WO2024029946A1

WO2024029946A1 - Method and device for providing customized mathematical concept through problem-solving image analysis

Info

Publication number: WO2024029946A1
Application number: PCT/KR2023/011376
Authority: WO
Inventors: 이재윤; 이용현; 유병용
Original assignee: 주식회사 프로키언
Priority date: 2022-08-03
Filing date: 2023-08-03
Publication date: 2024-02-08

Abstract

A method for providing a user-customized mathematical concept is provided in one embodiment of the present disclosure. The method comprises the steps of: receiving images including body parts, which include the head and/or hand of a user, and a solution process of the user for a preset problem; analyzing the solution process so as to extract mathematical concepts, used by the user, included in the solution process, and analyzing behavior patterns of the user on the basis of the movements of the body parts; and comparing the mathematical concepts used by the user and essential mathematical concepts matched to the preset problem, so as to provide, to a user terminal communicatively connected to a server, an explanation of a mathematical concept missing from the solution process, or provide, to the terminal, an explanation of a mathematical concept corresponding to a specific behavior pattern from among the behavior patterns.

Description

Method and device for providing customized math concepts through problem-solving video analysis

The present invention relates to a method and device for providing customized mathematical concepts through analysis of problem-solving videos. More specifically, a method and device for providing explanations of mathematical concepts that the learner lacks by analyzing user behavior videos and solving process videos. It's about.

With the post-corona era, the time spent studying at home increases, and the market for online learning is growing further. However, online learning has the problem that it is difficult to receive direct feedback from the instructor like offline learning.

In particular, the problem-solving process is important for problems that involve complex applications of various concepts, such as math problems. In relation to this, in offline learning, it is possible to identify deficiencies by analyzing the problem-solving process created by the learner, but in online learning, there is a problem that it is difficult to identify deficiencies by analyzing the problem-solving process.

Additionally, in online learning, it was not possible to determine how learners were using the content provided to them, such as not separately recording the problem-solving process or what actions were taken in the process of solving the problem. In addition, many math problems are provided in the form of multiple choice, but it was not possible to know whether the correct answer was obtained by solving the problem correctly or by guessing the correct answer.

Accordingly, in preparation for solving math problems through online learning, research is needed on methods to check the problem-solving process and provide explanations of insufficient math concepts.

The present disclosure is intended to solve the problems of the prior art described above, and seeks to provide a method and device for providing explanations of insufficient mathematical concepts to learners by analyzing user action videos and solution process videos.

The technical problems to be achieved by the present invention are not limited to the above-described technical problems, and other technical problems of the present invention can be derived from the following description.

As a technical means for solving the above-described technical problem, an embodiment according to the first aspect of the present disclosure provides a method of providing a learner-customized mathematical concept. The method includes the steps of receiving an image containing a body part including at least one of the user's head and hands and the user's solution process for a preset problem, analyzing the solution process to identify the user included in the solution process. Extracting mathematical concepts used, analyzing the user's behavior patterns based on movements of the body parts, and comparing the mathematical concepts used by the user with essential mathematical concepts matched to the preset problem to participate in the solving process. It includes providing an explanation of a missing mathematical concept to a user terminal that is in communication with the server, or providing an explanation of a mathematical concept corresponding to a specific behavior pattern among the behavior patterns to the terminal.

Additionally, an embodiment according to the second aspect of the present disclosure provides an apparatus for providing a learner-customized mathematical concept. The device includes a communication module, at least one processor, and a memory electrically connected to the processor and storing at least one code executed by the processor. When the memory is executed through the processor, the processor receives an image containing a body part including at least one of the user's head and hands and the user's solution process for a preset problem, and analyzes the solution process. extracting user-used mathematical concepts included in the solution process, analyzing the user's behavior patterns based on movements of the body parts, and essential mathematical concepts matching the user-used mathematical concepts with the preset problem. stores a code that compares them and provides an explanation of the mathematical concept missing in the solution process to a user terminal connected to communication with the server, or provides an explanation of a mathematical concept corresponding to a specific behavior pattern among the behavior patterns to the terminal do.

According to the present invention, it is possible to identify the learner's weaknesses by analyzing the learner's problem-solving process during online learning.

In addition, according to the present invention, it is possible to identify learners' weaknesses by recognizing formulas in images and videos of the mathematics problem solving process, thereby solving problems that occur in online mathematics education.

In addition, according to the present invention, it is possible to recognize the results of problem solving and identify which parts are weak through this, and because it automatically determines based on the collected data, it can replace the existing method that required a human.

In addition, by utilizing the discovered vulnerability data, good problems can be recommended to learners through a better recommendation system and content that can help learners learn about vulnerabilities can be provided.

The effects of the present invention are not limited to the effects described above, and include all effects understood from the following description.

Figure 1 is a diagram illustrating a device for providing a learner-customized mathematical concept and a terminal communication connected thereto according to an embodiment of the present invention.

FIG. 2 is a diagram showing the detailed configuration of the device for providing a learner-customized mathematical concept shown in FIG. 1.

FIG. 3 is a diagram illustrating an example of extracting a learner-customized math concept and a user's movement using the device for providing a learner-customized math concept shown in FIG. 1.

FIG. 4 is a diagram illustrating an example of listing user-used math concepts and user behavior patterns by time period using the learner-customized math concept providing device shown in FIG. 1.

Figure 5 is a flowchart showing the sequence of a method for providing a customized math concept to a learner according to another embodiment of the present invention.

FIGS. 6 to 8 are diagrams illustrating detailed steps for some steps of the method for providing customized math concepts to learners shown in FIG. 5.

Hereinafter, the present disclosure will be described in detail with reference to the attached drawings. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In addition, the attached drawings are only intended to facilitate understanding of the embodiments disclosed in this specification, and the technical idea disclosed in this specification is not limited by the attached drawings. All terms, including technical and scientific terms, used herein should be interpreted as meanings commonly understood by those skilled in the art in the technical field to which this disclosure pertains. Terms defined in the dictionary should be interpreted as having additional meanings consistent with the related technical literature and currently disclosed content, and should not be interpreted in a very ideal or limited sense unless otherwise defined.

In order to clearly explain the present disclosure in the drawings, parts not related to the description are omitted, and the size, shape, and shape of each component shown in the drawings may be modified in various ways. Throughout the specification, identical/similar parts are given identical/similar reference numerals.

The suffixes “module” and “part” for components used in the following description are given or used interchangeably only for the ease of preparing the specification, and do not have distinct meanings or roles in themselves. Additionally, in describing the embodiments disclosed in this specification, if it is determined that detailed descriptions of related known technologies may obscure the gist of the embodiments disclosed in this specification, the detailed descriptions are omitted.

Throughout the specification, when a part is said to be “connected (connected, contacted, or combined)” with another part, this means not only when it is “directly connected (connected, contacted, or combined),” but also when it has other members in between. It also includes cases where they are “indirectly connected (connected, contacted, or combined).” Additionally, when a part is said to "include (equip or provide)" a certain component, this does not exclude other components, unless specifically stated to the contrary, but rather "includes (provides or provides)" other components. It means that you can.

Terms representing ordinal numbers, such as first, second, etc., used in this specification are used only for the purpose of distinguishing one component from another component and do not limit the order or relationship of the components. For example, the first component of the present disclosure may be named a second component, and similarly, the second component may also be named a first component. As used herein, singular forms of expression should be construed to also include plural forms of expression, unless the contrary is clearly indicated.

Referring to FIG. 1, the device 100 for providing a learner-customized mathematical concept may be connected to the terminal 200 through a preset communication network.

The learner-customized mathematics concept providing device 100 may be implemented in the form of a server, computing device, or various smart devices, and may be implemented as SaaS (Software as a Service), PaaS (Platform as a Service), or IaaS (Infrastructure as a Service). It can operate under the same cloud computing service model. In addition, the device 100 for providing learner-customized math concepts may be constructed in a form such as a private cloud, public cloud, or hybrid cloud system, but the scope of the present invention is not limited thereto.

The learner-customized mathematical concept providing device 100 receives an image containing body parts including at least one of the user's head and hands and the user's solution process for a preset problem.

However, it is not limited to this, and the learner-customized mathematical concept providing device 100 includes a plurality of body parts including at least one of the user's head and hands and a plurality of predetermined time intervals that include the user's solution process for a preset problem. You can receive images of dogs.

The device 100 for providing learner-customized math concepts may receive video and images from at least one of the terminal 200, an internal camera, and an external camera. For example, the internal camera and the external camera can capture the user's actions and the text containing the problem passage and problem solution that the user is learning. Internal cameras and external cameras may be devices that include cameras for capturing videos and images, such as smart device cameras and webcams.

The learner-customized mathematical concept providing device 100 analyzes the solving process to extract the user-used mathematical concepts included in the solving process, and analyzes the user's behavior patterns based on the movements of body parts.

The learner-customized math concept providing device 100 compares the math concepts used by the user with essential math concepts matched to preset problems, and provides an explanation of the math concept corresponding to a specific behavior pattern among the behavior patterns to the terminal. Behavior patterns may include positive behavior patterns and negative behavior patterns, and a specific behavior pattern may be a negative behavior pattern. A pre-established essential mathematical concept may be a concept group consisting of a plurality of concepts. For example, if there are multiple explanations or solutions to a preset problem, the necessary mathematical concepts for solving the problem may differ depending on the solution method.

The terminal 200 may receive an explanation of essential mathematics concepts that are missing and explanations of essential mathematics concepts that are difficult depending on the user's learning status from the learner-customized mathematics concept providing device 100. The terminal 200 can transmit video and images including the movement of the user's body parts and the solution process to the learner-customized mathematical concept providing device 100.

The terminal 200 is a laptop equipped with a web browser, a desktop, a laptop, a wireless communication device that guarantees portability and mobility, or any type of handheld device such as a smartphone, tablet PC, etc. ) may refer to a wireless communication device based on

FIG. 2 is a diagram illustrating the detailed configuration of the device (hereinafter referred to as server) for providing customized math concepts shown in FIG. 1.

Referring to FIG. 2 , the server 100 may include a communication module 110, a processor 120, and a memory 130.

The communication module 110 may include a device including hardware and software necessary to transmit and receive signals such as control signals or data signals through wired or wireless connections with other network devices.

The communication module 110 may transmit to the terminal a description of essential math concepts that are missing and descriptions of essential math concepts that are difficult depending on the user's learning status. Additionally, the communication module 110 may receive video and images including the movement and resolution process of the user's body parts from the terminal.

The processor 120 may include various types of devices that control and process data. The processor 120 may refer to a data processing device built into hardware that has a physically structured circuit to perform functions expressed by codes or instructions included in a program.

In one example, the processor 120 may include a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), or an FPGA ( It may be implemented in the form of a field programmable gate array, etc., but the scope of the present invention is not limited thereto.

The processor 120 performs operations according to the code stored in the memory 130.

The memory 130 stores at least one of information and data input to the communication module 110, information and data required for functions performed by the processor 120, and data generated according to execution of the processor 120. You can.

Memory 130 should be interpreted as a general term for non-volatile storage devices that continue to retain stored information even when power is not supplied and volatile storage devices that require power to maintain stored information. The memory 130 may include magnetic storage media or flash storage media in addition to volatile storage devices that require power to maintain stored information, but the scope of the present invention is not limited thereto. no.

The memory 130 is electrically connected to the processor 120 and stores at least one code executed by the processor 120. The memory 130 stores code that, when executed through the processor 120, causes the processor 120 to perform the following functions and procedures.

The memory 130 stores a code that causes the user to receive an image containing body parts including at least one of the user's head and hands and the user's solution process for a preset problem.

The memory 130 stores a code that analyzes the solution process, extracts mathematical concepts used by the user included in the solution process, and analyzes the user's behavior pattern based on the movement of body parts.

The memory 130 compares the mathematical concepts used by the user with essential mathematical concepts matched to a preset problem and provides an explanation of the mathematical concepts missing in the solution process to the user terminal communicating with the server, or performs a specific action among the behavior patterns. A code that causes an explanation of a mathematical concept corresponding to a pattern to be provided to the terminal is stored.

The memory 130 may store a code that causes the solution process and body part movements to be analyzed by continuously receiving images containing the learner's actions and the solution process at preset time intervals. For example, the memory 130 may store a code that analyzes the movement value of the dots for the user's movements and actions on a frame-by-frame basis to determine whether the value changes over a certain period of time.

The memory 130 may store a code that causes the handwritten text in the image to be extracted to extract the user-used mathematical concepts included in the solution process. For example, the memory 130 may store a code that causes the solving process to be analyzed through a preset method and the text within the solving process to be extracted. Here, the preset method may be an OCR text recognition method.

A code that causes a formula to be extracted from the extracted text may be stored in the memory 130.

A code that causes the user to extract a mathematical concept corresponding to the extracted formula may be stored in the memory 130. For example, a mathematical concept highly related to the extracted formula may be extracted from the memory 130 and the extracted mathematical concept may be matched with a user-used mathematical concept.

In the memory 130, a list of mathematical concepts used by users can be created for each time period.

The memory 130 may store a code that generates an outline of a body part including at least one of the user's face and hands in the image and extracts corner points on the outline to determine movement.

A code that causes the user's movement to be extracted based on the corner point may be stored in the memory 130.

The memory 130 may store a code that causes the user's behavior pattern to be extracted based on an artificial intelligence model learned to extract the user's behavior pattern by taking the vector value of the user's movement as an input. Here, the artificial intelligence model may be a model based on an extreme multi-classification algorithm. The user's behavior pattern may include at least one of hand movement, hand movement stoppage, problem identification, and head tilt determined based on at least one of eye movement, head movement, and hand gesture.

The memory 130 may store a code that causes a list of user behavior patterns to be generated for each time period. As an example, a user's behavior pattern may include positive patterns and negative patterns. Movements in which the user's hands move within a certain period of time, movements in which the user writes down a solution, etc. can be classified as positive behavior patterns. The user's head is tilted, the user's gaze is turned back to the problem during the solution process, the user's hand does not move, the user touches a writing utensil, etc. can be classified as negative behavior patterns.

The memory 130 stores a code that causes the user to compare the mathematical concepts used by the user with essential mathematical concepts matched to a preset problem and provide an explanation of the mathematical concept corresponding to the preset negative behavior pattern among the behavior patterns to the terminal.

The memory 130 may store a code that causes a comparison between the user-used mathematical concepts and essential mathematical concepts matched to a preset problem.

The memory 130 stores a code that causes the user's learning status to be determined by comparing the user's used math concepts and the user's behavior patterns by time period when the essential math concepts are all included in the user-used math concepts as a result of the comparison. It can be. For example, the user's learning state may be at least one of negative, positive, and problem solving.

More specifically, if the user's behavior pattern during the same time period is head tilting and the user's mathematical concept is a quadratic polynomial, the user's learning state may be determined to be negative in the quadratic polynomial based on the code stored in the memory 130.

In the memory 130, if, as a result of the comparison, all of the essential mathematical concepts are not included in the mathematical concepts used by the user, a code that causes the terminal to provide explanations for essential mathematical concepts not included in the mathematical concepts used by the user may be stored. You can. For example, if the essential mathematical concepts are the multiplication formula, the polynomial theorem method, and the conditions for becoming a quadratic equation, and the user-used mathematical concepts are the multiplication formula and the polynomial theorem method, the conditions for becoming the quadratic equation are based on the code stored in the memory 130. An explanation may be provided through the terminal. As another example, the essential mathematical concepts are 'multiplication formula', 'method of organizing polynomials', and 'conditions for quadratic equations', and the mathematical concepts used by users are 'multiplication formula', 'method of organizing polynomials', 'perfect square equation', And in the case of 'rationalization of the denominator', an explanation of the conditions for becoming a quadratic equation may be provided to the terminal based on the code stored in the memory 130.

The memory 130 may store a code that causes the terminal to provide an explanation of a mathematical concept corresponding to the time period in which a preset fraudulent behavior pattern was extracted from among the user's behavior patterns based on the user's learning state. For example, if the user's learning state is negative in the quadratic polynomial, an explanation of the quadratic polynomial may be provided to the terminal based on the code stored in the memory 130.

In addition, according to one embodiment of the present invention, after the explanation of a mathematical concept is provided to the user terminal, a code that causes the provision of mathematical content such as mathematical problems and lecture videos related to the mathematical concept may be stored in the memory 130. .

Referring to Figure 3, a learner-customized mathematical concept providing device can recognize body parts and generate outlines of body parts. For example, a learner-customized mathematics concept providing device may generate the

outlines

310 and 320 of the user's face and hands.

The device for providing a learner-customized mathematical concept can extract the face corner point 311 on the face outline 310 created to identify movement.

The device for providing a learner-customized mathematical concept can extract the hand corner point 321 on the hand outline 320 created to identify the movement.

The device for providing a learner-customized mathematical concept can calculate the user's behavior pattern based on vector values according to changes in the extracted corner points 311 and 321.

The device for providing learner-customized mathematical concepts can extract text 330 in the video based on the OCR text recognition method.

Referring to FIG. 4, the learner-customized mathematical concept providing device may display mathematical concepts recognized in the solution process by time slot 410. For example, it can be indicated in chronological order that the multiplication formula is recognized at the first time and the condition for becoming a quadratic equation is recognized at the second time.

The device for providing a learner-customized mathematical concept can display the user's behavior pattern recognized during the solution process by time zone (420). For example, the problem recognition at the 3rd time, the hand movement at the 4th time, the problem re-recognition at the 5th time, the hand movement stopped at the 6th time, the head tilt at the 7th time, and the hand movement was recognized at the 8th time. You can. Each of the corresponding times may correspond to each frame of the user's video.

The learner-customized math concept provision device can provide missing essential math concepts to the terminal by comparing the math concepts shown sequentially based on the video start time and the user's behavior patterns.

For example, when the learner-customized mathematical concept provision device compares the concepts needed to solve the problem with the concepts used in the actual solution, if there is no method for organizing polynomials, it determines that the user does not understand how to organize polynomials, and determines that the method for organizing polynomials is not understood. An explanation of the method can be provided through the terminal.

In another example, a learner-customized math concept provision device knows the multiplication formula and recognizes hand movements and head tilting behavior while solving the problem, recognizes the behavior as negation, determines that the learner does not fully understand the multiplication formula, and uses the multiplication formula. An explanation can be provided through the terminal.

The method of providing a learner-customized math concept, which will be described below, can be performed by the learner-customized math concept providing device previously described with reference to FIGS. 1 to 4. Accordingly, the contents of the embodiments of the present disclosure previously described with reference to FIGS. 1 to 4 can be equally applied to the embodiments to be described below, and contents that overlap with the description described above will be omitted below. The steps described below do not necessarily have to be performed in order, the order of the steps may be set in various ways, and the steps may be performed almost simultaneously.

Referring to Figure 5, the method of providing a learner-customized math concept includes a step of receiving an image containing body parts and a solution process (S100), a step of extracting a math concept used by the user and analyzing the user's behavior pattern (S200), and providing an explanation of the math concept. Includes step S300.

The step of receiving an image including a body part and a solution process (S100) is a step of receiving an image containing a body part including at least one of the user's head and hands and the user's solution process for a preset problem.

The user-used mathematical concept extraction and user's behavior pattern analysis step (S200) is a step of analyzing the solution process to extract the user-used mathematical concepts included in the solution process and analyzing the user's behavior pattern based on the movement of body parts. .

In the step of providing explanations for mathematical concepts (S300), the mathematical concepts used by the user are compared with essential mathematical concepts matched to preset problems, and an explanation of mathematical concepts corresponding to specific behavioral patterns among behavioral patterns is provided to a terminal in communication with the server. This is the step.

Referring to Figure 6, in the user-used mathematical concept extraction and user's behavior pattern analysis step (S200), the text extraction step within the solution process (S211), the formula extraction step within the text (S212), and the user-used mathematical concept extraction step (S212), the user's behavior pattern analysis step (S200). It may include a step of extracting mathematical concepts to be used (S213) and a step of generating a list of mathematical concepts to be used by the user (S214).

The text extraction step (S211) within the solving process may be a step of extracting text within the solving process by analyzing the solving process using a preset method. For example, the preset method may be an OCR text recognition method.

The formula extraction step (S212) within the text may be a step of extracting a formula from the text. For example, in the formula extraction step (S212) within the text, the formula within the text can be extracted based on a pre-stored formula.

The user-used math concept extraction step (S213) may be a step of extracting the user-used math concept corresponding to the formula. For example, in the user-used math concept extraction step (S213), the user-used math concept may be extracted based on the math concept matched with the pre-stored formula.

The step S214 of generating a list of mathematical concepts used by users may be a step of generating a list of mathematical concepts used by users by time period.

Referring to FIG. 7, in order to extract the user's behavior pattern, a corner point extraction step (S221), a user's movement extraction step (S222), a user's behavior pattern extraction step (S223), and a user's behavior pattern list generation step (S224) ) may include.

The corner point extraction step (S221) may be a step of generating an outline of a user's body part and extracting a corner point on the outline.

The user's motion extraction step (S222) may be a step of extracting the user's motion based on a corner point. For example, the user's movement may be a vector value.

The user's behavior pattern extraction step (S223) may be a step of extracting the user's behavior pattern based on an artificial intelligence model learned to extract the user's behavior pattern by using a vector value for the user's movement as an input. For example, the user's behavior pattern may include at least one of hand movement, hand movement stoppage, head tilt, and problem recognition.

The user's behavior pattern list creation step (S224) may be a step of generating a list of the user's behavior patterns for each time period.

Referring to FIG. 8, the step of providing an explanation of a mathematical concept (S300) includes a step of determining whether the essential mathematical concept and the mathematical concept used by the user match (S311), a step of determining the user's learning status (S312), and a step of determining whether the required mathematical concept matches the mathematical concept used by the user (S312). It may include a step of providing math concept explanations (S313) and a step of explaining missing required math concepts (S314).

The step of determining whether the essential mathematical concept and the user-used mathematical concept match (S311) may be a step of comparing the user-used mathematical concept with the essential mathematical concepts matched to a preset problem. For example, in the step of determining whether the essential math concept and the user math concept match (S311), as a result of comparing the essential math concept and the user-used math concept, if the essential math concepts are all included in the user-used math concept, the user's learning status The judgment step (S312) can be performed, and if there is no match, the missing essential math concept explanation step (S314) can be performed.

The user's learning status determination step (S312) may be a step of determining the user's learning status by comparing the mathematical concepts used by the user and the user's behavior patterns over time. For example, in the user's learning status determination step (S312), if the user's behavior pattern is to tilt his head while solving the polynomial multiplication, it may be determined that the polynomial multiplication is negative.

The step of providing explanations of essential mathematics concepts according to the learning state (S313) may be a step of providing explanations of essential mathematics concepts corresponding to the time period in which a specific behavior pattern of the user's behavior patterns was extracted based on the user's learning state to the terminal. there is. For example, an explanation of polynomial multiplication may be provided to the terminal based on the user's learning state of negation in polynomial multiplication.

The missing essential math concept explanation step (S314) may be a step of providing explanations of essential math concepts that are not included in the math concepts used by the user to the terminal. For example, if the math concepts used by the user are 1, 3, and 4 and the required math concepts are 1, 2, 3, and 4, an explanation of required math concept 2 can be provided to the terminal in the missing required math concept explanation step (S313). .

After performing the step of explaining the missing essential math concepts (S314), the step of determining the user's learning status (S312) and the step of providing explanations of essential math concepts (S313) according to the learning status can be further performed sequentially.

In addition, according to an embodiment of the present invention, after the explanation of the mathematical concept provided to the user terminal, a step of providing mathematical content such as mathematical problems and lecture videos related to the mathematical concept may be further performed.

Those skilled in the art to which this disclosure pertains will be able to understand, based on the above description, that the present disclosure can be easily modified into another specific form without changing its technical idea or essential features. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. The scope of the present disclosure is indicated by the patent claims described later, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present disclosure. The scope of the present application is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present application.

The form for implementing the invention is substantially the same as the previous best form for implementing the invention.

The present invention can provide effective content to learners by receiving visual information or video information and analyzing the data using the same logic, so it can be applied to content provision services and metaverse virtual reality according to the video analysis results, thereby increasing industrial applicability. have

Claims

In a method of providing learner-customized math concepts performed by a server,

a) receiving an image containing body parts including at least one of the user's head and hands and the user's solution process for a preset problem;

b) analyzing the solving process to extract mathematical concepts used by the user included in the solving process, and analyzing the user's behavior patterns based on movements of the body parts; and

c) Comparing the mathematical concepts used by the user with essential mathematical concepts matched to the preset problem and providing an explanation of the mathematical concepts missing in the solution process to the user terminal communicating with the server, or providing a specific behavior pattern among the behavior patterns A method of providing a customized math concept to a learner, including providing an explanation of the math concept corresponding to the terminal.
According to paragraph 1,

The step b) further includes the step of continuously receiving the image at preset time intervals and analyzing the solution process and the movement of the body part.
According to paragraph 1,

In step b),

Extracting text within the solving process;

extracting a formula from the text;

extracting the user-used mathematical concept corresponding to the formula; and

A method of providing a customized mathematics concept to a learner, comprising the step of generating a list of the user-used mathematics concepts by time period.
According to paragraph 1,

In step b),

generating an outline for each body part of the user and extracting corner points on the outline;

extracting the user's movement based on the corner point;

Extracting the user's behavior pattern based on an artificial intelligence model learned to extract the user's behavior pattern by inputting a vector value for the user's movement; and

A method of providing a customized math concept to a learner, including generating a list of the user's behavior patterns by time period.
According to paragraph 1,

In step c),

Comparing the user-used mathematical concepts with essential mathematical concepts matched to the preset problem;

As a result of the comparison, if all of the essential mathematical concepts are included in the user-used mathematical concepts, comparing the user-used mathematical concepts and the user's behavior patterns over time to determine the user's learning status; and

A method of providing a customized math concept to a learner, including providing, to the terminal, an explanation of a math concept corresponding to a time period in which a preset negative behavior pattern was extracted from among the user's behavior patterns based on the user's learning state.
According to paragraph 1,

In step c),

Comparing the user-used mathematical concepts with essential mathematical concepts matched to the preset problem;

As a result of the comparison, if all of the essential mathematical concepts are not included in the user-used mathematical concepts, providing an explanation of mathematical concepts not included in the user-used mathematical concepts among the essential mathematical concepts to the terminal;

Comparing the math concepts used by the user and the user's behavior patterns over time to determine the user's learning status; and

A method of providing a customized math concept to a learner, including providing, to the terminal, an explanation of a math concept corresponding to a time period in which a preset negative behavior pattern was extracted from among the user's behavior patterns based on the user's learning state.
communication module;

at least one processor; and

A memory electrically connected to the processor and storing at least one code executed by the processor,

When the memory is executed through the processor, the processor

Receive an image containing the user's body part including at least one of the user's head and hands and the user's solution process for a preset problem, analyze the solution process, and extract the mathematical concepts used by the user included in the solution process. and analyzing the user's behavior patterns based on the movements of the body parts, and comparing the user-used mathematical concepts with essential mathematical concepts matched to the preset problem to explain the mathematical concepts missing in the solution process. A device for providing a learner-customized mathematical concept that provides a user terminal connected to communication with the communication module, or stores a code that causes an explanation of a mathematical concept corresponding to a specific behavior pattern among the behavior patterns to be provided to the terminal.
In clause 7,

The memory allows the processor to:

A learner-customized mathematical concept providing device that continuously receives the image at preset time intervals and further stores codes that cause analysis of the solution process and movement of the body parts.
In clause 7,

The memory allows the processor to:

Further storing code that causes the text in the solution process to be extracted, a formula to be extracted from the text, the user-used mathematical concept corresponding to the formula to be extracted, and a list of the user-used mathematical concept to be generated by time period. , a device that provides learners with customized math concepts.
In clause 7,

The memory allows the processor to:

Create an outline of the user's body part, extract a corner point on the outline, extract the user's movement based on the corner point, and input a vector value for the user's movement to determine the user's behavior. A device for providing a learner-customized mathematical concept, extracting the user's behavior pattern based on an artificial intelligence model learned to extract the pattern, and further storing code that causes the user to generate a list of the user's behavior pattern by time period.
In clause 7,

The memory allows the processor to:

The user-used mathematical concept is compared with essential mathematical concepts matched to the preset problem, and as a result of the comparison, if all of the essential mathematical concepts are included in the user-used mathematical concept, the user-used mathematical concept and the user's behavior pattern are determined. The user's learning status is determined by comparison by time zone, and an explanation of the mathematical concept corresponding to the time zone in which the preset fraudulent behavior pattern was extracted from the user's behavior pattern based on the user's learning state is sent to the terminal. A learner-customized mathematical concept provision device that further stores the code that causes it to be provided.
In clause 7,

The memory allows the processor to:

The user-used mathematical concept is compared with essential mathematical concepts matched to the preset problem, and as a result of the comparison, if the essential mathematical concepts are not all included in the user-used mathematical concept, the user-used mathematical concept among the essential mathematical concepts Provide an explanation of mathematical concepts not included in the terminal to the terminal, compare the mathematical concepts used by the user and the user's behavior patterns over time to determine the user's learning status, and based on the user's learning status A device for providing a learner-customized math concept, further storing a code that causes the terminal to provide an explanation of a math concept corresponding to the time period in which a preset negative action pattern was extracted from among the user's action patterns.