System and method for providing personalized mathematics learning based on objective and subjective difficulty assessment

Abstract

The present invention relates to a system and method for providing customized mathematics learning based on objective and subjective difficulty evaluations. More specifically, it relates to a system and method for providing customized mathematics learning based on objective and subjective difficulty evaluations that evaluates the objective difficulty determined by the characteristics of the problem itself and the subjective difficulty felt by the learner during the process of solving the problem, and comprehensively considers the results of the objective and subjective difficulty evaluations to provide customized mathematics learning tailored to the characteristics of individual learners.

Description

Technology Field

[0001] The present invention relates to a system and method for providing customized mathematics learning based on objective and subjective difficulty evaluations. More specifically, it relates to a system and method for providing customized mathematics learning based on objective and subjective difficulty evaluations that evaluates the objective difficulty determined by the characteristics of the problem itself and the subjective difficulty felt by the learner during the process of solving the problem, and comprehensively considers the results of the objective and subjective difficulty evaluations to provide customized mathematics learning tailored to the characteristics of individual learners. Background Technology

[0003] Mathematics fundamentally deals with many abstract concepts—such as numbers, symbols, and formulas—that are not directly related to concrete objects or situations in the real world. Since it is a discipline where basic concepts build upon each other to advance to advanced concepts, if students move on to the next stage without sufficiently understanding the basic concepts, subsequent learning becomes increasingly difficult.

[0004] Furthermore, recent math question types are increasingly requiring problem-solving skills rather than simply relying on formulas or calculations; students may face significant difficulties in solving these problems if they lack experience in analyzing problems, finding solutions, and applying those methods.

[0005] When students repeatedly struggle to solve math problems, their confidence drops and they gradually lose interest in learning. Due to this problem, the number of students who have given up on math, known as "math dropouts," has been increasing recently.

[0006] Recently, with the advancement of modern educational technology, there has been increasing interest in personalized learning systems tailored to the characteristics of individual learners. In particular, since mathematics is a subject that requires theoretical and logical thinking, and the degree of difficulty experienced by learners can vary significantly from person to person, the importance of learning methods that consider the learner's individual level and learning patterns is being further emphasized.

[0007] The difficulty of mathematical problems can be divided into objective difficulty, determined by the structural and mathematical characteristics of the problem itself, and subjective difficulty, which is the personal challenge learners experience during the problem-solving process. Existing mathematics learning systems have primarily relied on classifying problems by difficulty level based on objective criteria and assigning problems based on learners' achievement levels.

[0008] For example, most recent online learning platforms use methods that adjust difficulty based on the accuracy rate of problems solved by the learner or automatically provide more difficult problems once a certain level is reached. However, since these systems do not take into account the learner's subjective sense of difficulty at all, learners may easily feel bored or struggle during the learning process, and there is a problem in that it is difficult to provide personalized learning tailored to individual learners.

[0009] In other words, the objective difficulty of a problem does not necessarily correspond to the difficulty experienced by the learner, and since the subjective difficulty perceived by an individual can vary even for the same mathematical problem depending on the learner's background knowledge, learning style, problem-solving strategies, and psychological state, there is a need to develop a system capable of providing individualized learning feedback by simultaneously evaluating and comprehensively reflecting both objective and subjective difficulty in order to provide more effective learning. Prior art literature

[0011] 1. Korean Patent Publication No. 10-2562156 (Registered July 27, 2023) 2. Korean Patent Publication No. 10-2636079 (Registered February 6, 2024) The problem to be solved

[0012] The present invention has been devised to solve the problems of the prior art described above. The objective of the present invention is to provide a system and method for providing customized mathematics learning based on objective and subjective difficulty evaluations, which evaluate the objective difficulty defined by the content and format of mathematical problems and the subjective difficulty individually perceived by the learner during the problem-solving process, respectively, and comprehensively consider the evaluation results to provide customized mathematics learning tailored to the characteristics of the individual learner. means of solving the problem

[0014] The present invention for achieving the above objectives is,

[0015] A mathematics learning provision system may include: a database that stores mathematics problems to be provided to learners, classified by unit, type, and difficulty level; a data collection unit that collects biometric data generated during the process of a learner solving mathematics problems; and a main server connected via a network to the database and the data collection unit, which evaluates the objective difficulty level defined by the content and format of the mathematics problems and the subjective difficulty level individually felt by the learner during the problem-solving process, and provides customized mathematics learning tailored to the characteristics of individual learners by comprehensively considering the evaluation results.

[0016] At this time, the main server may include: an objective difficulty evaluation unit that evaluates objective difficulty determined according to the characteristics of the math problems provided to the learner; a subjective difficulty evaluation unit that evaluates subjective difficulty felt by learners during the problem-solving process using the learner's biometric data collected through the data collection unit; a learner diagnosis unit that diagnoses the learner's level by unit and type based on the objective difficulty and subjective difficulty evaluated through the objective difficulty evaluation unit and the subjective difficulty evaluation unit; and a feedback provision unit that provides feedback to compensate for the learner's weaknesses based on the diagnosis results from the learner diagnosis unit.

[0017] Here, the objective difficulty evaluation unit may include: a complexity measurement module that measures the complexity of a mathematical problem provided to a learner and evaluates the objective difficulty based on the complexity; a comparison group verification module that evaluates the objective difficulty of a mathematical problem by considering problem-solving information of other learners; and a first calculation module that quantifies the objective difficulty based on the objective difficulty evaluated through the complexity measurement module and the comparison group verification module.

[0018] Additionally, the subjective difficulty evaluation unit may include: a correct / incorrect answer type verification module that provides learners with a survey to write the reasons for correct / incorrect answers for each question regarding the problem-solving results and receives the written results; a correct / incorrect answer type classification module that classifies the learners' correct / incorrect answer types using biometric information-related data collected through the data collection unit; a correct / incorrect answer type evaluation and correction module that compares and evaluates the classification results of correct / incorrect answer types generated by the correct / incorrect answer type verification module and the correct / incorrect answer type classification module, respectively, and corrects the correct / incorrect answer types by confirming whether the learners consent to the evaluation; and a second calculation module that converts the correct / incorrect answer types corrected through the correct / incorrect answer type evaluation and correction module into an evaluation index to calculate the learner's subjective difficulty for each question.

[0019] In addition, the above correct / incorrect answer type classification module can automatically detect sections where the learner's concentration decreases during the entire problem-solving process based on the learner's biometric information, and exclude subjective difficulty evaluations of the math problems being solved in those sections.

[0020] Additionally, the learner diagnostic unit may include: an error type analysis module that analyzes the learner's error types in detail based on the learner's subjective difficulty level for each item evaluated by the subjective difficulty evaluation unit; an achievement evaluation module that evaluates the learner's achievement level by unit and type by calculating the correct answer rate by unit and type of math problems solved by the learner; and a diagnostic module that analyzes the learner's correct and incorrect answer types by classifying them according to objective difficulty level by calculating the correct answer rate by objective difficulty level evaluated by the objective difficulty evaluation unit.

[0021] Meanwhile, the method for providing customized mathematics learning based on objective and subjective difficulty evaluations according to the present invention is,

[0022] A method for providing customized mathematics learning for learners may include: a data collection step for collecting biometric data generated during the process of learners solving mathematics problems; an objective difficulty evaluation step for evaluating objective difficulty determined according to the characteristics of the mathematics problems provided to the learners; a subjective difficulty evaluation step for evaluating subjective difficulty felt by learners during the problem-solving process using the learners' biometric data collected through the data collection unit; a learner diagnosis step for diagnosing the learners' level by unit and type based on the objective difficulty and subjective difficulty evaluated through the objective difficulty evaluation step and the subjective difficulty evaluation step; and a feedback provision step for providing feedback to compensate for the learners' weaknesses based on the diagnosis results from the learner diagnosis step. Effects of the invention

[0024] According to the present invention, objective and subjective difficulty levels in mathematics learning are evaluated separately, and by comprehensively considering the evaluation results, customized mathematics learning tailored to the characteristics of individual learners can be provided, thereby increasing learners' motivation and allowing them to feel a sense of accomplishment, which has an excellent effect of maximizing the efficiency of learning.

[0025] In addition, according to the present invention, the difficulty level experienced by a learner can be evaluated in real time by analyzing the learner's problem-solving process and results, and the invention additionally has the effect of providing optimal feedback tailored to the learner's condition by considering various biological responses of the learner that occur during the problem-solving process.

[0026] In addition, according to the present invention, the accuracy of the learner's self-awareness is improved by comparing the learner's correct and incorrect answers with the degree of cognitive confidence, and the learning pattern can be adjusted by detecting patterns of decreased concentration through bio-response analysis. At the same time, if the pattern of decreased concentration is continuously repeated, expert counseling is recommended to resolve the learner's fundamental learning disability factors, thereby inducing the formation of sustainable and healthy learning habits. Brief explanation of the drawing

[0028] FIG. 1 is a schematic diagram showing the configuration of a learner-customized mathematics learning provision system based on objective and subjective difficulty evaluations according to the present invention. FIG. 2 is a conceptual drawing of the present invention shown in FIG. 1. FIG. 3 is a diagram exemplarily showing a correct / incorrect answer type input form provided to a learner terminal by the correct / incorrect answer type verification module of the present invention shown in FIG. 2. FIGS. 4(a) and 4(b) are diagrams exemplarily illustrating a mathematical problem selected by the problem type determination module of the present invention shown in FIG. 2 and a similar problem generated by the similar problem generation module. FIG. 4 is a flowchart sequentially illustrating a method for providing customized mathematics learning to learners based on objective and subjective difficulty evaluations according to the present invention. Specific details for implementing the invention

[0029] The embodiments of the present disclosure are illustrative for the purpose of explaining the technical concept of the present disclosure. The scope of rights according to the present disclosure is not limited to the embodiments presented below or the specific description thereof.

[0030] All technical and scientific terms used in this disclosure, unless otherwise defined, have the meaning generally understood by those skilled in the art to which this disclosure pertains. All terms used in this disclosure are selected for the purpose of further clarifying this disclosure and are not selected to limit the scope of the rights under this disclosure.

[0031] Expressions such as “comprising,” “comprising,” “having,” etc. used in this disclosure should be understood as open-ended terms implying the possibility of including other embodiments, unless otherwise stated in the phrase or sentence containing such expressions.

[0032] Unless otherwise stated, singular expressions described in this disclosure may include a plural meaning, and this applies likewise to singular expressions described in the claims.

[0034] Hereinafter, preferred embodiments of a system and method for providing customized mathematics learning based on objective and subjective difficulty evaluation according to the present invention will be described in detail with reference to the attached drawings.

[0035] FIG. 1 is a schematic diagram showing the configuration of a learner-customized mathematics learning provision system based on objective and subjective difficulty evaluation according to the present invention, FIG. 2 is a conceptual diagram showing the present invention shown in FIG. 1, FIG. 3 is an exemplary diagram showing a correct / incorrect answer type input form provided to a learner terminal by a correct / incorrect answer type verification module among the present invention shown in FIG. 2, FIG. 4 (a) and (b) are exemplary diagrams showing a mathematics problem selected by a problem type determination module and a similar problem generated by a similar problem generation module among the present invention shown in FIG. 2, FIG. 4 is a flowchart sequentially showing a learner-customized mathematics learning provision method based on objective and subjective difficulty evaluation according to the present invention.

[0037] The present invention relates to a system and method for providing customized mathematics learning based on objective and subjective difficulty evaluations, which evaluates the objective difficulty determined by the characteristics of the problem itself and the subjective difficulty felt by the learner during the process of solving the problem, and comprehensively considers the results of the objective and subjective difficulty evaluations to provide customized mathematics learning tailored to the characteristics of individual learners. The mathematics learning provision system (10) according to the present invention may include, as shown in FIG. 1, a database (100), a data collection unit (200), a main server (300), and a learner terminal (400).

[0038] First, the above database (100) serves to integrally store and manage information regarding mathematical problems and related content provided in the present invention, and the mathematical problems stored in the above database (100) can be provided to a learner terminal (400) through the main server (300) to be described later.

[0039] That is, the information that can be stored in the above database (100) may include math problems of various types and difficulty levels, learner information, etc., and each piece of information may be stored separately in a separate DB.

[0040] To explain in more detail, the above database (100) may include a problem DB (110), a learner DB (120), etc., as shown in FIG. 2. First, the problem DB (110) is configured to store math problems that may be included in a problem sheet to be transmitted to a learner terminal (400) by the main server (300), that is, customized problems that may be individually provided to learners by the feedback providing unit (340) described later. Various existing types of math problems, as well as problems newly generated by the similar problem generation module (346) of the main server (300) described later, may be stored separately by unit, type, and difficulty level.

[0041] Next, the above-mentioned learner DB (120) is configured to store information of learners using the learner terminal (400) described later. Student information entered into the main server (300) through the learner terminal (400) can be transmitted to the database (100) via a network and stored in the learner DB (120).

[0042] In addition, the learner DB (120) may additionally store the subjective difficulty of learners evaluated by the subjective difficulty evaluation unit (320) described later, the diagnosis results from the learner diagnosis unit (330), the feedback content from the feedback provision unit (340), and the improvement details based thereon.

[0043] Next, the data collection unit (200) is configured to collect bio-information related data generated during the process of learners solving math problems, and the bio-information may include eye movements, pupil dilation, physiological stress, facial and body movements, etc.

[0044] To explain in more detail, the data collection unit (200) may include a camera (210) and a heart rate monitor (220). The camera (210) serves to film the process of learners solving problems, and multiple cameras may be installed in front of and above the learner solving the problems to film the learner's problem-solving process from different directions.

[0045] That is, the video captured by the camera (210) installed in front of the learner can be used to check the learner's eye movements, pupil changes, facial and muscle reactions, etc., during the problem-solving process, and the video captured by the camera (210) installed above the learner can be used to check the learner's gaze changes or body movements, etc., during the problem-solving process.

[0046] In addition, the video captured by the camera (210) can be used to check the time required for each step of the solution process, and the time required for each step of the solution can be accurately calculated through frame analysis of the video captured by multiple cameras (210).

[0047] In addition, the heart rate measuring device (220) is configured to measure changes in the learner's heart rate during the problem-solving process, and the level of physiological stress of the learner can be checked through the measurement results.

[0048] As described above, the data captured and measured by the data collection unit (200) is transmitted to the main server (300) and used for the analysis of the learner's biometric information, and through this biometric information analysis, the subjective difficulty felt by the learner during the problem-solving process can be accurately measured.

[0049] Next, the main server (300) evaluates the objective difficulty defined by the content and format of the math problem and the subjective difficulty individually felt by the learner during the problem-solving process, and comprehensively considers the evaluation results to provide customized math learning tailored to the characteristics of the individual learner. As shown in FIG. 2, the configuration may include an objective difficulty evaluation unit (310), a subjective difficulty evaluation unit (320), a learner diagnosis unit (330), and a feedback provision unit (340).

[0050] First, the objective difficulty evaluation unit (310) is configured to evaluate the objective difficulty that can be determined according to the characteristics of the math problem provided to the learner, namely the content and format of the problem, and may include a complexity measurement module (312), a comparison group verification module (314), and a first operation module (316).

[0051] To explain in more detail, the complexity measurement module (312) is configured to measure the complexity of a math problem provided to a learner and to evaluate the objective difficulty level according to the complexity, and the number of concepts used, proximity between concepts, computational complexity, etc. may be considered in this complexity measurement.

[0052] First, the number of concepts used can refer to the number of mathematical concepts required to solve the problem, and mathematical concepts may include theorems, formulas, properties, etc.

[0053] The more concepts used, the higher the difficulty level may be, for example, 1 point may be awarded for each concept.

[0054] Next, the proximity between concepts is intended to verify how closely the concepts used in the problem-solving process are connected to each other. The complexity measurement module (312) classifies the proximity between concepts into direct connection (strongly connected), normal connection (some degree of connection), and no connection (no connection), and assigns 1 point, 2 points, and 3 points to direct connection, normal connection, and no connection, respectively, thereby increasing the objective difficulty as concepts that are far apart need to be combined.

[0055] In addition, when the number of concepts used is 1, the proximity between concepts may not be considered in the objective difficulty assessment.

[0056] Next, computational complexity is an item for evaluating the type and amount of operations required to solve a problem, and the complexity measurement module (312) can assign a higher score in the range of 1 to 3 points as the operation process is longer or more difficult, taking into account the types of operations such as arithmetic operations, equations, and differentiation.

[0057] In addition, the complexity measurement module (312) can analyze the number of steps in the solution process for solving the problem and similarly assign a higher score in the range of 1 to 3 points as the number of steps required or leaps in thinking are increased.

[0058] Next, the comparison group verification module (314) is configured to evaluate objective difficulty by considering problem-solving information of other learners (hereinafter referred to as the 'comparison group') that can be compared with the learner, and the problem-solving information of the comparison group may include the correct answer rate, time taken, and error pattern.

[0059] That is, the comparison group verification module (314) can evaluate the objective difficulty by measuring the accuracy rate of the comparison groups that solved the problem. For example, 1 point is given if the accuracy rate is 80% or higher, 2 points if the accuracy rate is 50% or higher but less than 80%, and 3 points if the accuracy rate is less than 50%, so that the lower the accuracy rate, the higher the difficulty.

[0060] In addition, the comparison group verification module (314) can evaluate the objective difficulty by considering the average time taken to solve the problem of the comparison groups. For example, 1 point is given if the time taken is within 1 minute, 2 points if it is between 1 minute and 3 minutes, and 3 points if it is 3 minutes or more, so that the longer the time taken, the higher the difficulty is evaluated.

[0061] In addition, the comparison group verification module (314) can evaluate the objective difficulty by considering the error patterns of the comparison groups, that is, the types of errors, trap elements included in the problem, and the degree of error induction. For example, 1 point is assigned for simple errors, 2 points for conceptual errors, and 3 points for other cases, so that the difficulty is evaluated as higher the more the error is not caused by standardized errors.

[0062] Next, the first calculation module (316) serves to quantify the objective difficulty based on the objective difficulty evaluated through the complexity measurement module (312) and the comparison group verification module (314), and the following equation (1) can be used to quantify the objective difficulty.

[0063] OD = w1 × S1 + w2 × S2 ... (1)

[0064] (Here, OD represents Objective Difficulty, S1 represents the difficulty score measured by the complexity measurement module (312), S2 represents the difficulty score measured by the comparison group verification module (314), and w1 and w2 represent the weights for each item.)

[0065] At this time, if the complexity of the problem itself is to be emphasized more in terms of objective difficulty, w1 can be set larger than w2, and S1 and S2 may be the sum of the scores for each item measured by the complexity measurement module (312) and the comparison group verification module (314), or the average of the scores for each item.

[0066] Next, the above-mentioned subjective difficulty evaluation unit (320) is configured to evaluate the subjective difficulty felt by learners during the problem-solving process and may include a correct / incorrect answer type verification module (322), a correct / incorrect answer type classification module (324), a correct / incorrect answer type evaluation and correction module (326), and a second calculation module (328).

[0067] To explain in more detail, the correct / incorrect answer type verification module (322) is responsible for providing learners with a survey to write the reasons for correct / incorrect answers for each problem regarding the problem-solving results and receiving the results. The correct / incorrect answer type verification module (322) transmits the survey content in the form shown in FIG. 3 to the learner's terminal through the communication unit (350) to be described later, and learners can fill out the received form and transmit it to the main server (300) through the network.

[0068] The correct / incorrect answer type checked in the above correct / incorrect answer type checking module (322) can be divided into four types: a case where the correct answer is correct and the understanding is perfect, a case where the correct answer is correct but the understanding is not perfect, a case where the answer is incorrect but the content of the question is understood and the answer was incorrect by mistake, and a case where the answer is incorrect and the content of the question is not perfectly understood, so that learners can select one of the four correct / incorrect answer types for each question.

[0069] Next, the correct / incorrect answer type classification module (324) is configured to classify the correct / incorrect answer types of learners using biometric information-related data generated during the process of learners solving math problems collected through the data collection unit (200), and can be configured to more accurately evaluate the learner's correct / incorrect answer type by comparing it with the correct / incorrect answer types directly written by the learners collected by the correct / incorrect answer type verification module (322).

[0070] To explain in more detail, the correct / incorrect answer type classification module (324) can classify the correct / incorrect answer types of learners by checking whether the learner's pupils are dilated, changes in the frequency of blinking, changes in eye movements, changes in facial muscles, changes in body movements, etc., through image analysis obtained through the camera (210) of the data collection unit (200), and by checking changes in the learner's stress during the problem-solving process through changes in heart rate collected through the heart rate measuring device (220) of the data collection unit (200).

[0071] For example, when a learner encounters a problem they find difficult, their pupils may dilate due to increased cognitive load, and while blinking may decrease initially due to high concentration, the frequency of blinking may increase when cognitive overload occurs.

[0072] In addition, when learners encounter problems they find difficult, patterns of eye movement may increase, changes in facial muscles such as furrowing brows or wrinkles on the forehead may occur, and there is a high likelihood that behaviors such as frequently changing posture or moving the body will increase compared to when solving easy problems.

[0073] In addition, since the heart rate may temporarily increase and the learner may show a state of stress when encountering a problem that the learner finds difficult, the correct / incorrect answer type classification module (324) can classify the correct / incorrect answer types into six problem types as follows by considering the learner's biometric information collected through the data collection unit (200) and the time required to solve the problem.

[0074] First, there is the completely confident correct answer problem (R1), which corresponds to a case where the learner solved the problem with confidence and got the correct answer; it is characterized by stable biological responses during the problem-solving process and a short time required to solve.

[0075] Second, there is the correct answer problem (R2) which includes minor errors; this corresponds to a case where an error occurred during the solution process but was corrected by self-correction during the review process, characterized by an accurate understanding of the concepts but the presence of calculation errors or notation errors.

[0076] Third, there are partially confident correct answer problems (R3), which correspond to cases where the student felt uncertainty during the solution process but ultimately got the correct answer. These problems are characterized by a tendency to take a somewhat longer time to solve or to verify answers multiple times during the process.

[0077] Fourth, there is the question that was unfortunately answered incorrectly (W1), which corresponds to a case where the solution process was almost correct but the correct answer was not given due to a mistake, and the learner's biometric information may show characteristics similar to the question that was answered with complete certainty (R1).

[0078] Fifth, the problem of lack of concept (W2) corresponds to a case where a problem is solved but the wrong concept to be applied is selected, resulting in a failure to get the correct answer. This can be characterized by a high likelihood of consistent mistakes occurring in other problems of a similar type.

[0079] Sixth, the completely unknown problem (W3) corresponds to cases where the learner could not grasp the direction of the solution at all or made no attempt even after seeing the problem; this may show the characteristic that new learning from the basics is necessary due to the learner's lack of conceptual understanding.

[0080] That is, the above correct / incorrect answer type classification module (324) can automatically classify correct / incorrect answer types using biometric information generated during the learners' problem-solving process through machine learning, using data obtained through the data collection unit (200) as input values ​​and the above-mentioned six classified correct / incorrect answer types as output values.

[0081] In addition, the above correct / incorrect answer type classification model can automatically detect sections where the learner's concentration decreases during the entire problem-solving process based on the learner's biometric information. For example, even if a problem is judged to have low objective difficulty and low subjective difficulty based on the classification results of correct / incorrect answers of other problems, if a section occurs where the learner's biometric information exhibits a pattern similar to that of solving a high-difficulty problem, it can be determined that the learner's concentration has decreased in that section.

[0082] Furthermore, in the above correct / incorrect answer type classification model, if a section where the learner’s biometric information exhibits patterns of solving high-difficulty problems—such as excessive pupil changes or changes in body movement—is detected for a certain period of time during a math problem-solving stage that is judged to have low objective difficulty and is not difficult for the learner, such as a simple calculation section, it is not judged as a weak area of ​​the learner but as a section of insufficient concentration, thereby excluding the subjective difficulty evaluation of the math problems solved in that section.

[0083] Next, the correct / incorrect answer type evaluation and correction module (326) may be configured to more accurately evaluate the subjective difficulty felt by learners by comparing the correct / incorrect answer type classification results generated by the correct / incorrect answer type verification module (322) and the correct / incorrect answer type classification module (324), respectively.

[0084] That is, the correct / incorrect answer type evaluation and correction module (326) can compare the correct / incorrect answer type written by the learner with the correct / incorrect answer type written through biometric information analysis, and if there is a difference, the correct / incorrect answer type evaluation result including the reason for classification of the correct / incorrect answer type through biometric information analysis can be written in a format such as (Table 1) below and transmitted to the learner's terminal.

[0085]

[0086] The learner uses a learner terminal to write down whether they agree to the evaluation for each question and transmits it to the main server (300). If the learner does not agree to the classification and evaluation of correct / incorrect answer types written through biometric information analysis, the correct / incorrect answer type written by the learner can be judged as the learner's actual skill level and made a final selection.

[0087] Accordingly, the above correct / incorrect answer type evaluation and correction module (326) can confirm whether the learner terminal consents to the evaluation for each question, and then finally correct the classification of correct / incorrect answer types for each question and store it in the learner DB (120) of the database (100).

[0088] Next, the second operation module (328) converts the correct / incorrect answer type, which is finally corrected through the correct / incorrect answer type evaluation and correction module (326), into an evaluation index to calculate the learner's subjective difficulty level for each question, and the calculated subjective difficulty level can be simultaneously stored in the problem DB (110) and the learner DB (120) of the database (100).

[0089] That is, in the second operation module (328), each correct / incorrect answer type can be converted into an evaluation index such as completely certain correct answer (R1) = 5, correct answer including small error (R2) = 4, partially certain correct answer (R3) = 3, incorrect error (W1) = 2, incorrect answer lacking concept (W2) = 1, and completely incorrect answer (W3) = 0, thereby allowing the subjective difficulty to be evaluated for each item, and the lower the evaluation index, the more difficult the subjective difficulty can be set.

[0090] At this time, if the above evaluation index is applied in reverse, such as completely wrong answer (W3) = 5 and completely certain correct answer (R1) = 0, it goes without saying that the higher the evaluation index, the more difficult the subjective difficulty can be set.

[0091] Next, the learner diagnostic unit (330) is configured to diagnose the learner's level by unit and type based on the objective difficulty and subjective difficulty evaluated through the objective difficulty evaluation unit (310) and the subjective difficulty evaluation unit (320), and may include an incorrect answer type analysis module (332), an achievement evaluation module (334), and a diagnostic module (336).

[0092] To explain in more detail, the above error type analysis module (332) is configured to analyze the learner's error type pattern in detail, and can analyze the learner's error type based on the learner's subjective difficulty level for each item evaluated by the subjective difficulty evaluation unit (320).

[0093] That is, the above error type analysis module (332) can identify the stage where an error occurred during the learner's problem-solving process and distinguish in detail whether the cause of the error is a calculation error or a lack of understanding of the concept.

[0094] In addition, the above error type analysis module (332) can analyze the frequency of each error type to determine whether the learner repeatedly makes mistakes in specific concepts or specific problem types, and to identify units or problem types where the understanding of the concepts is relatively lacking.

[0095] Next, the achievement evaluation module (334) is configured to evaluate the achievement of the learner by unit and by type, and can calculate the accuracy, i.e., the correct answer rate (%) in each unit and type by classifying the math problems solved by the learner by unit and type.

[0096] For example, a learner's understanding of the quadratic function unit can be evaluated by analyzing the number of problems solved and the number of correct answers in that unit; if the accuracy rate is low in a specific unit or type, units or types requiring additional study can be automatically recommended.

[0097] Next, the diagnostic module (336) is configured to analyze the learner's correct and incorrect answer types by classifying them according to objective difficulty levels. It classifies the objective difficulty level of each item evaluated by the objective difficulty evaluation unit (310) into high, medium, and low levels, and can calculate the correct answer rate for each objective difficulty level.

[0098] In the above diagnostic module (336), if the correct answer rate is low even in low-difficulty problems based on the analysis results by difficulty level, it can be determined that there is a lack of basic concepts, and if the correct answer rate is low only in high-difficulty problems, it can be determined that in-depth learning is needed for the relevant unit or type.

[0099] Accordingly, the learning direction of the learner can be set according to the diagnosis result in the above diagnosis module (336).

[0100] Next, the feedback providing unit (340) is configured to provide feedback to compensate for the learner's weaknesses based on the diagnosis results from the learner diagnosis unit (330), and can provide learner-specific feedback that can improve the learner's deficiencies derived through the learner diagnosis unit (330) by utilizing AI functions.

[0101] For example, the feedback providing unit (340) can learn the learner's repetitive error patterns or inefficient solution patterns derived through the learner diagnosis unit (330) and continuously provide feedback that can improve the learner's problem-solving method through machine learning such as reinforcement learning.

[0102] In addition, the feedback providing unit (340) can provide individual customized training content by automatically generating additional learning problems to compensate for the learner's weaknesses and providing them to the learner.

[0103] To explain in more detail, the feedback providing unit (340) may include a problem type determination module (342), a numerical transformation module (344), and a similar problem generation module (346). First, the problem type determination module (342) may select and retrieve math problems from the problem DB (110) of the database (100) to compensate for the learner's weaknesses.

[0104] That is, if the error rate in a specific unit or specific type is high as a result of diagnosis in the above learner diagnosis unit (330), the above problem type determination module (342) can select and retrieve math problems of the unit or type with a high error rate from the problem DB (110) of the database (100) in which math problems are stored separately by unit, type, and difficulty level.

[0105] In addition, the problem type determination module (342) can select a problem of a high difficulty level from the problem DB (110) of the database (100) for a student with a high correct answer rate for a specific type, such as function graph interpretation, and select and retrieve a problem of a low difficulty level from the problem DB (110) of the database (100) for a student with a low correct answer rate for a specific type, such as the application of equations.

[0106] Next, the numerical transformation module (344) is configured to generate similar problems that learners can train to compensate for weaknesses by transforming the numerical values ​​included in the math problem selected by the problem type determination module (342), and can randomly transform the numerical information included in the problem conditions and question content by utilizing AI functions.

[0107] For example, if the math problem selected by the problem type determination module (342) is a geometric sequence type problem such as (a) in FIG. 4, the numeric transformation module (344) can randomly transform the value of b4 = 6 included in the problem condition into c3 = 4, and transform b6 = 3b5 - 24 into a form such as c5 = 2c4 + 10, and at the same time change the value of b7 included in the question content to the value of c6, randomly generate options corresponding to incorrect answers based on the calculation result of c6.

[0108] At this time, the numerical transformation module (344) can maintain a constant problem difficulty by setting the transformed coefficient to an integer when the coefficient included in the problem condition is an integer, and can be configured so that the similar problem generation module (346) described later can form multiple similar problems for a single original problem with different difficulty levels by using methods such as transforming the coefficient into a rational number to adjust the difficulty.

[0109] Next, the similar problem generation module (346) is configured to generate similar problems by applying numerical values ​​modified by the numerical transformation module (344) to a mathematical problem selected from the problem type determination module (342), and the generated similar problems can be saved as digital files in formats that allow text editing, such as PDF, HWP, or web text.

[0110] That is, the above-mentioned similar problem generation module (346) can generate a similar problem as shown in FIG. 4 (b) by applying numerical values ​​modified by the numerical transformation module (344) to the mathematical problem shown in FIG. 4 (a).

[0111] Accordingly, the feedback providing unit (340) can prepare math problems selected by the problem type determination module (342) and similar problems generated by the similar problem generation module (346) in the form of a problem sheet and provide them to the learner through the learner terminal (400), and the learner's problem-solving process can be measured again by the data input unit and transmitted to the main server (300).

[0112] Meanwhile, the feedback providing unit (340) may further include a learning pattern management module (348), and the learning pattern management module (348) may be configured to induce adjustment of the learner's learning pattern when a decrease in the learner's concentration is detected.

[0113] That is, as described above, biometric information generated during the learner's problem-solving process can be collected by the data collection unit (200) and transmitted to the main server (300) in real time. If the biometric information analysis result determines that the learner is in a state of reduced concentration, the learning pattern management module (348) can send a warning signal to the learner's terminal to induce the learner to take an immediate rest or adjust their learning pattern.

[0114] At this time, if the learning pattern management module (348) determines that the learner's concentration has decreased for a certain period of time, it can automatically apply the Pomodoro learning technique, etc., and send an alarm signal through the learner's terminal to allow the learner to take a break for a certain period of time after studying for a certain period of time, thereby enabling the learner to maintain learning efficiency in the long term.

[0115] If the concentration period is repeated without decreasing due to the above short-term measures, the learning pattern management module (348) may provide feedback to improve the learner's health and lifestyle habits, recommend counseling with a psychiatric specialist, or recommend connecting to a psychiatric specialist system to remove mental disorder factors such as ADHD.

[0116] Next, the main server (300) may further include a communication unit (350), and the communication unit (350) is configured to perform wired and wireless communication processes with the database (100) and the learner terminal (400), and various known wired and wireless communication networks such as Ethernet, Internet, WIFI, and LTE may be utilized.

[0117] Next, the learner terminal (400) may be a desktop computer, laptop computer, notebook, smartphone, tablet PC, mobile phone, etc. that is capable of communication and is carried by the learner.

[0118] The above learner terminal (400) is equipped with a communication function and can be connected to the main server (300) via a network, and can receive a survey form for correct / incorrect answer types, a consent form for evaluation of correct / incorrect answer types, the learner's problem-solving analysis results and feedback provided therefrom, provided by the main server (300), or can receive a problem sheet and problem-solving provided by the main server (300) and simultaneously upload the problem sheet with completed solutions to the main server (300) in the form of an image file or a vector file.

[0120] Meanwhile, the method for providing customized mathematics learning based on objective and subjective difficulty evaluation according to the present invention relates to a mathematics learning method that can provide customized mathematics learning tailored to the characteristics of individual learners by comprehensively considering the results of objective and subjective difficulty evaluation using the aforementioned mathematics learning provision system (10). As shown in FIG. 5, the configuration may largely include a data collection step (S10), an objective difficulty evaluation step (S20), a subjective difficulty evaluation step (S30), a learner diagnosis step (S40), and a feedback provision step (S50).

[0121] First, the above data collection step (S10) is a process for collecting biometric data generated during the process of learners solving math problems, and can transmit to the main server (300) images captured by cameras (210) installed in multiple locations on the front and top of the learner to photograph the learner's problem-solving process from different directions, and heart rate measured by a heart rate monitor (220) worn by the learner during the problem-solving process.

[0122] Next, the objective difficulty evaluation step (S20) is a process for evaluating the objective difficulty that can be determined according to the content and format of the math problem provided to the learner, and may include a complexity measurement step (S22), a comparison group verification step (S24), and a first calculation step (S26).

[0123] That is, the complexity measurement step (S22) is a process for measuring the complexity of a math problem provided to a learner by the complexity measurement module (312) of the main server (300) to evaluate the objective difficulty according to the complexity. In the complexity measurement, the number of concepts used in the problem, the proximity between concepts, and computational complexity are considered as described above and can be scored for each item.

[0124] Next, the comparison group verification step (S24) is a process for evaluating objective difficulty by considering problem-solving information of other learners who can be compared with the learner, i.e., comparison groups. By the comparison group verification module (314) of the main server (300), objective difficulty can be evaluated by considering the correct answer rate, average time taken to solve the problem, and error patterns of the comparison groups that solved the problem, and can be scored by item.

[0125] Next, the first calculation step (S26) is a process of quantifying the objective difficulty based on the objective difficulty evaluated through the complexity measurement step (S22) and the comparison group verification step (S24), and the aforementioned formula (1) can be used to quantify the objective difficulty.

[0126] Next, the above-mentioned subjective difficulty evaluation step (S30) is a process for evaluating the subjective difficulty felt by learners during the problem-solving process, and may include a correct / incorrect answer type verification step (S32), a correct / incorrect answer type classification step (S34), a correct / incorrect answer type evaluation and correction step (S36), and a second calculation step (S38).

[0127] To explain in more detail, the correct / incorrect answer type verification step (S32) described above is a process for providing learners with a survey to write the reason for the correct / incorrect answer for each question regarding the problem-solving result through the correct / incorrect answer type verification module (322) of the main server (300) and receiving the written result. As described above, the correct / incorrect answer types for each question are classified into four categories: the case where the correct answer is correct and the understanding is perfect, the case where the correct answer is correct but the understanding is not perfect, the case where the answer is incorrect but the content of the question is understood and the answer was incorrect by mistake, and the case where the answer is incorrect and the content of the question is not perfectly understood. This allows learners to select one of the four correct / incorrect answer types for each question.

[0128] Next, the correct / incorrect answer type classification step (S34) is a process for classifying the correct / incorrect answer types of learners using biometric information-related data collected through the data collection step (S10) that is generated during the process of learners solving math problems. The correct / incorrect answer types classified using biometric information-related data can be used for the purpose of more accurately evaluating the learners' correct / incorrect answer types by comparing them with the correct / incorrect answer types directly written by the learners collected through the correct / incorrect answer type verification step (S32).

[0129] In the above correct / incorrect answer type classification step (S34), as described above, the correct / incorrect answer types can be classified into six types by considering the learner's biometric information and the time required to solve the problem, and the learner's biometric information can be used to automatically detect the section where the learner's concentration decreases during the entire problem-solving process, and the subjective difficulty evaluation of the math problem being solved in that section can be excluded.

[0130] Next, the correct / incorrect answer type evaluation and correction step (S36) is a process for more accurately evaluating the subjective difficulty felt by learners by comparing the correct / incorrect answer type classification results generated by the correct / incorrect answer type verification step (S32) and the correct / incorrect answer type classification step (S34), respectively. When there is a difference between the correct / incorrect answer type written by the learner and the correct / incorrect answer type written through biometric information analysis, the correct / incorrect answer type evaluation result including the reason for the classification of the correct / incorrect answer type through biometric information analysis can be transmitted to the learner's terminal.

[0131] In addition, in the above correct / incorrect answer type evaluation and correction step (S36), if the learner does not agree to the classification and evaluation of correct / incorrect answer types created through biometric information analysis, the correct / incorrect answer type created by the learner is determined to be the learner's actual skill level and is finally selected, and the classification of correct / incorrect answer types for each question is finally corrected and stored in the learner DB (120) of the database (100).

[0132] Next, the second calculation step (S38) is a process for calculating the learner's subjective difficulty level for each question by converting the correct / incorrect answer type, which is finally corrected through the correct / incorrect answer type evaluation and correction step (S36), into an evaluation index. In the second calculation module (328) of the main server (300), the correct / incorrect answer type classified into 6 types in the correct / incorrect answer type classification step (S34) can be converted into an evaluation index to evaluate the subjective difficulty level for each question.

[0133] Next, the learner diagnosis stage (S40) is configured to diagnose the learner's level by unit and type based on the objective difficulty and subjective difficulty evaluated through the objective difficulty evaluation stage (S20) and the subjective difficulty evaluation stage (S30), and may include an incorrect answer type analysis stage (S42), an achievement evaluation stage (S44), and a diagnosis stage (S46).

[0134] At this time, the process performed in the above-mentioned error type analysis step (S42), achievement evaluation step (S44), and diagnosis step (S46), and the technical configuration for performing the said process may be the same as described in the learner diagnosis unit (330) of the mathematics learning provision system (10) described above, so a more detailed explanation thereof will be omitted.

[0135] Next, the feedback provision step (S50) is a process for providing feedback to compensate for the learner's weaknesses based on the diagnosis results from the learner diagnosis step (S40), and can provide learner-specific feedback that can improve the learner's deficiencies identified through the learner diagnosis step (S40) by utilizing AI functions.

[0136] The above feedback provision step (S50) may include a problem type determination step (S52), a numerical transformation step (S54), a similar problem generation step (S56), and a learning pattern management step (S58). Likewise, the process performed in the above steps and the technical configuration for performing the process may be the same as described in the feedback provision unit (340) of the mathematics learning provision system (10) described above, so a more detailed explanation thereof will be omitted.

[0137] Accordingly, the system and method for providing customized mathematics learning based on objective and subjective difficulty evaluation according to the present invention as described above has various advantages, such as the ability to evaluate objective and subjective difficulty in mathematics learning and provide customized mathematics learning tailored to the characteristics of individual learners by comprehensively considering the evaluation results, thereby increasing learners' motivation and allowing them to feel a sense of accomplishment, thereby maximizing learning efficiency, analyzing the learner's problem-solving process and results to evaluate the difficulty experienced by the learner in real time, and providing optimal feedback tailored to the learner's condition by considering various biological reactions of the learner that occur during the problem-solving process, as well as improving the learner's self-awareness accuracy by comparing the learner's correct and incorrect answer types with the degree of cognitive confidence, and adjusting learning patterns by detecting patterns of decreased concentration through biological reaction analysis, while simultaneously recommending expert counseling when patterns of decreased concentration are continuously repeated to resolve the learner's fundamental learning obstacles and inducing the formation of sustainable and healthy learning habits.

[0139] The systems and methods described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. The processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0140] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave in order to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0141] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and may be recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to a person with ordinary knowledge in the field of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory.

[0142] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results can be achieved even if the described techniques are performed in a different order than described, and / or the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents. Explanation of the symbols

[0144] 10: Math learning provision system 100 : Database 110 : Problem DB 120 : Learner DB 200 : Data Collection Department 210 : Camera 220 : Heart rate monitor 300 : Main Server 310 : Objective Difficulty Evaluation Department 312 : Complexity Measurement Module 314 : Comparison group verification module 316 : 1st computation module 320 : Subjective Difficulty Evaluation Section 322 : Correct / Incorrect Answer Type Check Module 324 : Correct / Incorrect Answer Type Classification Module 326 : Correction Module for True / Incorrect Answer Type Evaluation 328 : Second arithmetic module 330 : Learner Diagnostic Section 332 : Incorrect Answer Type Analysis Module 334 : Achievement Assessment Module 336 : Diagnostic Module 340 : Feedback Provider 342 : Problem Type Determination Module 344 : Numerical transformation module 346 : Similar Problem Generation Module 348 : Learning Pattern Management Module 350 : Communications Department S10: Data collection stage S20: Objective difficulty evaluation level S22: Complexity measurement step S24: Comparison group verification step S26: First operation step S30: Subjective difficulty evaluation level S32: Correct / Incorrect Answer Type Verification Step S34: Classification stage of correct / incorrect answer types S36: Correction and evaluation of correct / incorrect answer types S38: Second operation step S40: Learner Diagnostic Stage S42: Error Type Analysis Stage S44: Achievement Evaluation Stage S46 : Diagnosis stage S50: Feedback provision stage S52: Problem Type Determination Stage S54: Numerical transformation stage S56: Similar problem generation stage S58: Learning Pattern Management Stage

Claims

Claim 1 A mathematics learning provision system comprising: a database that stores mathematics problems to be provided to learners, classified by unit, type, and difficulty level; a data collection unit that collects biometric data generated during the process of a learner solving mathematics problems; and a main server connected via a network to the database and the data collection unit, which evaluates the objective difficulty defined by the content and format of the mathematics problems and the subjective difficulty individually felt by the learner during the problem-solving process, and provides customized mathematics learning tailored to the characteristics of individual learners by comprehensively considering the evaluation results; a mathematics learning provision system tailored to learners based on objective and subjective difficulty evaluations. Claim 2 In claim 1, the main server comprises: an objective difficulty evaluation unit that evaluates objective difficulty determined according to the characteristics of the math problems provided to the learner; a subjective difficulty evaluation unit that evaluates subjective difficulty felt by learners during the problem-solving process using the learner's biometric data collected through the data collection unit; a learner diagnosis unit that diagnoses the learner's level by unit and type based on the objective difficulty and subjective difficulty evaluated through the objective difficulty evaluation unit and the subjective difficulty evaluation unit; and a feedback provision unit that provides feedback to compensate for the learner's weaknesses based on the diagnosis results from the learner diagnosis unit; thereby providing a learner-customized math learning system based on objective and subjective difficulty evaluations. Claim 3 In claim 2, the objective difficulty evaluation unit comprises: a complexity measurement module that measures the complexity of a math problem provided to a learner and evaluates the objective difficulty according to the complexity; a comparison group verification module that evaluates the objective difficulty of a math problem by considering problem-solving information of other learners; and a first calculation module that quantifies the objective difficulty based on the objective difficulty evaluated through the complexity measurement module and the comparison group verification module; thereby providing a learner-customized math learning system based on objective and subjective difficulty evaluation. Claim 4 In claim 2, the subjective difficulty evaluation unit comprises: a correct / incorrect answer type verification module that provides learners with a survey to write the reasons for correct / incorrect answers for each problem regarding problem-solving results and receives the written results; a correct / incorrect answer type classification module that classifies the learners' correct / incorrect answer types using biometric information-related data collected through the data collection unit; a correct / incorrect answer type evaluation and correction module that compares and evaluates the classification results of correct / incorrect answer types generated by the correct / incorrect answer type verification module and the correct / incorrect answer type classification module, respectively, and corrects the correct / incorrect answer types by confirming whether the learners consent to the evaluation; and a second calculation module that converts the correct / incorrect answer types corrected through the correct / incorrect answer type evaluation and correction module into an evaluation index to calculate the learner's subjective difficulty for each item; a system for providing customized mathematics learning for learners based on objective and subjective difficulty evaluations. Claim 5 A system for providing customized mathematics learning based on objective and subjective difficulty evaluation, characterized in that, in the third paragraph, the correct / incorrect answer type classification module automatically detects sections where the learner's concentration decreases during the entire problem-solving process from the learner's biometric information, and excludes subjective difficulty evaluations of the mathematics problems solved in those sections. Claim 6 In Clause 2, the learner diagnostic unit comprises: an error type analysis module that analyzes the learner's error types in detail based on the learner's subjective difficulty level for each item evaluated by the subjective difficulty evaluation unit; an achievement evaluation module that evaluates the learner's achievement level by unit and type by calculating the correct answer rate by unit and type of math problems solved by the learner; and a diagnostic module that analyzes the learner's correct and incorrect answer types by objective difficulty level by calculating the correct answer rate by objective difficulty level evaluated by the objective difficulty evaluation unit; thereby providing a learner-customized math learning system based on objective and subjective difficulty evaluations. Claim 7 A method for providing customized mathematics learning for learners, comprising: a data collection step for collecting biometric data generated during the process of learners solving mathematics problems; an objective difficulty evaluation step for evaluating objective difficulty determined according to the characteristics of the mathematics problems provided to the learners; a subjective difficulty evaluation step for evaluating subjective difficulty felt by learners during the problem-solving process using the learners' biometric data collected through the data collection unit; a learner diagnosis step for diagnosing the learners' level by unit and type based on the objective difficulty and subjective difficulty evaluated through the objective difficulty evaluation step and the subjective difficulty evaluation step; and a feedback provision step for providing feedback to compensate for the learners' weaknesses based on the diagnosis results from the learner diagnosis step; comprising a method for providing customized mathematics learning for learners based on objective and subjective difficulty evaluations.

Images