KR102550839B1 - Electronic apparatus for utilizing avatar matched to user's problem-solving ability, and learning management method - Google Patents

Abstract

A learning management method of an electronic device is disclosed. The learning management method includes identifying a user's problem-solving ability based on the user's answers to a plurality of problems, generating at least one artificial intelligence model matching the identified problem-solving ability, and the artificial intelligence model. The method includes inputting at least one problem to, obtaining an answer of an artificial intelligence model for the input problem, and providing evaluation information on the answer of the obtained artificial intelligence model.

Description

Electronic device using an avatar that matches the user's problem-solving ability, and learning management method

The present disclosure relates to an electronic device that provides a learning management method, and more particularly, to an electronic device that manages a user's learning by allowing an avatar based on an artificial intelligence model to solve test questions.

The size of the domestic private education market is increasing every year, and the growth of the edutech market, including artificial intelligence models, at home and abroad is particularly noteworthy.

In relation to edtech, conventional artificial intelligence model technology mainly focuses on conversation with students (communication), information provision, and performance analysis (analysis of academic ability), while minimizing the learning time of users (students), etc. There were deficiencies in terms of process management.

Registered Patent Publication No. 10-21916720000 (Customized learning method and system based on learning analysis and artificial intelligence)

The present disclosure provides an electronic device and a learning management method for managing learning of a user through an avatar based on an artificial intelligence model capable of solving problems on behalf of a user (student) or competitively with the user.

The objects of the present disclosure are not limited to the above-mentioned objects, and other objects and advantages of the present disclosure not mentioned above can be understood by the following description and will be more clearly understood by the embodiments of the present disclosure. Further, it will be readily apparent that the objects and advantages of the present disclosure may be realized by means of the instrumentalities and combinations indicated in the claims.

A learning management method of an electronic device according to an embodiment of the present disclosure includes identifying a user's problem-solving ability based on the user's answers to a plurality of problems, and at least one problem-solving ability matching the identified problem-solving ability. Generating an artificial intelligence model of, inputting at least one problem into the artificial intelligence model, obtaining an answer of the artificial intelligence model for the problem, evaluation information on the obtained answer of the artificial intelligence model It includes the step of providing.

The step of identifying the user's problem-solving ability may include the user's problem-solving ability for each type, based on the level of difficulty of each of the plurality of problems provided for each type and whether or not the user's answer to each of the plurality of problems is correct. can identify.

In this case, the generating of the artificial intelligence model may include generating at least one neural network model that outputs an answer that matches the user's problem-solving ability for each type.

In the generating of the artificial intelligence model, at least one neural network model may be updated based on the plurality of problems and the user's answer to each of the plurality of problems.

Meanwhile, the learning management method of the electronic device includes inputting a plurality of problems selected according to the user's input into the artificial intelligence model, obtaining a plurality of answers of the artificial intelligence model, and selecting an incorrect answer from among the plurality of answers. The method may further include providing the user with at least one problem matching the corresponding at least one answer.

In addition, the learning management method of the electronic device may include providing the user with a plurality of problems included in a learning process set according to the user's problem-solving ability, based on the plurality of problems included in the set learning process training the artificial intelligence model; obtaining the user's first answer to the evaluation problem by providing at least one evaluation problem related to the learning process when the learning period according to the set learning process expires; Acquiring a second answer of the trained artificial intelligence model for the evaluation problem, providing first evaluation information for the first answer and second evaluation information for the second answer .

In this case, in the step of training the artificial intelligence model, if the answer of the artificial intelligence model to at least one problem included in the learning process is an incorrect answer, the artificial intelligence model based on the problem and the correct answer to the problem The model can be trained.

Here, the learning management method of the electronic device may further include changing and setting at least one of a learning amount, a learning period, and a learning level of difficulty of the learning process based on the user's input. In this case, the providing of the plurality of problems may include providing a plurality of problems included in the changed learning process to the user, and the step of training the artificial intelligence model may include providing the user with a plurality of problems included in the changed learning process. AI models can be trained.

And, the learning management method of the electronic device compares and analyzes the first evaluation information and the second evaluation information to set a learning amount, a learning period, and a learning difficulty of at least one additional learning process after the learning process. The method may further include providing the user with a plurality of problems included in the additional learning process, and training the artificial intelligence model based on the plurality of problems included in the additional learning process.

In this case, the learning management method of the electronic device may include, when the first score according to the first evaluation information is lower than the second score according to the second evaluation information by a threshold value or more, the first additional learning with a smaller learning amount than the learning process. A plurality of problems included in the process are provided to the user, the artificial intelligence model is trained based on the plurality of problems included in the first additional learning process, and a first score according to the first evaluation information is obtained from the first evaluation information. 2 When the score is higher than the second score according to the evaluation information by a threshold value or higher, a plurality of problems included in the second additional learning process having a larger learning amount than the learning process are provided to the user, and a plurality of problems included in the second additional learning process are provided. The artificial intelligence model can also be trained based on problems.

The learning management method of an electronic device according to the present disclosure has the advantage of helping the user efficiently configure the learning time by replacing at least a part of the user's problem-solving process with an artificial intelligence model.

In addition, the learning management method of an electronic device according to the present disclosure has an effect of motivating a user and managing a learning schedule customized for the user based on competitive learning between the user and the artificial intelligence model.

1 is a block diagram for explaining the configuration of an electronic device according to an embodiment of the present disclosure;
2 is a flowchart for explaining a learning management method of an electronic device according to an embodiment of the present disclosure;
3 is a diagram for explaining the operation of an electronic device and a user terminal for guiding avatar creation according to an embodiment of the present disclosure;
4 is a diagram for explaining the operation of an electronic device and a user terminal that provides a user interface (UI) related to problem solving of an avatar (artificial intelligence model) according to an embodiment of the present disclosure;
5A and 5B are diagrams for explaining operations of an electronic device and a user terminal that provide answers and evaluation information of an artificial intelligence model according to an embodiment of the present disclosure;
6 is a block diagram for explaining an operation in which an electronic device manages a user's learning through competitive problem-solving training of an artificial intelligence model according to an embodiment of the present disclosure; and
7 is a block diagram for explaining the configuration of an electronic device according to various embodiments of the present disclosure.

Prior to a detailed description of the present disclosure, the method of describing the present specification and drawings will be described.

First, terms used in the present specification and claims are general terms in consideration of functions in various embodiments of the present disclosure. However, these terms may vary depending on the intention of a technician working in the art, legal or technical interpretation, and the emergence of new technologies. In addition, some terms are arbitrarily selected by the applicant. These terms may be interpreted as the meanings defined in this specification, and if there is no specific term definition, they may be interpreted based on the overall content of this specification and common technical knowledge in the art.

In addition, the same reference numerals or numerals in each drawing attached to this specification indicate parts or components that perform substantially the same function. For convenience of description and understanding, the same reference numerals or symbols are used in different embodiments. That is, even if all components having the same reference numerals are shown in a plurality of drawings, the plurality of drawings do not mean one embodiment.

Also, in the present specification and claims, terms including ordinal numbers such as “first” and “second” may be used to distinguish between elements. These ordinal numbers are used to distinguish the same or similar components from each other, and the meaning of the term should not be construed as being limited due to the use of these ordinal numbers. For example, the order of use or arrangement of elements associated with such ordinal numbers should not be limited by the number. If necessary, each ordinal number may be used interchangeably.

In this specification, singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "comprise" or "consist of" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other It should be understood that the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof is not precluded.

In the embodiments of the present disclosure, terms such as “module,” “unit,” and “part” are terms used to refer to components that perform at least one function or operation, and these components are hardware or software. It may be implemented or implemented as a combination of hardware and software. In addition, a plurality of "modules", "units", "parts", etc. are integrated into at least one module or chip, except for cases where each of them needs to be implemented with separate specific hardware, so that at least one processor can be implemented as

Also, in an embodiment of the present disclosure, when a part is said to be connected to another part, this includes not only a direct connection but also an indirect connection through another medium. In addition, the meaning that a certain part includes a certain component means that it may further include other components without excluding other components unless otherwise stated.

1 is a block diagram for explaining the configuration of an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 1 , an electronic device 100 may include a memory 110 and a processor 120 .

The electronic device 100 may correspond to a server device capable of communicating with various user terminals. In this case, the electronic device 100 may interwork with various user terminals through at least one web page or application, and may provide a learning management method according to various embodiments to be described later through the user terminal.

Alternatively, the electronic device 100 may correspond to various terminal devices such as a smart phone, a notebook PC, a desktop PC, a tablet PC, a wearable device, a TV, a set-top box, and a console device.

The memory 110 is a component for storing an operating system (OS) for controlling overall operations of elements in the electronic device 100, at least one instruction, and data.

The memory 110 may include non-volatile memory such as ROM and flash memory, and may include volatile memory such as DRAM. Also, the memory 110 may include a hard disk, a solid state drive (SSD), and the like.

Memory 110 may include one or more problems per category and/or type.

Categories are classified according to subjects and may include math, English, Korean (language), science, social studies, and the like.

*Categories can be divided according to the type of test even in the same subject. For example, even within English, English can be classified into elementary English, middle school English, English for college entrance exams, and English related to English tests certified by various leading companies/organizations.

The type may correspond to the nature or intention of each problem. Specifically, in the case of language or English problems, understanding the purpose of the text, understanding the mood/mind/tone, grasping the connotation, grasping the gist/argument, identifying the subject, identifying the content match/discord, grasping the appropriateness of vocabulary, grasping the accuracy of grammar, and inference of designation , it can correspond to various types such as flow identification, sequence identification, summary, and reading comprehension.

Memory 110 may contain one or more problems from various sources. The source refers to the entity that produces/provides the problem, and may correspond to various education-related companies, education-related institutions, test administration/management institutions, etc., but is not limited thereto.

The memory 110 may also include information about difficulty for each problem. Here, the level of difficulty may be set to a value preset by the problem maker, or may be set based on a correct answer ratio of a certain number or more of students who have solved the corresponding problem.

Difficulty may be matched with problem-solving ability for each stage. Here, the problem-solving ability means the ability or level of problem-solving, and can be understood as an index for evaluating the problem-solving level of at least one user (student) or an artificial intelligence model to be described later.

That is, in embodiments to be described later, it may be assumed that the problem solving ability of the user (student) or the artificial intelligence model is higher as the difficulty level of the problem that can be solved by the user (student) or the artificial intelligence model is higher. In addition, it may be assumed that the problem-solving ability of the user or the artificial intelligence model is high as the percentage of correct answers (of the user or artificial intelligence model) is higher for a plurality of problems of the same difficulty level.

Meanwhile, the memory 110 may include at least one artificial intelligence model for problem solving.

This artificial intelligence model may correspond to a network model (neural network model) based on a neural network. The network model may include a plurality of network nodes having weights. A plurality of network nodes may form a connection relationship based on weights between nodes of different layers.

Neural network models include Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN), GAN ( Generative Adversarial Network) and deep Q-Networks, etc., but are not limited thereto.

For example, when at least one problem (for solution) is input, at least one artificial intelligence model outputting an answer to the problem may be stored in the memory 110 .

Here, the question may correspond to a multiple-choice type (including an answer) or a subjective type, and the answer may be an answer for selecting at least one answer or a short-answer/explanatory answer.

As a specific example, it is assumed that multiple-choice questions including questions, fingerprints, and multiple answers (ex. Nos. 1 to 5) are input to the artificial intelligence model.

In this case, the artificial intelligence model may select at least one answer among a plurality of answers based on a text corresponding to a query, a fingerprint, and a plurality of answers.

To this end, the artificial intelligence model may include at least one layer (module) for natural language understanding, at least one layer (module) for selecting views, etc., but is not limited thereto.

Also, as a specific example, it is assumed that an open-ended question including a query or a question and a fingerprint is input.

In this case, the artificial intelligence model may output an answer (text) to the query based on text corresponding to the query and/or the fingerprint. To this end, the artificial intelligence model may include at least one layer for providing a response to a query.

At this time, the artificial intelligence model may extract at least one text (related to the query/fingerprint) from at least one answer database built to interwork with the artificial intelligence model, and construct an answer using the extracted text.

On the other hand, when the input problem is a hearing problem in the form of a voice, the electronic device 100 obtains text matching the voice of the hearing problem using a voice recognition module (ex. Automatic Speech Recognition), etc., and artificially converts the obtained text. It can also be input into an intelligence model.

The processor 120 is a component for overall controlling each component included in the electronic device 100, and various units such as a central processing unit (CPU), an application processor (AP), a graphic processing unit (GPU), a VPU, and an NPU. may consist of

The processor 120 may control the electronic device 100 by executing instructions stored in the memory 110 .

The operation of the processor 120 will be described through the following drawings.

2 is a flowchart illustrating a learning management method of an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 2 , the processor 120 may identify a user's problem-solving ability based on the user's answers to a plurality of problems (S210).

For example, the processor 120 of the electronic device 100 implemented as a server may communicate with the user terminal through a communication unit, and may control the user terminal to sequentially display a plurality of issues.

As a specific example, the electronic device 100 may identify the user when logging in is performed based on user information (eg, ID, password, etc.) received through the user terminal.

In addition, a plurality of problems may be provided through a user terminal according to a request of a user who has logged in.

Here, the user's request may be a request to receive a plurality of problems or a request to generate an avatar (artificial intelligence model) matching the user's problem-solving ability.

When a plurality of questions are provided, the processor 120 may obtain a user's answer for each question according to a user input received through a user terminal.

Here, the processor 120 may identify whether the user's answer is correct or incorrect, and may identify the user's problem-solving ability based on the correct answer ratio of the user's answer to each of a plurality of problems.

Specifically, the processor 120 may identify the user's problem-solving ability for each type based on the level of difficulty of each of the plurality of problems provided for each type and whether or not the user's answer to each of the plurality of problems is correct.

The problem-solving ability for each type may be classified into a plurality of steps (eg, steps 1 to 9), but is not limited thereto.

At this time, the processor 120 may set a time limit for each question (or for a plurality of questions), or may measure the time taken for each question to obtain the user's answer.

If the answer is correct, the processor 120 may identify the user's problem-solving ability as higher as the time taken from the time the problem is provided to the time the user's answer is obtained is smaller.

If the user's problem-solving ability is identified according to the above-described embodiment, the processor 120 may generate at least one artificial intelligence model that matches the identified problem-solving ability (S220).

Specifically, the processor 120 may generate at least one artificial intelligence model that outputs an answer that matches the user's problem-solving ability for each type.

Here, the processor 120 may train the neural network model based on problems of difficulty matching the user's problem-solving ability for each type.

As an example, it is assumed that the user's problem-solving ability for reading comprehension problems is level 3 and the user's problem-solving ability for designation inference problems is level 4.

In this case, the processor 120 may update the weights between nodes of the neural network model by using one or more reading comprehension problems matched to a level of difficulty of 3 or less and correct answers to the corresponding reading comprehension problems as inputs and outputs, respectively. In addition, the processor 120 may update the weight between nodes of the neural network model by taking as inputs and outputs one or more designation inference problems matching a level of difficulty of 4 or less and correct answers to the corresponding designation inference problems.

Also, the processor 120 may update at least one neural network model based on the plurality of problems previously provided to the user and the user's answers to the plurality of problems.

In this case, the updated neural network model (artificial intelligence model) is trained based on the user's answer whether the user's answer is correct or incorrect, so it may have problem solving ability that matches the user's problem solving ability.

As described above, when an artificial intelligence model that matches the user's problem-solving ability is generated, the processor 120 may obtain an answer by inputting at least one problem into the artificial intelligence model (S230).

At this time, the processor 120 may select at least one problem according to the user input and input the selected problem to the artificial intelligence model.

In this case, the processor 120 may provide evaluation information on the answer of the artificial intelligence model (S240).

Evaluation information corresponds to an indicator of the problem-solving ability of an artificial intelligence model.

The evaluation information may include information on whether or not the answer is correct. If the answer is incorrect, the evaluation information may include information about the correct answer (model answer).

The evaluation information may include the number of correct answers and the ratio of correct answers to a plurality of questions. The evaluation information may include information about total evaluation scores of answers to a plurality of questions.

Also, the evaluation information may include information about the number of correct answers or the ratio of correct answers for each type of problem. That is, the evaluation information may include an indicator of problem-solving ability for each type.

In the case of an answer to an open-ended problem, the evaluation information may include information about the score of the answer to the problem.

Specifically, in the case of an open-ended problem, the processor 120 may compare the text of an exemplary answer with the text of the answer to calculate an agreement rate, and calculate a score according to the calculated agreement rate. Alternatively, the processor 120 may identify at least one keyword included in the best answer and calculate a score depending on whether the identified keyword is included in the answer.

Also, the evaluation information may include information about the correct answer rate/score of at least one other user for the same problem, the correct answer rate/score of at least one other artificial intelligence model, and the like.

Through the following drawings, more specific operations of the above-described learning management method and related embodiments of the electronic device 100 will be described. Meanwhile, although FIGS. 3, 4, and 5A to 5B show only cases in which the electronic device 100 implemented as a server provides a learning management method through the user terminal 200, the electronic device 100 It goes without saying that it may be implemented as a user terminal (eg, a smart phone, a notebook PC, a desktop PC, etc.).

3 is a diagram for explaining operations of an electronic device and a user terminal for guiding avatar creation according to an embodiment of the present disclosure.

Referring to FIG. 3 , the electronic device 100 may provide a UI (User Interface) for generating at least one avatar that matches the user's problem-solving ability through the user terminal 200 .

An avatar is a medium for providing an artificial intelligence model service, may be defined as a virtual character or entity, and may have at least one name.

The electronic device 100 may generate an avatar (artificial intelligence model) for each category of problem. Referring to FIG. 3 , a user input for selecting a category in which an avatar (artificial intelligence model) will be created may be received through the UI 310 of the user terminal 200 .

In FIG. 3, the name of the avatar corresponds to “A.I Hong Gil-dong”, but it can be changed according to user input.

And, if at least one category is selected, the electronic device 100 may provide a plurality of problems matching the selected category through the user terminal 200 .

Specifically, referring to FIG. 3 , a plurality of problems may be displayed through the UI 320 of the user terminal 200, and each problem may be sequentially provided through a scroll 321.

The plurality of problems provided may include various types of problems. For example, the plurality of problems may include two problems for each of 18 types, but the number of types or problems is not limited thereto.

Here, the electronic device 100 may obtain the user's answer to each problem through a user input (eg, touch, keyboard input, mouse click, etc.) received through the user terminal 200 .

The UI 325 indicating the progress rate may indicate in real time the ratio of the number of questions for which the user's answer is obtained among a plurality of questions.

At this time, when a user input for selecting the UI 322 corresponding to completion is received, a process of obtaining user answers to a plurality of questions may be completed.

As such, the process of obtaining the user's answers to a plurality of problems corresponds to a precondition for generating an artificial intelligence model (avatar) that matches the user's problem-solving ability.

When the user's answers to the plurality of questions are obtained, the electronic device 100 may analyze the user's answers to identify the user's problem-solving ability.

Specifically, the electronic device 100 may determine the user's problem-solving ability for each type according to whether or not the answers to each type of problem are correct/ratio.

In addition, the electronic device 100 may generate at least one artificial intelligence model that matches the user's problem-solving ability for each type.

4 is a diagram for explaining the operation of an electronic device and a user terminal that provides a user interface (UI) related to problem solving of an avatar (artificial intelligence model) according to an embodiment of the present disclosure.

Referring to FIG. 4 , the electronic device 100 may control the user terminal 200 to provide UI items corresponding to 'AI problem solving 410' and 'self solving 420', respectively.

'AI problem solving 410' is an item for controlling the process of having an avatar (artificial intelligence model) solve a problem.

When the 'AI problem solving 410' item is selected, the electronic device 100 may obtain an answer of the artificial intelligence model by inputting at least one problem selected according to the user's input to the artificial intelligence model.

Referring to FIG. 4 , a problem to be solved by an artificial intelligence model may be selected according to a user input for each UI item 411 , 412 , and 413 .

Specifically, the UI item 411 is an item for selecting one or more problem categories, the UI item 412 is an item for selecting one or more problem sources, and the UI item 413 is an item for selecting other problems. It may correspond to an item for additionally setting filtering for various conditions (ex. period, difficulty, etc.).

As such, when the category and source of the problem are selected, the electronic device 100 may output a UI 415 for providing a plurality of selected problems through the user terminal 200 .

Referring to FIG. 4 , the UI 415 is designed to classify problems by source and solve the problems of each source (select “Solve”), but the configuration of the UI 415 does not need to be limited thereto.

Referring to FIG. 4 , a UI item 415' for receiving all selected problems may also be provided.

On the other hand, 'I solve 420' is an item for providing a plurality of problems so that the user can solve the problem himself.

When the item 'Solve by me (420)' is selected, the electronic device 100 may provide problems of various categories/sources, as shown in FIG. can be received.

Meanwhile, as the artificial intelligence model and/or the user's problem solving (410, 420) is performed as shown in FIG. 4, the electronic device 100 may provide evaluation information on the artificial intelligence model and/or the user's answer. .

In relation to this, FIGS. 5A and 5B are diagrams for explaining operations of an electronic device and a user terminal that provide answers and evaluation information of an artificial intelligence model according to an embodiment of the present disclosure.

Referring to FIG. 5A , the electronic device 100 displays 'view problems 510', 'AI report card 520', 'my solution 530', and 'my report card 540' through the user terminal 200. UI items such as can be provided.

'Problem view (510)' is an item to provide problems entered into the AI model, that is, solved by the AI model, and 'AI report card (520)' is an item to provide evaluation information on the answer of the AI model. , 'My solution (530)' is an item for providing the problem so that the user can solve the same problem as the problem solved by the artificial intelligence model, and 'my report card (540)' is the evaluation of the user's answer to the problem It is an item to provide information.

5A corresponds to a case where the 'view problem 510' item is selected according to the user's input.

Referring to FIG. 5A , the electronic device 100 may provide 'problems solved by AI 511' and 'view only incorrect answers 512' through the user terminal 200, respectively.

As shown in FIG. 5A, when the item 'problem 511 solved by AI' is selected, the electronic device 100 may provide a UI 511' including at least one problem solved by the artificial intelligence model.

The UI 511' may include a visual display (correct mark, wrong mark) for checking whether or not the answer of the artificial intelligence model for each problem is correct.

In addition, the UI 511' may include at least one UI item 511'-1 for providing a correct answer to a problem in which the artificial intelligence model is wrong.

If the item 'show only incorrect answers 512' is selected, the electronic device 100 may control the user terminal 200 to provide only the problems for which the artificial intelligence model answered incorrectly among the problems solved by the artificial intelligence model. can

In this way, by providing which problem the artificial intelligence model that matches the user's problem-solving ability failed, the electronic device 100 provides an incorrect answer problem based on a result similar to that of the user's own solution even if the user does not directly solve all of the plurality of problems. will be able to provide

In other words, since the user can solve only the problems for which the artificial intelligence model is wrong and receive the correct answer to the problem, there is no need to solve problems that the user would naturally know or problems that are too easy for the user. As a result, the user solves the problem himself The time required for this may be reduced.

The electronic device 100 may obtain an answer and evaluation information of at least one other artificial intelligence model for a problem solved by the artificial intelligence model.

Here, another artificial intelligence model may correspond to an artificial intelligence model (avatar) generated according to the problem-solving ability of another user.

As a specific example, the electronic device 100 may obtain an answer of another artificial intelligence model (avatar) by inputting a problem entered into the artificial intelligence model (avatar) of another user into the artificial intelligence model (avatar) of another user.

In addition, the electronic device 100 may provide evaluation information on an answer of an artificial intelligence model and evaluation information on an answer of another artificial intelligence model together.

In this regard, FIG. 5B corresponds to a case where the 'AI transcript 520' item is selected according to the user's input.

Referring to FIG. 5B , the electronic device 100 displays a user's avatar (artificial intelligence model) and other users' avatars (artificial intelligence models) by type (word, structure) through the UI 521 of the user terminal 200. , sentences, etc.) problem solving ability (evaluation information) can be provided respectively.

In this case, the problem-solving ability of the user and the problem-solving ability of other users can be indirectly compared, and evaluation information can be provided in a fun way according to the comparison method through the avatar.

Meanwhile, the electronic device 100 may provide an artificial intelligence model and competitive training of the user to motivate the user to learn and manage the user's learning schedule.

In this regard, FIG. 6 is a block diagram illustrating an operation of managing learning of a user through competitive problem-solving training of an artificial intelligence model by an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 6 , the electronic device 100 may provide the user with a plurality of problems included in a learning process set according to the user's problem-solving ability (S610).

The learning process may refer to a planned plan or schedule to learn a certain amount of educational material within a certain period of time.

The educational material may correspond to at least one problem, lecture video, textbook, and the like.

Specifically, the electronic device 100 may set a learning process corresponding to the amount of learning, the learning period, and the learning difficulty that match the user's problem-solving ability.

The amount of learning corresponds to the number of educational materials (ex. the number of problems to be solved), the learning period corresponds to the period (target period) given to learning educational materials, and the learning difficulty corresponds to the difficulty of educational materials (ex. average difficulty of the problem).

In this case, the electronic device 100 may set at least one of the learning amount and the learning period higher as the user's problem-solving ability increases. In addition, the electronic device 100 may increase the level of difficulty of provided educational materials as the user's problem-solving ability increases.

However, it goes without saying that the electronic device 100 may change and set at least one of a learning amount, a learning period, and a learning difficulty level of a learning process based on a user's input.

As such, when the learning process is set, the electronic device 100 may provide the user with a plurality of problems included in the learning process. At this time, the correct answer for each problem may be provided together according to the user's request.

In addition, the electronic device 100 may also perform training on the artificial intelligence model according to the above-described learning process set according to the user's problem-solving ability (S620).

If the learning process is changed and set according to the user's input, training of the artificial intelligence model may be performed with respect to the changed learning process.

Specifically, the electronic device 100 may train an artificial intelligence model based on a plurality of problems included in the learning process.

In this case, the electronic device 100 may obtain an answer of the artificial intelligence model for each question by inputting a plurality of questions to the artificial intelligence model.

Here, when the answer of the artificial intelligence model to at least one problem is incorrect, the electronic device 100 may train the artificial intelligence model based on the corresponding problem and the correct answer to the corresponding problem. In this case, the problem-solving ability of the artificial intelligence model can be improved.

In this way, after training of the user and the artificial intelligence model is performed, an evaluation problem may be given to each user and the artificial intelligence model.

As an example, when the learning period (eg, one week) according to the above-described learning process expires, the electronic device 100 provides the user with at least one evaluation problem related to the learning process, and provides the user with the first evaluation problem. An answer can be obtained (S630).

The evaluation problem is a problem for evaluating the learning achievement of the corresponding learning process, and may refer to a problem that is expected to be solved when the learning process is successfully completed.

In addition, the electronic device 100 may obtain a second answer of the artificial intelligence model by inputting the same evaluation problem to the trained artificial intelligence model (S640).

Then, the electronic device 100 may provide first evaluation information for the user's first answer and second evaluation information for the second answer of the artificial intelligence model (S650).

In this case, the user's achievement level for the learning process may be presented by comparison with an artificial intelligence model that has gone through the same learning process. In particular, since the user and the AI model are evaluated through the same learning process with substantially the same problem-solving ability, the effect of competition-based motivation for learning by period can be expected.

In addition, according to an embodiment, the electronic device 100 compares and analyzes the above-described first evaluation information and second evaluation information to determine the learning amount, learning period, and learning of at least one additional learning process after the above-described learning process. You can also set the difficulty level.

In this case, the additional learning process may be set differently according to a comparison between the first score of the first evaluation information for the user and the second score of the second evaluation information for the artificial intelligence model.

As a specific example, it is assumed that the first score according to the first evaluation information is lower than the second score according to the second evaluation information by a threshold value or more. This means that the user's achievement in the above-described learning process is relatively poor.

In this case, the electronic device 100 may set an additional learning process with a smaller amount of learning than the aforementioned learning process. Also, the electronic device 100 may set an additional learning process having a shorter learning period than the above-described learning process. In addition, the electronic device 100 may set an additional learning process having the same level of difficulty as the above-described learning process or having a higher level of difficulty than the above-described learning process by a first level difference (<threshold level).

However, if the first score is lower than the second score by a special threshold or more (learning achievement level is very low), the electronic device 100 may set an additional learning process having a lower level of difficulty than the above-described learning process.

As another example, it is assumed that the first score according to the first evaluation information is higher than the second score according to the second evaluation information by a threshold value or more. This means that the user's achievement in the above-described learning process is relatively good.

In this case, the electronic device 100 may set a second additional learning process having a larger amount of learning than the above-described learning process. Also, the electronic device 100 may set an additional learning process having a longer learning period than the above-described learning process. In addition, the electronic device 100 may set an additional learning process having the same difficulty level as the above-described learning process or having a higher level of difficulty than the above-described learning process by a difference of a second level (>threshold level) or more.

As another example, when the first score according to the first evaluation information and the second score according to the second evaluation information are the same, the electronic device 100 may set an additional learning process having the same learning period and learning amount as the above-described learning process. . In addition, the electronic device 100 may set an additional learning process with a level of difficulty higher than the difficulty level of the above-described learning process by a threshold level.

When the additional learning process is set according to the above-described embodiments, the electronic device 100 may provide a plurality of problems included in the additional learning process to the user, and artificial intelligence based on the plurality of problems included in the additional learning process The model can be trained.

And, when the learning period of the additional learning process expires, the electronic device 100 may also provide at least one evaluation problem (related to the additional learning process) to the user and the artificial intelligence model, similar to the above-described embodiment. Actions can be repeated.

Meanwhile, FIG. 7 is a block diagram illustrating a configuration of an electronic device according to various embodiments of the present disclosure.

Referring to FIG. 7 , the electronic device 100 may further include at least one of a communication unit 130, a user input unit 140, and an output unit 150 in addition to the memory 110 and the processor 120.

The communication unit 130 is a component through which the electronic device 100 transmits and receives data with various external devices, and may include at least one circuit for communication.

The communication unit 130 is TCP/IP (Transmission Control Protocol/Internet Protocol), UDP (User Datagram Protocol), HTTP (Hyper Text Transfer Protocol), HTTPS (Secure Hyper Text Transfer Protocol), FTP (File Transfer Protocol), SFTP ( Various types of information may be transmitted and received with one or more external electronic devices using communication protocols such as Secure File Transfer Protocol (MQTT) and Message Queuing Telemetry Transport (MQTT).

To this end, the communication unit 130 may be connected to an external device based on a network implemented through wired communication and/or wireless communication. In this case, the communication unit 130 may be directly connected to an external device, but may also be connected to an external electronic device through one or more external servers (eg, Internet Service Provider (ISP)) providing a network.

The network may be a Personal Area Network (PAN), a Local Area Network (LAN), a Wide Area Network (WAN), etc., depending on the area or size, and an intranet, It may be an extranet or the Internet.

Wireless communication includes LTE (long-term evolution), LTE-A (LTE Advance), 5G (5th generation) mobile communication, CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), GSM (Global System for Mobile Communications), DMA (Time Division Multiple Access), WiFi (Wi-Fi), WiFi Direct, Bluetooth, NFC (near field communication), Zigbee, etc. can include

Wired communication may include at least one of communication methods such as Ethernet, optical network, Universal Serial Bus (USB), and Thunderbolt.

Here, the communication unit 130 may include a network interface or network chip according to the wired/wireless communication method described above. On the other hand, the communication method is not limited to the above-described example, and may include a newly appearing communication method according to the development of technology.

When the electronic device 100 is a server, the electronic device 100 may communicate with various user terminals through the communication unit 130 and interwork with each user terminal through at least one web page or application to enable each user. It is possible to provide a learning management method according to the various embodiments described above for.

In this case, the electronic device 100 may receive information on user input received through the user terminal from the user terminal through the communication unit 130 .

In addition, the electronic device 100 may communicate with external servers in which various problems are stored through the communication unit 130 to receive information about problems and correct answers.

When the electronic device 100 is a user terminal such as a smartphone, the electronic device 100 manages learning according to various embodiments described above through an application/web page provided by at least one external server connected through the communication unit 130. You can also provide a way.

The user input unit 140 is a component for receiving a user command or user information.

When the electronic device 100 is implemented as a user terminal such as a smart phone or a notebook PC, the user input unit 140 may be implemented as a touch sensor, a button, a camera, a microphone, a keyboard, or the like.

When the electronic device 100 is a desktop PC, the user input unit 140 may be implemented as a terminal connected to various input interfaces such as a keyboard or a mouse.

The output unit 150 is a component for outputting various information and providing the information to the user.

When the electronic device 100 is implemented as a user terminal such as a smart phone, the output unit 150 may include a display, a speaker, an earphone/headset terminal, and the like.

As an example, the processor 120 may provide various problems, evaluation information, and UI according to various embodiments described above through the output unit 150 .

Meanwhile, the various embodiments described above may be implemented by combining a plurality of embodiments as long as they do not conflict with each other.

Meanwhile, various embodiments described above may be implemented in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof.

According to the hardware implementation, the embodiments described in this disclosure are application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), and field programmable gate arrays (FPGAs). ), processors, controllers, micro-controllers, microprocessors, and electrical units for performing other functions.

In some cases, the embodiments described herein may be implemented by a processor itself. According to software implementation, embodiments such as procedures and functions described in this specification may be implemented as separate software modules. Each of the software modules described above may perform one or more functions and operations described herein.

On the other hand, computer instructions or computer programs for performing processing operations in each device in the system according to various embodiments of the present disclosure described above are stored in a non-transitory computer-readable medium. can be stored Computer instructions or computer programs stored in such a non-transitory computer readable medium, when executed by a processor of a specific device, cause the above-described specific device to perform processing operations in the electronic device according to various embodiments described above.

A non-transitory computer readable medium is a medium that stores data semi-permanently and is readable by a device, not a medium that stores data for a short moment, such as a register, cache, or memory. Specific examples of the non-transitory computer readable media may include CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, and the like.

Although the preferred embodiments of the present disclosure have been shown and described above, the present disclosure is not limited to the specific embodiments described above, and is common in the technical field belonging to the present disclosure without departing from the gist of the present disclosure claimed in the claims. Of course, various modifications and implementations are possible by those with knowledge of, and these modifications should not be individually understood from the technical spirit or perspective of the present disclosure.

100: electronic device 110: memory
120: processor

Claims (1)

In the avatar-based learning management method of the electronic device performed by the processor of the electronic device,
Identifying the user's problem-solving ability based on the user's answers to the plurality of problems;
generating at least one artificial intelligence model matching the identified problem-solving ability;
inputting at least one problem into the artificial intelligence model and obtaining an answer of the artificial intelligence model for the problem; and
Including; providing evaluation information on the obtained answer of the artificial intelligence model;
The learning management method of the electronic device,
providing a plurality of problems included in a learning process set according to the user's problem-solving ability to the user;
training the artificial intelligence model based on the plurality of problems included in the set learning process;
obtaining a first answer of the user for the evaluation problem by providing at least one evaluation problem related to the learning process when the learning period according to the set learning process expires;
obtaining a second answer of the trained artificial intelligence model for the evaluation problem; and
Providing first evaluation information for the first answer and second evaluation information for the second answer;
The learning management method of the electronic device,
Based on the user's input, changing and setting at least one of the learning amount, learning period, and learning difficulty of the learning process; Further comprising,
The step of providing the plurality of problems,
Providing a plurality of problems included in the changed learning process to the user;
Training the artificial intelligence model,
Avatar-based learning management method of an electronic device, wherein the artificial intelligence model is trained based on the changed learning process.

Images