A method, apparatus, device, and readable storage medium for structuring teaching data

By acquiring data from camera equipment, recording equipment, and teaching software, voiceprint and person recognition are performed to generate structured teaching data, which solves the problem of unstructured data hindering the application of teaching data and improves the efficiency of value mining and application of teaching data.

CN115203187BActive Publication Date: 2026-11-17GUANGDONG ACAD OF EDUCATION +3
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202210789162.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-06
Publication Date
2026-11-17
Estimated Expiration
2042-07-06

AI Technical Summary

Technical Problem

In existing technologies, unstructured classroom teaching data hinders the value mining and application of teaching data.

Method used

Teaching data is acquired from camera equipment, recording equipment, and teaching software, separated and processed into audio, video, and teaching record data. The actor ID is labeled through voiceprint recognition and person recognition, start and end times and behavior patterns are established, and finally, comparison and calibration are performed between different tracks to generate structured teaching data.

Benefits of technology

It enables the structuring of teaching data, supports classroom teaching evaluation, sharing of teaching resources and teacher professional development, and improves the efficiency of value mining and application of teaching data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115203187B_ABST
    Figure CN115203187B_ABST
Patent Text Reader

Abstract

This application provides a method, apparatus, device, and readable storage medium for structuring teaching data. It acquires teaching data from camera equipment, recording equipment, and teaching software; separates the teaching data into initial behavioral data corresponding to the camera equipment, recording equipment, and teaching software, and processes the initial behavioral data independently and in parallel to obtain target behavioral data. The initial behavioral data includes audio data, video data, and teaching record data. The target behavioral data is compared across different tracks according to different behavioral patterns in chronological order, and calibrated based on the comparison results to obtain structured teaching data. By implementing this solution, after processing the audio data, video data, and teaching record data, the three types of data are compared and calibrated again to obtain structured teaching data, which is beneficial for the value mining and application of teaching data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of electronic technology, and in particular to a method, apparatus, device, and readable storage medium for structuring teaching data. Background Technology

[0002] Classroom teaching data is of significant value in classroom assessment, sharing of teaching resources, teacher professional development, and student learning. Classic models of classroom analysis all require structured classroom data. However, commonly available classroom teaching data, including audio, video, and software recordings of teaching activities, is multimodal and unstructured, which hinders the valuable extraction and application of this data. Summary of the Invention

[0003] This application provides a method, apparatus, device, and readable storage medium for structuring teaching data, which can at least solve the problem that unstructured teaching data hinders the value mining and application of teaching data in related technologies.

[0004] The first aspect of this application provides a method for structuring teaching data, including:

[0005] Teaching data is obtained from video recording equipment, audio recording equipment, and teaching software.

[0006] The teaching data is separated into initial behavioral data corresponding to the camera device, the recording device, and the teaching software, and the initial behavioral data is processed independently and in parallel to obtain target behavioral data; wherein, the initial behavioral data includes: audio data, video data, and teaching record data; the target behavioral data is a set of start and end time, actor, behavior mode, and behavior content;

[0007] The target behavior data is compared between different tracks according to different behavior patterns in chronological order, and the data is calibrated based on the comparison results to obtain structured teaching data; wherein, the tracks include: video track, audio track and teaching record track.

[0008] A second aspect of this application provides a teaching data structuring device, comprising:

[0009] The acquisition module is used to acquire teaching data from camera equipment, recording equipment, and teaching software respectively;

[0010] The processing module is used to separate the teaching data into behavioral data corresponding to the camera device, the recording device, and the teaching software, and to process the initial behavioral data independently and in parallel to obtain target behavioral data; wherein, the initial behavioral data includes: audio data, video data, and teaching record data; the target behavioral data is a set of start and end time, actor, behavior mode, and behavior content;

[0011] The calibration module is used to compare the target behavior data in chronological order with different tracks according to different behavior patterns, and to calibrate the data based on the comparison results to obtain structured teaching data; wherein, the tracks include: video track, audio track and teaching record track.

[0012] A third aspect of this application provides an electronic device, characterized in that it includes a memory and a processor, wherein the processor is configured to execute a computer program stored in the memory, and the processor executes the computer program in accordance with the steps of the teaching data structuring method provided in the first aspect of this application.

[0013] The fourth aspect of this application provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the steps of the teaching data structuring method provided in the first aspect of this application.

[0014] As can be seen from the above, according to the teaching data structuring method, apparatus, equipment, and readable storage medium provided in this application, teaching data is acquired from camera equipment, recording equipment, and teaching software respectively; the teaching data is separated into initial behavioral data corresponding to the camera equipment, recording equipment, and teaching software, and the initial behavioral data is processed independently and in parallel to obtain target behavioral data; wherein, the initial behavioral data includes: audio data, video data, and teaching record data; the target behavioral data is a set of start and end times, actors, behavioral methods, and behavioral content; the target behavioral data is compared between different tracks according to different behavioral methods in chronological order, and calibrated according to the comparison results to obtain structured teaching data; wherein, the tracks include: video track, audio track, and teaching record track. Through the implementation of this application, after processing the audio data, video data, and teaching record data, the three different types of data are compared and calibrated again to obtain structured teaching data, which is beneficial to the value mining and application of teaching data. Attached Figure Description

[0015] Figure 1 A basic flowchart illustrating the teaching data structuring method provided in the first embodiment of this application;

[0016] Figure 2 A detailed flowchart illustrating the teaching data structuring method provided in the second embodiment of this application;

[0017] Figure 3 A schematic diagram of the program modules of the teaching data structuring device provided in the third embodiment of this application;

[0018] Figure 4 This is a schematic diagram of the structure of an electronic device provided in the fourth embodiment of this application. Detailed Implementation

[0019] To make the inventive objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] To address the problem that unstructured teaching data hinders the value extraction and application of teaching data in related technologies, the first embodiment of this application provides a method for structuring teaching data, such as... Figure 1 This is a basic flowchart of the teaching data structuring method provided in this embodiment. The teaching data structuring method includes the following steps:

[0021] Step 101: Obtain teaching data from the camera equipment, recording equipment, and teaching software respectively.

[0022] Specifically, in this embodiment, whether it is online teaching or offline teaching, teaching data can be obtained from multiple sources. For example, video equipment can be used to capture the actions of teachers and students, such as lecturing and teacher-student interactions; audio equipment can be used to capture the voices of teachers and students; and teaching software can be used to capture classroom teaching records. All of these can be used as teaching data.

[0023] Step 102: Separate the teaching data into initial behavioral data corresponding to the camera equipment, recording equipment, and teaching software, and process the initial behavioral data independently and in parallel to obtain the target behavioral data.

[0024] Specifically, in this embodiment, the initial behavioral data includes audio data, video data, and teaching record data; the target behavioral data is a set of start and end times, actors, behavioral methods, and behavioral content. The teaching data obtained from the device and software is separated into audio, video, and teaching record formats, and each type of data is processed independently and in parallel.

[0025] In one optional implementation of this embodiment, the step of independently and in parallel processing the initial behavioral data to obtain the target behavioral data includes: when processing the audio data, performing voiceprint recognition on the audio data and labeling the speaker ID; if the same speaker ID reaches a speaking frequency threshold within a preset time, then establishing a first start and end time; performing audio recognition on the audio of the same speaker ID within the start and end time, and converting the recognized content into spoken text; repeating the above steps until all the audio data is processed into a first set including the start and end time, the actor, the behavior mode, and the behavior content; wherein, the actor is the speaker ID, the behavior mode is speaking, and the behavior content is the spoken text.

[0026] Specifically, in this embodiment, when processing audio data, voiceprint recognition is performed on the audio data. The speaker is identified based on the voiceprint and labeled with a speaker ID. It should be noted that voiceprint information, like ID card information, can identify a person's identity information. This embodiment first records and stores the voiceprints of students and teachers. When performing voiceprint recognition, the voice to be processed is compared with the voiceprint information stored in the preset voiceprint library to identify the voiceprint and label the corresponding speaker ID. When the same student or teacher speaks continuously within a preset time period, it can be determined that the student is answering a question or the teacher is lecturing. The start and end time of this period is established, and the audio of the speaker during this period is recognized. The recognized content is converted into text. The above steps are repeated until all audio data is processed into a set of (start and end time, actor, behavior mode, and behavior content). In the audio data, the actor is the person corresponding to the speaker ID, the behavior mode is speaking, and the behavior content is the converted text.

[0027] It should be noted that the processing of video data also requires first identifying the characters in the video. This involves using a facial recognition database to identify faces in the video and labeling them with actor IDs. After character identification, the behavior patterns corresponding to the actor IDs are collected and categorized. Based on preset behavior information, the ongoing behavior is determined; for example, a student raising their hand indicates they are answering a question. If a student or teacher continuously performs the same action for a preset period of time, reaching a certain number of times, a start and end time is established. These steps are repeated until all video data is processed into a set of (start and end time, actor, behavior pattern, and behavior content). In the video data, the behavior pattern is the action type.

[0028] It should also be noted that the processing of teaching record data includes, but is not limited to, teaching records in offline classrooms and records from online teaching software. Regardless of the method, when processing teaching record data, the start and end times of the teaching can be used as the start and end times in the set, and the teaching records can be obtained from the teaching record data. The teaching records mainly record the teacher's voice, actions or other behaviors. The above data is integrated into a set of (start and end times, actor, behavior, and content).

[0029] Step 103: Compare the target behavior data in chronological order across different tracks according to different behavior patterns, and calibrate based on the comparison results to obtain structured teaching data.

[0030] Specifically, the tracks include: video track, audio track, and teaching record track. In this embodiment, according to the start and end times of the three sets of audio, video, and teaching records, the actors and behaviors in each set are compared and calibrated. Audio data is placed in the audio track and compared with the audio data set; video data is placed in the video track and compared with the video data set; and teaching record data is placed in the teaching record track and compared with the teaching record set. Based on the comparison results, the probability of the actor is determined, and the one with the highest probability is adopted as the actor. For example, in the audio track, the probability that the current speaker is a teacher is 90%; in the video track, the probability that the current speaker is a student is 95%; therefore, the current speaker is considered a student. After comparison, the data in the three fields of start and end time, actor, and behavior in the calibration sets are calibrated, and naturally, the corresponding behavioral content is also calibrated, thus obtaining accurate structured teaching data.

[0031] In one optional implementation of this embodiment, after the step of calibrating based on the comparison results to obtain structured teaching data, the method further includes: evaluating classroom teaching based on the structured teaching data; wherein the classroom teaching evaluation includes: evaluating the teacher's teaching quality, evaluating whether students actively answer questions, and evaluating teacher-student interaction; or, analyzing teaching course resources based on the structured teaching data; and allocating the teaching course resources based on the analysis results.

[0032] Specifically, in this embodiment, after obtaining structured teaching data based on comparison and calibration, classroom teaching evaluation or teaching course resource analysis can be performed based on the teaching data. Classroom teaching evaluation includes: evaluation of the teacher's teaching quality, evaluation of whether students actively answer questions, and evaluation of teacher-student interaction. After analyzing the teaching course resources, teaching course resources can be allocated based on the analysis results.

[0033] Furthermore, in an optional implementation of this embodiment, after the step of evaluating classroom teaching based on the structured teaching data, the method further includes: classifying and storing the structured teaching data according to the teacher's teaching quality; and decomposing different categories of structured teaching data into teaching resource fragments according to teaching needs.

[0034] Specifically, in this embodiment, the evaluation of teachers' teaching quality can clarify a teaching style and the difficulty and comprehension level of the teaching content. By classifying and storing structured teaching data, and decomposing different categories of teaching data into teaching resource fragments according to teaching needs, it helps teachers to teach according to the corresponding teaching fragments, or students to choose teaching fragments for self-study, thereby improving the value mining and application of classroom teaching data.

[0035] Based on the embodiments of the above application, teaching data is acquired from a camera device, a recording device, and teaching software, respectively. The teaching data is separated into initial behavioral data corresponding to the camera device, the recording device, and the teaching software, and these initial behavioral data are processed independently and in parallel to obtain target behavioral data. The initial behavioral data includes audio data, video data, and teaching record data. The target behavioral data is a set of start and end times, actors, behavioral patterns, and behavioral content. The target behavioral data is compared between different tracks according to different behavioral patterns in chronological order, and calibrated based on the comparison results to obtain structured teaching data. The tracks include a video track, an audio track, and a teaching record track. By implementing this application's solution, after processing the audio data, video data, and teaching record data, the three different types of data are compared and calibrated again to obtain structured teaching data, which is beneficial for the value mining and application of teaching data.

[0036] Figure 2 The method described in the second embodiment of this application is a refined method for structuring teaching data, which includes:

[0037] Step 201: Obtain teaching data from the camera equipment, recording equipment, and teaching software respectively.

[0038] Step 202: Separate the teaching data into initial behavioral data corresponding to the camera equipment, recording equipment, and teaching software.

[0039] Step 203: When the initial behavioral data being processed is audio data, process all audio data into first target behavioral data that includes start and end time, actor, behavior mode, and behavioral content.

[0040] Specifically, in this embodiment, when processing audio data, voiceprint recognition is performed on the audio data, and speaker IDs are labeled; if the same speaker ID reaches a threshold number of times it speaks within a preset time period, a first start and end time is established; audio recognition is performed on the audio of the same speaker ID within the start and end time period, and the recognized content is converted into spoken text; the above steps are repeated until all audio data is processed into a first set containing start and end time, actor, behavior mode, and behavior content; wherein, the actor is the speaker ID, the behavior mode is speaking, and the behavior content is spoken text. This set is the final target behavior data obtained.

[0041] Step 204: When the initial behavioral data being processed is video data, process all video data into second target behavioral data that includes start and end times, actors, behavioral methods, and behavioral content.

[0042] Specifically, in this embodiment, when processing video data, person identification is performed on the video data and the actor ID is labeled; the behavior of the actor ID is classified; if the same actor ID reaches the behavior frequency threshold for the same behavior type within a preset time, a second start and end time is established; the above steps are repeated until all video data is processed into a second set including start and end time, actor, behavior type and behavior content; wherein, the actor is the actor ID and the behavior type is the behavior type.

[0043] Step 205: When the initial behavioral data being processed is teaching record data, all teaching record data is processed into third target behavioral data that includes start and end time, actor, behavior mode, and behavior content.

[0044] Specifically, in this embodiment, when processing teaching record data, the third start and end time of classroom teaching and the teaching content are obtained from the teaching record data; the actor ID and behavior mode are determined according to the teaching content; the above steps are repeated until all teaching record data are processed into a third set containing start and end time, actor, behavior mode and behavior content.

[0045] Step 206: Obtain the probability of the first actor corresponding to the target behavior by comparing the audio track data with the first target behavior data; obtain the probability of the second actor corresponding to the target behavior by comparing the video track data with the second target behavior data; and obtain the probability of the third actor corresponding to the target behavior by comparing the teaching record track data with the third target behavior data.

[0046] Step 207: Determine the corresponding actor for the target behavior within the target time period based on the maximum probability between different orbits.

[0047] Step 208: After comparison, the start and end times, actors, and behavior patterns are calibrated, and the behavior content corresponding to the actors is obtained. A set of start and end times, actors, behavior patterns, and behavior content is generated to obtain structured teaching data.

[0048] According to the teaching data structuring method provided in this application, teaching data is acquired from camera equipment, recording equipment, and teaching software respectively; the teaching data is separated into initial behavioral data corresponding to the camera equipment, recording equipment, and teaching software; when the initial behavioral data is audio data, all audio data is processed into first target behavioral data containing start and end time, actor, behavior mode, and behavior content; when the initial behavioral data is video data, all video data is processed into second target behavioral data containing start and end time, actor, behavior mode, and behavior content; when the initial behavioral data is teaching record data, all teaching record data is processed into data containing start and end time, actor, behavior mode, and behavior content. The method involves obtaining the third target behavior data, including the mode and content of the behavior. The probability of the first actor corresponding to the target behavior is obtained by comparing audio track data with the first target behavior data; the probability of the second actor corresponding to the target behavior is obtained by comparing video track data with the second target behavior data; and the probability of the third actor corresponding to the target behavior is obtained by comparing teaching record track data with the third target behavior data. Based on the maximum probability between different tracks, the corresponding actor for the target behavior within the target time period is determined. The start and end times, actors, and behavior modes after comparison are calibrated, and the corresponding behavior content is obtained, generating a set of start and end times, actors, behavior modes, and behavior content to obtain structured teaching data. Through the implementation of this application's solution, after processing audio data, video data, and teaching record data, the three different types of data are compared and calibrated again to obtain structured teaching data, which is beneficial for the value mining and application of teaching data.

[0049] Figure 3 A teaching data structuring device is provided in the third embodiment of this application. This teaching data structuring device can be used to implement the teaching data structuring method in the foregoing embodiments. For example... Figure 3 As shown, the teaching data structuring device mainly includes:

[0050] The acquisition module 301 is used to acquire teaching data from the camera device, the recording device, and the teaching software respectively;

[0051] The processing module 302 is used to separate the teaching data into behavioral data corresponding to the camera device, the recording device, and the teaching software, and to process the initial behavioral data independently and in parallel to obtain target behavioral data; wherein, the initial behavioral data includes: audio data, video data, and teaching record data; the target behavioral data is a set of start and end time, actor, behavior mode, and behavior content;

[0052] The calibration module 303 is used to compare the target behavior data in chronological order with different tracks according to different behavior patterns, and to calibrate the data based on the comparison results to obtain structured teaching data; wherein, the tracks include: video track, audio track and teaching record track.

[0053] In an optional implementation of this embodiment, the processing module is specifically used for: when processing the audio data, performing voiceprint recognition on the audio data and labeling the speaker ID; if the same speaker ID reaches a speaking frequency threshold within a preset time, then establishing a first start and end time; performing audio recognition on the audio of the same speaker ID within the start and end time, and converting the recognized content into spoken text; repeating the above steps until all the audio data is processed into a first set including the start and end time, the actor, the behavior mode, and the behavior content; wherein, the actor is the speaker ID, the behavior mode is speaking, and the behavior content is the spoken text.

[0054] In an optional implementation of this embodiment, the processing module is specifically used for: when processing the video data, performing person identification on the video data and labeling the actor ID; classifying the behavior patterns of the actor ID; if the same actor ID performs the same behavior type for the same time period to reach a behavior frequency threshold, then establishing a second start and end time; repeating the above steps until all the video data is processed into a second set including the start and end time, the actor, the behavior pattern, and the behavior content; wherein, the actor is the actor ID and the behavior pattern is the behavior type.

[0055] In an optional implementation of this embodiment, the processing module is specifically used to: when processing the teaching record data, obtain the third start and end time of the classroom teaching and the teaching content from the teaching record data; determine the actor ID and the behavior mode according to the teaching content; repeat the above steps until all the teaching record data are processed into a third set containing the start and end time, the actor, the behavior mode and the behavior content.

[0056] Furthermore, in an optional implementation of this embodiment, when the calibration module performs the function of comparing target behavior data in chronological order across different tracks according to different behavior patterns, it is specifically used to: compare the audio data of the audio track, the video data of the video track, and the teaching record data of the teaching record track within the same target time period from the set containing the start and end time, the actor, the behavior pattern, and the behavior content, respectively, with the corresponding set; obtain the probability of the first actor corresponding to the target behavior by comparing the audio track data with the first set, obtain the probability of the second actor corresponding to the target behavior by comparing the video track data with the second set, obtain the probability of the third actor corresponding to the target behavior by comparing the teaching record track data with the third set; and determine the actor corresponding to the target behavior within the target time period based on the maximum probability between different tracks.

[0057] In an optional implementation of this embodiment, the teaching data structuring device further includes an evaluation module and an analysis module. The evaluation module is used to: evaluate classroom teaching based on the structured teaching data; wherein the classroom teaching evaluation includes: evaluating the teacher's teaching quality, evaluating the students' active participation in answering questions, and evaluating teacher-student interaction. The analysis module is used to: analyze teaching course resources based on the structured teaching data; and allocate the teaching course resources based on the analysis results.

[0058] Furthermore, in an optional embodiment of this invention, the teaching data structuring device further includes: a storage module and a decomposition module. The storage module is used to classify and store the structured teaching data according to the teacher's teaching quality. The decomposition module is used to decompose different categories of structured teaching data into teaching resource fragments according to teaching needs.

[0059] According to the teaching data structuring device provided in this application, teaching data is acquired from a camera, a recording device, and teaching software respectively; the teaching data is separated into initial behavioral data corresponding to the camera, the recording device, and the teaching software, and the initial behavioral data is processed independently and in parallel to obtain target behavioral data; wherein, the initial behavioral data includes: audio data, video data, and teaching record data; the target behavioral data is a set of start and end times, actors, behavioral methods, and behavioral content; the target behavioral data is compared between different tracks according to different behavioral methods in chronological order, and calibrated according to the comparison results to obtain structured teaching data; wherein, the tracks include: video track, audio track, and teaching record track. Through the implementation of this application, after processing the audio data, video data, and teaching record data, the three different types of data are compared and calibrated again to obtain structured teaching data, which is beneficial for the value mining and application of teaching data.

[0060] Figure 4 An electronic device is provided in the fourth embodiment of this application. This electronic device can be used to implement the teaching data structuring method in the foregoing embodiments, and mainly includes:

[0061] The system includes a memory 401, a processor 402, and a computer program 403 stored on the memory 401 and executable on the processor 402. The memory 401 and the processor 402 are communicatively connected. When the processor 402 executes the computer program 403, it implements the teaching data structuring method described in the foregoing embodiments. The number of processors can be one or more.

[0062] The memory 401 can be a high-speed random access memory (RAM) or a non-volatile memory, such as a disk storage device. The memory 401 is used to store executable program code, and the processor 402 is coupled to the memory 401.

[0063] Furthermore, embodiments of this application also provide a computer-readable storage medium, which may be disposed in the electronic device described in the above embodiments, and the computer-readable storage medium may be as described above. Figure 4 The memory in the illustrated embodiment.

[0064] The computer-readable storage medium stores a computer program that, when executed by a processor, implements the teaching data structuring method described in the foregoing embodiments. Furthermore, the computer-readable storage medium can also be a USB flash drive, external hard drive, read-only memory (ROM), RAM, magnetic disk, or optical disk, or any other medium capable of storing program code.

[0065] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0066] The modules described as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0067] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0068] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0069] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0070] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0071] The above is a description of the teaching data structuring method, apparatus, device, and readable storage medium provided in this application. For those skilled in the art, based on the ideas of the embodiments of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method of structuring teaching data, characterized by, include: Teaching data is obtained from video recording equipment, audio recording equipment, and teaching software. The teaching data is separated into initial behavioral data corresponding to the camera device, the recording device, and the teaching software, and the initial behavioral data is processed independently and in parallel to obtain target behavioral data; wherein, the initial behavioral data includes: audio data, video data, and teaching record data; the target behavioral data is a set of start and end time, actor, behavior mode, and behavior content; The target behavior data is compared between different tracks according to different behavior patterns in chronological order, and the data is calibrated based on the comparison results to obtain structured teaching data; wherein, the tracks include: video track, audio track, and teaching record track; The step of independently and in parallel processing the initial behavior data to obtain the target behavior data includes: When processing the audio data, voiceprint recognition is performed on the audio data, and the speaker ID is labeled; If the same speaker ID reaches the speaking frequency threshold within a preset time, then a first start and end time is established; Audio recognition is performed on the audio of the same speaker ID within the first start and end time period, and the recognized content is converted into spoken text; Repeat the above steps until all the audio data is processed into a first set containing the start and end times, the actor, the behavior mode, and the behavior content; wherein the actor is the speaker ID, the behavior mode is speaking, and the behavior content is the spoken text; The step of independently and in parallel processing the initial behavior data to obtain the target behavior data includes: When processing the video data, person identification is performed on the video data, and the actor ID is labeled; The behavior patterns of the actors are categorized. If the same actor ID performs the same type of behavior within a preset time period, reaching the behavior frequency threshold, then a second start and end time period is established. Repeat the above steps until all the video data is processed into a second set containing the start and end times, the actor, the behavior mode, and the behavior content; wherein the actor is the actor ID and the behavior mode is the behavior type; The step of independently and in parallel processing the initial behavior data to obtain the target behavior data includes: When processing the teaching record data, the third start and end time of classroom teaching and the teaching content are obtained from the teaching record data; The actor ID and the behavior pattern are determined based on the teaching content; Repeat the above steps until all the teaching record data is processed into a third set containing the start and end times, the actors, the behavior patterns, and the content of the behavior. The step of comparing the target behavior data in chronological order across different tracks according to different behavior patterns includes: In chronological order, the audio data of the audio track, the video data of the video track, and the teaching record data of the teaching record track within the same target time period from the set containing the start and end time, the actor, the behavior mode, and the behavior content are compared with the corresponding set. The probability of a first actor corresponding to the target behavior is obtained by comparing the audio track data with the first set; the probability of a second actor corresponding to the target behavior is obtained by comparing the video track data with the second set; and the probability of a third actor corresponding to the target behavior is obtained by comparing the teaching record track data with the third set. The corresponding actor for the target behavior within the target time period is determined based on the maximum probability between different orbits.

2. The method of structuring educational data according to claim 1, wherein, After the step of calibrating based on the comparison results to obtain structured teaching data, the method further includes: Classroom teaching evaluation is conducted based on the structured teaching data; wherein, the classroom teaching evaluation includes: evaluation of the teacher's teaching quality, evaluation of whether students actively answer questions, and evaluation of teacher-student interaction; Alternatively, the teaching course resources can be analyzed based on the structured teaching data. The teaching course resources are allocated based on the analysis results.

3. The teaching data structuring method according to claim 2, characterized in that, Following the step of evaluating classroom teaching based on the structured instruction data, the method further includes: The structured teaching data is categorized and stored according to the teachers' teaching quality. Based on teaching needs, different categories of structured teaching data are broken down into teaching resource fragments.

4. A teaching data structuring device, characterized in that, For performing the method of claim 1, the teaching data structuring device comprises: The acquisition module is used to acquire teaching data from camera equipment, recording equipment, and teaching software respectively; The processing module is used to separate the teaching data into initial behavioral data corresponding to the camera device, the recording device, and the teaching software, and to process the initial behavioral data independently and in parallel to obtain target behavioral data; wherein, the initial behavioral data includes: audio data, video data, and teaching record data; the target behavioral data is a set of start and end time, actor, behavior mode, and behavior content; The calibration module is used to compare the target behavior data in chronological order with different tracks according to different behavior patterns, and to calibrate the data based on the comparison results to obtain structured teaching data; wherein, the tracks include: video track, audio track and teaching record track.

5. An electronic device, characterized in that, Includes memory and processor, of which: The processor is used to execute computer programs stored in the memory; When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

Citation Information

Patent Citations

  • Intelligent user identification method and device, and computer readable storage medium

    CN111382408A

  • Method and device for recognizing behaviors in classroom teaching video

    CN114067391A