Image processing-based instructor training manual automatic update and instructor competency test method, device and system

Abstract

An electronic device according to one embodiment may include memory and a processor. The processor stores in the memory a learning manual comprising at least one of chalk color combinations, chalk usage angles, writing size, eye contact time between the instructor and the learner, eye contact frequency, counseling topics with the learner, counseling time, counseling frequency, a method for registering and managing the instructor's lectures online, a method for managing learners during semesters or vacation seasons, a method for managing lecture folders, a management method based on the learner's gender, a management method based on the learner's age, counseling topics regarding the learner's parents, a method for responding to parents, a subject, the instructor's voice tone, voice volume, the instructor's class speed, or the instructor's speech speed; provides a guide for corresponding elements in the learning manual based on user input; learns the instructor's lecture videos using an artificial intelligence learning model; quantifies the evaluation of the instructor's lecture for each component of the learning manual; evaluates the instructor's lecture based on the evaluation numerical value for the instructor; stores in the memory; creates a database indicating the instructor's lecture level based on lecture evaluation records for at least one instructor; updates the database whenever a new lecture video is learned using an artificial intelligence learning model; and the learning stored in the memory Evaluation scores for multiple instructors are calculated for each component of the manual, an average value is determined for the evaluation scores, a relative evaluation grade is assigned to the instructor based on the average value, grade information is stored together in the database, and the grade information can be displayed on the display based on user input in the database.

Description

Technology Field

[0001] The following embodiments relate to a method, apparatus, and system for automatically updating an instructor training manual and testing instructor competency based on image processing. Background Technology

[0003] With the recent advancement of IT technology, online video lectures are becoming increasingly common in schools and private academies. Just like offline lectures, these online video lectures may require evaluation of the instructors.

[0004] Korean Published Patent No. 10-1710200 (Automatic attendance management system and method using face recognition) is a prior patent, but it discloses an automatic attendance management system that recognizes students' faces using a camera on a terminal installed in each classroom, and does not disclose a method for automatically updating instructor training manuals and testing instructor competencies based on image processing.

[0005] In addition, there is Korean Published Patent No. 10-2022-0061384 (Device and Method for Detecting a Learner's Participation in Non-Face-to-Face Online Class), but while it only verifies attendance by recognizing a learner's face or checks class concentration based on the learner's gaze, it does not disclose a method for automatically updating an instructor training manual and testing instructor competence based on image processing. Prior art literature

[0007] KR No. 10-1710200 KR No. 10-2022-0061384 The problem to be solved

[0008] Existing online or offline learning systems have limitations in instructor recruitment due to the restricted information available to verify candidates.

[0009] In reality, it is difficult to verify applicants beyond the information they submit, and since even this information does not include only factors that directly influence the learner, there is a problem in that it is difficult for the hiring side to verify them in advance.

[0010] In particular, online video learning services struggle to sustain learners' attention, as they rely primarily on electronic whiteboards or digital content as supplementary learning tools, and it can be difficult to maintain the focus of easily distracted learners. For this reason, existing online learning systems are limited to the instructor's one-way delivery of information to the learners, which consequently presents a limitation where learners easily feel fatigued and lose interest in learning.

[0011] Therefore, when hiring instructors in online or offline environments, an objective and quantifiable manual containing evaluation elements that can stimulate learners' interest may be necessary. means of solving the problem

[0013] An electronic device according to one embodiment may include memory and a processor. The processor stores in the memory a learning manual comprising at least one of chalk color combinations, chalk usage angles, writing size, eye contact time between the instructor and the learner, eye contact frequency, counseling topics with the learner, counseling time, counseling frequency, a method for registering and managing the instructor's lectures online, a method for managing learners during semesters or vacation seasons, a method for managing lecture folders, a management method based on the learner's gender, a management method based on the learner's age, counseling topics regarding the learner's parents, a method for responding to parents, a subject, the instructor's voice tone, voice volume, the instructor's class speed, or the instructor's speech speed; provides a guide for corresponding elements in the learning manual based on user input; learns the instructor's lecture videos using an artificial intelligence learning model; quantifies the evaluation of the instructor's lecture for each component of the learning manual; evaluates the instructor's lecture based on the evaluation numerical value for the instructor; stores in the memory; creates a database indicating the instructor's lecture level based on lecture evaluation records for at least one instructor; updates the database whenever a new lecture video is learned using an artificial intelligence learning model; and the learning stored in the memory Evaluation scores for multiple instructors are calculated for each component of the manual, an average value is determined for the evaluation scores, a relative evaluation grade is assigned to the instructor based on the average value, grade information is stored together in the database, and the grade information can be displayed on the display based on user input in the database.

[0014] An electronic device according to one embodiment may be combined with hardware and controlled by a computer program stored on a medium to execute the method of any one of the methods described above. Effects of the invention

[0015] An electronic device according to one embodiment can objectively perform verification of an instructor by using an objective and quantified manual that includes evaluation elements capable of inducing a learner's interest in learning when hiring an instructor in an online or offline environment.

[0016] An electronic device according to one embodiment may provide a platform that quantifies verification results for an instructor, creates a database by sharing with another external device (or server), and provides recruitment information for the instructor, evaluation of the instructor, and information on the instructor's learning. Brief explanation of the drawing

[0017] FIG. 1 is an example diagram of the configuration of an electronic device according to one embodiment. FIG. 2 is a flowchart illustrating a method of providing lecture content based on an analysis of learning participation in an online lecture according to one embodiment. FIG. 3 is a flowchart illustrating an image processing-based instructor training manual automatic update and instructor competency test method according to one embodiment. FIG. 4 is a diagram illustrating the configuration of an artificial intelligence model according to one embodiment. FIG. 5 shows a neural network of an artificial intelligence learning model for evaluating lecture videos according to one embodiment. FIG. 6 is a flowchart illustrating a method for subdividing lecture content and providing a purchasing platform service for subdivided lecture content according to one embodiment. Specific details for implementing the invention

[0018] Hereinafter, embodiments are described in detail with reference to the attached drawings. However, various modifications may be made to the embodiments, and thus the scope of the patent application is not limited or restricted by these embodiments. It should be understood that all modifications, equivalents, and substitutions to the embodiments are included within the scope of the rights.

[0019] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed forms, and the scope of this specification includes modifications, equivalents, or substitutions that fall within the technical concept.

[0020] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0021] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or coupled with that other component, or that there may be other components in between.

[0022] The terms used in the embodiments are for illustrative purposes only and should not be interpreted as intended to be limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0023] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments pertain. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0024] In addition, when describing with reference to the attached drawings, identical components are assigned the same reference numeral regardless of drawing symbols, and redundant descriptions thereof are omitted. In describing the embodiments, if it is determined that a detailed description of related prior art could unnecessarily obscure the essence of the embodiments, such detailed description is omitted.

[0025] The embodiments can be implemented in various forms of products such as personal computers, laptop computers, tablet computers, smartphones, televisions, smart home appliances, intelligent automobiles, kiosks, and wearable devices.

[0027] FIG. 1 is an example diagram of the configuration of an electronic device according to one embodiment.

[0028] An electronic device (101) according to one embodiment may include a processor (120) and a memory (130), and some of the illustrated components may be omitted or substituted. An electronic device (101) according to one embodiment may be a server or a terminal. According to one embodiment, the processor (120) may be composed of one or more processors, as a component capable of performing operations or data processing regarding the control and / or communication of each component of the electronic device (101). The memory (130) may store information related to the method described above or store a program in which the method described above is implemented. The memory (130) may be volatile memory or non-volatile memory. The memory (130) may store various file data, and the stored file data may be updated according to the operation of the processor (120).

[0029] According to one embodiment, the processor (120) can execute a program and control the device (101). The code of the program executed by the processor (120) can be stored in memory (130). Operations of the processor (120) can be performed by loading instructions stored in memory (130). The electronic device (101) can be connected to an external device (e.g., a personal computer or a network) through an input / output device (not shown in the drawing) and exchange data.

[0030] According to one embodiment, there are no limitations on the computation and data processing functions that the processor (120) can implement on an electronic device, but below, functions for automatically updating an instructor training manual and testing instructor competencies based on image processing will be described.

[0032] FIG. 2 is a flowchart illustrating a method of providing lecture content based on an analysis of learning participation in an online lecture according to one embodiment.

[0033] The operations described through FIG. 2 may be implemented based on instructions that can be stored in a computer recording medium or memory (e.g., memory (130) of FIG. 1). The illustrated method may be executed by an electronic device (e.g., electronic device (101) of FIG. 1) described above through FIG. 1, and the technical features described above will be omitted below. The order of each operation in FIG. 2 may be changed, some operations may be omitted, and some operations may be performed simultaneously.

[0034] In operation 210, the processor (e.g., the processor (120) of FIG. 1) can determine the face region of the learner using a camera, distinguish the head and eyes based on feature points in the face region of the learner, determine the direction of the user's gaze based on the movement of the learner's eyes, and determine the head rotation angle based on the movement of the learner's head.

[0035] In operation 220, the processor (120) can determine the level of concentration of the learner based on at least one of the following cases: the magnitude of the head rotation angle exceeds a certain level, the frequency of head rotation exceeds a certain level, or the learner's gaze direction points in a different direction than the gaze direction of other learners around the learner exceeds a specified level.

[0036] In operation 230, the processor (120) can transmit a signal to the instructor indicating that the students' concentration has decreased based on the fact that the concentration of a certain percentage of students among multiple students taking the same instructor's lecture within a specific area has decreased below a specified level.

[0037] In operation 240, the processor (120) separately stores in the memory at least one first section in which a signal indicating that the learners' concentration level has decreased during the instructor's lecture is transmitted, and can learn the lecture content, the learners' head movements, eye movements, and the concentration level corresponding to the first section separately stored in the memory using an artificial intelligence learning model.

[0038] In operation 250, the processor (120) can analyze at least one of the subject name, unit name, learning difficulty, the speed of the instructor's lecture, the tone of the instructor's voice, the speed of the instructor's speech, the time of the instructor's eye contact with the learners, the frequency of eye contact, the size of the handwriting when using the blackboard, or the time elapsed since the start of the lecture in a lecture corresponding to a section separately stored in memory (130).

[0039] In operation 260, the processor (120) can obtain numerical information regarding the analysis elements of the second or third section in which a signal indicating that the learners' concentration level has decreased has been transmitted through the server.

[0041] In operation 270, the processor (120) can provide feedback to the instructor regarding the elements among the analysis elements of the first section whose numerical value deviates from the level specified in the first value.

[0042] In one embodiment, the feature points of the learner's face region may be determined based on at least one of the vertical position of the eyes, the horizontal width of the eyes, the height of the eyes, the vertical position of the eyebrows, the distance between the eyes, the horizontal width of the nose, the vertical position of the nose, the vertical position of the mouth, the horizontal width of the mouth, the horizontal width of the jaw, the jaw sagging, the lips, the downward movement of the eyebrows, the upward movement of the eyebrows, and the downward movement of the corners of the mouth. The first value may refer to the average value of the numerical results of the analysis elements of the first section, the second section, and the third section. The second section and the third section may refer to sections different from the first section.

[0043] In one embodiment, the processor (120) may display a lecture screen in a first area on a display (not shown) and display content based on the lecture screen content in a second area separate from the first area. The processor (120) may separately store the content in memory (130) based on the learner's input regarding the content, and when the lecture ends, may provide at least one piece of content separately stored in memory to the learner. The processor (120) may provide the learner with at least one of the instructor's supplementary materials regarding the at least one piece of content, learning content related to the at least one piece of content, explanatory materials, difficulty of the problem, or the number of other learners who have separately stored the content, and may detect that a certain percentage or more of learners among multiple learners listening to the same instructor's lecture within a specific area are inputting regarding the specific content, and may transmit a signal to the instructor indicating that the learners do not understand the specific content well. The processor (120) can learn at least one of the subject, unit name, difficulty level, or the number of learners who clicked to save the content separately, for at least one piece of content separately stored in memory (130) using an artificial intelligence learning model. Based on at least one piece of content separately stored in memory (130), the processor (120) can provide information to the instructor regarding the learners' weak units or problems, and based on at least one piece of content separately stored in memory (130), provide personalized feedback and lecture recommendations regarding the weak units or problems to individual learners.

[0044] In one embodiment, the content based on the lecture screen content displayed in the second area may include any one of the textbook content being conducted by the instructor, the problem content being solved by the instructor, or lecture materials arbitrarily set by the instructor. The textbook content, the problem content, and the instructor's lecture materials may be stored on the memory (130) and then loaded by the processor (120). The processor (120) may save and provide the content shown by the instructor as an image file.

[0045] In one embodiment, the processor (120) provides search information related to a specific keyword in a second area on the display based on the input of a specific keyword by a learner, transmits a signal to the instructor indicating that the learners' understanding of the specific keyword is insufficient based on the number of learners who have entered the specific keyword exceeding a certain level, recognizes the instructor's voice during the lecture, and stores the number of times the specific keyword is pronounced in the instructor's voice on the memory (130). When the number of times the specific keyword is pronounced in the instructor's voice exceeds a specified level, the processor (120) proceeds with learning using the artificial intelligence learning model for the specific keyword entered by the learner, learns at least one of the textbook content, basic problems, or questions from other learners related to the specific keyword, and when the specific keyword learned in the instructor's voice is detected during the lecture, provides at least one of the textbook content, basic problems, or questions from other learners related to the specific keyword to the learner.

[0046] In one embodiment, the processor (120) determines the learner's score based on the number of times the learner participates in the lecture, the learner's access time to the lecture, the number of questions asked, the number of times pages are moved, the number of times the lecture index is clicked, or the number of times other programs are run, and provides a reward that enables viewing other lectures or one-on-one Q&A with the instructor based on the learner's score exceeding a specified level.

[0047] In one embodiment, the processor (120) may display on the display a first area showing a video or video lecture, a second area providing subtitles and additional text explaining the video or video lecture in real time, and a third area where learning activities can be shared between the instructor and the learner or between the learners. The processor (120) may provide an interface that prevents at least one of the first area, the second area, and the third area from being exposed, and an interface that can adjust the ratio of the first area, the second area, and the third area, display a lecture management page based on the reception of lecture information and lecture opening request information, and provide one or more recommendation information among related lectures, apps, books, materials, experts, and products along with an e-commerce link based on the learner's question or input.

[0049] FIG. 3 is a flowchart illustrating an image processing-based instructor training manual automatic update and instructor competency test method according to one embodiment.

[0050] The operations described through FIG. 3 may be implemented based on instructions that can be stored in a computer recording medium or memory (e.g., memory (130) of FIG. 1). The illustrated method may be executed by an electronic device (e.g., electronic device (101) of FIG. 1) described above through FIG. 1, and the technical features described above will be omitted below. The order of each operation in FIG. 3 may be changed, some operations may be omitted, and some operations may be performed simultaneously.

[0051] In operation 310, the processor (e.g., the processor (120) of FIG. 1) may store a learning manual in memory and provide a guide for a corresponding element of the learning manual based on user input. The learning manual may include at least one of chalk color combinations, chalk usage angles, writing size, eye contact time between the instructor and the learner, eye contact frequency, topics for counseling with the learner, counseling time, counseling frequency, methods for registering and managing the instructor's lectures online, methods for managing learners during semesters or vacation seasons, methods for managing lecture folders, management methods based on the learner's gender, management methods based on the learner's age, topics for counseling the learner's parents, methods for responding to parents, subjects, the instructor's voice tone, voice volume, the instructor's class speed, or the instructor's speaking speed.

[0052] In operation 320, the processor (120) learns the instructor's lecture video using an artificial intelligence learning model and can quantify the evaluation of the instructor's lecture for each component of the learning manual.

[0053] In operation 330, the processor (120) can evaluate the instructor's lecture based on the evaluation score for the instructor and store it in memory (130).

[0054] In operation 340, the processor (120) can create a database indicating the level of a lecturer's lecture based on a lecture evaluation record for at least one lecturer and update the database whenever a new lecture video is learned using an artificial intelligence learning model.

[0055] In operation 350, the processor (120) can calculate evaluation scores for multiple instructors for each component of the learning manual stored in memory (130) and determine an average value for the evaluation scores.

[0056] In operation 360, the processor (120) assigns a relative evaluation grade to the instructor based on the average value and can store the grade information together in the database.

[0057] In operation 370, the processor (120) can display the grade information on a display (not shown) based on user input on the database.

[0058] In one embodiment, the processor (120) may determine at least one element related to visual data in a learning manual, including at least one of the following: chalk color combination, chalk usage angle, writing size, eye contact time between the instructor and the learner, eye contact frequency, counseling topic with the learner, counseling time, counseling frequency, a method for registering and managing the instructor's lecture online, a method for managing learners by semester or vacation season, a method for managing lecture folders, a management method based on the learner's gender, a management method based on the learner's age, a counseling topic for the learner's parents, a method for responding to parents, a subject, the instructor's voice tone, voice volume, the instructor's class speed, or the instructor's speech speed. The processor (120) may analyze visual data related to the instructor's appearance in the instructor's lecture video and quantify the evaluation of the instructor for each of the at least one element related to visual data in the learning manual. The processor (120) calculates evaluation scores for multiple instructors, determines an average value for the evaluation scores, assigns a relative evaluation grade to the instructors based on the average value, and can provide lecture videos of instructors whose relative evaluation grade exceeds the specified level to instructors whose relative evaluation grade is below the specified level.

[0059] In one embodiment, the processor (120) may determine at least one element related to auditory data in a learning manual, including at least one of the following: a chalk color combination, a chalk usage angle, a writing size, eye contact time between the instructor and the learner, eye contact frequency, a topic of consultation with the learner, consultation time, consultation frequency, a method for registering and managing the instructor's lecture online, a method for managing learners by semester or vacation season, a method for managing lecture folders, a management method based on the learner's gender, a management method based on the learner's age, a topic of consultation with the learner's parents, a method for responding to parents, a subject, the instructor's voice tone, voice volume, the instructor's class speed, or the instructor's speech speed. The processor (120) may analyze auditory data related to the instructor's voice in the instructor's lecture video, quantify the evaluation of the instructor for each of the at least one element related to auditory data in the learning manual, calculate evaluation scores for multiple instructors, and determine an average value for the evaluation scores. The processor (120) assigns a relative evaluation grade to the instructor based on an average value, provides a lecture video of an instructor whose relative evaluation grade exceeds the designated level to an instructor whose relative evaluation grade is below the designated level, grants a specific qualification to an instructor whose evaluation grade exceeds the designated level, and can display information indicating that the specific qualification has been acquired in the database.

[0060] In one embodiment, the processor (120) quantifies the evaluation of the instructor's lecture by component on the learning manual, and quantifies the evaluation of the instructor's lecture by component on the learning manual including at least one of the following: chalk color combination, chalk usage angle, writing size, eye contact time between the instructor and the learner, eye contact frequency, counseling topic with the learner, counseling time, counseling frequency, method of registering and managing the instructor's lecture online, method of managing learners by semester or vacation season, method of managing lecture folders, management method based on the learner's gender, management method based on the learner's age, counseling topic with the learner's parents, method of responding to parents, subject, instructor's voice tone, voice volume, instructor's class speed, or instructor's speech speed, classifies components where the instructor's evaluation score is below a specified level, and for components where the evaluation score is below a specified level, provides lecture videos of other instructors whose relative evaluation grade exceeds the specified level, and can determine the instructor's competence, strengths, weaknesses, and performance based on the number of components where the evaluation score is below a specified level.

[0061] In one embodiment, the processor (120) can quantify the evaluation of the instructor's lecture by component of the learning manual using the instructor's lecture video at a first time point and store it on the memory (130), and can quantify the evaluation of the instructor's lecture by component of the learning manual using the instructor's lecture video at a second time point after the first time point and store it on the memory (130). The processor (120) can determine a first element among the components of the learning manual that has a value below the level specified at the first time point but has a value exceeding the level specified at the second time point, determine a second element among the components of the learning manual that has a value below the level specified at the first time point but remains below the level specified at the second time point, and determine a third element among the components of the learning manual that has a value exceeding the level specified at the first time point but has dropped to a value below the level specified at the second time point.

[0062] In one embodiment, the processor (120) may display information indicating that the level of the first element has been improved, provide an interface to describe a research method for the first element, display information indicating that improvement is needed for the second element, provide a lecture video of another instructor having a relatively high value for the second element, display information indicating that the level of the third element has been lowered, and provide a lecture video of the instructor at the first point in time and a lecture video of another instructor having a relatively high value for the third element.

[0064] FIG. 4 is a diagram illustrating the configuration of an artificial intelligence model according to one embodiment.

[0065] An artificial intelligence model according to one embodiment may include an input layer, a hidden layer, and an output layer.

[0066] The input layer is the layer associated with the input values ​​fed into the artificial intelligence model.

[0067] In the hidden layer, a feature map can be output by performing MAC (multiply-accumulate) and activation operations on the input values.

[0068] A MAC operation can be an operation that multiplies each input value by its corresponding weight and sums the multiplied values.

[0069] The activation operation may be an operation that inputs the result of the MAC operation into an activation function and outputs a result value. The activation function may be of various types. For example, the activation function may include a sigmoid function, a tangent function, a ReLU function, a Leaky ReLU function, a Max Out function, and / or an ELU function, but there are no restrictions on the types.

[0070] A hidden layer may consist of at least one layer. For example, if the hidden layer consists of a first hidden layer and a second hidden layer, the first hidden layer performs MAC operations and activation operations based on input values ​​of an input system to output a feature map, and the feature map, which is the result value of the first hidden layer, may become the input value of the second hidden layer. The second hidden layer may perform MAC operations and activation operations based on the feature map, which is the result value of the first hidden layer.

[0071] The output layer may be a layer associated with the result of an operation performed in the hidden layer.

[0072] In one embodiment, the learning model learns syllable (character) patterns that are frequently combined and used in a given corpus to automatically learn the boundaries of compound words and named entities, integrates object information from a first UI source with object information rendered in a browser to create a learning object information file, uses the learning object information file to create learning data for the learning of a deep learning network, receives data from various domains of a support system, standardizes the data from the various domains into an integrated format based on at least one standardization method corresponding to each of the various domains, learns and infers data from a specific domain, determines information to be transmitted for standardization from the data of the specific domain, and can perform post-processing on the data from the various domains. The first UI source includes an XML file, and the learning object information file includes an input JSON file for feature learning and an output JSON file which is the correct answer (label) data during learning, and the output JSON file includes a file containing HTML DOM Tree information implemented in compliance with web standards, and the various domains include at least one of a RAN (radio access network), a transport, or a core, and the post-processing may include a correlation function.

[0074] FIG. 5 shows a neural network of an artificial intelligence learning model for evaluating lecture videos according to one embodiment.

[0075] According to FIG. 5, the neural network (510) of the artificial intelligence learning model (500) may include a Convolutional Neural Network (CNN) model. The Convolutional Neural Network (CNN) model may be composed of layers that perform multiple convolution operations.

[0076] According to one embodiment, a neural network (510) may receive a lecture video (502) and lecture information (504) as inputs and output a lecture evaluation (520) while passing through internal layers. The lecture video (502) may refer to video or audio material recording a lecture by an instructor. The lecture information (504) may include at least one of chalk color combinations, chalk usage angles, writing size, eye contact time between the instructor and the learner, eye contact frequency, counseling topics with the learner, counseling time, counseling frequency, a method for registering and managing the instructor's lecture online, a method for managing learners by semester or vacation season, a method for managing lecture folders, a management method based on the learner's gender, a management method based on the learner's age, counseling topics for the learner's parents, a method for responding to parents, a subject, the instructor's voice tone, voice volume, the instructor's class speed, or the instructor's speaking speed. The lecture information (504) may include at least one of the concentration level of learners participating in the lecture, the length of the lecture, the subject matter of the lecture, the purpose of the lecture, and the difficulty level of the lecture.

[0077] In one embodiment, the artificial intelligence learning model (500) can evaluate and quantify the instructor's lecture based on at least one of the following information: the number of learners regarding lecture information (504) and lecture content, the learners' evaluation scores, the number of learners' reviews, the completion rate of the lecture content, or the ratio of learners who have completed learning the entire course of the lecture content.

[0078] In one embodiment, the lecture video (502) and lecture information (504) can be output in the form of a new feature map through operations with a filter determined for each convolution layer. The final feature map generated through operations repeated for each layer can be input to a fully-connected layer. An electronic device (e.g., the electronic device (101) of FIG. 1) can display information indicating a lecture evaluation (520) on a display. As illustrated in FIG. 4 and FIG. 5, the artificial intelligence learning model (500) of the present invention is composed of a CNN model including an input layer, a hidden layer, and an output layer. The input layer receives a lecture video (502) and lecture information (504). Here, in the lecture video (502), visual elements such as chalk color combinations, chalk usage angles, writing size, and eye contact time between the instructor and the learner are processed as input data, and in the lecture information (504), voice-related elements such as the instructor's voice tone, voice volume, and the instructor's class speed are processed. In the hidden layer, a multiply-accumulate (MAC) operation and an activation operation are performed on the input data to output a feature map. The sigmoid function, tangent function, ReLU function, etc., may be used as activation functions. In the output layer, based on the operation results of the hidden layer, the evaluation score for each component of the learning manual is quantified and It outputs the results. These evaluation results are stored in a database and can be used as a standard to judge the instructor's lecture level.

[0080] FIG. 6 is a flowchart illustrating a method for subdividing lecture content and providing a purchasing platform service for subdivided lecture content according to one embodiment.

[0081] The operations described through FIG. 6 may be implemented based on instructions that can be stored in a computer recording medium or memory (e.g., memory (130) of FIG. 1). The illustrated method may be executed by an electronic device (e.g., electronic device (101) of FIG. 1) described above through FIG. 1, and the technical features described above will be omitted below. The order of each operation in FIG. 6 may be changed, some operations may be omitted, and some operations may be performed simultaneously.

[0082] In operation 610, a processor (e.g., processor (120) of FIG. 1) may subdivide the lecture content based on at least one of the number of feedback requests from learners for a specific section of the lecture, the level of concentration of learners for a specific section of the lecture, the number of repeated playbacks of a specific section of the lecture, the age of learners, or changes in lecture materials. The level of concentration of learners for a specific section of the lecture may be determined based on at least one of the following cases: determining the learner's face area using a camera, distinguishing the head and eyes based on feature points in the learner's face area, determining the user's gaze direction based on the movement of the learner's eyes, determining the head rotation angle based on the movement of the learner's head, and determining the size of the head rotation angle exceeding a certain level, the frequency of head rotation exceeding a certain level, or the learner's gaze direction pointing in a different direction from the gaze direction of other learners around the learner exceeding a specified level.

[0083] In operation 620, the processor (120) can quantify the popularity level of the lecture content and the instructor based on at least one of the number of learners for the lecture content, the learners' evaluation scores, the number of learners' reviews, the completion rate of the lecture content, or the percentage of learners who have completed learning the entire course of the lecture content.

[0084] In operation 630, the processor (120) can set the price of the lecture content relatively high compared to when the numerical popularity level of the instructor is below a specified level, based on the numerical popularity level of the instructor exceeding a certain level.

[0085] In operation 640, the processor (120) may provide the learner with information regarding at least one of the number of buyers of the lecture content, the rating score of the buyers, the number of reviews of the buyers, the completion rate of the lecture content, or the percentage of learners who have completed learning the entire course of the lecture content.

[0086] In operation 650, the processor (120) can provide an interface that allows bidding on the price of the instructor's segmented lecture content.

[0087] In operation 660, the processor (120) stores user input for the interface in the memory and can determine the price of the lecture content based on the bid price listed in the user input.

[0088] In one embodiment, the processor (120) provides search information related to a specific keyword in a second area on the display based on the input of a specific keyword by the learner, and after the lecture ends, provides at least one of the textbook content, basic problems, question history of other learners, or detailed lecture content related to the specific keyword to the learner, inputs a lecture video to be evaluated and lecture information corresponding to the lecture video into an artificial intelligence learning model, and can derive lecture evaluation information. The lecture information may include at least one of the concentration level of learners participating in the lecture, the length of the lecture time, the purpose of the lecture subject, and the difficulty level of the lecture. The artificial intelligence learning model can evaluate and quantify the instructor's lecture based on at least one of the number of learners regarding the lecture information and lecture content, the learner's evaluation score, the number of reviews by the learner, the attendance rate of the lecture content, or the ratio of learners who have completed the entire course of the lecture content.

[0089] In one embodiment, the processor (120) receives information about the remaining lecture time or remaining amount from an external device, provides the right to take the subdivided lecture content based on the request of the external device, deducts the remaining lecture time of the external device by the amount of the subdivided lecture content, deducts the amount of the subdivided lecture content determined through bidding or the amount bid on the subdivided lecture content from the remaining amount, and can display information about the remaining lecture time or remaining amount.

[0090] In one embodiment, the processor (120) displays an interface that can increase the remaining lecture time or increase the remaining amount, and can control the external device to increase the remaining lecture time or increase the remaining amount based on user input and payment method authentication.

[0091] In one embodiment, the processor (120) determines the score of the learner based on the number of times the learner participates in the lecture, the time the learner accesses the lecture, the number of questions, the number of page navigations, the number of lecture index clicks, the number of quiz responses, the quiz accuracy rate, the number of evaluations by other learners regarding the learner's questions, or the number of times other programs are run, and may provide points that have the authority to bid on the price of the subdivided lecture content based on the learner's score exceeding a specified level.

[0093] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0094] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0095] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0096] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0097] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 An electronic device comprises: a memory for storing instructions; and a processor, wherein, when the instructions are executed by the processor, the electronic device quantifies an evaluation of the instructor's lecture by component of a learning manual using an instructor's lecture video at a first time point and stores it in the memory; quantifies an evaluation of the instructor's lecture by component of a learning manual using an instructor's lecture video at a second time point after the first time point and stores it in the memory; determines a face region of a learner taking the lecture using a camera; distinguishes the head and eyes based on feature points in the learner's face region; determines the direction of gaze based on the learner's eye movement; determines the head rotation angle based on the learner's head movement; determines the learner's level of concentration based on at least one of the cases where the magnitude of the head rotation angle exceeds a certain level or the frequency of head rotation exceeds a certain level; stores in the memory at least one first segment in which a signal indicating that the learners' level of concentration has decreased during the instructor's lecture is transmitted; and regarding the lecture, the learner's Determining the score of the said learner based on the number of participations, the learner's access time to the lecture, the number of questions, the number of page navigations, the number of lecture index clicks, the number of quiz responses, and the quiz correct answer rate; transmitting a signal to the said instructor indicating that the learners' concentration has decreased based on the fact that the concentration of a certain percentage of learners among multiple learners listening to the same instructor's lecture within a specific area has fallen below a designated level; providing search information related to a specific keyword in a second area on the display based on the learner's input of a specific keyword; and transmitting a signal to the instructor indicating that the learners' understanding of the specific keyword is insufficient based on the fact that the number of learners who have entered the specific keyword exceeds a certain level.Determining a first element among the components of the above learning manual that has a value below the level specified at the first time point but exceeds the level specified at the second time point; determining a second element among the components of the above learning manual that has a value below the level specified at the first time point but remains below the specified level at the second time point; determining a third element among the components of the above learning manual that has a value exceeding the level specified at the first time point but has dropped to below the level specified at the second time point; displaying information indicating that the level of the first element has improved and providing an interface to describe a research method for the first element; displaying information indicating that improvement is needed for the second element and providing a lecture video of another instructor having a relatively high value for the second element; displaying information indicating that the level of the third element has decreased and controlling to provide the lecture video of the instructor at the first time point and a lecture video of another instructor having a relatively high value for the third element; and the components of the above learning manual include at least one of voice volume, the instructor's class speed, whiteboard size, or chalk color combination An electronic device including one. Claim 2 delete Claim 3 delete

Images