Education management supervision method and system

Abstract

The invention is suitable for the technical field of education management, and particularly relates to an education management supervision method and system, and the method comprises the steps: obtaining a teaching video; determining teaching text data based on the teaching video; determining a classroom order score and classroom interaction behavior information based on the teaching video and the teaching text data; determining a classroom type based on the classroom interaction behavior information; determining the classroom participation degree of the student based on the classroom interaction behavior information and the classroom type; and determining education management quality based on the classroom order score and the classroom participation degree. According to the educational management supervision method provided by the embodiment of the invention, the problems that the evaluation dimension of the educational management quality is single, and the evaluation is not accurate and objective enough can be solved.

Description

Technical Field

[0001] The present application belongs to the field of educational management technology, and in particular, relates to an educational management supervision method and system. Background Art

[0002] Education management supervision is an effective means to promote the standardization and scientificization of education and teaching. It is an important guarantee for improving teachers' teaching ability, school quality and students' comprehensive quality. It is a process of comprehensive inspection, evaluation and guidance of the education management work of education administrative units and schools. It aims to ensure the implementation of education laws and policies and improve the level of education management and education quality.

[0003] In the existing technology, education management supervision often relies on on-site observation, questionnaire surveys, interviews and other methods. These methods are not only time-consuming and labor-intensive, but may also be subject to the subjective influence of the observer, resulting in the accuracy and objectivity of the supervision results being affected. At the same time, education management supervision methods often focus on direct observation of the classroom teaching process, which is difficult to fully reflect the quality of education management. Therefore, the current education management supervision methods have the problem of a single evaluation dimension for education management quality and the evaluation is not accurate and objective enough. Summary of the invention

[0004] The embodiment of the present application provides an education management supervision method and system, which can solve the problem that the evaluation dimension of education management quality is single and the evaluation is not accurate and objective.

[0005] In a first aspect, an embodiment of the present application provides an education management supervision method, including: Get instructional videos; Determining teaching text data based on the teaching video; wherein the teaching text data includes teacher text data and student text data; Determine a classroom order score and classroom interactive behavior information based on the teaching video and the teaching text data; wherein the classroom interactive behavior information includes the duration or average number of students participating in various classroom interactive behaviors in the teaching video, and the classroom interactive behaviors include discussions between students, students responding to the teacher's instructions, and questions and answers between the teacher and students; Determining a classroom type based on the classroom interaction behavior information; wherein the classroom types include teacher-led, student-led, and mixed; Determine the student's class participation based on the class interaction behavior information and the class type; The quality of educational management is determined based on the classroom order score and the classroom participation level.

[0006] The above technical solutions in the embodiments of the present application have at least the following technical effects: The education management inspection method provided in the embodiment of the present application obtains teaching videos; determines teaching text data based on teaching videos; determines classroom order scores and classroom interactive behavior information based on teaching videos and teaching text data; determines classroom types based on classroom interactive behavior information; determines students' classroom participation based on classroom interactive behavior information and classroom types; and determines the quality of education management based on classroom order scores and classroom participation. Therefore, the education management inspection method provided in the embodiment of the present application can avoid the subjectivity and one-sidedness in traditional inspection methods and improve the accuracy and reliability of evaluation results through technical means such as video analysis and text data mining; the method covers multiple key aspects such as classroom order, classroom interactive behavior, and students' classroom participation, which is conducive to comprehensive and objective evaluation of education management quality.

[0007] In a possible implementation manner of the first aspect, determining the teaching text data based on the teaching video includes: Extracting audio data from the teaching video; Obtain teacher audio data and student audio data according to the audio data; The teacher audio data and the student audio data are converted into corresponding teacher text data and the student text data to obtain the teaching text data.

[0008] In a possible implementation of the first aspect, determining the classroom order score and the classroom interactive behavior information based on the teaching video and the teaching text data includes: Obtaining a first key frame of the student according to the teaching video; wherein the first key frame is used to reflect the change of the student's head posture in the teaching video; Extracting first question information of teachers and / or students and first instruction information of teachers according to the teaching text data; wherein the first question information is a question raised by teachers and / or students in the teaching text data, and the first instruction information includes action instruction information representing the action of teachers instructing students to raise / lower their heads and discussion instruction information representing the action of teachers instructing students to discuss with each other; Extracting from the first key frame a second key frame which is after the time of the first indication information and whose time interval with the corresponding first indication information is less than a time interval threshold; Determine the total duration of a first behavior of each student according to the first key frame, the second key frame and the first indication information; wherein the first behavior is a behavior of the student not paying attention in class; Obtaining the classroom order score according to the total duration of each student's first behavior; Searching the teaching text data for the first text data corresponding to the time after the first question information and the discussion instruction information, to obtain the first interactive behavior information; wherein the first interactive behavior information includes the duration of each discussion between students and each question and answer between the teacher and students; Obtaining second interactive behavior information according to the action instruction information and the second key frame; wherein the second interactive behavior information is the number of students who respond to the teacher's instruction each time; The classroom interactive behavior information is obtained according to the first interactive behavior information and the second interactive behavior information.

[0009] In a possible implementation manner of the first aspect, obtaining the first key frame of the student according to the teaching video includes: Sampling a frame from the teaching video at fixed time intervals to obtain multiple video frames; Determine the head area of ​​each student in each video frame according to each video frame; Obtaining a tilt angle of the head according to the head area; wherein the tilt angle includes a pitch angle and a yaw angle of the head relative to a vertical direction; Calculating the difference of the tilt angle of each student in each two adjacent video frames; If the difference of the tilt angles of a student exceeds an angle threshold, the corresponding two adjacent video frames are determined as the first key frames corresponding to the student.

[0010] In a possible implementation manner of the first aspect, determining the total duration of the first behavior of each student according to the first key frame, the second key frame, and the first indication information includes: Determining whether the first indication information matches the tilt angle of each student in the corresponding second key frame; If the tilt angle of a student in the second key frame does not match the corresponding first indication information, it is determined that the student has the first behavior, and a first duration is determined according to the second key frame and the corresponding first indication information; If the tilt angle of a student in the first key frame is not within the angle range and the second time interval between the student and the adjacent next first key frame exceeds the first threshold, it is determined that the student has the first behavior; The total duration of the first behavior of the corresponding student is determined according to the first duration and the second duration.

[0011] In a possible implementation of the first aspect, searching the teaching text data for corresponding first text data after the time of the first question information and the discussion instruction information to obtain the first interactive behavior information includes: Searching the teaching text data for the first text data in a corresponding preset time period after the time of the first question information and the discussion instruction information; Calculating the relevance between the first question information and the discussion instruction information and the corresponding first text data respectively; Determining whether the first text data is related to the first question information or the discussion instruction information according to the correlation degree; If the first text data is related to the first question information or the discussion instruction information, the first interactive behavior information is determined according to the time of the first text data.

[0012] In a possible implementation manner of the first aspect, determining the class type based on the class interaction behavior information includes: Determine, based on the classroom interaction behavior information, the proportion of the average number of students participating in the classroom interaction behavior in the teaching video relative to the total number of corresponding students; Determine, based on the classroom interaction behavior information, the proportion of the duration of the student's participation in the classroom interaction behavior in the teaching video relative to the total duration of the teaching video; The class type is determined according to the proportion of various classroom interactive behaviors in the teaching video.

[0013] In a possible implementation of the first aspect, determining the student's class participation based on the class interaction behavior information and the class type includes: Determining participation weights corresponding to various classroom interactive behaviors based on the classroom type; The class participation degree is determined based on the class interaction behavior information and the participation weights corresponding to various class interaction behaviors.

[0014] In a possible implementation manner of the first aspect, determining the education management quality based on the classroom order score and the classroom participation includes: Determining an education management quality score based on the classroom order score and the classroom participation score; If the education management quality score exceeds the quality threshold, the education management quality is determined to be qualified; If the education management quality score does not exceed the quality threshold, the education management quality is determined to be unqualified.

[0015] In a second aspect, the embodiment of the present application provides an education management and inspection system, including: Acquisition module, used to acquire teaching videos; A teaching text module, used to determine teaching text data based on the teaching video; wherein the teaching text data includes teacher text data and student text data; A classroom module, used to determine a classroom order score and classroom interactive behavior information based on the teaching video and the teaching text data; wherein the classroom interactive behavior information includes the duration or average number of students participating in various classroom interactive behaviors in the teaching video, and the classroom interactive behaviors include discussions between students, students responding to the teacher's instructions, and questions and answers between the teacher and students; A type module, used to determine the class type based on the class interaction behavior information; wherein the class types include teacher-led, student-led and mixed; A participation module, used for determining the class participation of students based on the class interaction behavior information and the class type; An education management module is used to determine the quality of education management based on the classroom order score and the classroom participation.

[0016] In the third aspect, an embodiment of the present application provides an education management and inspection device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method as described in any one of the first aspects above when executing the computer program.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects above is implemented.

[0018] In the fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on an education management and supervision device, the education management and supervision device executes any method described in the first aspect above.

[0019] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 It is a flowchart of an education management inspection method provided by an embodiment of the present application; Figure 2 It is a schematic diagram of the implementation process of step S200 in the education management inspection method provided in one embodiment of the present application; Figure 3 It is a schematic diagram of the implementation process of steps S300, S340 and S360 in the education management inspection method provided in one embodiment of the present application; Figure 4 It is a schematic diagram of the implementation process of step S310 in the education management inspection method provided in one embodiment of the present application; Figure 5 It is a schematic diagram of the implementation process of steps S400, S500 and S600 in the education management inspection method provided in an embodiment of the present application; Figure 6 It is a structural diagram of the education management and inspection system provided in the embodiment of the present application; Figure 7 It is a structural diagram of the education management and inspection equipment provided in the embodiment of the present application. DETAILED DESCRIPTION

[0022] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0023] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0024] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0025] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0026] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0028] In related technologies, education management supervision often relies on on-site observation, questionnaires, interviews and other methods, which are not only time-consuming and labor-intensive, but may also be subject to subjective influences from observers, which may affect the accuracy and objectivity of the supervision results. At the same time, education management supervision methods often focus on direct observation of the classroom teaching process, which makes it difficult to fully reflect the quality of education management. Therefore, the current education management supervision methods have the problem of a single evaluation dimension for education management quality, and the evaluation is not accurate and objective enough.

[0029] To solve the above problems, the embodiment of the present application provides an education management supervision method and system. In the method, by obtaining teaching videos; determining teaching text data based on teaching videos; determining classroom order scores and classroom interactive behavior information based on teaching videos and teaching text data; determining classroom types based on classroom interactive behavior information; determining students' classroom participation based on classroom interactive behavior information and classroom types; and determining the quality of education management based on classroom order scores and classroom participation. Therefore, the education management supervision method provided by the embodiment of the present application can avoid the subjectivity and one-sidedness in traditional supervision methods and improve the accuracy and reliability of evaluation results through technical means such as video analysis and text data mining; the method covers multiple key aspects such as classroom order, classroom interactive behavior, and students' classroom participation, which is conducive to comprehensive and objective evaluation of education management quality.

[0030] The education management and supervision method provided in the embodiment of the present application can be applied to education management and supervision equipment. At this time, the education management and supervision equipment is the executor of the education management and supervision method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of education management and supervision equipment.

[0031] For example, the education management and inspection device can be a station (STAION, ST) in a WLAN, and can be a cellular phone, mobile phone, tablet computer, augmented reality (AR) / virtual reality (VR) device, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), desktop computer, smart screen, smart TV, computing device or other processing device connected to a wireless modem, computer, laptop computer, handheld computing device, etc.

[0032] In order to better understand the education management and supervision method provided in the embodiment of the present application, the specific implementation process of the education management and supervision method provided in the embodiment of the present application is exemplarily introduced below.

[0033] Figure 1 A schematic flow chart of an education management inspection method provided in an embodiment of the present application is shown, and the education management inspection method includes: S100, obtain the teaching video.

[0034] It can be understood that teaching videos include the teaching or learning process of teachers and students in class.

[0035] For example, teaching videos can be obtained through online education platforms, video libraries within schools or educational institutions, or by self-recording.

[0036] S200, determining teaching text data based on the teaching video, wherein the teaching text data includes teacher text data and student text data.

[0037] For example, the teaching video may be parsed and processed first to obtain the voice content of the teacher and the students, and further converted into a readable text form.

[0038] In one possible implementation, see Figure 2 , S200, determining teaching text data based on the teaching video, including: S210, extracting audio data from the teaching video.

[0039] Exemplarily, professional video processing software or libraries (such as FFmpeg, Adobe Premiere Pro, etc.) can be used to extract the audio track in the teaching video.

[0040] S220, obtaining teacher audio data and student audio data according to the audio data.

[0041] Exemplarily, through audio processing technology (such as speaker separation technology in speech recognition, audio editing, etc.), the extracted audio data can be further subdivided into teacher audio data and student audio data.

[0042] S230, converting the teacher audio data and the student audio data into corresponding teacher text data and student text data to obtain teaching text data.

[0043] Exemplarily, speech recognition technology (such as Speech-to-Text API, Azure SpeechService, etc.) can be used to convert teacher audio data and student audio data into corresponding teacher text data and student text data.

[0044] Through the above steps S210 to S230, teaching text data can be extracted and converted from the teaching video, which not only includes the teacher's teaching content but also the students' interactive information, providing more comprehensive data support for teaching analysis and evaluation.

[0045] S300, determining a classroom order score and classroom interactive behavior information based on the teaching video and teaching text data. The classroom interactive behavior information includes the duration or average number of students participating in various classroom interactive behaviors in the teaching video, and the classroom interactive behaviors include discussions between students, students responding to the teacher's instructions, and questions and answers between the teacher and students.

[0046] It can be understood that by using teaching videos and teaching text data, the student behaviors in the video are classified, and key information such as questions and instructions in the teaching text data are analyzed, so as to determine the classroom order score and classroom interactive behavior information.

[0047] In one possible implementation, see Figure 3 , S300, determines the classroom order score and classroom interactive behavior information based on the teaching video and teaching text data, including: S310, obtaining a first key frame of the student according to the teaching video, wherein the first key frame is used to reflect changes in the student's head posture in the teaching video.

[0048] For example, the head posture detection algorithm can be used to detect the change of the student's head posture to obtain the first key frame. For example, the teaching video has 72,000 frames, and the first key frame is detected: {100, 400, 700, ...}.

[0049] Optionally, see Figure 4 , S310, obtaining the first key frame of the student according to the teaching video, including: S311, sampling a frame from the teaching video at every fixed time interval to obtain multiple video frames.

[0050] Exemplarily, the fixed time interval may be set based on a comprehensive consideration of factors such as the total duration of the teaching video, computing resources, etc. For example, the fixed time interval may be set to 10 seconds, and one frame is sampled from a 40-minute teaching video every 10 seconds to obtain 240 video frames.

[0051] S312, determining the head region of each student in each video frame according to each video frame.

[0052] For example, a face detection algorithm (such as Haar feature, HOG+SVM, etc.) can be used to locate the head region of each student in each video frame.

[0053] S313, obtaining a tilt angle of the head according to the head region, wherein the tilt angle includes a pitch angle and a yaw angle of the head relative to a vertical direction.

[0054] It can be understood that the pitch angle represents the up and down tilt angle of the head relative to the vertical direction, and the yaw angle represents the left and right tilt angle of the head relative to the vertical direction.

[0055] For example, a facial key point detection algorithm (such as 68-point facial key point detection in the Dlib library, OpenCV, etc.) can be used to determine the key point positions of the face. According to the key point positions of the face, the vector from the nose tip to the chin is calculated, and the angle between the vector and the vertical direction (assuming the Y-axis direction) is calculated to obtain the pitch angle of the head; the vectors of the left and right eye corners are calculated, and the angle between the vector and the horizontal direction (assuming the X-axis direction) is calculated to obtain the yaw angle of the head.

[0056] S314, calculating the difference in the tilt angle of each student in every two adjacent video frames.

[0057] Exemplarily, the difference between the pitch angle and the yaw angle of each student's head in every two adjacent video frames may be calculated.

[0058] S315: If the difference in the tilt angle of a student exceeds the angle threshold, the corresponding two adjacent video frames are determined as the first key frames corresponding to the student.

[0059] It can be understood that the angle threshold is that the difference in the students' tilt angles does not exceed a preset specified value, and the preset specified value can be set by ordinary technicians in this field according to actual needs, and is not limited here.

[0060] For example, a reasonable angle threshold can be determined based on historical data and industry standards. For example, the angle threshold includes a pitch angle and a yaw angle difference threshold of 10°. If the difference in the tilt angle of a student exceeds the angle threshold, the corresponding two adjacent video frames are determined as the first key frame of the corresponding student.

[0061] Through the above steps S311 to S315, significant changes in students' head postures in teaching videos can be captured, providing key data for subsequent analysis of classroom order and interactive behavior, and helping to more accurately evaluate students' classroom participation, etc.

[0062] S320, extracting first question information of the teacher and / or the student and first instruction information of the teacher according to the teaching text data. The first question information is a question asked by the teacher and / or the student in the teaching text data, and the first instruction information includes action instruction information representing the teacher instructing the student to raise / lower his head and discussion instruction information representing the teacher instructing the students to discuss with each other.

[0063] Exemplarily, the teaching text data can be preprocessed using natural language processing (NLP) techniques, such as word segmentation, part-of-speech tagging, named entity recognition, etc. According to preset keywords or rules, the question information of teachers and / or students (such as "Excuse me...", "Who can tell me...", etc.) and the instruction information of teachers (such as "Please look at the blackboard", "Let's discuss in groups...", etc.) are extracted. The extracted information is classified into action instruction information and discussion instruction information, as shown in Table 1 below.

[0064] Table 1 S330: Extract from the first key frame a second key frame that is after the time of the first indication information and whose time interval with the corresponding first indication information is less than a time interval threshold.

[0065] It can be understood that the time interval threshold is a preset value after the time of the first indication information in the first key frame and the time interval with the corresponding first indication information does not exceed the preset value. The preset value can be set by ordinary technicians in this field according to actual needs and is not limited here.

[0066] For example, a reasonable time interval threshold may be determined based on historical data and industry standards, for example, the time interval threshold is 3 minutes.

[0067] Exemplarily, all first key frames may be traversed to check whether the timestamp of each key frame is after the time of a first indication information and the time interval between the key frame and the first indication information is less than a preset time interval threshold, and the key frame that meets the conditions is extracted as the second key frame.

[0068] S340, determining the total duration of each student's first behavior according to the first key frame, the second key frame and the first indication information, wherein the first behavior is the student's inattention in class.

[0069] Exemplarily, it can be determined whether each student has the first behavior based on the first key frame, the second key frame and the first indication information, and then the total duration can be calculated.

[0070] Optionally, see Figure 3 S340, determining the total duration of each student's first behavior according to the first key frame, the second key frame and the first indication information, including: S341, determining whether the first indication information matches the inclination angle of each student in the corresponding second key frame.

[0071] Exemplarily, the action that the student should make and the corresponding tilt angle can be determined based on the first indication information, as shown in Table 2 below, and the tilt angle corresponding to the first indication information is matched with the tilt angle of each student in the second key frame corresponding to the first indication information.

[0072] Table 2 S342: If there is a student whose tilt angle in the second key frame does not match the corresponding first indication information, it is determined that the student has the first behavior, and the first duration is determined according to the second key frame and the corresponding first indication information.

[0073] It can be understood that each first indication information corresponds to multiple second key frames. If the tilt angle of a student in the second key frame does not match the corresponding first indication information, it is determined that the student has the first behavior.

[0074] Exemplarily, the first duration may be determined according to the time point of the first indication information and the corresponding timestamp of the last second key frame.

[0075] S343: If the inclination angle of a student in the first key frame is not within the angle range and the second duration between the student and the adjacent next first key frame exceeds the first threshold, it is determined that the student has the first behavior.

[0076] It can be understood that the angle range means that the tilt angle of the student's head does not exceed a preset specified range. The preset specified range can be set by ordinary technicians in the field according to actual needs and is not limited here.

[0077] It can be understood that the first threshold is that the second duration between the first key frame and the adjacent subsequent first key frame does not exceed a preset specified value. The preset specified value can be set by ordinary technicians in this field according to actual needs and is not limited here.

[0078] For example, a reasonable angle range and a first threshold value may be determined based on historical data and industry standards. For example, the angle range is: pitch angle (Pitch) [-10°, 10°], yaw angle (Yaw) [-10°, 10°], and the first threshold value is 1 minute.

[0079] For example, the second duration between the first key frame and the adjacent next first key frame can be calculated according to the sequence number of the first key frame in the teaching video. For example, if it is found that the tilt angle of student A in the 210th frame (the first key frame) exceeds the angle threshold, the second duration between the 210th frame (the first key frame) and the 1110th frame (the adjacent next first key frame) is: (1110-210) / frame rate=900 / 30=30 seconds (assuming the frame rate is 30fps).

[0080] S344, determining the total duration of the first behavior of the corresponding student according to the first duration and the second duration.

[0081] For example, the starting and ending time points of the first duration and the second duration may be determined, and the first duration and the second duration are added together and the overlapping portion is removed to obtain the total duration of the first behavior of the corresponding student.

[0082] Through the above steps S341 to S344, the student's behavior of violating instructions within a specific time period can be accurately identified and recorded. Not only does it improve the accuracy of behavior recognition, but it can also more intuitively understand the student's behavior in class. In addition, by setting different thresholds and conditions, it can also flexibly adapt to different teaching scenarios and needs, providing strong support for classroom teaching management.

[0083] S350, obtaining a classroom order score according to the total duration of each student's first behavior.

[0084] For example, the classroom order score can be calculated based on the total duration of each student's first behavior. For example, the calculation formula for the classroom order score is: initial score - (total duration of students' inattention / total duration of class) × deduction coefficient, initial score: 10 points, total duration of class: 40 minutes = 2400 seconds, the total duration of all students' first behavior: 600 seconds, deduction coefficient: 2, classroom order score: 10-(600 / 2400)×2=9.5 (points).

[0085] S360, searching the teaching text data for the first text data corresponding to the time after the first question information and the discussion instruction information, and obtaining the first interactive behavior information, wherein the first interactive behavior information includes the duration of each discussion between students and each question and answer between the teacher and students.

[0086] For example, the first text data corresponding to the time of the first question information and the discussion instruction information can be searched to obtain the first interactive behavior information. For example, the duration of each discussion between students and each question and answer between teachers and students is shown in Table 3 below.

[0087] Table 3 Optionally, see Figure 3 , S360, searching the teaching text data for the first text data corresponding to the time after the first question information and the discussion instruction information, and obtaining the first interactive behavior information, including: S361, searching the teaching text data for first text data in a corresponding preset time period after the time of the first question information and the discussion instruction information.

[0088] Exemplarily, the time points of the first question information and the discussion indication information in the teaching text data can be located. After the time points of the first question information and the discussion indication information, if the first question information or the discussion indication information contains specific time requirements, the corresponding preset time period is determined according to the time requirements for searching for the relevant first text data (for example, if the time requirement is 5 minutes, a buffer time such as 1 minute can be added to the time requirement, then the preset time period can be set to 6 minutes); otherwise, a reasonable preset time period is determined according to historical data and industry standards for searching for the relevant first text data (for example, the preset time period can be set to 5 minutes after the first question information and 10 minutes after the discussion indication information).

[0089] S362, calculating the correlation between the first question information and the discussion instruction information and the corresponding first text data respectively.

[0090] Exemplarily, the first text data can be grouped by sentences through natural language processing technology (such as word segmentation, sentence boundary detection, etc.), and the semantic similarity between the first question information and discussion indication information and each corresponding group of first text data can be calculated through semantic similarity calculation tools (such as WordNet, BERT, etc.), so as to obtain the correlation.

[0091] S363: Determine whether the first text data is related to the first question information or the discussion instruction information according to the correlation degree.

[0092] Exemplarily, a reasonable relevance threshold can be determined based on historical data and industry standards. For example, if the relevance threshold is 0.7, if the relevance between the first text data and the first question information or discussion indication information is greater than 0.7, then the first text data is related to the first question information or discussion indication information; if the relevance between the first text data and the first question information or discussion indication information is not greater than 0.7, then the first text data is not related to the first question information or discussion indication information.

[0093] S364: If the first text data is related to the first question information or the discussion instruction information, determine the first interactive behavior information according to the time of the first text data.

[0094] Exemplarily, starting from the time point of the first question information or discussion indication information, the start time point of the first group of first text data whose correlation exceeds the threshold can be found; starting from the end point of the preset time period, a forward search can be found to find the end time point of the last group of first text data whose correlation exceeds the threshold, and the start and end time of each corresponding discussion between students and questions and answers between teachers and students can be recorded, thereby calculating the first interactive behavior information.

[0095] Through the above steps S361 to S364, the first text data related to the first question information and the discussion instruction information can be accurately found, thereby determining the student's first interactive behavior information. By presetting the time period and calculating the correlation, information related to questions and discussions can be quickly screened out, improving the efficiency of teaching analysis, providing an effective technical means for the analysis of teaching text data, and helping to better understand the student's interaction.

[0096] S370, obtaining second interactive behavior information according to the action instruction information and the second key frame, wherein the second interactive behavior information is the number of students who respond to the teacher's instruction each time.

[0097] Exemplarily, the action corresponding to the action instruction information can be analyzed, as shown in Table 4 below, to obtain the tilt angle corresponding to the action instruction information and match it with the tilt angle of the student's head in the second key frame. The number of students who respond to the teacher's instructions each time is determined, and after the action instruction information, the number of students who respond to the instruction in the second key frame is counted. Among them, a facial recognition algorithm (such as FaceNet, ArcFace, etc.) can be used to encode the facial features of the students, and each student generates a unique facial feature vector (i.e., a unique identifier). During the counting process, repeated counting is avoided by checking the unique identifier.

[0098] Table 4 S380, obtaining classroom interactive behavior information according to the first interactive behavior information and the second interactive behavior information.

[0099] For example, the duration of discussions between students and questions and answers between teachers and students can be obtained based on the first interactive behavior information, and the average number of students responding to the teacher's instructions can be obtained based on the second interactive behavior information, thereby obtaining classroom interactive behavior information. For example, the number of students who responded to the instructions each time was 10, 8, and 12, respectively, then the average number of responders was (10+8+12) / 3=10; the duration of each discussion between students and the duration of each question and answer between teachers and students are shown in Table 3 above, then the duration of the discussion between students is 9 minutes, and the duration of the question and answer between teachers and students is 5 minutes.

[0100] Through the above steps S310 to S380, identifying students' classroom behaviors, objectively evaluating classroom order, and deeply analyzing classroom interactions provide strong technical support for improving teaching quality, which is conducive to comprehensively and accurately evaluating classroom order and student participation, and understanding classroom interactions. Through quantitative analysis, it provides an objective basis for educational research and teaching quality evaluation.

[0101] S400, determining a class type based on the class interaction behavior information, wherein the class types include teacher-led, student-led, and mixed.

[0102] For example, the proportion of students participating in various classroom interactive behaviors in the teaching video can be determined based on the classroom interactive behavior information, thereby determining the class type.

[0103] In one possible implementation, see Figure 5 , S400, determining the class type based on the class interaction behavior information, including: S410, determining the ratio of the average number of students participating in the classroom interactive behavior in the teaching video to the total number of corresponding students based on the classroom interactive behavior information.

[0104] For example, the proportion of the average number of students responding to the teacher's instructions relative to the total number of students can be calculated. For example, the average number of students responding to the teacher's instructions is 20, the total number of students is 50, and the proportion is 20 / 50×100%=40%.

[0105] S420, based on the classroom interactive behavior information, determine the proportion of the duration of students' participation in the classroom interactive behavior in the teaching video relative to the total duration of the teaching video.

[0106] For example, the proportion of the time spent on discussion between students and questions and answers between teachers and students relative to the total duration of the teaching video can be calculated. For example, the duration of discussion between students is 10 minutes, the duration of questions and answers between teachers and students is 10 minutes, the total duration of the teaching video is 40 minutes, the proportion of discussion between students is 10 / 40×100%=25%, the proportion of questions and answers between teachers and students is 10 / 40×100%=25%.

[0107] S430, determining the class type according to the proportion of various classroom interactive behaviors in the teaching video.

[0108] It can be understood that if the proportion of students responding to the teacher's instructions is the highest, and the proportions higher than the other two are greater than the preset threshold (such as 15%), it is teacher-led. If the proportion of students discussing with each other is the highest, and the proportions higher than the other two are greater than the preset threshold (such as 15%), it is student-led. Other situations are considered mixed.

[0109] Through the above steps S410 to S430, the class type can be objectively and accurately judged based on the classroom interaction behavior information, which is conducive to a more accurate understanding of the actual interaction situation in the classroom, providing a basis for subsequent participation evaluation and education management quality analysis, and helping teachers and education managers understand the pattern of classroom interaction and optimize teaching strategies.

[0110] S500, determining the student's class participation based on the class interaction behavior information and the class type.

[0111] For example, the students' class participation can be comprehensively evaluated based on the class type and the information about the students' class interaction behaviors.

[0112] In one possible implementation, see Figure 5 , S500, determines the student's class participation based on the class interaction behavior information and the class type, including: S510, determining participation weights corresponding to various classroom interactive behaviors based on the class type.

[0113] Exemplarily, different participation weights may be assigned to classroom interaction behaviors according to different classroom types, as shown in Table 5 below.

[0114] Table 5 S520, determining the class participation degree based on the class interaction behavior information and the participation weights corresponding to various class interaction behaviors.

[0115] Exemplarily, the class participation can be determined according to the class interaction behavior information and the participation weights corresponding to the class interaction behaviors of different class types. For example, the average number of students responding to the teacher's instructions is 30, the total number of students is 50, the duration of discussion between students is 10 minutes, the duration of questions and answers between teachers and students is 10 minutes, and the total duration of teaching videos is 40 minutes. Then the average number of students responding to the teacher's instructions is 30 / 50×100%=60%, the proportion of students discussing with each other is 10 / 40×100%=25%, the proportion of questions and answers between teachers and students is 10 / 40×100%=25%, the proportion of students responding to the teacher's instructions is the highest, and the part higher than the other two is greater than the preset threshold (such as 15%), which is teacher-led, and the participation weight is as shown in Table 5 above, class participation=(30 / 50×0.5+10 / 40×0.2+10 / 40×0.3)×10=4.25 (points).

[0116] Through the above steps S510 to S520, the class type and the specific performance of students' participation in classroom interactive behaviors can be comprehensively considered. By determining the participation weight and calculating the class participation, the students' participation in the class can be quantified, which is helpful to evaluate the teaching effect and the students' learning status, and provide decision support for education managers.

[0117] S600, determines the quality of educational management based on classroom order scores and classroom participation.

[0118] For example, whether the quality of education management is qualified can be determined based on the classroom order score and classroom participation.

[0119] In one possible implementation, see Figure 5 , S600, determines the quality of education management based on classroom order scores and classroom participation, including: S610, determine the education management quality score based on the classroom order score and classroom participation.

[0120] For example, the classroom order score and classroom participation can be weighted to determine the education management quality score. For example, if the classroom order score is 8 points and the classroom participation is 5 points, the education management quality score = 8 × 0.6 + 5 × 0.4 = 6.8 (points).

[0121] S620: If the education management quality score exceeds the quality threshold, it is determined that the education management quality is qualified.

[0122] It can be understood that the quality threshold is that the education management quality score does not exceed a preset specified value. The preset specified value can be set by ordinary technicians in this field according to actual needs and is not a sole limitation here.

[0123] For example, a reasonable quality threshold can be determined based on historical data and industry standards. For example, the quality threshold can be 6 points. If the education management quality score exceeds 6 points, then it can be determined that the education management quality is qualified.

[0124] S630: If the education management quality score does not exceed the quality threshold, it is determined that the education management quality is unqualified.

[0125] It can be understood that if the education management quality score does not exceed the quality threshold (such as 6 points), then it can be determined that the education management quality is unqualified.

[0126] Through the above steps S610 to S630, it is helpful to objectively and comprehensively evaluate the quality of education management, quantify the actual effect of education management, provide a basis for education managers to improve education management work, and help education managers to discover problems in time and take measures to improve them.

[0127] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0128] Corresponding to the education management supervision method described in the above embodiment, the embodiment of the present application also provides an education management supervision system, and each module of the system can implement each step of the education management supervision method. Figure 6A structural block diagram of the education management and inspection system provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0129] Reference Figure 6 The system comprises: Acquisition module, used to acquire teaching videos; A teaching text module, used to determine teaching text data based on the teaching video; wherein the teaching text data includes teacher text data and student text data; A classroom module, used to determine a classroom order score and classroom interactive behavior information based on the teaching video and the teaching text data; wherein the classroom interactive behavior information includes the duration or average number of students participating in various classroom interactive behaviors in the teaching video, and the classroom interactive behaviors include discussions between students, students responding to the teacher's instructions, and questions and answers between the teacher and students; A type module, used to determine the class type based on the class interaction behavior information; wherein the class types include teacher-led, student-led and mixed; A participation module, used for determining the class participation of students based on the class interaction behavior information and the class type; An education management module is used to determine the quality of education management based on the classroom order score and the classroom participation.

[0130] It should be noted that the information interaction, execution process, etc. between the above-mentioned systems / modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0131] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0132] The present application also provides an education management inspection device. Figure 7 This is a schematic diagram of the structure of an education management and inspection device provided in one embodiment of the present application. Figure 7 As shown, the education management and inspection device 6 of this embodiment includes: at least one processor 60 ( Figure 7 Only one is shown), at least one memory 61 ( Figure 7 Only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the education management and supervision device 6 implements the steps in any of the above-mentioned education management and supervision method embodiments, or implements the functions of each module / unit in the above-mentioned system embodiments.

[0133] Exemplarily, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 62 in the education management and inspection device 6.

[0134] The education management and inspection device 6 can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The education management and inspection device can include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Figure 7 It is merely an example of the education management and inspection device 6 and does not constitute a limitation of the education management and inspection device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, buses, etc.

[0135] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0136] In some embodiments, the memory 61 may be an internal storage unit of the education management and inspection device 6, such as a hard disk or memory of the education management and inspection device 6. In other embodiments, the memory 61 may also be an external storage device of the education management and inspection device 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the education management and inspection device 6. Furthermore, the memory 61 may also include both an internal storage unit and an external storage device of the education management and inspection device 6. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0137] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0138] An embodiment of the present application provides a computer program product. When the computer program product runs on an education management and supervision device, it enables the education management and supervision device to implement the steps in any of the above-mentioned method embodiments.

[0139] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the education management inspection system / education management inspection device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0140] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0141] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0142] In the embodiments provided in the present application, it should be understood that the disclosed education management inspection system / education management inspection equipment and method can be implemented in other ways. For example, the education management inspection system / education management inspection equipment embodiment described above is only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0143] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for supervising education management, characterized in that: include: Get instructional videos; Determining teaching text data based on the teaching video; wherein the teaching text data includes teacher text data and student text data; Determine a classroom order score and classroom interactive behavior information based on the teaching video and the teaching text data; wherein the classroom interactive behavior information includes the duration or average number of students participating in various classroom interactive behaviors in the teaching video, and the classroom interactive behaviors include discussions between students, students responding to the teacher's instructions, and questions and answers between the teacher and students; Determining a classroom type based on the classroom interaction behavior information; wherein the classroom types include teacher-led, student-led, and mixed; Determine the student's class participation based on the class interaction behavior information and the class type; The quality of educational management is determined based on the classroom order score and the classroom participation level.

2. The educational management inspection method according to claim 1, characterized in that: The determining of teaching text data based on the teaching video comprises: Extracting audio data from the teaching video; Obtain teacher audio data and student audio data according to the audio data; The teacher audio data and the student audio data are converted into corresponding teacher text data and the student text data to obtain the teaching text data.

3. The educational management inspection method according to claim 1, characterized in that: The determining of the classroom order score and classroom interactive behavior information based on the teaching video and the teaching text data includes: Obtaining a first key frame of the student according to the teaching video; wherein the first key frame is used to reflect the change of the student's head posture in the teaching video; Extracting first question information of teachers and / or students and first instruction information of teachers according to the teaching text data; wherein the first question information is a question raised by teachers and / or students in the teaching text data, and the first instruction information includes action instruction information representing the action of teachers instructing students to raise / lower their heads and discussion instruction information representing the action of teachers instructing students to discuss with each other; Extracting from the first key frame a second key frame which is after the time of the first indication information and whose time interval with the corresponding first indication information is less than a time interval threshold; Determine the total duration of a first behavior of each student according to the first key frame, the second key frame and the first indication information; wherein the first behavior is a behavior of the student not paying attention in class; Obtaining the classroom order score according to the total duration of each student's first behavior; Searching the teaching text data for the first text data corresponding to the time after the first question information and the discussion instruction information, to obtain the first interactive behavior information; wherein the first interactive behavior information includes the duration of each discussion between students and each question and answer between the teacher and students; Obtaining second interactive behavior information according to the action instruction information and the second key frame; wherein the second interactive behavior information is the number of students who respond to the teacher's instruction each time; The classroom interactive behavior information is obtained according to the first interactive behavior information and the second interactive behavior information.

4. The educational management inspection method according to claim 3, characterized in that: The step of obtaining the first key frame of the student according to the teaching video comprises: Sampling a frame from the teaching video at fixed time intervals to obtain multiple video frames; Determine the head area of ​​each student in each video frame according to each video frame; Obtaining a tilt angle of the head according to the head area; wherein the tilt angle includes a pitch angle and a yaw angle of the head relative to a vertical direction; Calculating the difference of the tilt angle of each student in each two adjacent video frames; If the difference of the tilt angles of a student exceeds an angle threshold, the corresponding two adjacent video frames are determined as the first key frames corresponding to the student.

5. The educational management inspection method according to claim 4, characterized in that: The determining the total duration of each student's first behavior according to the first key frame, the second key frame and the first indication information includes: Determining whether the first indication information matches the tilt angle of each student in the corresponding second key frame; If the tilt angle of a student in the second key frame does not match the corresponding first indication information, it is determined that the student has the first behavior, and a first duration is determined according to the second key frame and the corresponding first indication information; If the tilt angle of a student in the first key frame is not within the angle range and the second time interval between the student and the adjacent next first key frame exceeds the first threshold, it is determined that the student has the first behavior; The total duration of the first behavior of the corresponding student is determined according to the first duration and the second duration.

6. The educational management inspection method according to claim 3, characterized in that: The step of searching the teaching text data for the first text data corresponding to the time after the first question information and the discussion instruction information to obtain the first interactive behavior information includes: Searching the teaching text data for the first text data in a corresponding preset time period after the time of the first question information and the discussion instruction information; Calculating the relevance between the first question information and the discussion instruction information and the corresponding first text data respectively; Determining whether the first text data is related to the first question information or the discussion instruction information according to the correlation degree; If the first text data is related to the first question information or the discussion instruction information, the first interactive behavior information is determined according to the time of the first text data.

7. The educational management inspection method according to claim 1, characterized in that: The determining of the class type based on the class interaction behavior information includes: Determine, based on the classroom interaction behavior information, the proportion of the average number of students participating in the classroom interaction behavior in the teaching video relative to the total number of corresponding students; Determine, based on the classroom interaction behavior information, the proportion of the duration of the student's participation in the classroom interaction behavior in the teaching video relative to the total duration of the teaching video; The class type is determined according to the proportion of various classroom interactive behaviors in the teaching video.

8. The educational management inspection method according to claim 1, characterized in that: The determining of the student's class participation based on the class interaction behavior information and the class type includes: Determining participation weights corresponding to various classroom interactive behaviors based on the classroom type; The class participation degree is determined based on the class interaction behavior information and the participation weights corresponding to various class interaction behaviors.

9. The educational management inspection method according to claim 1, characterized in that: The determining of the quality of education management based on the classroom order score and the classroom participation degree comprises: Determining an education management quality score based on the classroom order score and the classroom participation score; If the education management quality score exceeds the quality threshold, the education management quality is determined to be qualified; If the education management quality score does not exceed the quality threshold, the education management quality is determined to be unqualified.

10. An education management and inspection system, characterized in that: include: Acquisition module, used to acquire teaching videos; A teaching text module, used to determine teaching text data based on the teaching video; wherein the teaching text data includes teacher text data and student text data; A classroom module, used to determine a classroom order score and classroom interactive behavior information based on the teaching video and the teaching text data; wherein the classroom interactive behavior information includes the duration or average number of students participating in various classroom interactive behaviors in the teaching video, and the classroom interactive behaviors include discussions between students, students responding to the teacher's instructions, and questions and answers between the teacher and students; A type module, used to determine the class type based on the class interaction behavior information; wherein the class types include teacher-led, student-led and mixed; A participation module, used for determining the class participation of students based on the class interaction behavior information and the class type; An education management module is used to determine the quality of education management based on the classroom order score and the classroom participation.

Images