KR102651463B1 - Method, device and system for creating customized online lecture contents and providing educational curriculum based on artificial intelligence - Google Patents

Abstract

According to one embodiment, the device receives user information including a target test from the user's user terminal, provides evaluation questions evaluating the target test to the user terminal, and obtains skill evaluation results for the evaluation questions, Obtain learning history information from the user terminal, generate a learning intention map by extracting at least one of the number of lectures taken, accumulated lecture attendance time, and lecture cycle from the learning history information, and create a quiz related to the lecture taken from the learning history information. Extract the correct answer rate, create a learning level using the correct answer rate of the quiz and the results of the skill evaluation, obtain the test taking history of the target test from user information, and based on the learning intention, learning level, and test taking history, the first An educational curriculum can be selected through an artificial neural network, and a guidance message about the selected educational curriculum can be sent to the user terminal.

Description

Method, device and system for producing customized online lecture content and providing educational curriculum based on artificial intelligence

The examples below relate to technology that produces customized online lecture content and provides an educational curriculum based on artificial intelligence.

As the Internet develops, the number of people learning by taking online lectures rather than visiting academies in person is increasing. As the number of people taking these online lectures increases, the number of online instructors, online lecture content, and sites where online lectures can be viewed is also increasing, making it difficult for users to select an educational curriculum that suits their learning level.

Therefore, there is a need for the development of technology that uses artificial intelligence to create customized online lecture content and provide an educational curriculum.

Republic of Korea Patent No. 10-1805163 (announced on December 6, 2017) Republic of Korea Patent No. 10-2336900 (announced on December 8, 2021) Republic of Korea Patent No. 10-2266310 (announced on June 17, 2021) Republic of Korea Patent No. 10-2269837 (announced on June 28, 2021)

Embodiments seek to produce online lecture content tailored to students and provide an educational curriculum based on artificial intelligence.

Embodiments extract the user's learning ability using an artificial neural network, create customized difficulty levels and customized numbers of basic lecture content included in the education curriculum according to the user's learning ability, and modify the lecture content to improve the user's learning ability. We aim to provide a user-tailored educational curriculum according to the province.

Embodiments receive a passing education curriculum, utilization plan information for the passing education curriculum, and passing handwriting information from a successful candidate, provide the information to a user that matches the selected education curriculum, and provide a reward to the successful candidate depending on whether the user passes. We want to encourage people to voluntarily share information about the passing education curriculum.

According to one embodiment, a method performed by an apparatus includes receiving user information including a target test from a user terminal of a user; providing an evaluation question for evaluating the target test to the user terminal; Obtaining a skill evaluation result for the evaluation problem; Obtaining learning history information from the user terminal; generating a learning intention map by extracting at least one of the number of lectures taken, cumulative lecture attendance time, and lecture period from the learning history information; Extracting the correct answer rate of a quiz related to the lecture taken from the learning history information, and generating a learning level using the correct answer rate of the quiz and the result of the skill evaluation; Obtaining a history of taking the target test from the user information; selecting an educational curriculum through a first artificial neural network based on the learning intention map, the learning level, and the examination history; And it may include transmitting a guidance message about the selected education curriculum to the user terminal.

The step of selecting an educational curriculum through the first artificial neural network includes combining a first value corresponding to the learning intention map, a second value corresponding to the learning level, and a third value corresponding to the examination history to the first artificial neural network. It may include inputting into a neural network, extracting the learning ability of the user using the first artificial neural network, and selecting the education curriculum based on the learning ability.

The method performed by the device further includes the step of modifying lecture content included in the selected education curriculum, wherein the step of modifying the lecture content includes modifying the selected education curriculum according to the selection of the education curriculum. Extracting the difficulty level of basic lecture content included by default, applying a first weight to the difficulty level of the basic lecture content based on the learning ability to create a user-customized difficulty level, extracting the number of basic lecture contents generating the number of user-customized lecture contents by applying a second weight determined based on the user-customized difficulty level to the number of basic lecture contents; applying the generated customized difficulty level and the number of customized lecture contents to calculate the number of lecture contents; A step of modifying content, calculating a wrong answer rate for each unit from the results of the skill evaluation, comparing the wrong answer rate with a preset first standard and a second standard, a first step where the wrong answer rate is lower than the first standard If it corresponds to a unit, reducing the number of lecture content related to the first unit and adding in-depth lecture content for the first unit, a second step in which the incorrect answer rate is higher than the first standard and lower than the second standard If it corresponds to a unit, maintaining the number of lecture contents related to the second unit, and if it corresponds to a third unit where the incorrect answer rate is higher than the second standard, the number of lecture contents related to the third unit It may include the step of increasing and adding supplementary lecture content for the third unit.

The method performed by the device includes receiving the passing education curriculum used by the successful candidate from the successful candidate's terminal; Receiving utilization plan information and passing handwriting information for the passing education curriculum from the successful candidate terminal; If the selected education curriculum corresponds to the passing education curriculum, transmitting the utilization plan information and passing handwriting information to a user terminal provided with the selected education curriculum; Confirming whether the user who has received the selected education curriculum passes the exam; And it may further include paying a reward to the successful candidate terminal based on whether the successful candidate has passed the test.

The method performed by the device further includes the step of selecting an instructor who will teach the lecture content of the educational curriculum, and the step of selecting the instructor includes receiving information about the instructor from the instructor's instructor terminal, Based on the instructor's information, acquiring target information of the instructor including target age information and target gender information of the instructor, based on the instructor's lecture content information, the number of lecture contents, and the lecture content Obtaining the instructor's content interest information, including the average number of lectures taken, the average number of shares of the lecture content, and the average number of comments on the lecture content, the instructor's target information, the content interest information, and the lecture content information generating a second input signal using a second input signal, applying the second input signal to a second artificial neural network to generate a second output signal, and responding to the lecture content and the instructor based on the second output signal. generating matching information, checking the history of lectures of units included in the lecture content among the instructors and applying a weight proportional to the number of lectures to the matching information, and matching information to which the weights are applied. It may include the step of selecting an instructor who will teach the lecture content using .

The method performed by the apparatus includes calculating the number of views per section from lecture content of the educational curriculum; Comparing the number of views with a preset first reference number and a second reference number; extracting a section in which the number of views is less than the first reference number and determining to display it in a first color; extracting a section in which the number of views is greater than the first standard number but less than the second standard number and determining to display it in a second color; and extracting a section in which the number of views is greater than or equal to the second reference number and determining to display it in a third color.

The method performed by the apparatus further includes generating feedback of the educational curriculum based on a review of the educational curriculum, wherein the step of generating the feedback includes extracting text information of a review of the educational curriculum, Extracting keywords, setting keywords that are mentioned more than a preset standard number of times as main keywords, classifying the main keywords as positive keywords or negative keywords, and the proportion of the positive keywords among the keywords. calculating a positive rate, calculating a negative rate, which is the proportion of the negative keyword among the keywords, comparing the negative rate with a first and second preset reference values, and the negative rate is the first reference value. If lower than the standard value, generating feedback recommending maintenance of the composition of the educational curriculum; if the negative rate is higher than the first standard value and lower than the second standard value, the negative keywords are extracted in the order in which the most negative keywords are extracted; Sorting keywords, generating improvements in the educational curriculum based on the sorted negative keywords, and generating feedback on the negative keywords and the improvement points, and if the negative rate is higher than the second reference value, It may include generating feedback recommending changes in the composition of the educational curriculum.

The device according to one embodiment may be combined with hardware and controlled by a computer program stored in a medium to execute any one of the above-described methods.

Embodiments may produce online lecture content customized to students and provide an educational curriculum based on artificial intelligence.

Embodiments extract the user's learning ability using an artificial neural network, create customized difficulty levels and customized numbers of basic lecture content included in the education curriculum according to the user's learning ability, and modify the lecture content to improve the user's learning ability. It is possible to provide a user-tailored educational curriculum according to the province.

Embodiments receive a passing education curriculum, utilization plan information for the passing education curriculum, and passing handwriting information from a successful candidate, provide the information to a user that matches the selected education curriculum, and provide a reward to the successful candidate depending on whether the user passes. They can be encouraged to voluntarily share information about the passing education curriculum.

1 is a diagram for explaining the configuration of a system according to an embodiment.
Figure 2 is a flow chart to explain the process of creating customized online lecture content and providing an education curriculum based on artificial intelligence according to an embodiment.
Figure 3 is a flow chart to explain the process of selecting an educational curriculum through a first artificial neural network according to an embodiment.
Figure 4 is a diagram for explaining a first artificial neural network according to an embodiment.
Figure 5 is a flow chart to explain the process of modifying lecture content by creating customized difficulty level and customized number according to one embodiment.
Figure 6 is a flowchart illustrating a process for modifying lecture content according to the results of a skill evaluation according to an embodiment.
Figure 7 is a flow chart to explain the process of paying rewards to successful applicants' terminals according to one embodiment.
Figure 8 is a flow chart to explain the process of selecting an instructor to teach lecture content according to an embodiment.
Figure 9 is a flowchart for explaining a process of displaying colors according to the number of views per section of lecture content according to an embodiment.
Figure 10 is a flowchart for explaining the process of generating feedback of an educational curriculum according to an embodiment.
Figure 11 is an exemplary diagram of the configuration of a device according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the attached drawings. However, various changes can be made to the embodiments, so the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents, or substitutes for the embodiments are included in the scope of rights.

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 form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

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

When a component is referred to as being “connected” to another component, it should be understood that it may be directly connected or connected to the other component, but that other components may exist in between.

The terms used in the examples are for descriptive purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the embodiments belong. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

In addition, when describing with reference to the accompanying drawings, identical components will be assigned the same reference numerals regardless of the reference numerals, and duplicate descriptions thereof will be omitted. In describing the embodiments, if it is determined that detailed descriptions of related known technologies may unnecessarily obscure the gist of the embodiments, the detailed descriptions are omitted.

Embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

An artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, it is a system in which machines learn and make decisions on their own. As artificial intelligence systems are used, their recognition rates improve and they can more accurately understand user preferences, and existing rule-based smart systems are gradually being replaced by deep learning-based artificial intelligence systems.

Artificial intelligence technology consists of machine learning and element technologies using machine learning. Machine learning is an algorithmic technology that classifies/learns the characteristics of input data on its own, and elemental technology is a technology that mimics the functions of the human brain such as cognition and judgment by utilizing machine learning algorithms such as deep learning, including linguistic understanding and visual It consists of technical areas such as understanding, reasoning/prediction, knowledge expression, and motion control.

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology that recognizes and applies/processes human language/characters and includes natural language processing, machine translation, conversation systems, question and answer, and voice recognition/synthesis. Visual understanding is a technology that recognizes and processes objects like human vision, and includes object recognition, object tracking, image search, person recognition, scene understanding, spatial understanding, and image improvement. Inferential prediction is a technology that judges information to make logical inferences and predictions, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendations. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge construction (data creation/classification) and knowledge management (data utilization). Motion control is a technology that controls the autonomous driving of vehicles and the movement of robots, and includes motion control (navigation, collision, driving), operation control (behavior control), etc.

Generally, in order to apply machine learning algorithms to real life, learning is performed using a trial and error method due to the nature of the basic methodology of machine learning. In particular, deep learning requires hundreds of thousands of repeated executions. It is impossible to execute this in an actual physical external environment, so instead, the actual physical external environment is virtually implemented on a computer and learning is performed through simulation.

1 is a diagram for explaining the configuration of a system according to an embodiment.

First, a communication network can be configured regardless of the communication mode, such as wired or wireless, and can be implemented in various forms to enable communication between servers and between servers and terminals.

The user terminal 10 may be a terminal used by a user who takes online lecture content or is provided with an educational curriculum according to the present invention. The user terminal 10 may be a desktop computer, laptop, tablet, smartphone, etc. For example, as shown in FIG. 1, the user terminal 10 may be a smartphone and may be employed differently depending on the embodiment.

The user terminal 10 may be configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a typical computer. The user terminal 10 may be configured to communicate with the device 30 wired or wirelessly.

The user terminal 10 is connected to a web page operated by a person or organization providing services using the device 30, or an application developed and distributed by a person or organization providing services using the device 30. Can be installed. The user terminal 10 may be linked to the device 30 through a web page or application.

The user terminal 10 can access the device 30 through a web page or application provided by the device 30.

The successful candidate terminal 20 is a terminal of a successful candidate who has passed the test targeted by the user according to the present invention. The successful candidate terminal 20 may be a desktop computer, laptop, tablet, smartphone, etc. For example, as shown in FIG. 1, the successful candidate terminal 20 may be a smartphone and may be employed differently depending on the embodiment.

The successful candidate terminal 20 may be configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a typical computer. The successful candidate terminal 20 may be configured to communicate with the device 30 in a wired or wireless manner.

The successful candidate terminal 20 is connected to a web page operated by a person or organization providing services using the device 30, or an application developed and distributed by a person or organization providing services using the device 30. Can be installed. The successful candidate terminal 20 may be linked with the device 30 through a web page or application.

The singular expressions recited in the claims may be understood to include the plural. For example, the user in a claim may refer to one user or two or more users. For example, a successful candidate in a claim may refer to one successful candidate or two or more successful candidates.

The device 30 may be its own server owned by a person or organization that provides services using the device 30, a cloud server, or a p2p (peer-to-peer) collection of distributed nodes. It may be possible. The device 30 may be configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a typical computer.

The device 30 may be configured to communicate wired or wirelessly with the user terminal 10 and the successful candidate terminal 20, controls the operations of the user terminal 10 and the successful candidate terminal 20, and communicates with the user terminal 10 and the successful candidate terminal 20. It is possible to control which information is displayed on the screen of the terminal 20.

The device 30 may provide an educational curriculum for users, such as lecture content, through a web page or application.

Meanwhile, for convenience of explanation, only the user terminal 10 and the successful candidate terminal 20 are shown in FIG. 1, but the number of terminals may vary depending on the embodiment. As long as the processing capacity of the device 30 allows, the number of terminals is not particularly limited.

According to one embodiment, a database may be provided within the device 30, but the present invention is not limited to this, and the database may be configured separately from the device 30. Device 30 may include multiple artificial neural networks for performing machine learning algorithms.

Meanwhile, for convenience of explanation, only the user terminal 10 and the successful candidate terminal 20 are shown in FIG. 1, but the number of terminals may vary depending on the embodiment. As long as the processing capacity of the device 30 allows, the number of terminals is not particularly limited.

Figure 2 is a flow chart to explain the process of creating customized online lecture content and providing an education curriculum based on artificial intelligence according to an embodiment.

Referring to FIG. 2, first, in step S201, the device 30 may receive user information including a target test from the user's user terminal 10.

Here, the user information may include, but is not limited to, the user's name, gender, contact information, name of the target exam, subject, date, test take history, etc.

In step S202, the device 30 may provide the user terminal 10 with an evaluation question to evaluate the target test. Before providing the user with an education curriculum for the target exam, the device 30 may extract evaluation questions for testing prior knowledge of the target exam from the database and provide them to the user terminal 10. The database of the device 30 stores evaluation questions for testing prior knowledge about the target test, divided by test and unit, and the device 30 can extract the evaluation questions for the target test from the database. . The device 30 may provide evaluation questions for evaluating a target test to the user terminal 10 and control the evaluation questions to be displayed on the screen of the user terminal 10 .

In step S203, the device 30 may obtain a skill evaluation result for the evaluation problem.

The device 30 may receive an answer to the evaluation question from the user terminal 10. At this time, when the answer to the last question in the evaluation questions is input from the user terminal 10, the device 30 can receive answers to the evaluation questions all at once.

The device 30 can perform scoring of the evaluation questions by checking whether the answer to each evaluation question is correct or incorrect. To this end, the correct answer to the evaluation question can be stored in the database of the device 30, and the device 30 obtains the correct answer to the evaluation question, compares the obtained correct answer with the answer received from the user terminal 10, and , you can obtain the skill evaluation results for the evaluation problems by grading the evaluation problems.

In step S204, the device 30 may obtain learning history information from the user terminal 10. At this time, the learning history information may include, but is not limited to, the number of lectures the user has taken, accumulated lecture attendance time, course attendance cycle, and the correct answer rate of quizzes related to the lectures taken.

In step S205, the device 30 may generate a learning intention map from learning history information.

Specifically, the device 30 extracts at least one of the number of lectures taken, the accumulated lecture time, and the lecture period from the learning history information, and at least one of the extracted number of lectures taken, the accumulated lecture time, and the lecture period. You can create a learning intention map using .

According to one embodiment, the device 30 generates a higher learning intention as the number of lectures taken, the longer the cumulative lecture time, or the shorter the lecture cycle, and the smaller the number of lectures taken, the cumulative lecture time. The shorter this is or the longer the course attendance cycle, the lower the willingness to learn.

In step S206, the device 30 may generate a learning level from learning history information.

Specifically, the device 30 may extract the correct answer rate of a quiz related to a lecture taken from learning history information and generate a learning level using the correct answer rate of the extracted quiz and the result of the skill evaluation.

According to one embodiment, the device 30 generates a higher level of learning as the correct answer rate of the quiz related to the lecture taken is higher and the higher the correct answer rate of the skill evaluation result, and the lower the correct answer rate of the quiz related to the taken lecture is. , the lower the correct answer rate of the skill evaluation result, the lower the learning level can be generated.

In step S207, the device 30 may obtain test taking history from user information. Here, the test taking history may include information on whether the user has experience taking the target test, the number of times the user has taken the target test, the type of target test, and the date of application, etc. It is not limited to this.

In step S208, the device 30 may select an education curriculum through the first artificial neural network 100 based on the learning intention, learning level, and examination history. At this time, a detailed description of the process of selecting the educational curriculum will be described later with reference to FIGS. 3 and 4.

In step S209, the device 30 may transmit a guidance message about the selected education curriculum to the user terminal 10.

Figure 3 is a flowchart for explaining the process of selecting an educational curriculum through the first artificial neural network 100 according to an embodiment.

Referring to FIG. 3, first, in step S301, the device 30 inputs a first value corresponding to the learning intention map, a second value corresponding to the learning level, and a third value corresponding to the gaze history into the first artificial neural network 100. ) can be entered.

Here, the first input signal may include a first value corresponding to the learning intention, a second value corresponding to the learning level, and a third value corresponding to the gaze history. The input layer 110 of the first artificial neural network 100 may include input nodes respectively applied to the first value, second value, and third value.

In step S302, the device 30 may extract the user's learning ability using the first artificial neural network 100.

The output layer 120 of the first artificial neural network 100 may include an output node that generates an output value.

In step S303, the device 30 may select an education curriculum based on learning ability.

For example, the device 30 registers the education curriculum in the database by level, such as beginner, intermediate, and advanced, and when the learning ability is set to be output as an integer value between 0 and 10, the device 30 performs learning. If the learning ability is in the range of 0 to 3, a beginner's education curriculum is selected. If the learning ability is in the range of 4 to 7, an intermediate education curriculum is selected. If the learning ability is in the range of 8 to 10, the intermediate education curriculum is selected. In this case, you can select an advanced educational curriculum.

The device 30 generates the user's learning intention and learning level from the learning history information, obtains the gaze history from the user information, and applies the learning intent, learning level, and gaze history to the first artificial neural network 100. The user's learning ability can be extracted. The device 30 may select an education curriculum according to the user's learning ability based on the learning ability obtained using the first artificial neural network 100.

FIG. 4 is a diagram for explaining the first artificial neural network 100 according to an embodiment.

The device 30 may extract the user's learning ability using the first artificial neural network 100 and select an educational curriculum based on the extracted learning ability.

The device 30 may apply the first value corresponding to the learning intention map, the second value corresponding to the learning level, and the third value corresponding to the gaze history to the input node of the first artificial neural network 100. The input layer 110 of the first artificial neural network 100 may include input nodes respectively applied to the first value, second value, and third value.

The device 30 may generate a first output signal by applying the first input signal to the first artificial neural network 100. The output layer 120 of the first artificial neural network 100 may include an output node that generates an output value.

The device 30 may output the user's learning ability using the first artificial neural network 100. The device 30 may select an educational curriculum based on the user's learning ability.

Figure 5 is a flow chart to explain the process of modifying lecture content by creating customized difficulty level and customized number according to one embodiment.

Referring to FIG. 5 , first, in step S501, the device 30 may extract the level of difficulty of basic lecture content included in the selected education curriculum according to the selection of the education curriculum.

The database of the device 30 may store basic lecture content and the level of difficulty of the basic lecture content according to the selected educational curriculum in advance. When an education curriculum is selected, the device 30 may extract the level of difficulty of basic lecture content included in the selected education curriculum from the database.

In step S502, the device 30 may generate a user-customized difficulty level by applying a first weight to the difficulty of the basic lecture content based on the learning ability.

The device 30 generates a first weight based on the user's learning ability obtained through the first artificial neural network 100, and applies the generated first weight to the difficulty level of the basic lecture content to generate a user-customized difficulty level. can do.

For example, the device 30 may generate a higher first weight as the learning ability is higher, and may generate a lower first weight as the learning ability is lower.

In step S503, the device 30 may extract the number of basic lecture contents. The database of the device 30 may store in advance the basic lecture content and the number of basic lecture contents according to the selected educational curriculum.

Specifically, the device 30 may extract the number of basic lecture contents included in the selected education curriculum according to the selection of the education curriculum. When an education curriculum is selected, the device 30 may extract the number of basic lecture contents included in the selected education curriculum from the database.

In step S504, the device 30 may generate the number of user-customized lecture contents by applying the second weight determined based on the user-customized difficulty level to the number of basic lecture contents.

At this time, the second weight may be generated higher as the user-customized difficulty level increases, and may be generated lower as the user-customized difficulty level becomes lower.

In step S505, the device 30 may modify the lecture content by applying the generated customized difficulty level and customized number.

The device 30 generates a first weight based on the learning ability obtained using the first artificial neural network 100, and uses the generated first weight as basic lecture content included in the education curriculum selected by the user. By applying the difficulty level of , the difficulty level of user-customized lecture content can be created by adjusting the difficulty level of the basic content according to the user's learning ability.

The device 30 generates a second weight based on the customized difficulty level, and applies the generated second weight to the number of lecture contents included in the educational curriculum selected by the user to determine the level of lecture content according to the user's customized difficulty level. You can create the number of customized lecture contents by adjusting the number.

Figure 6 is a flowchart illustrating a process for modifying lecture content according to the results of a skill evaluation according to an embodiment.

Referring to FIG. 6, first, in step S601, the device 30 can calculate the percentage of incorrect answers for each unit from the results of the skill evaluation.

The device 30 can perform scoring of the evaluation questions by checking whether the answer to each evaluation question is correct or incorrect. To this end, the correct answer to the evaluation question can be stored in the database of the device 30, and the device 30 obtains the correct answer to the evaluation question, compares the obtained correct answer with the answer received from the user terminal 10, and , you can obtain the skill evaluation results for the evaluation problems by grading the evaluation problems.

The database of the device 30 stores evaluation questions for testing prior knowledge about the target test, divided by test and unit, and the device 30 can extract the evaluation questions for the target test from the database. .

The device 30 can separate and store the results of the skill evaluation for each unit, and calculate the percentage of incorrect answers for each unit from the results of the skill evaluation.

In step S602, the device 30 may compare the incorrect answer rate with a preset first standard. Here, the first standard may be set differently depending on the embodiment.

In step S603, if the error rate corresponds to the first unit that is lower than the first standard, the device 30 may reduce the number of lecture contents related to the first unit and add in-depth lecture content for the first unit. The database of the device 30 may separately store basic lecture content and advanced lecture content for each unit.

In step S604, the device 30 may compare the incorrect answer rate with a preset second standard. Here, the second standard may be set differently depending on the embodiment.

In step S605, the device 30 may maintain the number of lecture contents related to the second unit when the incorrect answer rate is higher than the first standard and lower than the second standard.

In step S606, if the third unit has a rate of incorrect answers higher than the second standard, the device 30 may increase the number of lecture contents related to the third unit and add supplementary lecture content for the third unit.

The database of the device 30 may store basic lecture content, advanced lecture content, and supplementary lecture content for each unit separately, and if the incorrect answer rate of the unit is higher than the second standard, the device 30 Supplementary lecture content can be extracted from the database.

The device 30 calculates the incorrect answer rate for each unit from the results of the skill evaluation, adjusts the number of lecture contents according to the incorrect answer ratio, and additionally configures in-depth lecture content or supplementary lecture content to teach the educational curriculum according to the user's unit-specific skills. Content can be organized.

Figure 7 is a flowchart for explaining the process of paying rewards to the successful candidate terminal 20 according to one embodiment.

Referring to FIG. 7, first, in step S701, the device 30 may receive the passing education curriculum used by the successful candidate from the successful candidate terminal 20.

In step S702, the device 30 may receive utilization plan information and passing handwriting information for the passing education curriculum from the successful candidate terminal 20. Here, the utilization plan information and passing testimonial information are related to the educational curriculum, such as the time the lecture content was taken, study method, study time, title of the lecture content taken, the instructor who conducted the lecture content taken, the type of exam targeted, and the course taken. It may include, but is not limited to, information about the number of lecture contents, subjects of lecture content taken, etc.

In step S703, if the selected education curriculum corresponds to the passing education curriculum, the device 30 may transmit utilization plan information and passing handwriting information to the user terminal 10 that has been provided with the selected education curriculum.

The device 30 may store the utilization plan information and the passing handwriting information for the passing education curriculum received from the successful applicant terminal 20 in a database, and compare the selected education curriculum and the user's passing curriculum to determine whether the selected education curriculum is If it corresponds to a passing education curriculum, utilization plan information and passing handwriting information can be extracted from the database and transmitted to the user terminal 10 that has been provided with the selected education curriculum.

In step S704, the device 30 can check whether the user who has received the selected education curriculum has passed. At this time, the device 30 can confirm whether the user has passed by receiving the result from the user terminal 10, but the process of determining whether the user has passed is not limited to this.

In step S705, the device 30 may pay a reward to the successful applicant's terminal 20 based on whether or not the applicant passed.

For example, the device 30 may provide a reward to the terminal 20 of the successful user when the user provided with the selected education curriculum passes the target test.

For example, the device 30 may provide a reward to the terminal 20 of the successful user when the user provided with the selected education curriculum passes the target test.

In general, applicants who have passed a specific exam do not voluntarily upload the passing education curriculum, information on plans to use the passing education curriculum, and information on passing notes.

Accordingly, utilization plan information and passing handwriting information for the passing education curriculum are received from the successful candidate terminal 20, and if the education curriculum selected by the user corresponds to the passing education curriculum, the utilization plan information and passing handwriting information are received from the selected user. By transmitting the education curriculum to the user terminal 10 provided, checking whether the user provided with the selected education curriculum has passed, and paying a reward to the successful candidate terminal 20 based on whether the user passed, the successful person voluntarily passes. It has the effect of encouraging the sharing of information on plans to use the educational curriculum and information on passing testimonials.

Figure 8 is a flow chart to explain the process of selecting an instructor to teach lecture content according to an embodiment.

Referring to FIG. 8, first, in step S801, the device 30 may obtain the instructor's target information including the instructor's target age information and target gender information based on the instructor's information.

At this time, the device 30 can receive the instructor's information from the instructor's instructor terminal. Here, the instructor's information may include, but is not limited to, the instructor's name, age, contact information, course content, age information of the person taking the course content, and gender information of the person taking the course content.

Specifically, the device 30 can obtain information on the age of those who took the lecture content based on the instructor's information, and analyze the age information to determine whether the instructor's target age group is teenagers, 20s, or 30s. You can determine whether someone is in their 40s or 50s, and obtain information on the instructor's target age based on the results.

The device 30 can acquire gender information of those who have taken the lecture content based on the instructor's information, analyze the gender information, and determine whether the instructor's target gender is female or male, and based on the determination result, You can obtain the instructor's target gender information.

In step S802, the device 30 may obtain the instructor's content interest information based on the instructor's lecture content information. Here, the content interest information may include the number of lecture contents, the average number of lectures taken, the average number of shares of lecture contents, and the average number of comments on lecture contents.

In step S803, the device 30 may generate a second input signal using the instructor's target information, content interest information, and lecture content information.

Specifically, the device 30 may perform a process of preprocessing the instructor's target information, the instructor's content interest information, and lecture content information. The preprocessed instructor's target information, instructor's content interest information, and lecture content information can be used as input to the second artificial neural network 200, or the input can be generated through normal processing to remove unnecessary information.

In step S804, the device 30 may apply the second input signal to the second artificial neural network 200 to generate a second output signal.

Here, the device 30 acquires training target information, training content interest information, training lecture content information, second output signals, and training matching information, and pre-trains the second artificial neural network 200 based on this. You can do it. The device 30 may generate a second output signal by applying the second input signal to the pre-trained second artificial neural network 200. At this time, the training matching information may be matching information respectively corresponding to training target information, training content interest information, and training lecture content information. The first output signals may be output signals generated by applying second training input signals generated based on training target information, training content interest information, and training lecture content information to the second artificial neural network 200.

According to one embodiment, the device 30 may obtain training outputs by applying training target information, training content interest information, and training lecture content information to the second artificial neural network 200. The device 30 may learn the second artificial neural network 200 based on the training outputs, second output signals, and training matching information. The device 30 may generate a second output signal by applying the second input signal to the pre-trained second artificial neural network 200.

The device 30 may learn the second artificial neural network 200 based on the training outputs, second output signals, and training matching information. The device 30 can learn the second artificial neural network 200 by calculating training errors corresponding to the training outputs and optimizing the connection relationship of the nodes in the second artificial neural network 200 to minimize the training errors. there is. The device 30 may extract matching information from target information, content interest information, and lecture content information using the second artificial neural network 200 on which learning has been completed.

In step S805, the device 30 may generate matching information corresponding to lecture content and instructor based on the second output signal. Here, the matching information is the degree of matching between the instructor and lecture content and may be a real number between 0 and 1.

In step S806, the device 30 may check the instructor's history of teaching the lecture content included in the unit and apply a weight proportional to the number of lectures to the matching information.

According to one embodiment, the device 30 checks the number of times lectures of the lecture content included in the unit have been taught, generates a weight proportional to the number of lectures of the lecture content included in the unit, and applies it to the matching information. can do.

In step S807, the device 30 may select an instructor who will teach the lecture content using weighted matching information.

The device 30 may apply the weight generated to the matching information obtained using the second artificial neural network 200 to update the matching information and store it in the database. The device 30 may select an instructor with a high value of the weighted matching information as the instructor to teach the lecture content.

Figure 9 is a flowchart for explaining a process of displaying colors according to the number of views per section of lecture content according to an embodiment.

Referring to FIG. 9, first, in step S901, the device 30 may calculate the number of views per section from the lecture content of the educational curriculum.

For example, if the lecture content is 10 minutes and the section is 1 minute, the device 30 can be used for 0 minutes to 2 minutes, 2 minutes to 4 minutes, 4 minutes to 6 minutes, 6 minutes to 8 minutes, and 8 minutes of the lecture content. By classifying sections of ~10 minutes, the number of views per classified section can be calculated.

In step S902, the device 30 may compare the number of views with a first preset reference number. At this time, the first reference number of times may be set differently depending on the embodiment.

In step S903, the device 30 may determine to extract a section in which the number of views is less than the first standard number and display it in the first color.

For example, if the section of the lecture content in which the number of views is less than the first standard number is 2 minutes to 4 minutes, the device 30 may decide to display the lecture content belonging to the section of 2 minutes to 4 minutes in the first color. there is.

In step S904, if the number of views is greater than or equal to the first standard number, the device 30 may compare the number of views with a preset second standard number. At this time, the second reference number of times may be set differently depending on the embodiment.

In step S905, the device 30 may determine to extract a section in which the number of views is less than the second standard number and display it in a second color.

That is, the device 30 may determine to extract a section in which the number of views is greater than the first standard number but less than the second standard number and display it in the second color.

For example, if the section of the lecture content in which the number of views is greater than the first standard number but less than the second standard number is 6 minutes to 8 minutes, the device 30 selects the lecture content belonging to the section of 6 minutes to 8 minutes as the second standard number. You can decide to display it in color.

In step S906, the device 30 may determine to extract a section in which the number of views is greater than or equal to the second standard number and display it in a third color.

For example, if the section of the lecture content in which the number of views is less than the second standard is 8 minutes to 10 minutes, the device 30 may decide to display the lecture content belonging to the section of 8 minutes to 10 minutes in a third color. there is.

The device 30 classifies the sections of the lecture content, calculates the number of views per section, and displays the color of the section differently depending on the number of views, so that when the user reaches a section with a relatively high number of views while watching the lecture content, the corresponding section You can display different colors to focus more on sections with high views.

Figure 10 is a flowchart for explaining the process of generating feedback of an educational curriculum according to an embodiment.

Referring to FIG. 10, device 30 may generate feedback about the educational curriculum based on a review of the educational curriculum.

First, in step S1001, the device 30 may extract text information of a review of the educational curriculum and extract keywords. At this time, reviews of the educational curriculum are written by users who have experience in receiving the educational curriculum, and the number, length, images included in the review, text included in the review, and video included in the review are registered in relation to the educational curriculum. It may include the like, and may be stored in the database of the device 30.

In step S1002, the device 30 may set keywords mentioned more than a preset standard number of extracted keywords as main keywords. At this time, the reference number of times may be set differently depending on the embodiment.

In step S1003, the device 30 may classify the main keyword as a positive keyword or a negative keyword.

In step S1004, the device 30 can calculate the positive rate and negative rate. At this time, the positive ratio may refer to the ratio of positive keywords among keywords, and the negative ratio may refer to the ratio of negative keywords among keywords.

In step S1005, the device 30 may compare the fraud rate with a preset first reference value. At this time, the first reference value may be set differently depending on the embodiment.

If the denial rate is lower than the first reference value in step S1006, the device 30 may generate feedback recommending maintenance of the structure of the educational curriculum.

In step S1007, the device 30 may compare the fraud rate with a preset second reference value. At this time, the second reference value may be set differently depending on the embodiment.

If the denial rate is higher than the first reference value and lower than the second reference value in step S1008, the device 30 sorts the negative keywords in the order in which the most negative keywords were extracted, and generates improvements in the education curriculum based on the sorted negative keywords. Thus, feedback on negative keywords and improvements can be generated.

According to one embodiment, the device 30 may sort negative keywords in the order in which the most negative keywords are extracted, and create improvements in the educational curriculum based on the sorted negative keywords.

For example, if the negative keywords are 'poor image quality' and 'no picture', the device 30 sorts them in the order in which the most negative keywords are extracted, and based on the negative keywords, 'bad image quality' and 'no picture'. 'It is possible to create improvements in the educational curriculum.

In step S1009, the device 30 may generate feedback recommending a change in the composition of the educational curriculum when the denial rate is higher than the second reference value.

Figure 11 is an exemplary diagram of the configuration of the device 30 according to one embodiment.

Device 30 according to one embodiment includes a processor 31 and memory 32. The device 30 according to one embodiment may be the server or terminal described above. The processor 31 may include at least one device described above with reference to FIGS. 1 to 10 or may perform at least one method described with reference to FIGS. 1 to 10 . The memory 32 may store information related to the above-described method or store a program in which the above-described method is implemented. Memory 32 may be volatile memory or non-volatile memory.

The processor 31 can execute programs and control the device 30. The code of the program executed by the processor 31 may be stored in the memory 32. The device 30 is connected to an external device (eg, a personal computer or a network) through an input/output device (not shown) and can exchange data.

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

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., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be 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 media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced 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 operations of the embodiments, and vice versa.

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

Although the embodiments have been described with limited drawings as described above, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the following claims.

Claims (3)

In a method performed by a device,
Receiving user information including a target test from the user's user terminal;
providing an evaluation question for evaluating the target test to the user terminal;
Obtaining a skill evaluation result for the evaluation problem;
Obtaining learning history information from the user terminal;
generating a learning intention map by extracting at least one of the number of lectures taken, cumulative lecture attendance time, and lecture period from the learning history information;
Extracting the correct answer rate of a quiz related to the lecture taken from the learning history information, and generating a learning level using the correct answer rate of the quiz and the result of the skill evaluation;
Obtaining a history of taking the target exam from the user information;
selecting an educational curriculum through a first artificial neural network based on the learning intention map, the learning level, and the examination history; and
Comprising the step of transmitting a guidance message about the selected educational curriculum to the user terminal,
The step of selecting an educational curriculum through the first artificial neural network is,
Inputting a first value corresponding to the learning intention map, a second value corresponding to the learning level, and a third value corresponding to the gaze history into the first artificial neural network,
Extracting the user's learning ability using the first artificial neural network,
Comprising the step of selecting the educational curriculum based on the learning ability,
Further comprising: modifying lecture content included in the selected educational curriculum,
The step of modifying the lecture content is,
Extracting the difficulty level of basic lecture content included in the selected education curriculum according to the selection of the education curriculum,
Applying a first weight to the difficulty of the basic lecture content based on the learning ability to create a user-customized difficulty level;
Extracting the number of basic lecture contents,
Generating the number of user-customized lecture contents by applying a second weight determined based on the user-customized difficulty level to the number of basic lecture contents;
Modifying the lecture content by applying the generated customized difficulty level and the number of customized lecture contents;
Calculating the percentage of incorrect answers for each unit from the results of the skill evaluation,
Comparing the incorrect response rate with a preset first standard and a second standard,
Reducing the number of lecture content related to the first unit, which is the unit corresponding to the incorrect answer rate lower than the first standard, and adding in-depth lecture content for the first unit,
maintaining the number of lecture contents related to the second unit corresponding to an incorrect response rate that is higher than the first criterion and lower than the second criterion, and
Including the step of increasing the number of lecture contents related to the third unit corresponding to a rate of incorrect answers higher than the second standard and adding supplementary lecture content for the third unit,
Receiving the passing education curriculum used by the successful applicant from the successful applicant's terminal;
Receiving utilization plan information and passing handwriting information for the passing education curriculum from the successful candidate terminal;
If the selected education curriculum corresponds to the passing education curriculum, transmitting the utilization plan information and passing handwriting information to a user terminal provided with the selected education curriculum;
Confirming whether the user who has received the selected education curriculum passes the exam; and
It further includes; paying a reward to the successful candidate terminal based on whether the successful candidate passed the test,
Further comprising the step of selecting an instructor who will teach the lecture content of the educational curriculum,
The steps for selecting the instructor are:
Receiving instructor information from the instructor's instructor terminal,
Based on the instructor's information, acquiring target information of the instructor including target age information and target gender information of the instructor,
Based on the instructor's lecture content information, obtain the instructor's content interest information, including the number of lecture contents, the average number of lectures of the lecture content, the average number of shares of the lecture content, and the average number of comments on the lecture content. steps to do,
Generating a second input signal using the instructor's target information, the content interest information, and the lecture content information,
Applying the second input signal to a second artificial neural network to generate a second output signal,
generating matching information corresponding to the lecture content and the instructor based on the second output signal;
Checking the history of lectures of lecture content included in the unit among the instructors and applying a weight proportional to the number of lectures to the matching information, and
A step of selecting an instructor who will teach the lecture content using the weighted matching information,
calculating the number of views per section from the lecture content of the educational curriculum;
Comparing the number of views with a preset first reference number and a second reference number;
extracting a section in which the number of views is less than the first reference number and determining to display it in a first color;
extracting a section in which the number of views is greater than the first standard number but less than the second standard number and determining to display it in a second color; and
Further comprising the step of extracting a section in which the number of views is greater than or equal to the second reference number and determining to display it in a third color,
Further comprising generating feedback of the educational curriculum based on the review of the educational curriculum,
The step of generating the feedback is,
Extracting text information of the review of the educational curriculum and extracting keywords,
Setting keywords mentioned more than a preset standard number of times from the extracted keywords as main keywords;
Classifying the main keywords as positive keywords or negative keywords,
Calculating a positive rate, which is the proportion of the positive keywords among the keywords,
Calculating a negative ratio, which is the proportion of the negative keywords among the keywords,
Comparing the denial rate with a preset first and second reference values,
If the denial rate is lower than the first threshold, generating feedback recommending maintenance of the structure of the educational curriculum;
If the negative rate is higher than the first reference value and lower than the second reference value, the negative keywords are sorted in the order in which the negative keywords are extracted most, and improvements in the educational curriculum are generated based on the sorted negative keywords. , generating feedback on the negative keyword and the improvement point, and
If the denial rate is higher than the second threshold, generating feedback recommending a change in the composition of the educational curriculum.
Method for creating customized online lecture content and providing educational curriculum based on artificial intelligence. delete delete