

[0019] Apply cv2.GaussianBlur function to smooth the facial expression area image to reduce noise interference in the facial expression image;

[0020] The processed facial expression area images are combined with the cv2.resize function to adjust to a uniform size to obtain facial expression images with the same resolution;

[0021] The resized facial expression area image is normalized using the cv2.normalize function.

[0022] As a preferred solution of the remote intelligent teaching management method of the present invention, the key features are extracted and dimension reduction operations are performed based on the preprocessed facial expression image. The specific steps are as follows:

[0023] The preprocessed facial expression images are combined with the ORB algorithm to perform feature point detection and descriptor extraction to obtain the position, shape and local feature information of the eyes, nose, mouth and eyebrows.

[0024] Combine the geometric shape key points of each facial region and its local feature information as facial expression features;

[0025] The facial expression features are combined with the PCA algorithm and projected into a low-dimensional space to obtain the main facial expression feature vector;

[0026] The main facial expression feature vector is combined with the Z-score standardization method to obtain the main facial expression standard feature vector.

[0027] As a preferred solution of the remote intelligent teaching management method of the present invention, wherein: calculating the comprehensive value of expression intensity and evaluating the emotional state of the student according to the comprehensive value of expression intensity, the specific steps are as follows: constructing an expression intensity model according to the main facial expression standard feature vector, expressed as:

[0028]

[0029] Among them, I is the comprehensive value of expression intensity, w i is the weight of the ith facial region, f i is the eigenvalue of the standard eigenvector of the main facial expression in the i-th facial region;

[0030] A large amount of student facial expression data combined with machine learning training to obtain fatigue threshold, confusion threshold and concentration threshold;

[0031] When the comprehensive value of expression intensity is less than or equal to the fatigue threshold, the student's emotional state is judged to be fatigued;

[0032] When the comprehensive value of expression intensity is greater than the fatigue threshold and less than or equal to the confusion threshold, the student's emotional state is judged to be confused;

[0033] When the comprehensive value of expression intensity is greater than the confusion threshold and less than or equal to the concentration threshold, the student's emotional state is judged to be a concentration state;

[0034] When the comprehensive value of expression intensity is greater than the concentration threshold, the student's emotional state is judged to be excited;

[0035] The assessed emotional state of the students is associated with the timestamp and knowledge point ID and stored.

[0036] As a preferred solution of the remote intelligent teaching management method of the present invention, the teacher creates an exam based on the student's emotional state and the learning process data to obtain the student's test results for each course. The specific steps are as follows:

[0037] Teachers use students' emotional states and learning process data at various knowledge points as parameters to create personalized exams that automatically adjust the difficulty and content of questions based on students' emotional changes and learning progress;

[0038] Teachers issue personalized exams, and students answer questions based on the exam content arranged by the teacher;

[0039] After the test is over, the test results are generated according to the students' answers;

[0040] The test results are associated with the knowledge point ID and timestamp, and a detailed test report is generated and fed back to teachers and students.

[0041] As a preferred solution of the remote intelligent teaching management method of the present invention, students and teachers conduct remote guidance learning based on the test reports of each course. The specific steps are as follows:

[0042] Students develop revision plans based on feedback from their test reports;

[0043] Teachers provide one-on-one tutoring based on students’ test reports and their revision plans through online Q&A via video conferences to help students solve problems encountered during their studies;

[0044] During the remote instruction process, students’ learning process data and facial expression images will continue to be recorded and analyzed, and teachers can view students’ emotional states in real time and adjust instruction content and teaching methods accordingly.

[0045] After completing remote guided learning, students can take the test again, and the test results will be compared with previous learning data to update the student's test report and emotional state assessment.

[0046] In a second aspect, the present invention provides a remote intelligent teaching management system, including a learning behavior recording and preprocessing module, an expression processing and emotion evaluation module, an intelligent test generation module, and a remote guidance and learning feedback module;

[0047] The learning behavior recording module is used for students to conduct online learning of various courses based on teaching information, record learning process data and capture facial expression images of students during learning of various courses through cameras, and perform pre-processing;

[0048] The expression processing and emotion assessment module is used to extract key features and perform dimensionality reduction operations based on the preprocessed facial expression images, calculate the expression intensity comprehensive value and assess the student's emotional state based on the expression intensity comprehensive value;

[0049] The intelligent test generation module is used by teachers to create tests based on students’ emotional states and learning process data, and obtain students’ test reports for each course;

[0050] The remote guidance and learning feedback module is used for students and teachers to conduct remote guidance learning based on the test reports of each course.

[0051] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the remote intelligent teaching management method described in the first aspect of the present invention is implemented.

[0052] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the remote intelligent teaching management method as described in the first aspect of the present invention is implemented.

[0053] The beneficial effects of the present invention are as follows: by combining the emotional state of students with the knowledge point learning situation, an intelligent remote teaching management method is provided. It is possible to monitor the emotional changes of students in the learning process in real time, identify emotional states such as confusion and fatigue, and associate them with the specific knowledge point learning effects for analysis. According to the students' emotional fluctuations and the knowledge point mastery, the teaching content and the difficulty of the questions can be dynamically adjusted to ensure that students learn in the best state, while helping teachers to promptly discover the weak links of students in certain knowledge points and provide targeted guidance. This method of combining emotion with knowledge point learning helps to improve students' learning efficiency and personalized learning experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0055] Figure 1 This is a flow chart of the remote intelligent teaching management method in Example 1.

[0056] Figure 2 This is a flow chart of judging the emotional state of students in Example 1. DETAILED DESCRIPTION

[0057] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0058] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0060] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a remote intelligent teaching management method, comprising the following steps:

[0061] S1. Students conduct online learning of each course based on teaching information, record learning process data and capture facial expression images of students during learning of each course through cameras, and perform preprocessing, including the following steps:

[0062] Teaching information includes course learning plans, electronic textbooks, handouts and online homework uploaded by teachers; learning process data includes the completion rate and accuracy rate of online homework; facial expression images include facial expression images of students when viewing the learning plan, facial expression images when reading handouts, facial expression images when studying electronic textbooks and facial expression images when completing online homework; preprocessing includes adding knowledge point IDs and timestamps to teaching information, learning process data and facial expression images, image grayscale, histogram equalization, face detection, face alignment, image size standardization, image normalization and noise removal.

[0063] The preprocessing details include adding corresponding knowledge point IDs and timestamps to each teaching information (such as course study plans, textbooks, handouts, online homework, etc.) and learning process data (such as the completion rate and accuracy rate of online homework). By associating knowledge point IDs, the system can clearly identify the specific knowledge points corresponding to each data or image, which is convenient for subsequent personalized analysis. Timestamps help track the time process of learning, allowing the system to analyze the distribution of students' learning time and the time points of emotional changes.

[0064] The facial region in the image is detected based on the Haar algorithm, and the facial expression region images of students are extracted when they are checking the study plan, reading the handouts, studying the textbooks and completing the homework. It should be noted that the Haar algorithm is an algorithm used for object detection (especially face detection), which detects the target area in the image through rectangular features similar to the Haar wavelet.

[0065] The extracted facial expression area image is used in combination with the Dlib library for face alignment. It should be noted that the Dlib library is a modern C++ tool library that provides a variety of machine learning algorithms and image processing functions, and is widely used in face recognition and expression analysis. The shape_predictor model of the Dlib library can detect 68 key points on the face, which are used to align facial images. The coordinates after key point detection are used to adjust the angle and position of the facial image to standardize facial features.

[0066] OpenCV (Open Source Computer Vision Library) is an open source computer vision library that provides a wealth of image processing functions. It is widely used in image processing, object detection, video analysis and other fields. The cv2.cvtColor function in the OpenCV library is used for image color conversion.

[0067] The cv2.equalizeHist function applies histogram equalization to the grayscale image, adjusts the brightness contrast of the image, and enhances the details of the image.

[0068] The cv2.GaussianBlur function uses a Gaussian filter to blur an image. It is mainly used to remove noise from an image and make the image smoother.

[0069] The cv2.resize function is used to adjust the size of the image to ensure that all images have the same resolution for subsequent model processing.

[0070] The cv2.normalize function normalizes the pixel values ​​of an image to a specific range (such as [0,1] or [0,255]), thereby reducing the impact of brightness differences on subsequent analysis.

[0071] In the present invention, the functions in the OpenCV library are specifically applied as follows: the facial expression area image after face alignment is combined with the cv2.cvtColor function to perform grayscale processing to reduce the dimension of the facial expression image; the cv2.equalizeHist function is applied to the grayscale facial expression area image to perform histogram equalization to enhance the contrast; the cv2.GaussianBlur function is applied to the facial expression area image to perform smoothing processing to reduce noise interference in the facial expression image; the processed facial expression area image is combined with the cv2.resize function to adjust to a uniform size to obtain facial expression images with the same resolution; the resized facial expression area image is combined with the cv2.normalize function to perform normalization processing.

[0072] S2. Based on the preprocessed facial expression images, extract key features and perform dimensionality reduction operations, calculate the comprehensive value of expression intensity and evaluate the emotional state of students based on the comprehensive value of expression intensity, including the following steps:

[0073] The preprocessed facial expression images are combined with the ORB algorithm to perform feature point detection and descriptor extraction to obtain the position, shape and local feature information of the eyes, nose, mouth and eyebrows.

[0074] It should be noted that the ORB algorithm will find important feature points in the image. These points are usually parts of the image that change significantly, such as edges or corners. The ORB algorithm will also generate a descriptor for each feature point. The descriptor contains local feature information of the area around the feature point for subsequent expression analysis.

[0075] Combine the geometric shape key points of each facial region and its local feature information as facial expression features;

[0076] The facial expression features are combined with the PCA algorithm and projected into a low-dimensional space to obtain the main facial expression feature vector;

[0077] It should be noted that PCA (Principal Component Analysis) is a statistical method for data dimensionality reduction. By finding the direction with the largest variance in the data, high-dimensional data is projected into a low-dimensional space to retain the most representative features. The principal components extracted by PCA can represent the main changing characteristics of facial expressions, remove noise and redundant information, and make the subsequent expression intensity model calculation more efficient.

[0078] The main facial expression feature vector is combined with the Z-score standardization method to obtain the main facial expression standard feature vector.

[0079] It should be noted that after the facial expression feature vector is reduced by PCA, there may still be scale differences between different feature dimensions. Z-score standardization converts these features into a standardized form so that different facial features have the same metric. After standardization, the features of different facial regions can be treated more fairly, avoiding excessive influence of some features on the results due to excessively large or small dimensions.

[0080] According to the standard feature vectors of the main facial expressions, the expression intensity model is constructed, which is expressed as:

[0081]

[0082] Among them, I is the comprehensive value of expression intensity, which represents the overall facial expression intensity of the students, and w i is the weight of the i-th facial region, reflecting the importance of this region for emotion recognition, and f iis the eigenvalue of the standard eigenvector of the main facial expression in the i-th facial region;

[0083] A large amount of student facial expression data combined with machine learning training to obtain fatigue threshold, confusion threshold and concentration threshold;

[0084] It should be noted that by collecting a large amount of students' facial expression data and performing preprocessing (such as facial detection, feature extraction and standardization), these expression data are associated with emotional labels (such as tiredness, confusion, concentration, etc.). Then, a machine learning model (such as SVM, random forest or neural network) is used to train the model to predict the probability distribution of different emotional states. By analyzing these probability distributions, the optimal thresholds for tiredness, confusion and concentration states are determined. Ultimately, these thresholds are used to evaluate students' emotional states in real time, and emotional feedback and personalized learning support are provided in combination with learning content.

[0085] When the comprehensive value of expression intensity is less than or equal to the fatigue threshold, the student's emotional state is judged to be fatigued;

[0086] When the comprehensive value of expression intensity is greater than the fatigue threshold and less than or equal to the confusion threshold, the student's emotional state is judged to be confused;

[0087] When the comprehensive value of expression intensity is greater than the confusion threshold and less than or equal to the concentration threshold, the student's emotional state is judged to be a concentration state;

[0088] When the comprehensive value of expression intensity is greater than the concentration threshold, the student's emotional state is judged to be excited;

[0089] The assessed emotional state of the students is associated with the timestamp and knowledge point ID and stored.

[0090] S3. The teacher creates an exam based on the student's emotional state and the learning process data to obtain the student's test report for each course, including the following steps. The teacher creates an exam based on the student's emotional state and the learning process data to obtain the student's test results for each course. The specific steps are as follows:

[0091] Teachers use students' emotional states and learning process data at various knowledge points as parameters to create personalized exams that automatically adjust the difficulty and content of questions based on students' emotional changes and learning progress;

[0092] It should be noted that by dynamically adjusting the difficulty of the exam, the system ensures that students will neither feel frustrated because the exam is too difficult nor lose the challenge because it is too easy, thereby improving the effectiveness and pertinence of the exam.

[0093] Teachers issue personalized exams, and students answer questions based on the exam content arranged by the teacher;

[0094] After the test is over, the test results are generated according to the students' answers;

[0095] It should be noted that timely generated test results can help teachers and students understand students’ mastery of various knowledge points and provide a basis for subsequent learning and teaching adjustments.

[0096] The test results are associated with the knowledge point ID and timestamp, and a detailed test report is generated and fed back to teachers and students.

[0097] It should be noted that the test results are associated with the knowledge point ID and timestamp, and the system generates a detailed test report. The report not only shows the student's performance, but also provides more comprehensive feedback by combining learning process data and emotional state. The test report provides teachers and students with detailed analysis, helping them identify students' knowledge weaknesses and the impact of their emotional state, and facilitating the development of personalized review and teaching plans.

[0098] S4. Students and teachers conduct remote guidance learning based on the test reports of each course, including the following steps:

[0099] Students can make review plans based on the feedback from the test reports. Students can review the knowledge points that they did not perform well in the test in a targeted manner to ensure the efficiency and effectiveness of the review.

[0100] Based on the students' test reports and their revision plans, teachers provide one-on-one tutoring through online Q&A sessions via video conferences to help students solve problems encountered during their studies. Through personalized tutoring, teachers can directly help students solve specific problems and adjust teaching methods in real time based on students' emotions, thus improving the effectiveness of remote guidance.

[0101] During the remote guidance process, students' learning process data and facial expression images will continue to be recorded and analyzed, and teachers can view students' emotional states in real time and adjust guidance content and teaching methods accordingly. Real-time analysis of emotional states helps teachers adjust teaching strategies in a timely manner. For example, when students show fatigue or confusion, teachers can slow down the pace or provide more explanations to improve learning outcomes.

[0102] After completing remote guided learning, students can take the test again, and the test results will be compared with previous learning data to update the student's test report and emotional state assessment. Through comparative analysis of test results, teachers and students can clearly see the effect of review and tutoring, and adjust subsequent learning plans based on the latest report to ensure that students' learning progress is continuously tracked and optimized.

[0103] This embodiment also provides a remote intelligent teaching management system, including: a learning behavior recording and preprocessing module, an expression processing and emotion evaluation module, an intelligent test generation module and a remote guidance and learning feedback module; the learning behavior recording module is used for students to conduct online learning of various courses based on teaching information, record learning process data and capture facial expression images of students in each course through a camera, and perform preprocessing; the expression processing and emotion evaluation module is used to extract key features and perform dimensionality reduction operations based on the preprocessed facial expression images, calculate the comprehensive value of expression intensity and evaluate the student's emotional state based on the comprehensive value of expression intensity; the intelligent test generation module is used for teachers to create tests based on the student's emotional state and combined with the learning process data to obtain the student's test report for each course; the remote guidance and learning feedback module is used for students and teachers to conduct remote guidance learning based on the test report for each course.

[0104] This embodiment also provides a computer device suitable for the remote intelligent teaching management method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the remote intelligent teaching management method proposed in the above embodiment.

[0105] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0106] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the remote intelligent teaching management method proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0107] In summary, the present invention provides an intelligent remote teaching management method by combining students' emotional states with their knowledge point learning. It can monitor students' emotional changes in the learning process in real time, identify emotional states such as confusion and fatigue, and analyze their correlation with specific knowledge point learning effects. According to students' emotional fluctuations and knowledge point mastery, it can dynamically adjust the teaching content and question difficulty to ensure that students learn in the best state, while helping teachers to promptly discover students' weak links in certain knowledge points and provide targeted guidance. This method of combining emotions with knowledge point learning helps to improve students' learning efficiency and personalized learning experience.

[0108] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A remote intelligent teaching management method, characterized in that: include, Students study online for each course based on the teaching information, record the learning process data, and capture the facial expression images of students during the course learning through the camera, and perform pre-processing; Based on the preprocessed facial expression images, key features are extracted and dimension reduction is performed, the comprehensive value of expression intensity is calculated, and the emotional state of students is evaluated according to the comprehensive value of expression intensity; Teachers create exams based on students’ emotional states and learning process data, and get students’ test reports for each course; Students and teachers conduct remote guided learning based on the test reports of each course.

2. The remote intelligent teaching management method according to claim 1, characterized in that: The teaching information includes the course learning plan, electronic textbooks, handouts and online homework uploaded by the teacher; the learning process data is the completion rate and accuracy rate of the online homework; the facial expression images include facial expression images of students when viewing the learning plan, facial expression images when reading handouts, facial expression images when studying electronic textbooks and facial expression images when completing online homework; the preprocessing includes adding knowledge point IDs and timestamps to the teaching information, learning process data and facial expression images, image grayscale, histogram equalization, face detection, face alignment, image size standardization, image normalization and noise removal.

3. The remote intelligent teaching management method according to claim 2, characterized in that: The preprocessing includes adding knowledge point ID and timestamp to teaching information, learning process data and facial expression images, image grayscale, histogram equalization, face detection, face alignment, image normalization, image size standardization and noise removal. The specific steps are as follows: Add corresponding knowledge point ID and timestamp to each teaching information and learning process data; Detect the facial area in the image based on the Haar algorithm and extract the facial expression area image; The extracted facial expression area images are used in conjunction with the Dlib library for face alignment operations; The facial expression area image after face alignment is grayed out with cv2.cvtColor function to reduce the dimension of the facial expression image. Apply cv2.equalizeHist function to the grayscale facial expression area image for histogram equalization to enhance the contrast; Apply cv2.GaussianBlur function to smooth the facial expression area image to reduce noise interference in the facial expression image; The processed facial expression area images are combined with the cv2.resize function to adjust to a uniform size to obtain facial expression images with the same resolution; The resized facial expression area image is normalized using the cv2.normalize function.

4. The remote intelligent teaching management method according to claim 3, characterized in that: Based on the preprocessed facial expression images, key features are extracted and dimension reduction is performed. The specific steps are as follows: The preprocessed facial expression images are combined with the ORB algorithm to perform feature point detection and descriptor extraction to obtain the position, shape and local feature information of the eyes, nose, mouth and eyebrows. Combine the geometric shape key points of each facial region and its local feature information as facial expression features; The facial expression features are combined with the PCA algorithm and projected into a low-dimensional space to obtain the main facial expression feature vector; The main facial expression feature vector is combined with the Z-score standardization method to obtain the main facial expression standard feature vector.

5. The remote intelligent teaching management method according to claim 4, characterized in that: Calculate the comprehensive value of expression intensity and evaluate the emotional state of students based on the comprehensive value of expression intensity. The specific steps are as follows: According to the standard feature vectors of the main facial expressions, the expression intensity model is constructed, which is expressed as: Among them, I is the comprehensive value of expression intensity, w i is the weight of the ith facial region, f i is the eigenvalue of the standard eigenvector of the main facial expression in the i-th facial region; A large amount of student facial expression data combined with machine learning training to obtain fatigue threshold, confusion threshold and concentration threshold; When the comprehensive value of expression intensity is less than or equal to the fatigue threshold, the student's emotional state is judged to be fatigued; When the comprehensive value of expression intensity is greater than the fatigue threshold and less than or equal to the confusion threshold, the student's emotional state is judged to be confused; When the comprehensive value of expression intensity is greater than the confusion threshold and less than or equal to the concentration threshold, the student's emotional state is judged to be a concentration state; When the comprehensive value of expression intensity is greater than the concentration threshold, the student's emotional state is judged to be excited; The assessed emotional state of the students is associated with the timestamp and knowledge point ID and stored.

6. The remote intelligent teaching management method according to claim 5, characterized in that: The teacher creates an exam based on the student's emotional state and the learning process data to obtain the student's test results for each course. The specific steps are as follows: Teachers use students' emotional states and learning process data at various knowledge points as parameters to create personalized exams that automatically adjust the difficulty and content of questions based on students' emotional changes and learning progress; Teachers issue personalized exams, and students answer questions based on the exam content arranged by the teacher; After the test is over, the test results are generated according to the students' answers; The test results are associated with the knowledge point ID and timestamp, and a detailed test report is generated and fed back to teachers and students.

7. The remote intelligent teaching management method according to claim 6, characterized in that: Students and teachers conduct remote guidance learning based on the test reports of each course. The specific steps are as follows: Students develop revision plans based on feedback from their test reports; Teachers provide one-on-one tutoring based on students’ test reports and their revision plans through online Q&A via video conferences to help students solve problems encountered during their studies; During the remote instruction process, students’ learning process data and facial expression images will continue to be recorded and analyzed, and teachers can view students’ emotional states in real time and adjust instruction content and teaching methods accordingly. After completing remote guided learning, students can take the test again, and the test results will be compared with previous learning data to update the student's test report and emotional state assessment.

8. A remote intelligent teaching management system, based on the remote intelligent teaching management method according to any one of claims 1 to 7, characterized in that: Including, learning behavior recording and preprocessing module, expression processing and emotion assessment module, intelligent test generation module and remote guidance and learning feedback module; The learning behavior recording module is used for students to conduct online learning of various courses based on teaching information, record learning process data and capture facial expression images of students during learning of various courses through cameras, and perform pre-processing; The expression processing and emotion assessment module is used to extract key features and perform dimensionality reduction operations based on the preprocessed facial expression images, calculate the expression intensity comprehensive value and assess the student's emotional state based on the expression intensity comprehensive value; The intelligent test generation module is used by teachers to create tests based on students’ emotional states and learning process data, and obtain students’ test reports for each course; The remote guidance and learning feedback module is used for students and teachers to conduct remote guidance learning based on the test reports of each course.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the remote intelligent teaching management method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the remote intelligent teaching management method according to any one of claims 1 to 7 are implemented.

Images