Method for generating new learning question

Abstract

Disclosed, according to one embodiment of the present disclosure, is a method, performed by a computing device, for generating a new learning question. The method may comprise the steps of: obtaining a plurality of pieces of information related to a learning question; converting each of the plurality of pieces of information into a first format; converting each of the plurality of pieces of information converted into the first format into a second format; decomposing elements included in each of the plurality of pieces of information converted into the second format; and generating a new learning question by using the decomposed elements.

Description

How to create new learning questions

[0001] The present invention relates to a method for generating new learning questions, and more specifically, to a technology for automatically generating new learning questions by extracting information such as problems, solutions, and correct answers from learning questions, such as mathematical problems, and structurally transforming said information.

[0002] Conventional automatic learning question generation technology primarily generated new questions by converting existing problems stored in a database, searching for similar questions, and changing variable ranges or partially modifying numerical values.

[0003] This approach is limited to simple formula substitutions or value changes because it does not fundamentally understand the mathematical structure of the items, and it has the limitation of being difficult to generate new types of items.

[0004] Korean Registered Patent No. 10-1620818 (May 6, 2016) discloses a method for providing a service for automatically generating mathematical problems.

[0005] The present disclosure aims to provide a method for generating new learning questions that can automatically generate new learning questions within an acceptable range in an educational curriculum by extracting information such as problems, solutions, and answers included in learning questions using artificial intelligence, converting it into LaTeX capable of mathematical expression, restructuring it into a format capable of structural expression (e.g., JSON), and analyzing and decomposing the relationships between formulas, symbols, variables, and text.

[0006] Meanwhile, the technical problem that the present disclosure aims to solve is not limited to the technical problem mentioned above, and various technical problems may be included within the scope obvious to a person skilled in the art from the contents described below.

[0007] A method for generating a new learning item performed by a computing device according to an embodiment of the present disclosure for realizing the aforementioned task is disclosed. The method may include the steps of: acquiring a plurality of pieces of information related to a learning item; converting each of the plurality of pieces of information into a first standard; converting each of the plurality of pieces of information converted into the first standard into a second standard; decomposing elements included in each of the plurality of pieces of information converted into the second standard; and generating a new learning item by utilizing the decomposed elements.

[0008] In one embodiment, the step of converting each of the plurality of pieces of information into the first standard may include: a step of converting elements other than text included in each of the plurality of pieces of information acquired as an image type into the first standard; or a step of converting elements other than text included in each of the plurality of pieces of information acquired as a PDF (Portable Document Format) type into the first standard using an artificial intelligence model.

[0009] In one embodiment, the step of converting each of the plurality of pieces of information converted to the first standard into the second standard may include the step of converting the text and elements other than the text included in each of the plurality of pieces of information converted to the first standard into the second standard.

[0010] In one embodiment, the learning item is a learning item related to mathematics, and the elements other than the text may include mathematical elements including any one of numbers, formulas, symbols, variables, or diagrams.

[0011] In one embodiment, the step of decomposing elements included in each of the plurality of pieces of information converted to the second standard may include: a step of analyzing the relationship between the text and the mathematical elements included in each of the plurality of pieces of information converted to the second standard; and a step of decomposing the mathematical elements based on the analyzed relationship.

[0012] In one embodiment, the step of generating a new learning item using the decomposed elements may include: a step of variableizing the decomposed mathematical elements; a step of dividing the variableized elements into predefined window sizes; a step of concatenating the divided variableized elements to generate a dataset for generating the new learning item; and a step of generating the new learning item based on the dataset using an artificial intelligence model.

[0013] In one embodiment, the step of generating a new learning item using the decomposed elements may further include: a step of obtaining educational course information associated with the learning item; a step of setting constraints for generating the new learning item based on the educational course information; and a step of generating the new learning item based on the set constraints.

[0014] In one embodiment, the first specification may be a LaTeX specification capable of mathematical expression, and the second specification may be a specification capable of structural expression.

[0015] In one embodiment, a plurality of pieces of information related to the learning item may include a problem, a solution, and a correct answer.

[0016] A computer program stored on a computer-readable storage medium is disclosed in accordance with one embodiment of the present disclosure for realizing the aforementioned task. When the computer program is executed on one or more processors, the one or more processors are configured to perform the following operations for generating a new learning item, wherein the operations may include: an operation of acquiring a plurality of pieces of information related to a learning item; an operation of converting each of the plurality of pieces of information into a first standard; an operation of converting each of the plurality of pieces of information converted into the first standard into a second standard; an operation of decomposing elements included in each of the plurality of pieces of information converted into the second standard; and an operation of generating a new learning item by utilizing the decomposed elements.

[0017] In one embodiment, the operation of converting each of the plurality of pieces of information into the first standard may include: an operation of converting elements other than text included in each of the plurality of pieces of information acquired as an image type into the first standard; or an operation of converting elements other than text included in each of the plurality of pieces of information acquired as a PDF (Portable Document Format) type into the first standard using an artificial intelligence model.

[0018] In one embodiment, the step of converting each of the plurality of pieces of information converted to the first standard into the second standard may include the operation of converting text and elements other than text included in each of the plurality of pieces of information converted to the first standard into the second standard.

[0019] In one embodiment, the learning item is a learning item related to mathematics, and the elements other than the text may include mathematical elements including any one of numbers, formulas, symbols, variables, or diagrams.

[0020] In one embodiment, the operation of decomposing elements included in each of the plurality of pieces of information converted to the second standard may include: an operation of analyzing the relationship between the text and the mathematical elements included in each of the plurality of pieces of information converted to the second standard; and an operation of decomposing the mathematical elements based on the analyzed relationship.

[0021] In one embodiment, the operation of generating a new learning item using the decomposed elements may include: the operation of variableizing the decomposed mathematical elements; the operation of dividing the variableized elements into predefined window sizes; the operation of concatenating the divided variableized elements to generate a dataset for generating the new learning item; and the operation of generating the new learning item based on the dataset using an artificial intelligence model.

[0022] In one embodiment, the operation of generating a new learning item using the decomposed elements may further include: the operation of obtaining educational course information associated with the learning item; the operation of setting constraints for generating the new learning item based on the educational course information; and the operation of generating the new learning item based on the set constraints.

[0023] In one embodiment, the first specification may be a LaTeX specification capable of mathematical expression, and the second specification may be a specification capable of structural expression.

[0024] In one embodiment, a plurality of pieces of information related to the learning item may include a problem, a solution, and a correct answer.

[0025] A computing device according to one embodiment of the present disclosure for realizing the aforementioned task is disclosed. The device comprises at least one processor; and memory, wherein the at least one processor may be configured to acquire a plurality of pieces of information related to a learning item; convert each of the plurality of pieces of information converted to the first specification into a first specification; convert each of the plurality of pieces of information converted to the first specification into a second specification; decompose elements included in each of the plurality of pieces of information converted to the second specification; and generate a new learning item by utilizing the decomposed elements.

[0026] In one embodiment, the at least one processor may include an operation of converting non-text elements included in each of the plurality of pieces of information acquired as an image type into the first standard; or an operation of converting non-text elements included in each of the plurality of pieces of information acquired as a PDF (Portable Document Format) type into the first standard using an artificial intelligence model.

[0027] In one embodiment, the at least one processor may be configured to convert text and elements other than text included in each of the plurality of pieces of information converted to the first standard into the second standard.

[0028] In one embodiment, the learning item is a learning item related to mathematics, and the elements other than the text may include mathematical elements including any one of numbers, formulas, symbols, variables, or diagrams.

[0029] In one embodiment, the at least one processor may be configured to analyze the relationship between the text and the mathematical elements included in each of the plurality of pieces of information converted into the second specification; and to decompose the mathematical elements based on the analyzed relationship.

[0030] In one embodiment, the at least one processor may be configured to variableize the decomposed mathematical elements; divide the variableized elements into predefined window sizes; concatenate the divided variableized elements to generate a dataset for generating the new learning item; and utilize an artificial intelligence model to generate the new learning item based on the dataset.

[0031] In one embodiment, the at least one processor may be further configured to acquire educational course information associated with the learning item; set constraints for generating the new learning item based on the educational course information; and generate the new learning item based on the set constraints.

[0032] In one embodiment, the first specification may be a LaTeX specification capable of mathematical expression, and the second specification may be a specification capable of structural expression.

[0033] In one embodiment, a plurality of pieces of information related to the learning item may include a problem, a solution, and a correct answer.

[0034] The present disclosure extracts problem, solution, and answer information from learning items, converts them into a first specification capable of mathematical expression and a second specification capable of structural expression, analyzes the relationships between elements to construct a dataset capable of learning by artificial intelligence, and then automatically generates new learning items according to curriculum-based constraints, thereby enabling efficient restructuring of even items containing diagrams and generating learning items of various levels without a database.

[0035] In addition, the present disclosure improves the level of automation for generating learning questions and enables the efficient generation of new questions by level and unit that are suitable for the curriculum.

[0036] Meanwhile, the effects of the present disclosure are not limited to those mentioned above, and various effects may be included within the scope obvious to a person skilled in the art from the contents described below.

[0037] FIG. 1 is a block diagram of a computing device for generating a new learning item according to one embodiment of the present disclosure.

[0038] FIG. 2 illustrates an exemplary structure of an artificial intelligence-based model according to one embodiment of the present disclosure.

[0039] FIG. 3 is a flowchart illustrating a method for generating a new learning item according to one embodiment of the present disclosure.

[0040] FIG. 4 is a diagram schematically illustrating the operation of generating a new learning item according to one embodiment of the present disclosure.

[0041] FIG. 5 is a brief and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0042] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to provide an understanding of the present disclosure. However, it is evident that these embodiments can be practiced without such specific descriptions.

[0043] As used herein, terms such as “component,” “module,” “system,” etc. refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or executions of software. For example, a component may be, but is not limited to, a procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer. For example, both an application executed on a computing device and the computing device itself may be a component. One or more components may reside within a processor and / or an execution thread. A component may be localized within a single computer. A component may be distributed among two or more computers. Additionally, these components may be executed from various computer-readable media having various data structures stored therein. Components may communicate through local and / or remote processes, for example, according to signals having one or more data packets (e.g., data from a component interacting with another component in a local system or distributed system, and / or data transmitted through signals to other systems and networks such as the Internet).

[0044] Furthermore, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related items.

[0045] Additionally, the terms “comprising” and / or “comprising” should be understood to mean that such features and / or components are present. However, the terms “comprising” and / or “comprising” should be understood not to exclude the presence or addition of one or more other features, components and / or groups thereof. Furthermore, unless otherwise specified or clearly evident from the context to indicate a singular form, the singular in this specification and claims should generally be interpreted to mean “one or more.”

[0046] And, the term "at least one of A or B" should be interpreted to mean "a case including only A," "a case including only B," or "a combination of A and B."

[0047] Those skilled in the art should recognize that the various exemplary logical blocks, configurations, modules, circuits, means, logics, and algorithmic steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or a combination of both. To clearly exemplify the interchangeability of hardware and software, various exemplary components, blocks, configurations, means, logics, modules, circuits, and steps have been generally described above in terms of their functionality. Whether such functionality is implemented in hardware or software depends on the specific application and design constraints imposed on the overall system. Skilled technicians may implement the described functionality in various ways for each specific application. However, such decisions regarding implementation should not be construed as going beyond the scope of this disclosure.

[0048]

[0049] FIG. 1 is a block diagram of a computing device for generating a new learning item according to one embodiment of the present disclosure.

[0050] The configuration of the computing device (100) illustrated in FIG. 1 is merely a simplified example. In one embodiment of the present disclosure, the computing device (100) may include other configurations for performing the computing environment of the computing device (100), and only some of the disclosed configurations may constitute the computing device (100).

[0051] The computing device (100) may include a processor (110), memory (130), and a network unit (150).

[0052] The processor (110) may be composed of one or more cores and may include processors for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. The processor (110) may read a computer program stored in memory (130) and perform data processing for machine learning according to one embodiment of the present disclosure. According to one embodiment of the present disclosure, the processor (110) may perform operations for learning a neural network. The processor (110) may perform calculations for learning a neural network, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (110) may process the learning of a network function. For example, a CPU and a GPGPU can work together to process the learning of a network function and data classification using the network function. Additionally, in one embodiment of the present disclosure, processors of a plurality of computing devices can be used together to process the learning of a network function and data classification using the network function. Furthermore, a computer program executed on a computing device according to one embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

[0053] According to one embodiment of the present disclosure, the memory (130) can store any form of information generated or determined by the processor (110) and any form of information received by the network unit (150).

[0054] According to one embodiment of the present disclosure, the memory (130) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, a magnetic disk, and an optical disk. The computing device (100) may operate in conjunction with web storage that performs the storage function of the memory (130) on the internet. The description of the memory described above is merely an example and the present disclosure is not limited thereto.

[0055] A network unit (150) according to one embodiment of the present disclosure can use various wired communication systems such as a public switched telephone network (PSTN), xDSL (x Digital Subscriber Line), RADSL (Rate Adaptive DSL), MDSL (Multi Rate DSL), VDSL (Very High Speed ​​DSL), UADSL (Universal Asymmetric DSL), HDSL (High Bit Rate DSL), and a local area network (LAN).

[0056] In addition, the network unit (150) presented in this specification may use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA), and other systems.

[0057] In the present disclosure, the network unit (150) can be configured regardless of the communication mode, such as wired and wireless, and can be configured as various communication networks such as a Local Area Network (LAN), a Personal Area Network (PAN), and a Wide Area Network (WAN). In addition, the network may be a known World Wide Web (WWW) and may utilize wireless transmission technology used for short-range communication, such as Infrared Data Association (IrDA) or Bluetooth.

[0058] The technologies described in this specification can be used not only in the networks mentioned above but also in other networks.

[0059]

[0060] FIG. 2 illustrates an exemplary structure of an artificial intelligence-based model according to one embodiment of the present disclosure.

[0061] Throughout this specification, artificial intelligence model, artificial intelligence-based model, computational model, neural network, network function, and neural network may be used interchangeably.

[0062] A neural network can be composed of a set of interconnected computational units that may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node. The nodes (or neurons) constituting neural networks may be interconnected by one or more links.

[0063] In a neural network, one or more nodes connected via links can form relative input and output node relationships. The concepts of input and output nodes are relative; any node in an output node relationship with respect to one node may be in an input node relationship with respect to another node, and vice versa. As described above, the input node versus output node relationship can be generated based on links. One or more output nodes may be connected to a single input node via links, and vice versa.

[0064] In a relationship between an input node and an output node connected through a single link, the value of the output node's data can be determined based on the data input to the input node. Here, the link interconnecting the input node and the output node may have a weight. The weight can be variable and can be varied by the user or an algorithm to enable the neural network to perform the desired function. For example, if one or more input nodes are interconnected to a single output node by respective links, the output node's value can be determined based on the values ​​input to the input nodes connected to the output node and the weights set on the links corresponding to each input node.

[0065] As described above, a neural network consists of one or more nodes interconnected through one or more links, forming input-output node relationships within the network. The characteristics of a neural network can be determined by the number of nodes and links within the network, the relationships between the nodes and links, and the weight values ​​assigned to each link. For example, if two neural networks exist with the same number of nodes and links but different weight values ​​for the links, the two neural networks may be recognized as different from each other.

[0066] A neural network can be composed of a set of one or more nodes. A subset of nodes constituting a neural network can form a layer. Some of the nodes constituting a neural network can form a layer based on their distances from an initial input node. For example, a set of nodes with a distance of n from an initial input node can form n layers. The distance from the initial input node can be defined by the minimum number of links that must be traversed to reach that node from the initial input node. However, this definition of a layer is arbitrary for illustrative purposes, and the degree of a layer within a neural network can be defined in a way different from that described above. For example, a layer of nodes may be defined by its distance from a final output node.

[0067] In one embodiment of the present disclosure, a set of neurons or nodes may be defined by the expression a layer.

[0068] Initial input nodes may refer to one or more nodes within a neural network to which data is directly input without passing through links in their relationships with other nodes. Alternatively, in terms of link-based relationships between nodes within the neural network, they may refer to nodes that do not have other input nodes connected by links. Similarly, final output nodes may refer to one or more nodes within a neural network that do not have output nodes in their relationships with other nodes. Furthermore, hidden nodes may refer to nodes constituting the neural network that are neither initial input nodes nor final output nodes.

[0069] A neural network according to one embodiment of the present disclosure may have the number of nodes in the input layer equal to the number of nodes in the output layer, and may be a neural network in which the number of nodes decreases and then increases again as it progresses from the input layer to the hidden layer. Additionally, a neural network according to another embodiment of the present disclosure may have the number of nodes in the input layer less than the number of nodes in the output layer, and may be a neural network in which the number of nodes increases as it progresses from the input layer to the hidden layer. Additionally, a neural network according to yet another embodiment of the present disclosure may have the number of nodes in the input layer greater than the number of nodes in the output layer, and may be a neural network in which the number of nodes decreases as it progresses from the input layer to the hidden layer. A neural network according to yet another embodiment of the present disclosure may be a neural network in which the above-described neural networks are combined.

[0070] An artificial intelligence-based model according to one embodiment of the present disclosure may include a deep neural network (DNN). A deep neural network may refer to a neural network that includes a plurality of hidden layers in addition to an input layer and an output layer. By using a deep neural network, latent structures of data can be identified. That is, latent structures of photos, text, video, voice, protein sequence structures, gene sequence structures, peptide sequence structures, music (e.g., what objects are in the photo, what is the content and emotion of the text, what is the content and emotion of the voice, etc.), and / or binding affinity between peptides and MHCs can be identified. Deep neural networks may include convolutional neural networks (CNN), recurrent neural networks (RNN), autoencoders, restricted Boltzmann machines (RBM), deep belief networks (DBN), Q networks, U networks, Siamese networks, Generative Adversarial Networks (GAN), Transformers, etc. The description of deep neural networks described above is merely illustrative and the present disclosure is not limited thereto.

[0071] The artificial intelligence-based model of the present disclosure may be represented by a network structure of any structure described above, including an input layer, a hidden layer, and an output layer.

[0072] A neural network that can be used in an artificial intelligence-based model of the present disclosure may be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, transfer learning, active learning, or reinforcement learning. Training of a neural network may be a process of applying knowledge to the neural network to perform a specific operation.

[0073] Neural networks can be trained to minimize the error in their output. The training process involves repeatedly inputting training data into the network, calculating the error between the network's output and the target for the training data, and updating the weights of each node by backpropagating the error from the output layer to the input layer in a direction that reduces the error. In supervised learning, training data is used where the correct answer is labeled for each data point (i.e., labeled training data), whereas in unsupervised learning, the correct answer may not be labeled for each training data point. For instance, in the case of supervised learning for data classification, the training data may consist of data where each training point is labeled with a category. Labeled training data is input into the neural network, and the error can be calculated by comparing the network's output (category) with the labels of the training data. As another example, in the case of unsupervised learning for data classification, the error can be calculated by comparing the input training data with the neural network's output. The calculated error is backpropagated in the neural network (i.e., from the output layer to the input layer), and through backpropagation, the connection weights of each node in each layer of the neural network can be updated. The amount of change in the connection weights of each node being updated can be determined by the learning rate. The neural network's calculation of the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle. For example, a high learning rate can be used in the early stages of training to quickly achieve a certain level of performance and increase efficiency, while a low learning rate can be used in the later stages to improve accuracy.

[0074] In the training of neural networks, the training data is generally a subset of the real-world data (i.e., the data intended to be processed using the trained neural network). Consequently, a training cycle may exist where errors decrease on the training data but increase on the real-world data. Overfitting is a phenomenon where the network learns excessively on the training data, leading to increased errors on the real-world data. For example, a neural network trained on yellow cats might fail to recognize cats when seeing anything other than yellow, which can be considered a type of overfitting. Overfitting can act as a cause for increased errors in machine learning algorithms. Various optimization methods can be used to prevent this overfitting. To prevent overfitting, methods such as increasing the training data, regularization, dropout (which disables some nodes in the network during training), and the use of batch normalization layers can be applied.

[0075]

[0076] FIG. 3 is a flowchart illustrating a method for generating a new learning item according to one embodiment of the present disclosure. For reference, the method for generating a new learning item may be performed by a computing device (100).

[0077]

[0078] According to one embodiment of the present disclosure, a computing device (100) may acquire a plurality of pieces of information related to a learning question (S110). The plurality of pieces of information related to the learning question may include a problem, a solution, and a correct answer. The plurality of pieces of information related to the learning question may include various visual elements having mathematical meaning, such as numbers, formulas, symbols, variables, shapes, graphs, tables, and coordinate planes, which are included in the problem, solution, and correct answer. The learning question mentioned below may be a learning question related to mathematics. However, it is not limited thereto, and the learning question may include questions in subjects capable of mathematical expression, such as mathematics and science.

[0079] The computing device (100) can receive multiple pieces of information related to learning questions in the form of uploaded image files, scan data, or PDF files from a user terminal. In this process, the computing device (100) can analyze the metadata of the files to obtain classification information such as the type, subject, unit, and difficulty level of the questions, and may additionally collect auxiliary information from an external database (e.g., a learning content server, a question bank, etc.) as needed.

[0080]

[0081] According to one embodiment of the present disclosure, a computing device (100) can convert each of a plurality of pieces of information into a first specification (S120). The first specification may be a LaTeX specification capable of mathematical expression. The computing device (100) can take the original data of a learning question obtained in step S110 (e.g., image, PDF, etc.) as input, recognize elements having mathematical meaning within the question, and convert them into a string of the first specification (LaTeX format). By converting each of the plurality of pieces of information into the first specification, the computing device (100) can express visual representations such as mathematical symbols, formulas, fractions, exponents, roots, etc., in a standardized text-based formula language. The plurality of pieces of information (LaTeX data) converted into the first specification can be used as an intermediate representation to be converted into a second specification capable of structural expression (e.g., JSON, XML, etc.) in a subsequent step (S130). The computing device (100) can convert each of the problem, solution, and answer into a first standard. The computing device (100) can recognize and convert into a first standard diagram, such as a table, building blocks, two-dimensional shapes, three-dimensional shapes, a coordinate plane (graph), a box plot, a calendar, a clock, a line graph, a pie chart, a bar graph, a bar graph, a set, etc., used in mathematics subjects, included in each of the problem, solution, and answer.

[0082] Meanwhile, elements other than text mentioned below may include mathematical elements comprising any one of numbers, formulas, symbols, variables, or diagrams. For example, diagrams may include shapes, graphs, tables, coordinate planes, etc.

[0083] According to one embodiment, a computing device (100) can convert non-text elements included in each of the plurality of pieces of information acquired as an image type into a first standard. The computing device (100) can analyze pixel data within an image to segment problem, solution, and answer areas, and apply an optical character recognition (OCR) engine and a mathematical formula recognition model (Math OCR) to non-text areas (formulas, symbols, shapes, etc.). The computing device (100) may also use a string mapping table and a mathematical formula structure recognition algorithm to convert the recognized mathematical elements into a first standard (LaTeX standard). For example, an image in the form of a fraction can be converted into the form / frac{a}{b}, a square expression into the form x^{2}, and a square root expression into the form / sqrt{x}. The computing device (100) can also convert a question acquired in the form of an image into a text-based standard while maintaining its mathematical expression. For example, the computing device (100) can convert non-text elements into a first standard if non-text elements are included in each of the multiple pieces of information. The computing device (100) can convert non-text elements included in the problem and solution into a first standard if non-text elements are included only in the problem and solution.

[0084] According to one embodiment, a computing device (100) can utilize an artificial intelligence model to convert elements other than text included in each of the multiple pieces of information obtained in PDF (Portable Document Format) type into a first standard. The computing device (100) may use a layout analyzer or an artificial intelligence model for document recognition to analyze the structure of questions within the PDF. The artificial intelligence model can classify objects (e.g., text blocks, images, shapes, etc.) within each page of the PDF, automatically detect the problem area, solution area, and correct answer area within the question, and then recognize mathematical elements in each area to convert them into a first standard (LaTeX standard). For example, areas marked as “mathematical objects” within the PDF can be parsed at the symbol level and converted into LaTeX commands such as / sum, / int, / frac, and graph or shape objects can have their coordinate and label information extracted and be converted into LaTeX tikz or pgfplots formats. This AI-based conversion method enables more precise area-unit recognition than image forms and can automatically subdivide complex item structures to improve the efficiency of structural analysis in subsequent steps (S130).

[0085]

[0086] According to one embodiment of the present disclosure, a computing device (100) can convert each of the plurality of pieces of information converted into a first specification into a second specification (S130). The second specification may be a specification capable of structural expression. The first specification is a LaTeX format capable of mathematical expression, in which expressions such as formulas, symbols, variables, and diagrams are defined as a text-based formula language, but does not include hierarchical information indicating the overall structure of the question or the relationships between elements. Therefore, the computing device (100) can explicitly express the semantic relationships between each component within the question by converting such LaTeX-based expressions into a second specification (e.g., JSON, XML, etc.) that can be structurally analyzed by a machine. The computing device (100) can recognize diagrammatic content included in the problem, solution, and answer, etc., and extract it into a second specification (e.g., JSON, XML, etc.) which is its own specification.

[0087] According to one embodiment, the computing device (100) can convert text and non-text elements included in each of the plurality of pieces of information converted to a first standard into a second standard. The computing device (100) can convert a “problem” converted to a first standard into a second standard capable of structural representation. For example, the computing device (100) can separate the text information (problem description) and mathematical formula (LaTeX expression) of a question and store them as respective attributes within a “problem” object. The problem object may include fields such as the context of the problem, the formula used, the question content (question_text), and input variables. For example, a question such as “This function represents the total number of participants when the number of classes participating in the sports day is x” can be converted into a second standard. Additionally, the computing device (100) can convert a “solution” converted to a first standard into a second standard capable of structural representation. The solution process can be separated into step-by-step calculation procedures and expressed as a procedural structure capable of AI learning. For example, the solution expression “f(12)=12(12)+6=150” can be converted into a second specification by being separated into the order of substitution, calculation, and simplification. The computing device (100) can convert the “correct answer” converted into the first specification into a second specification capable of structural representation. The correct answer object may include fields for the value of the correct answer, the type of the correct answer, and the basis from which the correct answer was derived (derived_from).

[0088] According to one embodiment, the computing device (100) can integrate the converted problem, solution, and answer data into a “question set” structure, which is a higher-level object. At this time, the problem-solution-answer have a logically hierarchical relationship, and each lower-level object can be mutually referenced while maintaining independent attributes. For example, the “problem,” “solution,” and “answer” of the question can each be defined as a higher-level node, and within each node, detailed elements such as sentences, formulas, symbols, variables, and graphs can be included as lower-level nodes. In this process, the computing device (100) can analyze LaTeX grammar to hierarchically define the structure of each formula (e.g., fraction, exponent, root, etc.), the role of symbols (e.g., operator, comparator, etc.), and the relationship between text and formula (e.g., the relationship of including formulas within a sentence such as “Find the following formula)).

[0089] Alternatively, in the case of a mathematical question containing a diagram, the computing device (100) can separate non-text elements such as shapes, tables, and graphs into object units and structure attribute information (e.g., coordinate values, axis units, data points, etc.) of each object into a separate field within the second specification. Additionally, the computing device (100) can express the connection relationship between the text elements and formula elements of the question in the form of a reference during the second specification conversion process. For example, if a specific variable (x) that appears in the body of the question is used again in the formula during the solution step, a unique identifier (ID) can be assigned to this variable object to enable variable tracking and semantic interpretation within the question.

[0090] According to one embodiment of the present disclosure, a computing device (100) can decompose elements included in each of the plurality of pieces of information converted into a second standard (S140). The computing device (100) can analyze the relationship between text and mathematical elements included in each of the plurality of pieces of information converted into a second standard. The relationship analysis may be a process for identifying semantic associations between text and formulas, symbols, and variables within the structural objects of each problem, solution, and answer. For example, when a sentence “This function represents the total number of participants when the number of classes participating in the sports day is x” and a formula “f(x)=12x+6” exist together, the computing device (100) can recognize that the variable x in the sentence represents the 'number of classes' and the term 12x+6 in the formula represents the 'total number of participants'. In addition, in the case of a solution object, the computing device (100) can recognize that a formula such as “f(12)=12(12)+6” is connected to the variable assignment and calculation process. In the case of a correct answer object, the computing device (100) can analyze that the result of the solution step, “150”, is a result derived from the formula of the problem.

[0091] Additionally, the computing device (100) can decompose mathematical elements based on the analyzed relationship. For example, in the case of the formula “f(x)=12x+6”, the computing device (100) can decompose the formula into sub-components such as a function name (f), a variable (x), a coefficient (12), a constant term (6), and operators (=, +). Thus, the computing device (100) can generate base data for generalizing and variableizing the mathematical structure of the question by analyzing the semantic relationship between the text and mathematical elements included in each of the problem, solution, and answer converted to the second standard, and by subdividing and decomposing the mathematical elements according to the result.

[0092]

[0093] According to one embodiment of the present disclosure, a computing device (100) can generate new learning questions by utilizing decomposed elements (S150). The computing device (100) can generate one or more new learning questions by utilizing decomposed elements. The generation of new learning questions can be performed by generalizing the mathematical structure of existing questions and combining new formulas, conditions, or question forms based thereon. For example, the computing device (100) can variableize the decomposed mathematical elements. For example, if the formula “f(x)=12x+6” is generalized as “f(x)=a*b*c*x+a*b”, the computing device (100) can recognize each variable (a, b, c, x) and operator (+, *) as independent elements and variableize them into the smallest learnable units. The computing device (100) can divide the variableized elements into predefined window sizes. The computing device (100) can separate variable elements according to a predefined window size. Here, the window size refers to the range of combinations of elements within a mathematical expression. For example, if the window size is set to 3, the formula “x+a+b” can be divided into all possible sub-combinations such as [x, x+a, x+a+b, a, a+b, b]. These separated sub-sequences can be organized into a single dataset based on a proprietary standard (e.g., structured JSON format) in which the mathematical logical structure is decomposed.

[0094] A computing device (100) can generate a dataset for generating new learning questions by concatenating separated variable elements. The computing device (100) can concatenate the dataset generated as described above to convert it into a learnable input sequence, and by utilizing this for the training of an artificial intelligence model, it can learn the mathematical structure or logical pattern of the new questions. The computing device (100) can generate new learning questions based on the dataset by utilizing an artificial intelligence model. The artificial intelligence model may be, for example, a deep learning-based language model (LLM) or a transformer model dedicated to generating mathematical questions, and can automatically generate new learning questions by applying new numbers, variables, conditions, etc., while having the same type of mathematical structure as existing questions, using the learned question structure. By learning the mathematical logical structure of existing questions, the artificial intelligence model can generate new learning questions that have a similar form but new combinations of variables, combinations of constants, or sentence structures. Meanwhile, the computing device (100) can recombine the decomposed elements into variable units and, based on this, use an artificial intelligence model to automatically generate new learning questions that correspond to the level of the curriculum.

[0095] According to one embodiment, a computing device (100) may obtain educational course information associated with a learning question. The educational course information may include educational metadata such as the subject, grade, unit, learning achievement standard, or concept hierarchy to which the learning question belongs. For example, in the case of a question belonging to the unit “Graph of a Linear Function,” the computing device (100) may manage it so that concepts such as “Properties of a Quadratic Function” or “Limit of a Function” that follow the unit are not included. The computing device (100) may set constraints for generating a new learning question based on the educational course information. The constraints may include the unit or concept range, difficulty level (e.g., beginner, intermediate, advanced), variable range (number, unit, symbol, etc.), question type (multiple choice, descriptive, calculation type, etc.), and set of available mathematical concepts. The computing device (100) may generate a new learning question based on the set constraints. The computing device (100) can automatically adjust permissible concepts and mathematical complexity according to the level of the learner (e.g., elementary, middle, or higher education stage) of the item creation target during the constraint setting process. The artificial intelligence model can be controlled to combine variables or change formulas only within the permissible range of the curriculum. Through this, the generated item can be limited to content that aligns with the educational objectives of the unit. Meanwhile, the computing device (100) can utilize curriculum information to impose logical constraints on item creation, thereby enabling the item generated by the AI ​​to be created as a level-specific item that is suitable for the actual curriculum level and aligns with the learner's learning stage.

[0096]

[0097] FIG. 4 is a diagram schematically illustrating the operation of generating a new learning item according to one embodiment of the present disclosure.

[0098] According to one embodiment of the present disclosure, a computing device (100) can acquire a plurality of pieces of information related to a learning question (S110). For example, the computing device (100) can acquire a problem (10) included in a plurality of pieces of information related to a learning question, which includes a formula “f(x)=12x+6” and a problem text “This function represents the total number of participants when the number of classes participating in the sports day is x. When there are 12 classes, how many total participants are there?” In addition, the computing device (100) can also acquire the solution and correct answer (e.g., f(12)=12(12)+6=150) of the problem (10). For example, the computing device (100) can acquire a plurality of pieces of information related to a learning question in an image type or PDF type, etc.

[0099] The computing device (100) can convert each of the multiple pieces of information into a first standard (e.g., LaTeX) capable of mathematical expression (S120). The computing device (100) can convert elements other than text included in each of the multiple pieces of information acquired as an image type into the first standard (11). Additionally, the computing device (100) can utilize an artificial intelligence model to convert elements other than text included in each of the multiple pieces of information acquired as a PDF (Portable Document Format) type into the first standard. For example, referring to FIG. 4, the computing device (100) can convert the formula “f(x)=12x+6” included in the problem among the acquired items into LaTeX syntax ($ / displaystyle f(x)=12x+6$). Additionally, it can convert the function x to $x$ and the number 12 to $ / displaystyle 12$. In other words, the computing device (100) can convert expressions other than text (mathematical expressions) included in the problem into a first standard. Although the drawing shows only the mathematical expressions included in the problem (10) converted into a first standard, the computing device (100) can convert expressions other than text included in the problem, solution, and answer, respectively, into a first standard capable of mathematical expression.

[0100] A computing device (100) can convert each of the plurality of pieces of information converted into a first standard into a second standard (e.g., JSON) capable of structural representation (S130). Text and non-text elements included in each of the plurality of pieces of information converted into the first standard can be converted into the second standard.

[0101] The computing device (100) can decompose (12) the elements included in each of the multiple pieces of information converted to the second standard (S140). First, the computing device (100) can analyze the relationship between the text and mathematical elements included in each of the multiple pieces of information converted to the second standard. Next, the computing device (100) can decompose the mathematical elements based on the analyzed relationship. For example, within the problem object, it can analyze the semantic connection relationship between the instruction included in the text sentence (e.g., “Find the value of the following expression”) and the formula (f(x)=12x+6), within the solution object, it can identify the logical order of the variable substitution (x=12) and the calculation process (12×12+6), and within the answer object, it can recognize which formula the final result (150) was derived from. Next, the computing device (100) can decompose the mathematical elements based on the analyzed relationship. For example, in the case of the formula “f(x)=12x+6”, the computing device (100) can break down the function name (f), variable (x), coefficient (12), constant term (6), and operator (=, +) into independent subcomponents.

[0102] The computing device (100) can generate new learning questions by utilizing decomposed elements (S150). The computing device (100) can generate one or more new learning questions by utilizing decomposed elements. For example, the computing device (100) can convert decomposed mathematical elements into variables. The computing device (100) can convert decomposed mathematical elements into variables by converting them into a second standard. For example, if the equation “f(x)=12x+6” is generalized into the form “f(x)=a*b*c*x+a*b”, the computing device (100) can convert each element (a, b, c, x) into a variable and define it as a basic unit of learning data capable of new combinations. Additionally, the computing device (100) can divide the variableized elements into predefined window sizes. For example, the window size refers to the range of combinations of elements within a formula, and if the formula “x+a+b” is set to a window size of 3, the computing device (100) can separate it into subsequences such as [x, x+a, x+a+b, a, a+b, b]. The computing device (100) can concatenate the separated variable elements to generate a dataset for creating new learning questions. These separated elements can be utilized as learning sub-sequences containing respective mathematical logical units. The computing device (100) can concatenate these separated variable elements to form a dataset for creating new learning questions. Additionally, the computing device (100) can generate new learning questions based on the dataset by utilizing an artificial intelligence model. The computing device (100) can generate new learning questions based on the dataset by utilizing an artificial intelligence model (e.g., a large-scale language model, a sequence-to-sequence model, etc.).In this process, the artificial intelligence model can automatically generate new learning questions based on learned mathematical logical structures, which are similar in form to existing questions but have different combinations of formulas, variable configurations, or sentence expressions. The computing device (100) can generalize the structural patterns of mathematical questions into a learnable form by variableizing the decomposed elements and combining them based on a window, thereby automatically generating new learning questions of various types, difficulty levels, expressions, etc., without relying on an existing database.

[0103] According to one embodiment, a computing device (100) may obtain educational course information linked to learning questions in order to generate new questions (20, 30). The computing device (100) may set constraints for generating new learning questions based on the educational course information. The computing device (100) may generate new learning questions based on the set constraints. The computing device (100) may generate a first new question (20) and a second new question (30), respectively, according to the constraints. The first new question (20) may be a question similar to the mathematical structure of the original learning question, but with the variable values, coefficients, or constant terms changed. For example, when the existing question is “f(x)=12x+6”, the first new question (20) may be generated in a form where the difficulty or numerical conditions are adjusted by changing the coefficients and constants while maintaining the same function structure, such as “f(x)=8x+10”. The second new question (30) may be based on the same mathematical concept (e.g., linear function) but with a modified question type or expression method. For example, if the existing question was “What is the total number of people when there are 12 teachers?”, the second new question (30) may be generated by modifying the context and description, such as “What is the total number of participants when there are 12 classes?”. The computing device (100) can control the generated question to match the level and unit range of the learner by setting constraints on question generation based on curriculum information, and as a result, can realize rational and step-by-step question generation based on the curriculum.

[0104]

[0105] The steps mentioned in the foregoing description may be further subdivided into additional steps or combined into fewer steps, depending on the embodiment of the present disclosure. Additionally, some steps may be omitted as necessary, and the order of the steps may be changed.

[0106]

[0107] Meanwhile, a computer-readable medium storing a data structure is disclosed according to an embodiment of the present disclosure.

[0108] A data structure can refer to the organization, management, and storage of data that enables efficient access and modification of data. A data structure can refer to the organization of data to solve specific problems (e.g., data retrieval, data storage, data modification in the shortest possible time). A data structure may also be defined by physical or logical relationships between data elements designed to support specific data processing functions. Logical relationships between data elements may include connections between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements physically stored on a computer-readable storage medium (e.g., a permanent storage device). Specifically, a data structure may include sets of data, relationships between data, and functions or instructions applicable to the data. Through an effectively designed data structure, a computing device can perform operations while minimizing the use of the device's resources. Specifically, through an effectively designed data structure, a computing device can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and retrieval.

[0109] Data structures can be classified into linear and non-linear data structures based on their form. A linear data structure is one where only one piece of data is connected to the next. Linear data structures can include lists, stacks, queues, and deques. A list can refer to a set of data that maintains an internal order. Lists can include linked lists. A linked list is a data structure where data is connected in a line, with each piece of data possessing a pointer. In a linked list, the pointer can contain information regarding the connection to the next or previous data. Depending on its form, a linked list can be represented as a singly linked list, a doubly linked list, or a circular linked list. A stack is a data arrangement structure that allows for restricted access to data. A stack can be a linear data structure where data can be processed (e.g., insertion or deletion) only at one end. Data stored in a stack can be a Last-In, First-Out (LIFO) data structure, meaning that the later an item is entered, the sooner it is retrieved. A queue is a data sequence structure that allows for limited access to data; unlike a stack, it can be a FIFO (First in First Out) data structure where data stored later is retrieved later. A deque is a data structure that can process data at both ends.

[0110] Non-linear data structures can be structures where multiple data are connected after a single piece of data. Non-linear data structures may include graph data structures. A graph data structure can be defined by vertices and edges, and an edge may include a line connecting two different vertices. Graph data structures may include tree data structures. A tree data structure may be a data structure where there is only one path connecting two different vertices among the multiple vertices included in the tree. In other words, it may be a data structure that does not form a loop in a graph data structure.

[0111] Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, the term neural network will be used consistently. A data structure may include a neural network. Furthermore, a data structure including a neural network may be stored on a computer-readable medium. A data structure including a neural network may also include data preprocessed for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. A data structure including a neural network may include any of the components disclosed above. That is, a data structure including a neural network may be configured to include all or any combination thereof, such as data preprocessed for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, and loss functions for learning the neural network. In addition to the configurations described above, a data structure including a neural network may include any other information that determines the characteristics of the neural network. Furthermore, the data structure may include any form of data used or generated during the computational process of the neural network, and is not limited to the foregoing. A computer-readable medium may include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network may be composed of a set of interconnected computational units that may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node.

[0112] A data structure may include data input to a neural network. A data structure including data input to a neural network may be stored on a computer-readable medium. Data input to a neural network may include training data input during the neural network learning process and / or input data input to a neural network after training is complete. Data input to a neural network may include pre-processed data and / or data subject to pre-processing. Pre-processing may include a data processing process for inputting data into a neural network. Accordingly, a data structure may include data subject to pre-processing and data generated by pre-processing. The aforementioned data structure is merely an example, and the present disclosure is not limited thereto.

[0113] The data structure may include weights of the neural network. (In this specification, weights and parameters may be used interchangeably.) The data structure including the weights of the neural network may be stored on a computer-readable medium. The neural network may include multiple weights. The weights may be variable and may be varied by a user or an algorithm to enable the neural network to perform a desired function. For example, if one or more input nodes are interconnected to a single output node by respective links, the output node may determine the data value output from the output node based on values ​​input to the input nodes connected to the output node and weights set on the links corresponding to each input node. The aforementioned data structure is merely an example and the present disclosure is not limited thereto.

[0114] As an example rather than a limitation, weights may include weights that vary during the neural network learning process and / or weights for which neural network learning is completed. Weights that vary during the neural network learning process may include weights at the start of the learning cycle and / or weights that vary during the learning cycle. Weights for which neural network learning is completed may include weights for which the learning cycle is completed. Accordingly, a data structure containing the weights of a neural network may include a data structure containing weights that vary during the neural network learning process and / or weights for which neural network learning is completed. Therefore, the weights and / or combinations of each weight described above are included in the data structure containing the weights of a neural network. The aforementioned data structure is merely an example and the present disclosure is not limited thereto.

[0115] Data structures containing the weights of a neural network may be stored on a computer-readable storage medium (e.g., memory, hard disk) after undergoing a serialization process. Serialization may be a process of converting a data structure into a form that can be stored on the same or different computing devices and later reconstructed for use. A computing device may serialize the data structure to transmit and receive data over a network. A serialized data structure containing the weights of a neural network may be reconstructed on the same or different computing devices through deserialization. Data structures containing the weights of a neural network are not limited to serialization. Furthermore, data structures containing the weights of a neural network may include data structures designed to increase computational efficiency while minimizing the use of computing device resources (e.g., B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree in non-linear data structures). The foregoing is merely an example and the present disclosure is not limited thereto.

[0116] The data structure may include hyperparameters of the neural network. The data structure including the neural network hyperparameters may be stored on a computer-readable medium. The hyperparameters may be variables that are varied by the user. The hyperparameters may include, for example, a learning rate, a cost function, the number of learning cycle iterations, weight initialization (e.g., setting the range of weight values ​​subject to weight initialization), and the number of hidden units (e.g., the number of hidden layers, the number of nodes in the hidden layers). The aforementioned data structure is merely an example, and the present disclosure is not limited thereto.

[0117]

[0118] FIG. 5 is a brief and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0119] Although the present disclosure has been described as generally being implementable by a computing device, a person skilled in the art will be well aware that the present disclosure may be implemented in combination with computer-executable instructions and / or other program modules that can be executed on one or more computers and / or as a combination of hardware and software.

[0120] Generally, a program module includes routines, programs, components, data structures, etc., that perform a specific task or implement a specific abstract data type. Furthermore, a person skilled in the art will be well aware that the method of the present disclosure can be implemented in other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. (each of which may be connected to and operated with one or more associated devices).

[0121] The embodiments described in this disclosure may also be implemented in a distributed computing environment in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0122] Computers typically include various computer-readable media. Any medium accessible by a computer may be a computer-readable medium, and such computer-readable media include volatile and non-volatile media, transitory and non-transitory media, and removable and non-removable media. By example, but not limiting, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media include volatile and non-volatile media, transitory and non-transitory media, and removable and non-removable media implemented by any method or technique for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, DVD (digital video disk) or other optical disk storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other media that can be accessed by a computer and used to store desired information.

[0123] Computer-readable transmission media typically include all information transmission media that implement computer-readable instructions, data structures, program modules, or other data, etc., on a modulated data signal, such as a carrier wave or other transport mechanism. The term modulated data signal means a signal in which one or more of the characteristics of the signal are set or modified to encode information within the signal. By example, not limiting, computer-readable transmission media include wired media, such as wired networks or direct-wired connections, and wireless media, such as acoustic, RF, infrared, and other wireless media. Any combination of the media described above is also considered to be within the scope of computer-readable transmission media.

[0124] An exemplary environment for implementing various aspects of the present disclosure, including a computer (1102), is shown, wherein the computer (1102) includes a processing unit (1104), system memory (1106), and a system bus (1108). The system bus (1108) connects system components, including system memory (1106) (but not limited thereto), to the processing unit (1104). The processing unit (1104) may be any processor among various commercial processors. Dual processors and other multiprocessor architectures may also be used as the processing unit (1104).

[0125] The system bus (1108) may be any of several types of bus structures that can be additionally interconnected to a local bus using any of the memory bus, peripheral bus, and various commercial bus architectures. System memory (1106) includes read-only memory (ROM) (1110) and random access memory (RAM) (1112). The basic input / output system (BIOS) is stored in non-volatile memory (1110), such as ROM, EPROM, EEPROM, etc., and this BIOS includes basic routines that help transfer information between components within the computer (1102) at times such as during startup. The RAM (1112) may also include high-speed RAM, such as static RAM, for caching data.

[0126] The computer (1102) also includes an internal hard disk drive (HDD) (1114) (e.g., EIDE, SATA)—this internal hard disk drive (1114) may also be configured for external use within a suitable chassis (not shown)—a floppy disk drive (FDD) (1116) (e.g., for reading from or writing to a removable diskette (1118)), and an optical disk drive (1120) (e.g., for reading from a CD-ROM disk (1122) or reading from or writing to other high-capacity optical media such as a DVD). The hard disk drive (1114), the floppy disk drive (1116), and the optical disk drive (1120) may each be connected to the system bus (1108) by a hard disk drive interface (1124), a magnetic disk drive interface (1126), and an optical drive interface (1128). The interface (1124) for implementing an external drive includes at least one or both of USB (Universal Serial Bus) and IEEE 1394 interface technologies.

[0127] These drives and associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, etc. In the case of a computer (1102), the drives and media correspond to storing any data in a suitable digital format. Although the description of computer-readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, a person skilled in the art will know that other types of computer-readable media, such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc., may also be used in exemplary operating environments and that any of these media may contain computer-executable instructions for performing the methods of the present disclosure.

[0128] A number of program modules, including an operating system (1130), one or more application programs (1132), other program modules (1134), and program data (1136), may be stored in the drive and RAM (1112). All or part of the operating system, application, module and / or data may also be cached in RAM (1112). It will be well known that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

[0129] The user can input commands and information into the computer (1102) through one or more wired / wireless input devices, such as a pointing device like a keyboard (1138) and a mouse (1140). Other input devices (not shown) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, etc. These and other input devices are often connected to the processing unit (1104) via an input device interface (1142) connected to the system bus (1108), but may also be connected via other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, etc.

[0130] A monitor (1144) or other type of display device is also connected to the system bus (1108) via an interface such as a video adapter (1146). In addition to the monitor (1144), the computer generally includes other peripheral output devices (not shown), such as speakers, a printer, and so on.

[0131] The computer (1102) may operate in a networked environment using a logical connection to one or more remote computers, such as remote computer(s) (1148), via wired and / or wireless communication. The remote computer(s) (1148) may be a workstation, a computing device computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other conventional network node, and generally include many or all of the components described for the computer (1102), but for brevity, only the memory storage device (1150) is illustrated. The illustrated logical connection includes a wired / wireless connection to a local area network (LAN) (1152) and / or a larger network, e.g., a wide area network (WAN) (1154). Such LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a global computer network, e.g., the Internet.

[0132] When used in a LAN networking environment, the computer (1102) is connected to the LAN (1152) via a wired and / or wireless communication network interface or adapter (1156). The adapter (1156) may facilitate wired or wireless communication to the LAN (1152), and the LAN (1152) may also include a wireless access point installed therein to communicate with the wireless adapter (1156). When used in a WAN networking environment, the computer (1102) may include a modem (1158), be connected to a communication computing device on the WAN (1154), or have other means of establishing communication through the WAN (1154), such as through the Internet. The modem (1158), which may be an internal or external and a wired or wireless device, is connected to the system bus (1108) via an input device interface (1142). In a networked environment, the program modules described for the computer (1102) or parts thereof may be stored in a remote memory / storage device (1150). It will be well known that the illustrated network connection is exemplary and that other means of establishing a communication link between computers may be used.

[0133] The computer (1102) operates to communicate with any wireless device or object that is deployed and operated via wireless communication, for example, a printer, scanner, desktop and / or portable computer, PDA (portable data assistant), communication satellite, any equipment or place associated with a wireless detectable tag, and a telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network, or simply ad hoc communication between at least two devices.

[0134] Wi-Fi (Wireless Fidelity) enables connectivity to the Internet and other sources without wires. Wi-Fi is a wireless technology, similar to a cell phone, that allows devices, such as computers, to transmit and receive data indoors and outdoors—that is, anywhere within the coverage area of ​​a base station. Wi-Fi networks use a wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in unlicensed 2.4 and 5 GHz wireless bands at data rates, for example, 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band).

[0135] Those skilled in the art of the present disclosure will understand that information and signals may be represented using any various different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0136] Those skilled in the art will understand that the various exemplary logic blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented by electronic hardware, various forms of programs or design code (referred to herein as software for convenience), or a combination of all such. To clearly illustrate this interoperability between hardware and software, various exemplary components, blocks, modules, circuits, and steps have been generally described above in relation to their functions. Whether such functions are implemented as hardware or software depends on the design constraints imposed on the specific application and the overall system. Those skilled in the art may implement the functions described in various ways for each specific application, but such implementation decisions should not be interpreted as being outside the scope of this disclosure.

[0137] The various embodiments presented herein may be implemented as methods, devices, or articles manufactured using standard programming and / or engineering techniques. The term "article manufactured" includes a computer program, a carrier, or a medium accessible from any computer-readable storage device. For example, computer-readable storage media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical discs (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Additionally, the various storage media presented herein include one or more devices and / or other machine-readable media for storing information.

[0138] It should be understood that the specific order or hierarchy of steps in the presented processes is merely an example of exemplary approaches. It should be understood that, based on design priorities, the specific order or hierarchy of steps in the processes may be rearranged within the scope of this disclosure. The appended method claims provide elements of various steps in a sample order, but do not imply being limited to the specific order or hierarchy presented.

[0139] Description of the presented embodiments is provided so that a person skilled in the art may use or practice the present disclosure. Various modifications to these embodiments will be apparent to a person skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not limited to the embodiments presented herein, but should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

[0140] As described above, the relevant details have been described in the best mode for carrying out the invention.

Claims

1. A method for generating new learning items performed by a computing device, A step of acquiring multiple pieces of information related to learning items; A step of converting each of the above plurality of pieces of information into a first standard; A step of converting each of the plurality of pieces of information converted to the first standard into the second standard; A step of decomposing the elements included in each of the plurality of pieces of information converted to the second standard; and A step of generating new learning questions by utilizing the aforementioned decomposed elements; including, method.

2. In Paragraph 1, The step of converting each of the above plurality of pieces of information into the above first standard is, A step of converting elements other than text included in each of the plurality of pieces of information acquired as an image type into the first specification; or A step of converting non-text elements included in each of the plurality of pieces of information obtained in PDF (Portable Document Format) type into the first standard using an artificial intelligence model. including, method.

3. In Paragraph 2, The step of converting each of the plurality of pieces of information converted to the first standard into the second standard is, A step of converting the text included in each of the plurality of pieces of information converted to the first standard and elements other than the text into the second standard. including, method.

4. In Paragraph 3, The above learning questions are learning questions related to mathematics, and Elements other than the text above are, Mathematical elements including any one of numbers, formulas, symbols, variables, or diagrams, method.

5. In Paragraph 4, The step of decomposing the elements included in each of the plurality of pieces of information converted to the second standard is, A step of analyzing the relationship between the text included in each of the plurality of pieces of information converted to the second standard and the mathematical elements; and A step of decomposing the mathematical elements based on the analyzed relationship above; including, method.

6. In Paragraph 1, The step of generating new learning questions by utilizing the aforementioned decomposed elements is, A step of converting the above-mentioned decomposed mathematical elements into variables; A step of dividing the above variableized elements into predefined window sizes; A step of generating a dataset for generating the new learning item by concatenating the aforementioned distinguished variable elements; and A step of generating the new learning questions based on the above data set using an artificial intelligence model; including, method.

7. In Paragraph 6, The step of generating new learning questions by utilizing the aforementioned decomposed elements is, A step of obtaining educational curriculum information linked to the above learning items; A step of setting constraints for generating the new learning items based on the above educational course information; and A step of generating the new learning questions based on the constraints set above. including, method.

8. In Paragraph 1, The above-mentioned first specification is a LaTeX specification capable of mathematical expression, and The above second standard is a standard capable of structural expression, method.

9. In Paragraph 1, Multiple pieces of information related to the above learning questions are, including questions, solutions, and answers method.

10. A computer program stored on a computer-readable storage medium, wherein, when the computer program is executed on one or more processors, the one or more processors are configured to perform the following operations for generating new learning items, said operations being: The action of acquiring multiple pieces of information related to learning items; An operation of converting each of the above plurality of pieces of information into a first standard; An operation of converting each of the plurality of pieces of information converted to the first standard into the second standard; An operation of decomposing elements included in each of the plurality of pieces of information converted to the above second standard; and The operation of generating new learning questions by utilizing the aforementioned decomposed elements; including, A computer program stored on a computer-readable storage medium.

11. In Paragraph 10, The operation of converting each of the above plurality of pieces of information into the above first standard is, An operation of converting elements other than text included in each of the plurality of pieces of information acquired as an image type into the first specification; or An operation of converting non-text elements included in each of the plurality of pieces of information obtained in PDF (Portable Document Format) type into the first standard using an artificial intelligence model. including, A computer program stored on a computer-readable storage medium.

12. In Paragraph 11, The step of converting each of the plurality of pieces of information converted to the first standard into the second standard is, The operation of converting the text included in each of the plurality of pieces of information converted to the first standard and elements other than the text into the second standard. including, A computer program stored on a computer-readable storage medium.

13. In Paragraph 12, The above learning questions are learning questions related to mathematics, and Elements other than the text above are, Mathematical elements including any one of numbers, formulas, symbols, variables, or diagrams, A computer program stored on a computer-readable storage medium.

14. In Paragraph 13, The operation of decomposing the elements included in each of the plurality of pieces of information converted to the above second standard is, An operation of analyzing the relationship between the text included in each of the plurality of pieces of information converted to the above second standard and the mathematical elements; and Based on the above-analyzed relationship, the operation of decomposing the above mathematical elements including, A computer program stored on a computer-readable storage medium.

15. In Paragraph 10, The operation of generating new learning questions by utilizing the aforementioned decomposed elements is, The operation of converting the above-mentioned decomposed mathematical elements into variables; The operation of dividing the above variableized elements into predefined window sizes; The operation of concatenating the aforementioned distinguished variable elements to generate a dataset for generating the aforementioned new learning items; and The operation of generating the new learning items based on the above data set using an artificial intelligence model; including, A computer program stored on a computer-readable storage medium.

16. In Paragraph 15, The operation of generating new learning questions by utilizing the aforementioned decomposed elements is, An action of acquiring educational course information linked to the above learning items; The operation of setting constraints for generating the new learning questions based on the above educational course information; and The operation of generating the new learning questions based on the constraints set above. including more, A computer program stored on a computer-readable storage medium.

17. In Paragraph 10, The above-mentioned first specification is a LaTeX specification capable of mathematical expression, and The above second standard is a standard capable of structural expression, A computer program stored on a computer-readable storage medium.

18. In Paragraph 10, Multiple pieces of information related to the above learning questions are, including questions, solutions, and answers A computer program stored on a computer-readable storage medium.

19. As a computing device, At least one processor; and Memory; Includes, The above-mentioned at least one processor is, Acquire multiple pieces of information related to learning items; Convert each of the above plurality of pieces of information into a first standard; Converting each of the plurality of pieces of information converted to the first standard to the second standard; Decompose the elements included in each of the plurality of pieces of information converted to the above second standard; and Configured to generate new learning questions by utilizing the aforementioned decomposed elements, device.

20. In Paragraph 19, The above-mentioned at least one processor is, An operation of converting elements other than text included in each of the plurality of pieces of information acquired as an image type into the first specification; or An operation of converting non-text elements included in each of the plurality of pieces of information obtained in PDF (Portable Document Format) type into the first standard using an artificial intelligence model. including, device.

21. In Paragraph 20, The above-mentioned at least one processor is, Configured to convert the text included in each of the plurality of pieces of information converted to the first standard and elements other than the text into the second standard. device.

22. In Paragraph 21, The above learning questions are learning questions related to mathematics, and Elements other than the text above are, Mathematical elements including any one of numbers, formulas, symbols, variables, or diagrams, device.

23. In Paragraph 22, The above-mentioned at least one processor is, Analyze the relationship between the text included in each of the plurality of pieces of information converted to the above second standard and the mathematical elements; and Based on the above-analyzed relationship, configured to decompose the above-mentioned mathematical elements device.

24. In Paragraph 19, The above-mentioned at least one processor is, Variableization of the above-mentioned decomposed mathematical elements; The above variableized elements are separated by a predefined window size; Generating a dataset for generating the new learning items by concatenating the aforementioned distinguished variable elements; and Configured to generate the aforementioned new learning items based on the aforementioned dataset using an artificial intelligence model, device.

25. In Paragraph 24, The above-mentioned at least one processor is, Obtain educational curriculum information linked to the above learning items; Set constraints for generating the new learning items based on the above educational curriculum information; and Additionally configured to generate the new learning items based on the constraints set above, device.

26. In Paragraph 19, The above-mentioned first specification is a LaTeX specification capable of mathematical expression, and The above second standard is a standard capable of structural expression, device.

27. In Paragraph 19, Multiple pieces of information related to the above learning questions are, including questions, solutions, and answers device.

Images